会员服务
Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
Arxiv
0+阅读 · 3月17日
Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning
Arxiv
0+阅读 · 3月16日
ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
Arxiv
0+阅读 · 3月8日
SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference
Arxiv
0+阅读 · 3月5日
Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
Arxiv
0+阅读 · 2月20日
Ouroboros: Wafer-Scale SRAM CIM with Token-Grained Pipelining for Large Language Model Inference
Arxiv
0+阅读 · 3月3日
Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
Arxiv
0+阅读 · 3月11日
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
Arxiv
0+阅读 · 2月20日
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
Arxiv
0+阅读 · 2月13日
Challenges and Research Directions for Large Language Model Inference Hardware
Arxiv
0+阅读 · 2月6日
LLM-CoOpt: A Co-Design and Optimization Framework for Efficient LLM Inference on Heterogeneous Platforms
Arxiv
0+阅读 · 2月10日
Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms
Arxiv
0+阅读 · 2月5日
RAudit: A Blind Auditing Protocol for Large Language Model Reasoning
Arxiv
0+阅读 · 1月30日
Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
Arxiv
0+阅读 · 2月3日
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
Arxiv
0+阅读 · 2月3日
参考链接
微信扫码咨询专知VIP会员
Top