-
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
score 10
入选 HF Daily Papers；HF 热度: 64 upvotes (+4)；有代码实现；关键词(4): agentic, coding, reasoning, text-to-video
-
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
score 10
入选 HF Daily Papers；HF 热度: 49 upvotes (+4)；有代码实现；关键词(3): scaling, pretraining, reasoning
-
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
score 10
入选 HF Daily Papers；HF 热度: 47 upvotes (+4)；有代码实现；关键词(3): agentic, tool use, reasoning
-
MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing
score 10
入选 HF Daily Papers；HF 热度: 37 upvotes (+4)；有代码实现；关键词(1): text-to-image
-
RefCaptioner: Multi-Reference Image-Grounded Video Captioning
score 10
入选 HF Daily Papers；HF 热度: 25 upvotes (+4)；有代码实现；关键词(3): GRPO, post-training, open-source
-
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
score 9
入选 HF Daily Papers；HF 热度: 31 upvotes (+4)；有代码实现
-
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
score 9
入选 HF Daily Papers；HF 热度: 16 upvotes (+3)；有代码实现；关键词(1): fine-tuning
-
OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation
score 9
入选 HF Daily Papers；HF 热度: 12 upvotes (+3)；有代码实现；关键词(1): reasoning
-
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
score 8
入选 HF Daily Papers；HF 热度: 281 upvotes (+4)；关键词(1): lightweight
-
Multi-Head Attention Residuals
score 8
入选 HF Daily Papers；HF 热度: 8 upvotes (+2)；有代码实现；关键词(1): throughput