Recalibrating the Critic Lifts Reasoning Models 18 Points

Featured

• CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation score 10
  入选 HF Daily Papers; HF 热度: 79 upvotes (+4); 有代码实现; 关键词(2): lightweight, MoE
• AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model score 10
  入选 HF Daily Papers; HF 热度: 35 upvotes (+4); 有代码实现; 关键词(2): compression, distillation
• TEMPO: Scaling Test-time Training for Large Reasoning Models score 10
  入选 HF Daily Papers; HF 热度: 28 upvotes (+4); 有代码实现; 关键词(2): scaling, reasoning
• ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning score 10
  入选 HF Daily Papers; HF 热度: 23 upvotes (+4); 有代码实现; 关键词(5): scaling, latency, edge, fine-tuning, pretraining
• Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language score 9
  入选 HF Daily Papers; HF 热度: 16 upvotes (+3); 有代码实现; 关键词(1): agentic
• Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items score 8
  入选 HF Daily Papers; HF 热度: 226 upvotes (+4); 关键词(4): deployment, serving, latency, real-time
• SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing score 8
  入选 HF Daily Papers; HF 热度: 41 upvotes (+4); 关键词(2): pretraining, reasoning
• What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search score 7
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 有代码实现; 关键词(1): agentic
• CityRAG: Stepping Into a City via Spatially-Grounded Video Generation score 7
  入选 HF Daily Papers; HF 热度: 11 upvotes (+3); 关键词(1): robotics
• Micro Language Models Enable Instant Responses score 6
  入选 HF Daily Papers; 有代码实现; 关键词(2): latency, edge

Also Worth Noting

• Evaluation-driven Scaling for Scientific Discovery score 5
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 关键词(1): scaling
• STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming score 4
  关键词(1): jailbreak; 顶会接收: ACL
• Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection score 4
  关键词(1): reasoning; 顶会接收: ACL
• Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors score 4
  关键词(1): pre-training; 顶会接收: ICLR
• STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation score 4
  关键词(3): fine-tuning, MoE, reasoning; 顶会接收: ACL
• RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora score 4
  关键词(3): deployment, retrieval-augmented, RAG; 顶会接收: ACL
• SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization score 4
  关键词(1): distillation; 顶会接收: ACL
• Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images score 4
  关键词(1): synthetic data; 顶会接收: CVPR
• Explicit Trait Inference for Multi-Agent Coordination score 4
  关键词(1): lightweight; 顶会接收: ACL
• Are Large Language Models Economically Viable for Industry Deployment? score 4
  关键词(6): scaling, compression, quantization, deployment, latency; 顶会接收: ACL
• DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing score 4
  关键词(1): compression; 顶会接收: ACL
• Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval score 4
  关键词(1): lightweight; 顶会接收: CVPR
• GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models score 4
  关键词(6): scaling, lightweight, pruning, latency, fine-tuning; 顶会接收: ACL