arXiv AI
Jun 9
End-to-End Context Compression at Scale
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
Linear-Time Context Compression with State-Space Encoding
Related stories
Hugging Face Trending Papers
Jun 8
End-to-End Context Compression at Scale
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.
arXiv Computation and Language
Sep 14
SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
arXiv:2608.00311v2 Announce Type: replace Abstract: Long-context inference with large language models (LLMs) is costly: self-attention during prefill scales quadratically with sequence length, and th...
arXiv Computation and Language
Sep 23
Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
arXiv Machine Learning
Jul 14
Controllably Efficient Language Models
arXiv:2511. 05313v2 Announce Type: replace Abstract: The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and linear attention.
arXiv AI
Jul 31
ARC-Encoder: learning compressed text representations for large language models
arXiv:2510. 20535v2 Announce Type: replace-cross Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs.
arXiv Computation and Language
Oct 16
From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models
The paper surveys memory‑centric compression techniques for large language models, framing long‑context handling as a memory‑management problem. It distinguishes compute‑active memory from compute‑inactive memory, and models operations such as writing, offloading, recall, and forgetting as state transitions within an information lifecycle. The authors propose a unified cost model and argue that future research should focus on dynamic, lifecycle‑aware memory management rather than static compression.
arXiv AI
Jun 24
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.
arXiv Machine Learning
Aug 4
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
arXiv:2608. 02032v1 Announce Type: new Abstract: Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures.
Hugging Face Trending Papers
Jun 23
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
Hugging Face Trending Papers
Aug 3
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attention memories, while recurrent models such as state space models (SSMs) and linear attention maintain compact recurrent states.
arXiv Machine Learning
Sep 21
Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.