-
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
score 13
机构: Shanghai AI Lab; 入选 HF Daily Papers; HF 热度: 22 upvotes (+4); 有代码实现; 关键词(2): text-to-image, data curation
-
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
score 12
入选 HF Daily Papers; HF 热度: 10 upvotes (+3); 有代码实现; 关键词(1): lightweight; 顶会接收: CVPR
-
EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
score 11
机构: Shanghai AI Lab; 入选 HF Daily Papers; HF 热度: 9 upvotes (+2); 有代码实现; 关键词(2): scaling, reasoning
-
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
score 10
入选 HF Daily Papers; HF 热度: 49 upvotes (+4); 有代码实现; 关键词(2): agentic, reasoning
-
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
score 10
入选 HF Daily Papers; HF 热度: 35 upvotes (+4); 有代码实现; 关键词(5): lightweight, distillation, production, serving, agentic
-
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
score 10
入选 HF Daily Papers; HF 热度: 28 upvotes (+4); 有代码实现; 关键词(1): vision-language
-
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
score 10
入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 有代码实现; 关键词(2): tool use, reasoning
-
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
score 10
机构: Peking University; 入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 有代码实现; 关键词(4): PPO, GRPO, post-training, pretraining
-
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
score 9
入选 HF Daily Papers; HF 热度: 69 upvotes (+4); 有代码实现
-
DVD: Deterministic Video Depth Estimation with Generative Priors
score 9
入选 HF Daily Papers; HF 热度: 17 upvotes (+3); 有代码实现; 关键词(1): open-source