Skip to yearly menu bar Skip to main content


Workshop Fri, Oct 9, 2026 • 8:30 AM – 6:00 PM PDT Franciscan A&B / Ballroom Level

COLM Workshop on Context Beyond the Window: Persistent Knowledge in Language Models

Dane Malenfant ⋅ Siddarth Venkatraman ⋅ Emiliano Penaloza ⋅ Benjamin Thérien ⋅ Sharut Gupta ⋅ Thomas Jiralerspong ⋅ Alicia Sun
Project Page

Abstract

Chat is not available.

Schedule

Time zone: Conference local time zone
9:00 AM
Welcome Remarks
10:40 AM
Express Language Modeling
Albert Gong ⋅ Annabelle M Carrell ⋅ Raaz Dwivedi ⋅ Lester Mackey
10:55 AM
ORCA-bench: How Ready Are Language Model Agents for Oncall?
Kyuseong Choi ⋅ Albert Gong ⋅ Abhineet Agarwal ⋅ Anish Agarwal ⋅ Raaz Dwivedi
12:10 PM
Lunch
2:50 PM
Neural Garbage Collection: Learning to Forget while Learning to Reason
Michael Y Li ⋅ Jubayer I Hamid ⋅ Emily Fox ⋅ Noah Goodman
H$^{2}$MT: Semantic Hierarchy-Aware Context-Time Memory for Beyond-Window Language Modeling
Maryam Haghifam ⋅ Zifan He ⋅ Jason Cong ⋅ Yizhou Sun
Position: Task-Triggered Memory Evolution Can Destroy Memories with High Long-Term Utility
Afrin Dange ⋅ Rahul Rahaman ⋅ Deepak Gupta ⋅ Sankalp Dayal
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Jeonghye Kim ⋅ Xufang Luo ⋅ Minbeom Kim ⋅ Sangmook Lee ⋅ Dohyung Kim ⋅ Jiwon Jeon ⋅ Dongsheng Li ⋅ Yuqing Yang
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur ⋅ Narutatsu Ri ⋅ Yinghui He ⋅ Liam H Fowl ⋅ Sanjeev Arora
Beyond Merging and Dropping: Adaptive Online KV Cache Compaction
Izaaz Inhar ⋅ Faeyza R Ardi ⋅ Muhammad R Qorib ⋅ Alham Aji ⋅ Farid Adilazuarda
Temporal Conflict Resolution in Video Large Language Models
Evan Do ⋅ Samuel Maddux ⋅ Steven Ngo ⋅ Ahaan Narang ⋅ Shivank Garg ⋅ Kevin Zhu ⋅ Vasu Sharma
Borrow-Use-Return: Lossless and Efficient Memory Management for Deep Research Agents
Minheng Wang ⋅ Rulin Shao ⋅ Luke Zettlemoyer ⋅ Pang Wei Koh
TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling
Youngjun Son ⋅ Jongyeon Park ⋅ Jaejin Lee
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Shashwat Goel ⋅ Nikhil Chandak ⋅ Arvindh Arun ⋅ Ameya Prabhu ⋅ Steffen Staab ⋅ Moritz Hardt ⋅ Maksym Andriushchenko ⋅ Jonas Geiping
Neural Garbage Collection: Learning to Forget while Learning to Reason
Michael Y Li ⋅ Jubayer I Hamid ⋅ Emily Fox ⋅ Noah Goodman
AutoIndex: Learning Representation Programs for Retrieval
Sam ONuallain ⋅ Nithya Rajkumar ⋅ Hanna Jiang ⋅ Ramya Narayanasamy ⋅ Andrew Drozdov ⋅ Shreyas Chaudhari
The Future of Facts: Tracing the Factual Generation-Verification Gap
Tim R Davidson ⋅ Anja Surina ⋅ Caglar Gulcehre
Decluttering Context with Query-Aware Snippets
Pallavi Koppol ⋅ Tommy Xiang ⋅ Jialu Liu ⋅ Andrew Drozdov ⋅ Michael Bendersky
ORCA-bench: How Ready Are Language Model Agents for Oncall?
Albert Gong ⋅ Kyuseong Choi ⋅ Abhineet Agarwal ⋅ Anish Agarwal ⋅ Raaz Dwivedi
Speculative Self-Distillation enables Efficient Knowledge Internalization
Shayan Talaei ⋅ Agam Bhatia ⋅ Arshia Soltani Moakhar ⋅ Jonas Hübotter ⋅ Amin Saberi ⋅ Azalia Mirhoseini
Chain-of-Experience for Continual LLM Improvement
Haoqin Tu ⋅ Yunhao Fang ⋅ Yizhong Wang ⋅ Cihang Xie ⋅ Shen Yan
Merging Adapted Models via Data-Free Covariance Estimation
Marawan Gamal ⋅ Derek Tam ⋅ Pascal J Notsawo ⋅ Colin Raffel ⋅ Guillaume Rabusseau
Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA
Nikhil Reddy Pottanigari ⋅ Sepideh Kharaghani ⋅ Saverio Vadacchino ⋅ Alejandro Posada ⋅ Ying Zhang
Natively Unlearnable Large Language Models
Gaurav R Ghosal ⋅ Pratyush Maini ⋅ Aditi Raghunathan
Iterative Memory Reconstruction for Long-Horizon Conversational Agents
Nitin Vetcha ⋅ Pragnya Yadav ⋅ Hrishikesh Vinay ⋅ Banaj Mahajan ⋅ Ahan Phatak ⋅ Tejas K
Memorilla: Latent Semantic Memory for LLMs
Adibvafa Fallahpour ⋅ Parsa Idehpour ⋅ Vignesh Kothapalli ⋅ Nikita Mounier ⋅ Shirley Wu ⋅ Shayan Pardis ⋅ Jure Leskovec
When Worlds Collide: Mediating Conflicts Between Parametric and External Knowledge in RAG
Tessa E Andersen ⋅ Drew Galbraith ⋅ Jay Orten ⋅ Nancy Fulda
Context-Aware RL for Agentic and Multimodal LLMs
Peiyang Xu ⋅ Bangzheng Li ⋅ Sijia Liu ⋅ Karthik Narasimhan ⋅ Pramod Viswanath ⋅ Prateek Mittal ⋅ Xingyu Fu
Knowledge-Centric Self-Improvement
Xuefei Wang ⋅ Lauren Hyoseo Yoon ⋅ Chengrui Qu ⋅ Amanda Z Wang ⋅ Atharva Sehgal ⋅ Eric Mazumdar ⋅ Yisong Yue
Parametric Skills
Xuan Zhao ⋅ Haonan He ⋅ Qingyu Yang ⋅ Minglei Li ⋅ Jingqi Ye ⋅ Zelin Tan ⋅ Bo Wan ⋅ Peng Ye
Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction
Mohammad Saifullah ⋅ Thomas Kornmaier ⋅ Taaha Kazi ⋅ Vasu Sharma ⋅ Aditya S Kanade
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
Mengmeng Ji ⋅ Ravi S Raju ⋅ Jonathan L Li ⋅ Chen Wu
Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
Xu Pan ⋅ Ely Hahami ⋅ Jingxuan Fan ⋅ Ziqian Xie ⋅ Haim Sompolinsky
The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
Mikhail L Arbuzov ⋅ Sisong Bei ⋅ Ziwei Dong ⋅ Dmitri Kalaev ⋅ Alexey Shvets
ContextRotBench: Measuring Long-Horizon Degradation in Coding Agents
Dylan Lu ⋅ Surya Gunukula ⋅ Saaket Agashe ⋅ Kexun Zhang ⋅ Eric Wang
MemFail: Stress-Testing Failure Modes of LLM Memory Systems
Ishir Garg ⋅ Neel Kolhe ⋅ Dawn Song ⋅ Xuandong Zhao
Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
Shelly Bensal ⋅ Axel Magnuson ⋅ Aparna Balagopalan ⋅ Daniel M Bikel
DR-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
Yi Lu ⋅ Zhuofeng Li ⋅ Ping Nie ⋅ Haoxiang Zhang ⋅ Yuyu Zhang ⋅ Kai Zou ⋅ Wenhu Chen ⋅ Jimmy Lin ⋅ Dongfu Jiang ⋅ Yu Zhang
Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules
Karim Galliamov ⋅ Rochelle Choenni ⋅ Ivan Titov
MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects
Jason Luo ⋅ Saibilila Abudukelimu ⋅ Judy Song ⋅ Andrew Feng ⋅ Shivank Garg ⋅ Vasu Sharma ⋅ Kevin Zhu
Express Language Modeling
Albert Gong ⋅ Annabelle M Carrell ⋅ Raaz Dwivedi ⋅ Lester Mackey
Gating Mechanisms for Continually Adapting Compressed KV Memory
Quang M Nguyen ⋅ Phudish Prateepamornkul ⋅ Tri Q Vo ⋅ Muhammad R Qorib ⋅ Alham Aji ⋅ Farid Adilazuarda
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Rishabh Tiwari ⋅ Kusha Sareen ⋅ Lakshya A Agrawal ⋅ Joseph E Gonzalez ⋅ Matei Zaharia ⋅ Kurt Keutzer ⋅ Inderjit S Dhillon ⋅ Rishabh Agarwal ⋅ Fnu Devvrit