arXiv Machine Learning
TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 3
Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning
arXiv:2607. 01241v1 Announce Type: cross Abstract: Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic dependencies and global semantic relations.
arXiv AI
Jun 15
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
arXiv:2505. 23277v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts.
arXiv Machine Learning
1d ago
CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
CommunityKV is a new framework that treats sparse attention as a community detection problem, building a token graph from $QK^T$ scores and partitioning it into semantically coherent communities. It updates token communities in constant time during streaming decoding, avoiding costly global re‑partitioning. Experiments on Qwen3 and Llama‑3.1 show that CommunityKV can increase end‑to‑end generation throughput by up to 1.25×, and with query‑group graph aggregation up to 1.71×, while maintaining comparable accuracy.
arXiv Computation and Language
Sep 24
EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering
arXiv:2603.09222v2 Announce Type: replace Abstract: Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved context...
arXiv AI
Jul 21
SALT: Salience-Aware Lexical Trie for Long-Context Compression
arXiv:2607. 17486v1 Announce Type: cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems.
arXiv AI
Jul 7
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.