-
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
score 10
入选 HF Daily Papers;HF 热度: 68 upvotes (+4);有代码实现;关键词(3): compression, reasoning, vision-language
-
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
score 8
入选 HF Daily Papers;HF 热度: 84 upvotes (+4);关键词(3): distillation, latency, real-time
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
score 8
入选 HF Daily Papers;HF 热度: 67 upvotes (+4);关键词(3): quantization, throughput, open-source
-
Does Synthetic Layered Design Data Benefit Layered Design Decomposition?
score 8
入选 HF Daily Papers;HF 热度: 6 upvotes (+2);有代码实现;关键词(1): synthetic data
-
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
score 8
入选 HF Daily Papers;HF 热度: 8 upvotes (+2);有代码实现;关键词(3): distillation, real-time, GRPO
-
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
score 7
入选 HF Daily Papers;HF 热度: 17 upvotes (+3);关键词(4): latency, GRPO, agentic, reasoning
-
Towards Self-Evolving Agentic Literature Retrieval
score 7
入选 HF Daily Papers;HF 热度: 2 upvotes (+1);有代码实现;关键词(2): lightweight, agentic
-
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
score 6
入选 HF Daily Papers;HF 热度: 4 upvotes (+1);有代码实现
-
Quantitative Video World Model Evaluation for Geometric-Consistency
score 5
入选 HF Daily Papers;有代码实现