会员服务
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Arxiv
0+阅读 · 6月7日
ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs
Arxiv
0+阅读 · 2月19日
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
Arxiv
0+阅读 · 5月25日
Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
Arxiv
0+阅读 · 4月20日
When Contextual Inference Fails: Cancelability in Interactive Instruction Following
Arxiv
0+阅读 · 3月20日
Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
Arxiv
0+阅读 · 3月10日
Contextual Safety Reasoning and Grounding for Open-World Robots
Arxiv
0+阅读 · 2月23日
The Limits of Long-Context Reasoning in Automated Bug Fixing
Arxiv
0+阅读 · 3月6日
Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning
Arxiv
0+阅读 · 2月19日
The Limits of Long-Context Reasoning in Automated Bug Fixing
Arxiv
0+阅读 · 2月17日
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
Arxiv
0+阅读 · 2月9日
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
Arxiv
0+阅读 · 2月11日
RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
Arxiv
0+阅读 · 2月5日
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
Arxiv
0+阅读 · 2月5日
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
Arxiv
0+阅读 · 2月3日
参考链接
微信扫码咨询专知VIP会员
Top