Skip to yearly menu bar Skip to main content


Time zone: Conference local time zone
Full Schedule Tue 10/6 Wed 10/7 Thu 10/8 Fri 10/9
Filter Events
Registration Desk
8:00 AM - 5:30 PM
Invited Talk
9:00 AM - 10:00 AM

Our modern mythologies about LLMs distract us from what they have in common with actual human myths. Instead of being a big step on the road towards autonomous individual intelligence, LLMs compress extensive corpora of collectively generated human cultural knowledge, enabling new uses of myths, traditions, stock elements, formulas, nostrums, tropes and collective rules-of-thumb. This may have unexpected uses: a decade ago, few would have anticipated that the creativity of the bard and the creativity of the programmer had much in common. LLMs are automated culture machines, but humans have constructed non-automated culture machines in the past. We can learn a great deal about LLMs' limits and potential from studying previous culture machines such as Homeric epics, folk tales and structuralist literary experiments.

... more
Speaker Bio
Henry Farrell
Henry Farrell is the SNF Agora Professor of International Affairs at Johns Hopkins School of Advanced International Studies, an External Professor at the Santa Fe Institute, and the 2019 recipient of the Friedrich Schiedel Prize for Politics and Technology. He is a member of the Council on Foreign Relations, and a Council Member of the European Council on Foreign Relations, as well as an affiliated scholar at Stanford University Law School’s Center for the Internet and Society, and an international correspondent for Stato e Mercato.
... more
Oral
10:00 AM - 11:00 AM
4 Events in this session
More Than Words: Compositional Tokenization for Efficient Language Models
Yuval Reif ⋅ Guy Kaplan ⋅ Roy Schwartz
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Xinyue Liu ⋅ Niloofar Mireshghallah ⋅ Jane C Ginsburg ⋅ Tuhin Chakrabarty
Message Passing Enables Efficient Reasoning
Xuecheng Liu ⋅ Daman Arora ⋅ Gokul Swamy ⋅ Andrea Zanette
A Mirage of Coherence: How Metaphor Impacts Language Models' Discourse Coherence Assessment
Wanting Ning ⋅ Brian Choi ⋅ Eun Jin Paek ⋅ Hyeju Jang
Go to Event Page
Poster
11:00 AM - 1:00 PM

Imperial Ballroom (#1-73), Franciscan A (#74-80), Franciscan B (#81-90), Franciscan C (#91-100), Grand Ballroom (#101-145)

... more
144 Events in this session
Towards Comprehensive Mobile Application Testing for User-centric Feature Coverage via Simulating Real-World Users with Personas
Ha Min Son ⋅ Huan Ren ⋅ Huan Song ⋅ Zhe Zhao ⋅ Xin Liu
CocoaBench: Evaluating unified digital agents in the wild
Shibo Hao ⋅ Zhining Zhang ⋅ Zhiqi Liang ⋅ Tianyang Liu ⋅ Yuheng Zha ⋅ Qiyue Gao ⋅ Jixuan Chen ⋅ Zilong Wang ⋅ Zhoujun Cheng ⋅ Haoxiang Zhang ⋅ Junli Wang ⋅ Hexi Jin ⋅ Boyuan Zheng ⋅ Kun Zhou ⋅ Yu Wang ⋅ Feng Yao ⋅ Licheng Liu ⋅ Yijiang Li ⋅ Zhifei Li ⋅ Zhengtao Han ⋅ Pracha Promthaw ⋅ Tommaso Cerruti ⋅ Xiaohan Fu ⋅ Ziqiao Ma ⋅ Jingbo Shang ⋅ Lianhui Qin ⋅ Julian McAuley ⋅ Eric Xing ⋅ Zhengzhong Liu ⋅ Rupesh K Srivastava ⋅ Zhiting Hu
AlphaEval: Evaluating Agents in Production
Pengrui Lu ⋅ Bingyu Xu ⋅ Wenjun Zhang ⋅ Shengjia Hua ⋅ Xuanjian Gao ⋅ Ranxiang Ge ⋅ Lyumanshan Ye ⋅ Linxuan Wu ⋅ Yiran Li ⋅ Junfei F Yu ⋅ Yibo Zhang ⋅ Ruixin Li ⋅ Manxiang Li ⋅ Xiao Han ⋅ Xiaocong Zhou ⋅ Guangyao Chi ⋅ Zisheng Chen ⋅ Kaishen Chen ⋅ Kun Wang ⋅ Qihua Xu ⋅ Fengyuemeng ⋅ Yuchen Ni ⋅ Jiajun Li ⋅ Jinxiu Liu ⋅ Danfeng Zhang ⋅ Jingru Zhao ⋅ Pengfei Liu
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Xiangyi Li ⋅ Kyoung Whan Choe ⋅ Yimin Liu ⋅ Xiaokun Chen ⋅ Chujun Tao ⋅ Bingran You ⋅ Wenbo Chen ⋅ Zonglin Di ⋅ Jiankai Sun ⋅ Shenghan Zheng ⋅ Jiajun Bao ⋅ Yuanli Wang ⋅ Weixiang Yan ⋅ Yiyuan Li ⋅ Hanchung Lee
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Yu Li ⋅ Haoyu Luo ⋅ Yuejin Xie ⋅ Yuqian Fu ⋅ Zhonghao Yang ⋅ Shuai Shao ⋅ Qihan Ren ⋅ Wanying Qu ⋅ Yanwei Fu ⋅ Yujiu Yang ⋅ Jing Shao ⋅ Dongrui Liu
PM-Bench: Evaluating Prospective Memory of LLM Agents
Genglin Liu ⋅ Saadia Gabriel
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs
Raphael Shu ⋅ Yusen Zhang ⋅ Jeffrey (Young Min) Cho ⋅ Jin Mo Yang ⋅ Yuan Yuan ⋅ Wenliang Zheng ⋅ Sharath Chandra Guntuku ⋅ Lyle Ungar ⋅ Zhou Yu ⋅ Rui Zhang
MT-PINGEVAL: Evaluating Multi-Turn Collaboration with Private Information Games
Jacob Eisenstein ⋅ Fantine Huot ⋅ Adam Fisch ⋅ Jonathan Berant ⋅ Mirella Lapata
AI Assistance Reduces Persistence and Hurts Independent Performance
Grace Liu ⋅ Brian Christian ⋅ Tsvetomira Dumbalska ⋅ Michiel A Bakker ⋅ Rachit Dubey
Verbalizing LLMs' assumptions to explain and control sycophancy
Myra Cheng ⋅ Isabel Sieh ⋅ Humishka Zope ⋅ Sunny Yu ⋅ Lujain Ibrahim ⋅ Aryaman Arora ⋅ Jared Moore ⋅ Desmond Ong ⋅ Dan Jurafsky ⋅ Diyi Yang
Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks
Shitanshu Bhushan ⋅ Yunxiang Zhang ⋅ Lu Wang
Synthetic Sandbox for Training ML Engineering Agents
Yuhang Zhou ⋅ Lizhu Zhang ⋅ Yifan Wu ⋅ Jiayi Liu ⋅ Xiangjun Fan ⋅ Zhuokai Zhao ⋅ Hong Yan
TritonRL: Training LLMs to Think and Code Triton Without Cheating
Jiin Woo ⋅ Shaowei Zhu ⋅ Allen Nie ⋅ Zhen Jia ⋅ Yida Wang ⋅ Youngsuk Park
Quasar: A Programming Language Specialized for LLM Code Actions
Stephen Mell ⋅ Botong Zhang ⋅ David Mell ⋅ Shuo Li ⋅ Ramya Ramalingam ⋅ Nathan Yu ⋅ Stephan Zdancewic ⋅ Osbert Bastani
MetaLint: Easy-to-Hard Generalization for Code Linting
Atharva Naik ⋅ Lawanya Baghel ⋅ Dhatchinamoorthi Kunde Govindarajan ⋅ Darsh Agrawal ⋅ Yiqing Xie ⋅ Daniel Fried ⋅ Carolyn Rose
MAPLE: Metadata Augmented Private Language Evolution
Eli Chien ⋅ Yuzheng Hu ⋅ Ryan McKenna ⋅ Shanshan Wu ⋅ Zheng Xu ⋅ Peter Kairouz
PolicyLong: Towards On-Policy Context Extension
Junlong Jia ⋅ Ziyang Chen ⋅ Xing Wu ⋅ Chaochen Gao ⋅ TingHao YU ⋅ feng zhang ⋅ Songlin Hu ⋅ Binghui Guo
Studying the Soupability of Documents in State Space Models
Yasaman Jafari ⋅ Zixian Wang ⋅ Leon Bergen ⋅ Taylor Berg-Kirkpatrick
Reflective Context Learning: Studying the Optimization Primitives of Context Space
Nikita Vassilyev ⋅ William Berrios ⋅ RUOWANG ZHANG ⋅ Bo Han ⋅ Douwe Kiela ⋅ Shikib Mehri
Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover
Jui-Hui Chung ⋅ Hongzhou Lin ⋅ Lai Jiang ⋅ Shange Tang ⋅ Chi Jin
Recovering Wasted Compute in Autoresearch Agents
Au K Chun ⋅ Amrutha Rao ⋅ Abhigyan Acherjee ⋅ Zaiqian Chen ⋅ Kazem Meidani ⋅ C. B Bruss ⋅ Micah Goldblum
Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
Sijie Li ⋅ Shanda Li ⋅ Haowei Lin ⋅ Weiwei Sun ⋅ Ameet Talwalkar ⋅ Yiming Yang
Prescriptive Scaling Laws for Data Constrained Training
Justin Lovelace ⋅ Christian Belardi ⋅ Srivatsa Kundurthy ⋅ Shriya Sudhakar ⋅ Kilian Weinberger
The Finetuner’s Fallacy: When to Pretrain with Your Finetuning Data
Christina Baek ⋅ Ricardo P Monti ⋅ David J Schwab ⋅ Amro Abbas ⋅ Rishabh Adiga ⋅ Cody Blakeney ⋅ Maximilian Böther ⋅ Paul Burstein ⋅ Aldo G Carranza ⋅ Alvin Deng ⋅ Parth Doshi ⋅ Vineeth Dorna ⋅ Alex Fang ⋅ Tony Jiang ⋅ Siddharth Joshi ⋅ Brett W Larsen ⋅ Jason C Lee ⋅ Katherine L Mentzer ⋅ Luke Merrick ⋅ Haakon Mongstad ⋅ Fan Pan ⋅ Anshuman Suri ⋅ Darren Teh ⋅ Jason Telanoff ⋅ Jack Urbanek ⋅ Zhengping Wang ⋅ Josh Wills ⋅ Haoli Yin ⋅ Aditi Raghunathan ⋅ J Kolter ⋅ Bogdan Gaza ⋅ Ari S Morcos ⋅ Matthew L Leavitt ⋅ Pratyush Maini
Domain-Aware Scaling Laws Uncover Data Synergy
Kimia Hamidieh ⋅ Lester Mackey ⋅ David Alvarez-Melis
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
Jikai Jin ⋅ Vasilis Syrgkanis ⋅ Sham Kakade ⋅ Hanlin Zhang
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Zhenyu Zhao ⋅ Sander Land ⋅ Daniel M Bikel ⋅ Waseem Alshikh
Message Passing Enables Efficient Reasoning
Xuecheng Liu ⋅ Daman Arora ⋅ Gokul Swamy ⋅ Andrea Zanette
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean McLeish ⋅ Ang Li ⋅ John Kirchenbauer ⋅ Dayal Singh Kalra ⋅ Brian R Bartoldson ⋅ Bhavya Kailkhura ⋅ Avi Schwarzschild ⋅ Jonas Geiping ⋅ Tom Goldstein ⋅ Micah Goldblum
Disentangling the Expressivity of RoPE
Selim Jerad ⋅ Anej Svete ⋅ Jiaoda Li ⋅ Ryan Cotterell
Compliments to the Complementizer: Indirect Routing of Syntactic Structure in a Transformer Language Model
Lasse van den Berg ⋅ Robert Frank
Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge
Pengxiao Lin ⋅ Zheng-An Chen ⋅ Zhi-Qin J Xu
KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval
Xiaochen Wang ⋅ Yuan Zhong ⋅ Haoyu Wang ⋅ Ting Wang ⋅ Fenglong Ma
CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
Jie He ⋅ Richard He Bai ⋅ Sinead Williamson ⋅ Jeff Z Pan ⋅ Navdeep Jaitly ⋅ Yizhe Zhang
SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
Haozhou Xu ⋅ Dongxia Wu ⋅ Matteo Chinazzi ⋅ Ruijia Niu ⋅ Rose Yu ⋅ Yian Ma
Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Differentially Private
Ruihan Wu ⋅ Erchi Wang ⋅ Zhiyuan Zhang ⋅ Yu-Xiang Wang
Evaluating the Retrieval Robustness of Large Language Models
Shuyang Cao ⋅ Karthik Radhakrishnan ⋅ David S Rosenberg ⋅ Steven Lu ⋅ Pengxiang Cheng ⋅ Lu Wang ⋅ Shiyue Zhang
Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation
Jesse St. Amand ⋅ Callum Canavan ⋅ Sohaib Imran ⋅ Joseph Hewson ⋅ Aaron Lutz ⋅ Shi Feng ⋅ Puria Radmard ⋅ Lennie Wells
QualAlign: Benchmarking Automated Qualitative Coding Against Human Schemas
Taggert Smith ⋅ Chuong Nguyen ⋅ Qisen Yang ⋅ Oishani Bandopadhyay ⋅ Yaru Su ⋅ Nadia Polikarpova ⋅ Xinyu Pi
How social context shapes value-related content in Large Language Model outputs
Maryam Ghorbansabagh ⋅ Eugene Yu Ji ⋅ Amir-Hossein Karimi ⋅ Igor Grossmann
Ideological Bias in LLMs’ Economic Causal Reasoning
Donggyu Lee ⋅ Hyeok Yun ⋅ Jungwon Kim ⋅ Junsik Min ⋅ Sungwon Park ⋅ Sangyoon Park ⋅ Jihee Kim
Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
Azza Bouleimen ⋅ Nicolò Pagan ⋅ Ancsa Hannak
Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
Jiayuan Liu ⋅ Barry Wang ⋅ Jiarui Gan ⋅ Tonghan Wang ⋅ Leon Xie ⋅ Mingyu Guo ⋅ Vincent Conitzer
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Mengjie Ren ⋅ Jie Lou ⋅ Boxi Cao ⋅ Xueru Wen ⋅ Hongyu Lin ⋅ Xianpei Han ⋅ Le Sun ⋅ XingYu Li ⋅ Yaojie Lu
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
Xuehang Guo ⋅ Pingyue Zhang ⋅ Ruiyi Zhang ⋅ Zhenhailong Wang ⋅ Hanrui Lyu ⋅ Heng Ji ⋅ Tong Sun ⋅ Qingyun Wang ⋅ Manling Li
Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
Ji Young Byun ⋅ Young-Jin Park ⋅ Jean-Philippe Corbeil ⋅ Asma Ben Abacha
What do your logits know?
Masha Fedzechkina ⋅ Eleonora Gualdoni ⋅ Rita Ramos ⋅ Sinead Williamson
Attr-Kit: An Efficient Toolkit for No-Decode Source Attribution
Sai Sundaresan ⋅ Archit Gupta ⋅ Debabrata Mahapatra
Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
Ziqian Zhong ⋅ Aashiq Muhamed ⋅ Mona Diab ⋅ Virginia Smith ⋅ Aditi Raghunathan
When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Suchit Gupte ⋅ Xueru Zhang ⋅ Mohammad Mahdi Khalili
Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
Jialu Wang ⋅ Jianing Deng ⋅ Shuqing Luo ⋅ Yuanzhe Li ⋅ Dongwei Wang ⋅ Jingtong Hu ⋅ Huanrui Yang ⋅ Song Wang ⋅ Tianlong Chen
More Than Words: Compositional Tokenization for Efficient Language Models
Yuval Reif ⋅ Guy Kaplan ⋅ Roy Schwartz
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
Yiwei Chen ⋅ Bingqi Shang ⋅ Sijia Liu
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
Maheep Chaudhary ⋅ Fazl Barez
Detecting Safety Violations Across Many Agent Traces
Adam Stein ⋅ Davis Brown ⋅ Hamed Hassani ⋅ Mayur Naik ⋅ Eric Wong
Training Agents to Self-Report Misbehavior
Bruce W Lee ⋅ Chen Yueh-Han ⋅ Tomek Korbak
Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Mingwen Dong ⋅ Wei Zou ⋅ Miguel R Calvo ⋅ Shuaichen Chang ⋅ Jiang Guo ⋅ Dongkyu Lee ⋅ Xing Niu ⋅ Xiaofei Ma ⋅ Yanjun Qi ⋅ Jiarong Jiang
BrowseSafe: Understanding and Detecting Prompt Injection Within AI Browser Agents
Kaiyuan Zhang ⋅ Mark Tenenholtz ⋅ Kyle Polley ⋅ Jerry Ma ⋅ Denis Yarats ⋅ Ninghui Li
CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization
Xinting Liao ⋅ Behnoosh Zamanlooy ⋅ Masoumeh Shafieinejad ⋅ D. B Emerson ⋅ Ruinan Jin ⋅ Deval Pandya ⋅ Xiaoxiao Li
Extended to Reality: Prompt Injection in 3D Environments
Zhuoheng Li ⋅ Ying Chen
Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks
Atri Vivek Sharma ⋅ Brian Formento ⋅ Alessio Lomuscio
When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets
Matteo Silvestri ⋅ Fabiano Veglianti ⋅ Flavio Giorgi ⋅ Fabrizio Silvestri ⋅ Gabriele Tolomei
TRUST: A Crowdsourcing Framework for Auditing Large Language Model Reasoning
Yu-Chao Huang ⋅ Zhen Tan ⋅ Mohan Zhang ⋅ Pingzhi Li ⋅ Zhuo Zhang ⋅ Tianlong Chen
Auditing Moderation Robustness Under Realistic Settings
Bargav Jayaraman ⋅ Hamid Mozaffari ⋅ Virendra Marathe ⋅ Swetasudha Panda
Back to Basics: Revisiting ASR in the Age of Voice Agents
Geeyang Tay ⋅ Wentao Ma ⋅ Jaewon Lee ⋅ Yuzhi Tang ⋅ Daniel Lee ⋅ Weisu Yin ⋅ Dongming Shen ⋅ Silin Meng ⋅ Yi Zhu ⋅ Mu Li ⋅ Alex Smola
SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers
Keyang Xuan ⋅ Pengda Wang ⋅ Chongrui Ye ⋅ Haofei Yu ⋅ Tal August ⋅ Jiaxuan You
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
Mingqian Zheng ⋅ Malia Morgan ⋅ Liwei Jiang ⋅ Carolyn Rose ⋅ Maarten Sap
Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
Cameron Pattison ⋅ Lorenzo Manuali ⋅ Seth Lazar
When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift
Zhecheng Sheng ⋅ Yongsen Tan ⋅ Xiruo Ding ⋅ Trevor Cohen ⋅ Serguei V Pakhomov
SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
Jefferson Hernandez ⋅ Jaywon Koo ⋅ Zilin Xiao ⋅ Chen Wei ⋅ Vicente Ordonez
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Xinyue Liu ⋅ Niloofar Mireshghallah ⋅ Jane C Ginsburg ⋅ Tuhin Chakrabarty
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Qingyu Yin ⋅ Chak Tou Leong ⋅ Wenxuan Huang ⋅ Jaehong Yoon ⋅ Linyi Yang ⋅ Xiting Wang ⋅ Wenjie Li ⋅ Jinjin Gu
Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations
Eunkyu Park ⋅ Wesley H Deng ⋅ Gunhee Kim ⋅ Motahhare Eslami ⋅ Maarten Sap
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
尹 诚 ⋅ Yankai Lin ⋅ Wang Xu ⋅ Sikyuen Tam ⋅ Xiangrui Zeng ⋅ Zhiyuan Liu ⋅ Zhouping Yin
Decoupling Planning and Control for Instructable Agents
Zineng Tang ⋅ Kelsey R Allen ⋅ Sjoerd v Steenkiste ⋅ Ishita Dasgupta ⋅ Alane Suhr
Aligning Language Models from User Interactions
Thomas Kleine Buening ⋅ Jonas Hübotter ⋅ Barna Pásztor ⋅ Idan Shenfeld ⋅ Giorgia Ramponi ⋅ Andreas Krause
Peer-Predictive Self-Training for Language Model Reasoning
Shi Feng ⋅ Hanlin Zhang ⋅ Fan Nie ⋅ Sham Kakade ⋅ Yiling Chen
Variational Co-Evolution via Reinforcement Learning
Qiahao Zheng ⋅ Hancong Jin ⋅ Junbo Niu ⋅ Yinjie Wang ⋅ Wentao Zhang ⋅ Ruixun Zhang
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Jacob Dineen ⋅ Aswin RRV ⋅ Zhikun Xu ⋅ Ben Zhou
On Epistemic Diversity in Large Language Models
Elisabeth Kirsten ⋅ Nicole C Krämer ⋅ Muhammad Bilal Zafar
CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse
Samuel Schapiro ⋅ Core Francisco Park ⋅ Felix A Sosa ⋅ Lav Varshney
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
Shouren Wang ⋅ wang yang ⋅ Chuang Ma ⋅ Debargha Ganguly ⋅ Vikash Singh ⋅ Chaoda Song ⋅ Xinpeng Li ⋅ Xianxuan Long ⋅ Vipin Chaudhary ⋅ Xiaotian Han
The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs
Eric So
Reasoning Fine-Tuning Induces Persistent Latent Policy States
Abir Harrasse ⋅ Michael Lan ⋅ Hunar Batra ⋅ Fateme Hashemi Chaleshtori ⋅ Chaithanya Bandi
Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
Parsa Mirtaheri ⋅ Mikhail Belkin
A Mirage of Coherence: How Metaphor Impacts Language Models' Discourse Coherence Assessment
Wanting Ning ⋅ Brian Choi ⋅ Eun Jin Paek ⋅ Hyeju Jang
Should We be Pedantic About Reasoning Errors in Machine Translation?
Calvin Bao ⋅ Marine Carpuat
MELD: Multilingual Ensemble via Logical Debate
Sehyeok Kang ⋅ Jaejun Ryu ⋅ Se-Young Yun
TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
Andre G Viveiros ⋅ Patrick Fernandes ⋅ Saul Santos ⋅ Sonal Sannigrahi ⋅ Emmanouil Zaranis ⋅ Nuno Guerreiro ⋅ Amin Farajian ⋅ Graham Neubig ⋅ Andre Martins
LF²AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models
Santiago Cuervo ⋅ Adel Moumen ⋅ Yanis Labrak ⋅ Sameer Khurana ⋅ Antoine LAURENT ⋅ Mickael Rouvier ⋅ Phil Woodland ⋅ Ricard Marxer
DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
Jingyi Yang ⋅ Yuxian Jiang ⋅ Xuhao Hu ⋅ Shuang Cheng ⋅ Biqing Qi ⋅ Jing Shao
A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models
Theo X. Olausson ⋅ Metod Jazbec ⋅ Xi Wang ⋅ Armando Solar-Lezama ⋅ Christian A. Naesseth ⋅ Stephan Mandt ⋅ Eric Nalisnick
Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
Ruochen Jin ⋅ Zhanliang Wang ⋅ Zongyu Dai ⋅ Jiancong Xiao ⋅ Bojian Hou
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
Pardis Sadat Zahraei ⋅ Janvijay Singh ⋅ Gokhan Tur ⋅ Dilek Hakkani-Tür
Overconfident and Blind to Details: Fixing Prompt Insensitivity with Abductive Preference Learning
Yijin Ni ⋅ Simon Yu ⋅ Peng Qi
Uniform Information Density-Based Preference Optimization
Yongyuan Li ⋅ Yang Xu
A11yn: Aligning LLMs for Web Accessibility-Aware UI Generation
Janghan Yoon ⋅ Jaegwan Cho ⋅ Junhyeok Kim ⋅ Jiwan Chung ⋅ Jaehyun Jeon ⋅ Seungwon Lim ⋅ Youngjae Yu
Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
Eunki Kim ⋅ Na Min An ⋅ Wan Ju Kang ⋅ Sangryul Kim ⋅ James Thorne ⋅ Hyunjung Shim
GLAZE: A Gaze-Language Benchmark for Grounding Human Gaze on Web User Interfaces
Yiran Ma ⋅ Yi-Hao Peng ⋅ Jiayang Shi ⋅ Isha Swaminathan ⋅ Aritra Dutta ⋅ Andrew Begel
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
Yichen Feng ⋅ Yuetai Li ⋅ Chunjiang Liu ⋅ Fengqing Jiang ⋅ Yue Huang ⋅ Yuanyuan Chen ⋅ Hang Hua ⋅ Zhengqing Yuan ⋅ Kaiyuan Zheng ⋅ Luyao Niu ⋅ Bhaskar Ramasubramanian ⋅ Basel Alomair ⋅ Xiangliang Zhang ⋅ Misha Sra ⋅ Zichen Chen ⋅ Radha Poovendran ⋅ Zhangchen Xu
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
Hippolyte Gisserot-Boukhlef ⋅ Nicolas Boizard ⋅ Emmanuel Malherbe ⋅ CELINE HUDELOT ⋅ Pierre Colombo
Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees
Sher Badshah ⋅ Ali Emami ⋅ Hassan Sajjad
Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
Ruomeng Ding ⋅ Yifei Pang ⋅ He Sun ⋅ Yizhong Wang ⋅ Steven Wu ⋅ Zhun Deng
Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
José Pombal ⋅ Ricardo Rei ⋅ Andre Martins
Efficient Safety Alignment of Language Models via Latent Personality Traits
Mohamed Amine Merzouk ⋅ Nolan Smyth ⋅ Damiano Fornasiere ⋅ Linh Le ⋅ David Williams-King ⋅ Adam Oberman
Comparing Developer and LLM Biases in Code Evaluation
Ryan Shar ⋅ Aditya Mittal ⋅ Zichu Wu ⋅ Shyam Agarwal ⋅ Sherry Wu ⋅ Chris Donahue ⋅ Ameet Talwalkar ⋅ Wayne Chi ⋅ Valerie Chen
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Hardy Chen ⋅ Nancy Lau ⋅ Haoqin Tu ⋅ Shuo Yan ⋅ Xiangyan Liu ⋅ Zijun Wang ⋅ Juncheng Wu ⋅ Michael Q Shieh ⋅ Alvaro A Cardenas ⋅ Cihang Xie ⋅ Yuyin Zhou
Agent Psychometrics: Task-Level Performance Prediction in Agentic Coding Benchmarks
Chris Ge ⋅ Daria Kryvosheieva ⋅ Daniel Fried ⋅ Uzay Girit ⋅ Kaivalya Hariharan
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Yuling Shi ⋅ Jinghan Xu ⋅ Kelin Fu ⋅ Wenhao Zeng ⋅ YINGWEI MA ⋅ Shilin He ⋅ Lei Zhang ⋅ Yue Liu ⋅ Zelin Zhao ⋅ Terry Yue Zhuo ⋅ Jialun Cao ⋅ Siyu Ye ⋅ Tianyu Liu ⋅ Kai Cai ⋅ Shing-Chi Cheung ⋅ Xiaodong Gu
Constraint decay: The Fragility of LLM Agents in Backend Code Generation
Francesco Dente ⋅ Dario Satriani ⋅ Paolo Papotti
When Correct Patches Become Vulnerable: Red Teaming LLM-Based Program Repair Agents
Simin Chen ⋅ Yixin He ⋅ Suman Jana ⋅ Baishakhi Ray
CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
Baicheng Chen ⋅ Yu Wang ⋅ Ziheng Zhou ⋅ Xiangru Liu ⋅ Juanru Li ⋅ Yilei Chen ⋅ Tianxing He
FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?
Weimin Fu ⋅ Hejia Zhang ⋅ Minghao Shao ⋅ Zeng Wang ⋅ Johann Knechtel ⋅ Ozgur Sinanoglu ⋅ Muhammad Shafique ⋅ Ramesh Karri ⋅ Xiaolong Guo
AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems
Sumeet Motwani ⋅ Chuan Du ⋅ Aleksandar Petrov ⋅ Christopher E Davis ⋅ Philip Torr ⋅ Antonio R Papania-Davis ⋅ Weishi Yan
Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks
Adam Štorek ⋅ Vikas Upadhyay ⋅ Marianne Menglin Liu ⋅ Daniel W Peterson ⋅ Anshul Mittal ⋅ Sujeeth Bharadwaj ⋅ Fahad Shah ⋅ Sujith Ravi ⋅ Dan Roth
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
Niklas Herbster ⋅ Martin Zborowski ⋅ Alberto Tosato ⋅ Gauthier Gidel ⋅ Tommaso Tosato
SkillRouter: Skill Routing for LLM Agents at Scale
Yanzhao Zheng ⋅ Zhentao Zhang ⋅ Chao Ma ⋅ Yuanqiang Yu ⋅ Jihuai Zhu ⋅ Yong Wu ⋅ Tianze Xu ⋅ Baohua Dong ⋅ Hangcheng Zhu ⋅ Ruohui Huang ⋅ Gang Yu
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Yujian Liu ⋅ Jiabao Ji ⋅ Li An ⋅ Tommi Jaakkola ⋅ Yang Zhang ⋅ Shiyu Chang
EvoSkill: Automated Skill Discovery for Multi-Agent Systems
Salaheddin Alzubi ⋅ Noah Provenzano ⋅ Jaydon Bingham ⋅ Christian A Calvo ⋅ Weiyuan Chen ⋅ Tu Vu
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
Zeyu Ren ⋅ Ling Yue ⋅ Ran Li ⋅ Yishu Wang ⋅ Shengxiang Xu ⋅ Hanmo Liu ⋅ Shaowu Pan ⋅ Shimin Di
Dr. Zero: Self-Evolving Search Agents without Training Data
Zhenrui Yue ⋅ Kartikeya Upasani ⋅ Xianjun Yang ⋅ Suyu Ge ⋅ Shaoliang Nie ⋅ Yuning Mao ⋅ Zhe Liu ⋅ Dong Wang
AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback
Zhitao Gao ⋅ Jie Ma ⋅ Xuhong Li ⋅ Pengyu Li ⋅ Ning Qu ⋅ Yaqiang Wu ⋅ Hui Liu ⋅ Jun Liu
Neural Architecture Discovery via Autonomous Evolution
Weixian Xu ⋅ Yixiu Liu ⋅ Yang Nan ⋅ Lyumanshan Ye ⋅ Xiangkun Hu ⋅ Zhen Qin ⋅ Pengfei Liu
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Ao Qu ⋅ Han Zheng ⋅ Zijian Zhou ⋅ Yihao Yan ⋅ Yihong Tang ⋅ Shao Yong Ong ⋅ Fenglu Hong ⋅ Kaichen Zhou ⋅ Chonghe Jiang ⋅ Minwei Kong ⋅ Jiacheng Zhu ⋅ Sirui Li ⋅ Cathy Wu ⋅ Bryan Kian Hsiang Low ⋅ Jinhua Zhao ⋅ Paul Pu Liang
EvoX: Meta-Evolution for Automated Discovery
Shu Liu ⋅ Shubham Agarwal ⋅ Monish Maheswaran ⋅ Mert Cemri ⋅ Qiuyang Mang ⋅ Zhifei Li ⋅ Ashwin Naren ⋅ Ethan Boneh ⋅ Audrey Cheng ⋅ Alexander Du ⋅ Melissa Pan ⋅ Kurt Keutzer ⋅ Alvin Cheung ⋅ Koushik Sen ⋅ Alex Dimakis ⋅ Matei Zaharia ⋅ Ion Stoica
EvoLen: Evolution-Guided Tokenization for DNA Language Model
Nan Huang ⋅ Xiaoxiao Zhou ⋅ Junxia Cui ⋅ Mario Tapia-Pacheco ⋅ Tiffany Amariuta ⋅ Yang E Li ⋅ Jingbo Shang
From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs
Shengjie Xu
Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
Shikun Liu ⋅ Haoyu P Wang ⋅ Mufei Li ⋅ Pan Li
Structure Before Collapse: Transient Semantic Geometry in Next-Token Prediction
Yize Zhao ⋅ Isabel Papadimitriou ⋅ Christos Thrampoulidis
Why Your Prompt Compressor Is Deleting the Wrong Tokens: An Information-Theoretic Diagnosis
Jinheng Wu ⋅ Di Zhang
Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs
Mohanad Odema ⋅ Gabrielle De Micheli ⋅ Dayin Gou ⋅ Nilesh Malpeddi ⋅ Prathamesh Vaste ⋅ Jacob Song
CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference
Hung-Hsuan Chen
Super Weights in LLMs and the Failure of Selective Training
Shreyas Subramanian ⋅ Adewale Akinfaderin ⋅ Akarsha Sehwag
Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning
Haoze He ⋅ Xingyuan Ding ⋅ Xuan Jiang ⋅ Xinkai Zou ⋅ Alex Cheng ⋅ Yibo Zhao ⋅ Juncheng B Li ⋅ Heather Miller
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
Shengkun Tang ⋅ Zekun Wang ⋅ Bo Zheng ⋅ Liangyu Wang ⋅ Rui Men ⋅ Siqi Zhang ⋅ Xiulong Yuan ⋅ Zihan Qiu ⋅ Zhiqiang Shen ⋅ Dayiheng Liu
Direct Multi-Token Decoding
Xuan Luo ⋅ Weizhi Wang ⋅ Xifeng Yan
Accelerating Speculative Decoding with Block Diffusion Draft Trees
Liran Ringel ⋅ Yaniv Romano
Latent Structure of Affective Representations in Large Language Models
Benjamin Choi ⋅ Melanie Weber
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
Quang Hieu Pham ⋅ Yang He ⋅ Ping Nie ⋅ Canwen Xu ⋅ Davood Rafiei ⋅ Yuepeng Wang ⋅ Xi Ye ⋅ Jocelyn Qiaochu Chen
BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
Mathew J Koretsky ⋅ Maya Willey ⋅ Owen Bianchi ⋅ Chelsea X Alvarado ⋅ Tanay Nayak ⋅ Nicole Kuznetsov ⋅ Sungwon Kim ⋅ Michael Nalls ⋅ Daniel Khashabi ⋅ Faraz Faghri
DeepScholar-Bench: A Live Benchmark for Automated Evaluation of Generative Research Synthesis
Liana Patel ⋅ Negar Arabzadeh ⋅ Harshit Gupta ⋅ Ankita Sundar ⋅ Alon Y Halevy ⋅ Ion Stoica ⋅ Matei Zaharia ⋅ Carlos Guestrin
WebReal: Benchmarking DeepSearch Agents on Real-world User Information Needs
Yifei Wang ⋅ Shangwen Lv ⋅ Zhiyuan Xiong ⋅ Haoyuan Zhang ⋅ Yue Zhang ⋅ Rex Wang ⋅ Runquan Xie ⋅ Linjing Li ⋅ Zhanhui Kang ⋅ Daniel D Zeng
Attractor States Emerge in Multi-Turn LLM Conversations
Ting-Wen Ko ⋅ Jonas Geiping
STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
Zachary E Bamberger ⋅ Till Raphael Saenger ⋅ Gilad Morad ⋅ Ofra Amir ⋅ Brandon M Stewart ⋅ Amir Feder
Go to Event Page
Expo Talk Panel
1:00 PM - 2:30 PM
Social
1:30 PM - 2:30 PM

Meet us after the poster session for an informal LGBTQ+ & allies outing to the Castro. We’ll head over together from the Hilton, grab food/coffee, and hang out in one of San Francisco’s historic LGBTQ+ neighborhoods. Come for all or part of it!

We’ll meet in Franciscan D at 1:30 on Thursday then head out to the Castro directly

... more
Invited Talk
2:30 PM - 3:30 PM

Everyone nowadays is building and evaluating LLM workflows. It's easy to get something running, but we don't yet have an engineering discipline for zeroing in on the most accurate and cost-effective system. There are many ways to break a given task into subtasks -- each of which may benefit from evaluation and revision. There are many components to try, including prompts, examples, rewards, LLMs, and external tools -- as well as humans in the loop, human annotators before the loop, and human evaluators after the loop. Many of these components are trainable or configurable and have varying costs. Do we really have to search this space by hand? Or could AI guide our use of annotation and computation?

The problem is more general than NLP. For example, medicine develops workflows for diagnosis and treatment. I'll outline a general approach based on active feature acquisition: every human annotation, LLM output, tool call, or medical test result is a random variable that we could pay to observe. Since random variables are often correlated, observing cheap variables can help us predict more expensive variables and evaluate whether they are worth observing as well. (Which step should we try next, and with what prompt? Should we double-check or revise the result? Should we ask a human?) Ultimately, gathering information is a reinforcement learning problem. I'll describe how to train an environment model that predicts distributions over any missing variables, much as BERT predicts distributions over any missing tokens. This model could be extended into a policy model that chooses which missing variable to observe next. Any data gathered by the system can immediately be used to train it further, including on counterfactual trajectories, which exploit the fact that our actions have no side effects (observing variables does not change the values of other variables).

... more
Speaker Bio
Jason Eisner
Jason Eisner is Professor of Computer Science at Johns Hopkins University and a Fellow of the Association for Computational Linguistics. At Johns Hopkins, he is also affiliated with the Center for Language and Speech Processing, the Mathematical Institute for Data Science, the Cognitive Science Department, and the Data Science and AI Institute. His goal is to develop the probabilistic modeling, inference, and learning techniques needed for a unified model of all kinds of linguistic structure, and to connect existing models (such as LLMs) to commonsense reasoning, formal reasoning, and downstream applications. His 180+ papers have presented various algorithms for parsing, machine translation, and weighted finite-state machines; formalizations, algorithms, theorems, and empirical results in computational phonology; unsupervised or semi-supervised learning methods for syntax, morphology, and word-sense disambiguation; and principled methods for conversational AI, including neural language modeling and semantic parsing. From 2019-2024 he was Director of Research at Microsoft Semantic Machines, which developed new approaches to conversational AI. He is also the lead designer of Dyna, a declarative programming language that provides an infrastructure for AI algorithms. He has received 3 school-wide awards for excellence in teaching, most recently in 2025, as well as recent Best Paper Awards at ACL 2017, EMNLP 2019, and NAACL 2021 and Outstanding Paper Awards at ACL 2022, EMNLP 2024, and COLM 2025.
... more
Oral
3:30 PM - 4:30 PM
4 Events in this session
Diversity or Precision? A Deep Dive into Next Token Prediction
Haoyuan Wu ⋅ Hai Wang ⋅ jiajia wu ⋅ Jinxiang Ou ⋅ keyaowang ⋅ Weile Chen ⋅ Zihao Zheng ⋅ Bei Yu
MEMENTO: Teaching LLMs to Manage Their Context
Vasilis Kontonis ⋅ Yuchen Zeng ⋅ Shivam Garg ⋅ Lingjiao Chen ⋅ Hao Tang ⋅ Ziyan Wang ⋅ Ahmed H Awadallah ⋅ Eric Horvitz ⋅ John Langford ⋅ Dimitris Papailiopoulos
What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks
Meera Desai ⋅ Sang Truong ⋅ Hanna Wallach ⋅ Alex Chouldechova ⋅ A. Feder Cooper ⋅ Jean Garcia-Gathright ⋅ Daniel Ho ⋅ Abigail Z Jacobs ⋅ Sanmi Koyejo ⋅ Nicholas Pangakis ⋅ Angelina Wang
Introspective Diffusion Language Models
Yifan Yu ⋅ Yuqing Jian ⋅ Junxiong Wang ⋅ Zhongzhu Zhou ⋅ Donglin Zhuang ⋅ Xinyu Fang ⋅ Xiaoxia Wu ⋅ Qingyang Wu ⋅ Shuaiwen L Song ⋅ Tri Dao ⋅ Ben Athiwaratkun ⋅ James Zou ⋅ Fan Lai ⋅ Chenfeng Xu
Go to Event Page
Remarks
4:30 PM - 4:40 PM
Poster
4:40 PM - 6:30 PM

Imperial Ballroom (#1-73), Franciscan A (#74-80), Franciscan B (#81-90), Franciscan C (#91-100), Grand Ballroom (#101-145)

... more
144 Events in this session
Model Merging via Data-Free Covariance Estimation
Marawan Gamal ⋅ Derek Tam ⋅ Pascal J Notsawo ⋅ Colin Raffel ⋅ Guillaume Rabusseau
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
Mario Iacobelli ⋅ Adrian Robert Minut ⋅ Tommaso Mencattini ⋅ Donato Crisostomi ⋅ Andrea Santilli ⋅ Iacopo Masi ⋅ Emanuele Rodolà
ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimization
Ruibo Duan ⋅ Yuxin Liu ⋅ Haoran Ye ⋅ Xinyao Dong ⋅ zhiqiang xu ⋅ Chenglin Fan
Learning Reusable Program Transformations via LLM-Guided Rule Synthesis
Avaljot Singh ⋅ Dushyant Bharadwaj ⋅ Stefanos Baziotis ⋅ Kaushik Varadharajan ⋅ Charith Mendis
Models Can Model, But Can’t Bind: Structured Grounding in Text-to-Optimization
Zhiqi Gao ⋅ Albert Ge ⋅ Alexander M Berenbeim ⋅ Nathaniel D Bastian ⋅ Frederic Sala
The Format Tax: Separating the Cost of Requesting Structure from the Cost of Enforcing It
Ivan Lee ⋅ Loris DAntoni ⋅ Taylor Berg-Kirkpatrick
Syntax Without Semantics: Teaching LLMs to Code in an Unseen Language
Vinayshekhar Bannihatti Kumar ⋅ Disha Makhija ⋅ Manoj Ghuhan Arivazhagan ⋅ Rashmi Gangadharaiah
Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization
Changsheng Wang ⋅ Xin Chen ⋅ Sijia Liu ⋅ Ke Ding
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
Jacob Morrison ⋅ Sanjay Adhikesaven ⋅ Akshita Bhagia ⋅ Matei Zaharia ⋅ Noah Smith ⋅ Sewon Min
DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
Guanzhi Deng ⋅ Bo Li ⋅ Ronghao Chen ⋅ Xiujin Liu ⋅ Huacan Wang ⋅ Zhuo Han ⋅ Lijie Wen ⋅ Linqi Song
MoANT: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning
Rongyu Zhang ⋅ Yijiang Liu ⋅ Huanrui Yang ⋅ Shenli Zheng ⋅ Li Du ⋅ Dan Wang ⋅ Yuan Du ⋅ Shanghang Zhang
MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
Sangmin Lee ⋅ Woojin Chung ⋅ Woongjib Choi ⋅ Hong-Goo Kang
Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling
Fan Jiang ⋅ Yu Zhao ⋅ Chenyang Lyu ⋅ Tianqi Shi ⋅ Yichao Du ⋅ Feihu Jiang ⋅ Longyue Wang ⋅ Weihua Luo
PreMoE: Proactive Inference for Efficient Mixture-of-Experts
Zehua Pei ⋅ Ying Zhang ⋅ Hui-Ling Zhen ⋅ Tao Yuan ⋅ Xianzhi Yu ⋅ Zhenhua Dong ⋅ Sinno Pan ⋅ Mingxuan Yuan ⋅ Bei Yu
Path-Constrained Mixture-of-Experts
Zijin Gu ⋅ Tatiana Likhomanenko ⋅ Vimal Thilak ⋅ Jason Ramapuram ⋅ Navdeep Jaitly
Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing
Hanchi Sun ⋅ Yixin Liu ⋅ Yonghui Wu ⋅ Lichao Sun
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
Shuibai Zhang ⋅ Xialie Zhuang ⋅ Chihan Cui ⋅ Zhihan Yang ⋅ Fred Peng ⋅ Yanxin Zhang ⋅ Haoyue Bai ⋅ Zack Jia ⋅ Yang Zhou ⋅ Guanhua Chen ⋅ Ming Liu
Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation
Xinyi Ling ⋅ Ye Liu ⋅ Reza Averly ⋅ Xia Ning
TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
Lingjie Chen ⋅ Ruizhong Qiu ⋅ Yuyu Fan ⋅ Yanjun Zhao ⋅ Hanghang Tong
Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
Meihua Dang ⋅ Jiaqi Han ⋅ Minkai Xu ⋅ Kai Xu ⋅ Akash Srivastava ⋅ Stefano Ermon
MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models
Kejing Xia ⋅ Mingzhe Li ⋅ Lixuan Wei ⋅ Zhenbang Du ⋅ Xiangchi Yuan ⋅ Dachuan Shi ⋅ Qirui Jin ⋅ Wenke Lee
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
Yufan Wu ⋅ Yinghui He ⋅ Zhengyi Hu ⋅ Lang Wei ⋅ Ruichen Li ⋅ Qifan Yang ⋅ Ting Zhu
RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback
Qiaoyu Tang ⋅ Hao Xiang ⋅ Le Yu ⋅ Bowen Yu ⋅ Hongyu Lin ⋅ Yaojie Lu ⋅ Ben He ⋅ Xianpei Han ⋅ Le Sun ⋅ Junyang Lin
Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks
Delip Rao ⋅ Chris Callison-Burch
Mitigating LLM biases toward spurious social contexts using direct preference optimization
Hyunji (Alex) Nam ⋅ Dorottya Demszky
WorldPM: Scaling Human Preference Modeling via Real-World Feedback
Binghai Wang ⋅ Runji Lin ⋅ Keming Lu ⋅ Le Yu ⋅ Zhenru Zhang ⋅ Fei Huang ⋅ Chujie Zheng ⋅ Kai Dang ⋅ Yang Fan ⋅ An Yang ⋅ Binyuan Hui ⋅ Dayiheng Liu ⋅ Tao Gui ⋅ Qi Zhang ⋅ Xuanjing Huang ⋅ Yu-Gang Jiang ⋅ Bowen Yu ⋅ Jingren Zhou ⋅ Junyang Lin
Beyond expert users: agents should help users construct preferences, not just elicit them
Irena Saracay ⋅ Ludwig Schmidt ⋅ Carlos Guestrin
LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers
Patrick Sui
Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
Nathaniel Getachew ⋅ Abulhair Saparov
INSIDE the Student’s Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
Rose Niousha ⋅ Minwoo Kang ⋅ Narges Norouzi
HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning
Runchuan Zhu ⋅ Hongbin Lai ⋅ Bowen Jiang ⋅ Junrui Zhang ⋅ Zhangheng LI ⋅ Ostap Kilbasovych Shevtsiv ⋅ Junyuan Hong
Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems
Yufei Xia ⋅ Anjun Gao ⋅ Yueyang Quan ⋅ Zhuqing Liu ⋅ Minghong Fang
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
Eric H Jiang ⋅ Levina Li ⋅ Rui Sun ⋅ Xiao Liang ⋅ Yubei Li ⋅ Yuchen Wu ⋅ Haozheng Luo ⋅ Hengli Li ⋅ Zhi Zhang ⋅ Zhaolu Kang ⋅ Kai-Wei Chang ⋅ Ying Nian Wu
Stabilizing Off-Policy Training for Long-Horizon LLM Agents via Turn-Level Importance Sampling and Clipping-Triggered Normalization
Chenliang Li ⋅ Adel Elmahdy ⋅ Alex J Boyd ⋅ Zhongruo Wang ⋅ Siliang Zeng ⋅ Alfredo Garcia ⋅ Parminder Bhatia ⋅ Taha Kass-Hout ⋅ Cao Xiao ⋅ Mingyi Hong
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Fanchao Chen ⋅ Ziheng Jiang ⋅ Ziyun Wei ⋅ Zheng Zhong ⋅ Du Li ⋅ Chi Zhang ⋅ Haibin L ⋅ Shivaram Venkataraman
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Yaswanth Chittepu ⋅ Ativ Joshi ⋅ Sohini Chintala ⋅ Scott Niekum
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
Haoran Sun ⋅ Yongjian Guo ⋅ Zhong Guan ⋅ shuai di ⋅ Xiaodong Bai ⋅ Jing Long ⋅ Tianyun Zhao ⋅ LUOMINGXI ⋅ Xiaotie Deng ⋅ Xu Chu ⋅ Hongke Zhao ⋅ Likang Wu ⋅ Xi Xiao ⋅ Sheng Wen ⋅ Yicheng Gong ⋅ Xiong J Wu
Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning
Heyang Jiang ⋅ Henry Liu ⋅ Baharan Mirzasoleiman
ExpRL: Exploratory RL for LLM Mid-Training
Violet Xiang ⋅ Amrith Setlur ⋅ Chase Blagden ⋅ Nick Haber ⋅ Aviral Kumar
Diversity or Precision? A Deep Dive into Next Token Prediction
Haoyuan Wu ⋅ Hai Wang ⋅ Wujiajia ⋅ Jinxiang Ou ⋅ keyaowang ⋅ Weile Chen ⋅ Zihao Zheng ⋅ Bei Yu
Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization
Wenxiao Zhao ⋅ Shu Wang ⋅ Ying Nian Wu
Token-Level Control or Just a Better Mean? Isolating the Gains of Adaptive Decoding
Qingyun Li ⋅ Ruoyun Li
Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport
Bohan Zhang ⋅ Anqi Ni ⋅ Yixin Wang ⋅ Paramveer Dhillon
Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics
Changho Shin ⋅ David Alvarez-Melis
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Jiali Cheng ⋅ Hadi Amiri
On the Impossibility of Retrain Equivalence in Machine Unlearning
Jiatong Yu ⋅ Sanjeev Arora ⋅ Yinghui He ⋅ Anirudh Goyal
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
Matteo Boglioni ⋅ Thibault Rousset ⋅ Siva Reddy ⋅ Marius Mosbach ⋅ Verna Dankers
MoRFI: Monotonic Sparse Autoencoder Feature Identification
Dimitris Dimakopoulos ⋅ Shay B Cohen ⋅ Ioannis Konstas
UNMASK Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Chidaksh Ravuru ⋅ Shashank Srivastava
Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts
Ellis Brown ⋅ Jihan Yang ⋅ Shusheng Yang ⋅ Rob Fergus ⋅ Saining Xie
TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language Models
Junyi Zhang ⋅ Jia-Chen Gu ⋅ Wenbo Hu ⋅ Yu Zhou ⋅ Robinson Piramuthu ⋅ Nanyun (Violet) Peng
CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs
Yongkang Du ⋅ Xiaohan Zou ⋅ Minhao Cheng ⋅ Lu Lin
The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems?
Samrajnee Ghosh ⋅ Ashish Goswami ⋅ Naman Agarwal ⋅ Hemanshu Garg ⋅ Chinmay Mittal ⋅ Mausam . ⋅ Parag Singla
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
Tao Zhang ⋅ Xiangtai Li ⋅ Zilong Huang ⋅ Yanwei Li ⋅ Xueqing Deng ⋅ Weixian Lei ⋅ Shihao Chen ⋅ Shunping Ji ⋅ Jiashi Feng
CoVLA: Vision-Language Alignment with Fewer Vision Tokens
Junyong Park ⋅ Yong-Ju Lee ⋅ Daeyoung Kim
EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
Ting-Wei Li ⋅ Sirui Chen ⋅ Jiaru Zou ⋅ Yingbing Huang ⋅ Tianxin Wei ⋅ Jingrui He ⋅ Hanghang Tong
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
Shujin Wu ⋅ Cheng Qian ⋅ Xiusi Chen ⋅ Heng Ji
EvoSkillBank: Hierarchical Skill Self-Evolution and Skill-Bank Governance for Continual Agent Learning
Shuaiyu Zhou ⋅ Jiaying Zhang ⋅ Taoyuan Li ⋅ Lei Shi ⋅ Fengpeng Yue ⋅ Cao Liu ⋅ Ke Zeng
Toward Scalable Terminal Task Synthesis via Skill Graphs
Zhiyuan Fan ⋅ TingHao YU ⋅ Yuanjun Cai ⋅ Jiangtao Guan ⋅ Yun Yang ⋅ Dingxin Hu ⋅ Xing Wu ⋅ Zhuo Han ⋅ feng zhang ⋅ Lilin Wang
Budget-Aware Tool Use Enables Effective Agent Scaling
Kexun Zhang ⋅ Zifeng Wang ⋅ Jin Miao ⋅ I-Hung Hsu ⋅ Jun Yan ⋅ Jiefeng Chen ⋅ Rujun Han ⋅ Fangyuan Xu ⋅ Yanfei Chen ⋅ Ke Jiang ⋅ Samira Daruki ⋅ Yi Liang ⋅ William Yang Wang ⋅ Tomas Pfister ⋅ Chen-Yu Lee
Thought-Level Beam Search for Reasoning
Lijie Yang ⋅ Hongyin Luo ⋅ Jiawei Zhao ⋅ Tri Dao ⋅ Ravi Netravali
TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
Yannis Belkhiter ⋅ Seshu Tirupathi ⋅ Giulio Zizzo ⋅ John Kelleher
HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces
Ishita Kakkar ⋅ Enze Zhang ⋅ Rheeya Uppaal ⋅ Junjie Hu
TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
Sung-Hoon Yoon ⋅ Ruizhi Qian ⋅ Minda Zhao ⋅ Weiyue Li ⋅ Mengyu Wang
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
Devang Kulshreshtha ⋅ Hang Su ⋅ Haibo Jin ⋅ Chinmay Hegde ⋅ Haohan Wang
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
Chenlong Yin ⋅ Runpeng Geng ⋅ Yanting Wang ⋅ Jinyuan Jia
Improved Robustness against Indirect Prompt Injection Can Be Built into LLMs
Mehmet Özdinçer ⋅ Samuel Simko ⋅ Bernhard Schölkopf ⋅ Zhijing Jin
Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense
Zhehao Zhang ⋅ Weijie Xu ⋅ Shixian Cui ⋅ Chandan Reddy
MEMENTO: Teaching LLMs to Manage Their Context
Vasilis Kontonis ⋅ Yuchen Zeng ⋅ Shivam Garg ⋅ Lingjiao Chen ⋅ Hao Tang ⋅ Ziyan Wang ⋅ Ahmed H Awadallah ⋅ Eric Horvitz ⋅ John Langford ⋅ Dimitris Papailiopoulos
What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks
Meera Desai ⋅ Sang Truong ⋅ Hanna Wallach ⋅ Alex Chouldechova ⋅ A. Feder Cooper ⋅ Jean Garcia-Gathright ⋅ Daniel Ho ⋅ Abigail Z Jacobs ⋅ Sanmi Koyejo ⋅ Nicholas Pangakis ⋅ Angelina Wang
Introspective Diffusion Language Models
Yifan Yu ⋅ Yuqing Jian ⋅ Junxiong Wang ⋅ Zhongzhu Zhou ⋅ Donglin Zhuang ⋅ Xinyu Fang ⋅ Xiaoxia Wu ⋅ Qingyang Wu ⋅ Shuaiwen L Song ⋅ Tri Dao ⋅ Ben Athiwaratkun ⋅ James Zou ⋅ Fan Lai ⋅ Chenfeng Xu
Lost in Distraction: LLM Planning Agents Recognize but Fail to Utilize Relevant Information under Context Noise
Weijie LIANG ⋅ Yuanfeng SONG ⋅ Xing Chen ⋅ Caleb C Cao ⋅ Sirui Han ⋅ Yike Guo
Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
TAO JIN ⋅ Phuong Minh Nguyen ⋅ Naoya Inoue
Statistically-Lossless Quantization of Large Language Models
Michael A. Helcig ⋅ Eldar Kurtic ⋅ Dan Alistarh
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
Mengting Ai ⋅ Tianxin Wei ⋅ Sirui Chen ⋅ Jingrui He
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
Haoyang Fang ⋅ Shuai Zhang ⋅ Yifei Ma ⋅ Hengyi Wang ⋅ Cuixiong Hu ⋅ Katrin Kirchhoff ⋅ Bernie Wang ⋅ George Karypis
Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
Qiheng Lu ⋅ Nicholas D Sidiropoulos
Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models
Issa Sugiura ⋅ Keito Sasagawa ⋅ Keisuke Nakao ⋅ Koki Maeda ⋅ Ziqi Yin ⋅ Zhishen Yang ⋅ Shuhei Kurita ⋅ Yusuke Oda ⋅ Ryoko Tokuhisa ⋅ Daisuke Kawahara ⋅ Naoaki Okazaki
Opusanimation: Code-based dynamic chart generation
Bozheng Li ⋅ Miao Yang ⋅ Zhenhan Chen ⋅ Jiawang Cao ⋅ Mushui Liu ⋅ Yi Lu ⋅ Yongliang Wu ⋅ Bin Zhang ⋅ Yangguang Ji ⋅ Licheng Tang ⋅ Jay Wu ⋅ Wenbo Zhu
Co-Director: Agentic Generative Video Storytelling
Yale Song ⋅ Yiwen Song ⋅ Nick Losier ⋅ Nathan Hodson ⋅ Ye Jin ⋅ Rhyard Zhu ⋅ Yan Xu ⋅ Daniel Vlasic ⋅ Carina Claassen ⋅ Jasmine Leon ⋅ Khanh G LeViet ⋅ Zack Chomyn ⋅ Joe Timmons ⋅ Brett Slatkin ⋅ Scott Penberthy ⋅ Tomas Pfister
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs
Xingyu Fu ⋅ Siyi Liu ⋅ Yinuo Xu ⋅ Pan Lu ⋅ Viola (Guangqiuse) Hu ⋅ Tianbo Yang ⋅ Taran Anantasagar ⋅ Christopher Shen ⋅ Yikai Mao ⋅ Yuanzhe Liu ⋅ Keyush Shah ⋅ Chung U Lee ⋅ Yejin Choi ⋅ James Zou ⋅ Dan Roth ⋅ Chris Callison-Burch
Detecting and Suppressing Reward Hacking with Gradient Fingerprints
Songtao Wang ⋅ Quang Hieu Pham ⋅ Fangcong Yin ⋅ Xinpeng Wang ⋅ Jocelyn Qiaochu Chen ⋅ Greg Durrett ⋅ Xi Ye
$\textit{Hidden in the Haystack:}$ Smaller Needles are More Difficult for LLMs to Find
Owen Bianchi ⋅ Mathew J Koretsky ⋅ Tanay Nayak ⋅ Maya Willey ⋅ Chelsea X Alvarado ⋅ Adi Asija ⋅ Nicole Kuznetsov ⋅ Michael Nalls ⋅ Faraz Faghri ⋅ Daniel Khashabi
Voice of Reason: Reinforcement Learning for Spoken Math
Timothée Weisselberger ⋅ Edouard Grave ⋅ Alexandre Défossez
Do We Need Frontier Models to Verify Mathematical Proofs?
Aaditya Naik ⋅ Guruprerana Shabadi ⋅ Rajeev Alur ⋅ Mayur Naik
Ill-Defined Math: Benchmarking LLM Reasoning Beyond Well-Defined Problems
Huaibo Chen ⋅ Yixiao Lin ⋅ Zihan Zhao ⋅ Pengcheng Chen ⋅ Nuohao Liu ⋅ Yue Hu ⋅ Qian Xie ⋅ Qinbo Bai ⋅ Ning Yan ⋅ Masood S. Mortazavi ⋅ KAMAL YOUCEF-TOUMI
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Gabrielle Liu ⋅ Avi Caciularu ⋅ Gal Yona ⋅ Idan Szpektor ⋅ Arman Cohan
GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
Yujing Wang ⋅ Yuanbang Liang ⋅ Yu-Kun Lai ⋅ Hainan Zhang ⋅ Hanqi Yan
Grammatical ``grandmother neurons'' are rare in LLMs
Linyang He ⋅ Nima Mesgarani
Vocabulary embeddings organize linguistic structure early in language model training
Isabel Papadimitriou ⋅ Jacob S Prince
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Nathan Godey ⋅ Yoav Artzi
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs
Nicolas Boizard ⋅ Théo Deschamps-Berger ⋅ Hippolyte Gisserot-Boukhlef ⋅ CELINE HUDELOT ⋅ Pierre Colombo
REFRAMED: Towards Realistic Audio Description Generation for Movies
Igor Sterner ⋅ Mirella Lapata ⋅ Alex Lascarides ⋅ Frank Keller
Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension
Amanda Bertsch ⋅ Luca Soldaini ⋅ Matthew R Gormley ⋅ Graham Neubig ⋅ Hanna Hajishirzi ⋅ Kyle Lo ⋅ Dirk Groeneveld
TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics
Heechan Lee ⋅ Jeonggyu Kang ⋅ Junho Myung ⋅ Jaywoong Jeong ⋅ Juho Kim ⋅ Joseph Seering
MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook
Yi Feng ⋅ Chen Huang ⋅ Zhibo Man ⋅ Ryner Tan ⋅ Long P Hoang ⋅ Shaoyang Xu ⋅ Wenxuan Zhang
CooperBench: Why coding agents cannot be your teammates yet
Arpandeep Khatua ⋅ Hao Zhu ⋅ Peter Tran ⋅ Arya Prabhudesai ⋅ Frederic Sadrieh ⋅ Johann K Lieberwirth ⋅ Xinkai Yu ⋅ Yicheng Fu ⋅ Michael J Ryan ⋅ Jiaxin Pei ⋅ Diyi Yang
When Does Personality Composition Matter for Multi-Agent LLM Teams?
Aryan Keluskar ⋅ Amrita (Amy) Bhattacharjee ⋅ Huan Liu
High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination
Sahaj Singh Maini ⋅ Robert L Goldstone ⋅ Zoran Tiganj
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Minh Khoi Ho ⋅ Zihao Zhu ⋅ Runchuan Zhu ⋅ Levina Li ⋅ Zhiwen Fan ⋅ Zhangyang Wang ⋅ Junyuan Hong
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Addison J. Wu ⋅ Ryan Liu ⋅ Stella Li ⋅ Yulia Tsvetkov ⋅ Thomas Griffiths
“I Didn’t Make the Micro Decisions”: Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration
Eunsu Kim ⋅ Jessica R Mindel ⋅ Kyungjin Kim ⋅ Sherry Wu
CCBench: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries
Vasudha Varadarajan ⋅ Akhila Yerukola ⋅ Mona Diab ⋅ Maarten Sap
In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores
Zeyu Tang ⋅ Sang Truong ⋅ Deonna Owens ⋅ Shreyas Sharma ⋅ Yibo Jacky Zhang ⋅ Brando Miranda ⋅ Sanmi Koyejo
Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths
Xuezhe (Max) Ma ⋅ Shicheng Wen ⋅ Linghao Jin ⋅ Bilge Acun ⋅ Ruihang Lai ⋅ Bohan Hou ⋅ Will Lin ⋅ Hao Zhang ⋅ Songlin Yang ⋅ Ryan Lee ⋅ Mengxi Wu ⋅ Jonathan May ⋅ Luke Zettlemoyer ⋅ Carole-Jean Wu
RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
Ming Zhu ⋅ Juntao Tan ⋅ Rithesh Murthy ⋅ Jielin Qiu ⋅ Liangwei Yang ⋅ Wenting Zhao ⋅ Silvio Savarese ⋅ Shelby Heinecke ⋅ Huan Wang
ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
Michael Gu ⋅ Rohan Kadekodi ⋅ Sahi Chitrapu ⋅ Aradhya Agrawal ⋅ Camille Sawa ⋅ Hoang D Nguyen ⋅ Keisuke Kamahori ⋅ Yiyu Liu ⋅ Baris Kasikci
MolDesignBench: Evaluating LLM-based Agent for Scenario- grounded Molecular Design
Yongjun Jeong ⋅ Hanbum Ko ⋅ Ye R Kim ⋅ Chanhui Lee ⋅ Rodrigo Hormazabal ⋅ Jaewan Lee ⋅ Sehui Han ⋅ Sungbin Lim ⋅ Sungwoong Kim
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
Yanqiao Zhu ⋅ Jingru Gan ⋅ Xiaoqi Sun ⋅ Fang Sun ⋅ Yidan Shi ⋅ Md Mofijul Islam ⋅ Chao Shang ⋅ Wenhao Gao ⋅ Connor W Coley ⋅ Yizhou Sun ⋅ Wei Wang
Can Coding Agents Reproduce Findings in Computational Materials Science?
Ziyang Huang ⋅ Yi Cao ⋅ Ali K Shargh ⋅ Jing Luo ⋅ Ruidong Mei ⋅ Mohd Zaki ⋅ Zhan Liu ⋅ Wyatt Bunstine ⋅ William Jurayj ⋅ Somdatta Goswami ⋅ Tyrel McQueen ⋅ Michael Shields ⋅ Jaafar El-Awady ⋅ Paulette Clancy ⋅ Benjamin Van Durme ⋅ Nicholas Andrews ⋅ William Walden ⋅ Daniel Khashabi
Stargazer: A Scalable Model-fitting Benchmark Environment for AI Agents under Astrophysical Constraints
Xinge Liu ⋅ Terry J Zhang ⋅ Bernhard Schölkopf ⋅ Zhijing Jin ⋅ Kristen Menou
Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
Lawrence Keunho Jang ⋅ Jing Yu Koh ⋅ Daniel Fried ⋅ Ruslan Salakhutdinov
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking
Jiwan Chung ⋅ JiHyuk Byun ⋅ Vibhav Vineet ⋅ Seon Joo Kim
Agent Alpha: Unifying Generation, Exploration and Evaluation via Tree Search for Computer-Use Solution Discovery
Sizhe Tang ⋅ Rongqian Chen ⋅ Tian Lan
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Teng Xiao ⋅ Yige Yuan ⋅ Hamish Ivison ⋅ Huaisheng Zhu ⋅ Faeze Brahman ⋅ Nathan Lambert ⋅ Pradeep Dasigi ⋅ Noah Smith ⋅ Hanna Hajishirzi
MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution
Prasoon Dev ⋅ Anirudh Sankar ⋅ Vasudeva Varma
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Sohyun An ⋅ Shuibenyang Yuan ⋅ Hayeon Lee ⋅ Cho-Jui Hsieh ⋅ Alexander Min
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
yuwen du ⋅ Rui Ye ⋅ Shuo Tang ⋅ Xinyu Zhu ⋅ Yijun Lu ⋅ Yuzhu Cai ⋅ Siheng Chen
GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
Shuwen Xu ⋅ Yao Xu ⋅ Jiaxiang Liu ⋅ Chenhao Yuan ⋅ Wenshuo Peng ⋅ Jun Zhao ⋅ Kang Liu
Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge
Shashank Kirtania ⋅ Param Biyani ⋅ Priyanshu Gupta ⋅ Yasharth Bajpai ⋅ Roshni Iyer ⋅ Sumit Gulwani ⋅ Gustavo Soares
TierMem: Balancing Compressed Memory and Raw Evidence for Long-Horizon Agent Memory
Qiming Zhu ⋅ Shunian Chen ⋅ Rui Yu ⋅ Zhehao Wu ⋅ Benyou Wang
Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression
Lingjie Zeng ⋅ Xiaofan Chen ⋅ Yanbo Wang ⋅ Xiuying Chen
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Keshav Ramji ⋅ Tahira Naseem ⋅ Ramón Fernandez Astudillo
Fractured Chain-of-Thought Reasoning
Baohao Liao ⋅ Hanze Dong ⋅ Yuhui Xu ⋅ Doyen Sahoo ⋅ Christof Monz ⋅ Junnan Li ⋅ Caiming Xiong
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road
Hieu N. Nguyen ⋅ Parshin Shojaee ⋅ Nguyen M Phuc ⋅ Nan Zhang ⋅ Chandan Reddy ⋅ Khoa D Doan ⋅ Rui Zhang
Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
Cai Zhou ⋅ Zekai Wang ⋅ Menghua Wu ⋅ Qianyu Zhu ⋅ Flora C Shi ⋅ Chenyu Wang ⋅ Ashia C Wilson ⋅ Tommi Jaakkola ⋅ Stephen Bates
DepthSSD: Rethinking Residual Connections via State Space Models on the Depth Axis
Zhengqing Yuan ⋅ Xiaoyu Ma ⋅ Yunhong He ⋅ Zhengtao Yao ⋅ Lichao Sun ⋅ Yanfang (Fanny) Ye
Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models
Jean de Dieu Nyandwi ⋅ Leena Mathur ⋅ Yonatan Bisk ⋅ Graham Neubig
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
Fnu pramono ⋅ John Cai ⋅ Sourabh Kulkarni
Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models
Bhuvan Koduru ⋅ Dareen Alharthi ⋅ Rita Singh ⋅ Bhiksha Raj
OpenStamp: A Watermark for Open-Source Language Models
Miroojin Bakshi ⋅ Saksham Rastogi ⋅ Danish Pruthi
Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs
Nghia T Le ⋅ Alan Ritter ⋅ Kartik Goyal
Human vs Machine Translation Detection: A Cross-Model, Cross-Domain, and Low-Resource Analysis
Yabsera Yemanberhan ⋅ Prasenjit Mitra ⋅ Roald Eiselen
We Hebben Een Serieus Translatie: Modeling Intercomprehension as Probabilistic Inference
Thomas H Clark ⋅ Roger P Levy ⋅ Edward Gibson
PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts
Juliette Woodrow ⋅ Christopher J Piech
Risk Profiling and Modulation for LLMs
Yikai Wang ⋅ Guanting Chen ⋅ Xiaocheng Li
Understanding In-context Learning of Addition via Activation Subspaces
Xinyan Hu ⋅ Kayo Yin ⋅ Michael I Jordan ⋅ Jacob Steinhardt ⋅ Lijie Chen
MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
Yu Li ⋅ Binxu Li ⋅ Tian Lan
Reasoning Models Know What’s Important, and Encode It in Their Activations
Yaniv Nikankin ⋅ Martin Tutek ⋅ Tomer Ashuach ⋅ Jonathan S Rosenfeld ⋅ Yonatan Belinkov
Component and Dimension Sparsity in Transformer Refusal Mechanisms
Vincent Siu ⋅ Glenn Grant-Richards ⋅ Vlad Pavlovich ⋅ Yizhou Sun ⋅ Dawn Song ⋅ Chenguang Wang
Prism-$\Delta$: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Yuyao Ge ⋅ Shenghua Liu ⋅ Yiwei Wang ⋅ Baolong Bi ⋅ Lingrui Mei ⋅ Jiayu Yao ⋅ Tianyu Liu ⋅ Jiafeng Guo ⋅ Xueqi Cheng
Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
Yancheng Huang ⋅ Changsheng Wang ⋅ Chongyu Fan ⋅ Yicheng Lang ⋅ Bingqi Shang ⋅ Yang Zhang ⋅ Mingyi Hong ⋅ Qing Qu ⋅ Alvaro Velasquez ⋅ Sijia Liu
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
Amir Ziashahabi ⋅ Hossein Entezari Zarch ⋅ Lei Gao ⋅ Murali Annavaram ⋅ Salman Avestimehr
SPEED: Specialized Position Experts for Efficient Speculative Decoding
Langlin Huang ⋅ Chengsong Huang ⋅ Jixuan Leng ⋅ Di Huang ⋅ Jiaxin Huang
Go to Event Page
Social

Operational Safety for Language Model Agents

Raphael Kalandadze ⋅ Tatia Tsmindashvili
6:30 PM - 8:00 PM

As language model agents gain access to tools, external services, persistent context, and increasingly autonomous workflows, safety depends not only on model behavior but also on the systems in which agents operate. This social will bring together researchers and practitioners working on agent safety, language model evaluation, security, monitoring, and deployment to discuss operational approaches for safely running increasingly capable agents. Topics may include sandboxing, permissions and access control, monitoring of agent actions, human approval mechanisms, long-horizon execution, recovery from unexpected behavior, incident detection, and post-deployment evaluation. Recent cases - including OpenAI models escaping intended isolation and reaching Hugging Face systems, Claude models accessing real third-party infrastructure during evaluations, and Hacktron using Claude to help develop an exploit chain that reached OpenAI internal repositories - highlight the growing importance of operational controls around capable agents. The event will combine short invited talks with moderated and audience discussion, with the goal of connecting research on model behavior with practical questions around deployment and oversight.

... more