Streaming Hand-offs Make Multi-Agent Sharper, ZipSplat Splats With 1/6 the Gaussians

Featured

• MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation score 9
  入选 HF Daily Papers; HF 热度: 16 upvotes (+3); 有代码实现; 关键词(5): production, throughput, agentic, reasoning, vision-language
• M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks score 10
  入选 HF Daily Papers; HF 热度: 26 upvotes (+4); 有代码实现; 关键词(1): reasoning
• Streaming Communication in Multi-Agent Reasoning score 10
  入选 HF Daily Papers; HF 热度: 28 upvotes (+4); 有代码实现; 关键词(3): scaling, latency, reasoning
• Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning score 9
  入选 HF Daily Papers; HF 热度: 37 upvotes (+4); 有代码实现
• Self-Distilled Policy Gradient score 10
  入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 有代码实现; 关键词(1): distillation
• ZipSplat: Fewer Gaussians, Better Splats score 10
  入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 有代码实现; 关键词(1): lightweight
• AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks? score 10
  入选 HF Daily Papers; HF 热度: 27 upvotes (+4); 有代码实现; 关键词(1): open-source
• Stateful Visual Encoders for Vision-Language Models score 8
  入选 HF Daily Papers; HF 热度: 6 upvotes (+2); 有代码实现; 关键词(3): finetuning, agentic, vision-language
• GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards score 7
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 有代码实现; 关键词(2): GRPO, reasoning
• DAR: Deontic Reasoning with Agentic Harnesses score 7
  入选 HF Daily Papers; HF 热度: 4 upvotes (+1); 有代码实现; 关键词(2): agentic, reasoning

Also Worth Noting

• MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation score 5
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 关键词(3): scaling, compression, serving
• Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game score 4
  入选 HF Daily Papers; 关键词(1): instruction tuning
• Impostor: An Agent-Curated Benchmark for Realistic AIGC Manipulation Localization score 4
  机构: Tsinghua; 关键词(1): vision-language
• Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning score 3
  入选 HF Daily Papers