ICML 2025PastLarge language models
ICML 2025 Workshop on Long-Context Foundation Models
LCFM 2025
- Submission deadline
- May 29, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (35)
Fetched from OpenReview (v2) on 2026-06-10.
Accelerated Inference with Long-Sequence Transformers on CPUs
ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction
BSA: Ball Sparse Attention for Large-scale Geometries
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
Dynamic Causal‐Graph Memory: Structured Retrieval for Million–Token Reasoning
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
Enhancing Retrieval-Augmented Generation with Dehallucinating Parallel Context Extension
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Foreign Sparse Attention: Effective Distillation into Sparse Attention
GSM-Infinite: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
How Much Context Does Natural Language Actually Require? An Analysis Using LLMs as Statistical Oracles
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
Jailbreaking in the Haystack
Kinetics: Rethinking Test-Time Scaling Laws
Language Modeling with Learned Meta-Tokens
Looking beyond the next token
Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement
MatMuls are Enough for Efficient and Performant Linear-Time Attention
MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling
NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
OracleKV: Oracle Guidance for Question-Independent KV Cache Eviction
Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
pLSTM: parallelizable Linear Source Transition Mark networks
Say as It Is: Verbatim Fidelity Evaluation of Long-Context Language Model
Scalable LLM Math Reasoning Acceleration with Low-rank Distillation
Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
Simple, Scalable Reasoning via Iterated Summarization
SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling
Thinformer: Guaranteed Attention Approximation via Low-Rank Thinning
Towards Understanding Self-Pretraining for Sequence Classification
Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length