HuggingFace
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existin...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
DEPICT: Scoring Text-to-Image Alignment by Answer Agreement
Image-text alignment is a core problem in computer vision with applications in caption evaluation, hallucination dete...
HuggingFace
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments re...
HuggingFace
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, whi...
HuggingFace
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) aims to combine the strengths of RL-trained teachers in a single student,...
HuggingFace
Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control
Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structur...
HuggingFace
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cac...
HuggingFace
Latent-MOPD: Latent Multi-Teacher On-Policy Distillation
On-policy distillation (OPD) trains a student on the responses it generates. Existing LLM multi-teacher OPD transfers...
HuggingFace
MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception
Modeling spatiotemporal coupling is a key challenge in building physical intelligence across scales, from microscopic...
HuggingFace
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
A companion that talks with a person for months should come to understand them. It should remember what they said, in...
HuggingFace
Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification
Retrieval-based factuality evaluation, where LLM-generated claims are verified against evidence from authoritative me...
HuggingFace
KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding
Vision-language models are increasingly used to understand long videos and continuous streams. However, dense visual ...