KV-cache

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

09:16

2026-06-15

discuss.huggingface.co

large-language-models

[Dataset] Efficient LLM papers (quantization, LoRA, MoE, FlashAttention) from arXiv + Semantic Scholar — 1,734 records, quality-scored, JSONL

A new dataset, fineset-io/efficient-llm-papers, compiles 1,734 records of arXiv and Semantic Scholar papers on efficient LLM techniques like quantization, LoRA, MoE, and FlashAttention, each quality-s…

04:00

2026-06-03

arxiv.org

machine-learning

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

Researchers have developed AURA-Mem, a memory system for robot policies that maintains a constant 4,224-byte inference state regardless of episode length, compared to a KV-cache that grows 6,061 times…

// co-occurs with top 8 entities

AURA-Mem 1 OpenVLA-OFT 1 LIBERO-Long 1 arXiv 1 Semantic Scholar 1 fineset-io/efficient-llm-papers 1 LoRA 1 FlashAttention 1

// topics top 6 topics

machine learning 2 ai research 2 robotics 1 artificial intelligence 1 neural networks 1 large language models 1