Arbor科研增益2.5倍，50环境抵300个

重点关注

• Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application score 8
  入选 HF Daily Papers；HF 热度: 58 upvotes (+4)；关键词(2): scaling, agentic
• InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning score 8
  入选 HF Daily Papers；HF 热度: 20 upvotes (+4)；关键词(7): distillation, fine-tuning, pretraining, agentic, tool use
• ICA Lens: Interpreting Language Models Without Training Another Dictionary score 8
  入选 HF Daily Papers；HF 热度: 15 upvotes (+3)；有代码实现
• Toward Generalist Autonomous Research via Hypothesis-Tree Refinement score 9
  入选 HF Daily Papers；HF 热度: 102 upvotes (+4)；有代码实现
• World Model Self-Distillation: Training World Models to Solve General Tasks score 8
  入选 HF Daily Papers；HF 热度: 8 upvotes (+2)；有代码实现；关键词(5): distillation, fine-tuning, reasoning, vision-language, robotics
• Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization score 6
  入选 HF Daily Papers；HF 热度: 7 upvotes (+2)；关键词(2): scaling, reasoning

也值得关注

• Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay score 5
  入选 HF Daily Papers；HF 热度: 2 upvotes (+1)；关键词(2): fine-tuning, instruction tuning
• Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling score 7
  入选 HF Daily Papers；HF 热度: 19 upvotes (+3)；关键词(5): throughput, post-training, agentic, code generation, reasoning
• Information-Theoretic Decomposition for Multimodal Interaction Learning score 4
  关键词(1): fine-tuning；顶会接收: CVPR
• Automated Creativity Evaluation of Language Models Across Open-Ended Tasks score 4
  关键词(1): reasoning；顶会接收: ACL
• Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning score 4
  关键词(2): compression, pruning；顶会接收: ICML
• When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models score 4
  关键词(2): vision-language, embodied；顶会接收: ACL
• Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models score 4
  关键词(4): fine-tuning, post-training, coding, reasoning；顶会接收: ACL
• Context-Driven Incremental Compression for Multi-Turn Dialogue Generation score 4
  关键词(3): lightweight, compression, latency；顶会接收: ICML
• On the Limits of LLM-as-Judge for Scientific Novelty Assessment score 4
  入选 HF Daily Papers；HF 热度: 3 upvotes (+1)
• 4DP-QA: Scalable QA for 4D Perception in Vision Language Models score 3
  机构: NVIDIA
• Tree-Structured Orthonormal Decomposition of the Aitchison Simplex score 3
  顶会接收: ICML
• Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization score 3
  顶会接收: IJCAI
• Towards Responsibly Non-Compliant Machines score 3
  机构: Google