-
AI for Auto-Research: Roadmap & User Guide
score 10
入选 HF Daily Papers; HF 热度: 59 upvotes (+4); 有代码实现; 关键词(2): deployment, coding
-
OProver: A Unified Framework for Agentic Formal Theorem Proving
score 10
入选 HF Daily Papers; HF 热度: 30 upvotes (+4); 有代码实现; 关键词(3): post-training, pretraining, agentic
-
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
score 9
入选 HF Daily Papers; HF 热度: 49 upvotes (+4); 有代码实现
-
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
score 9
入选 HF Daily Papers; HF 热度: 11 upvotes (+3); 有代码实现; 关键词(1): serving
-
NGM: A Plug-and-Play Training-Free Memory Module for LLMs
score 8
入选 HF Daily Papers; HF 热度: 8 upvotes (+2); 有代码实现; 关键词(2): MoE, code generation
-
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
score 8
入选 HF Daily Papers; HF 热度: 7 upvotes (+2); 有代码实现; 关键词(4): agentic, tool use, coding, reasoning
-
A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
score 7
入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 有代码实现; 关键词(2): scaling, reasoning
-
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
score 6
入选 HF Daily Papers; HF 热度: 5 upvotes (+2); 关键词(3): distillation, fine-tuning, reasoning
-
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
score 7
入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 有代码实现; 关键词(4): production, agentic, coding, open-source
-
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
score 6
入选 HF Daily Papers; 有代码实现; 关键词(4): quantization, deployment, serving, post-training