Retrofitting Unbounded Context onto Stock Language Models
cs.CL, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/mark-oskin/unbounded-attention
Terminology
Sources
- Star Attention: Efficient LLM Inference over Long Sequences
- Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
- BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models
- Training-Free Long-Context Scaling of Large Language Models
- Why Does the Effective Context Length of LLMs Fall Short?
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
- TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
- Round and Round We Go! What makes Rotary Positional Encodings useful?
- Why do LLMs attend to the first token?
- Transactional Attention: Semantic Sponsorship for KV-Cache Retention
- Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Unlimiformer: Long-Range Transformers with Unlimited Length Input
- Birth of a Transformer: A Memory Viewpoint
- Improving language models by retrieving from trillions of tokens
- SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
- Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
- Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data