Browsing: Hugging Face
The Long CoT Collection dataset, generated by short CoT LLMs, enhances general reasoning skills and provides a strong foundation for…
LumosFlow uses LMTV-DM for key frame generation and LOF-DM followed by MotionControlNet for smooth intermediate frame interpolation, ensuring temporally coherent…
High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant…
Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing…
ActiveKD integrates active learning with knowledge distillation using large vision-language models to efficiently select diverse, unlabeled samples for annotation. Knowledge…
A new framework, Multimodal DeepResearcher, enables Large Language Models to generate high-quality multimodal reports combining text and diverse visualizations through…
A new multilingual, multi-sector, and multi-task benchmark, M³FinMeeting, evaluates large language models’ performance in understanding financial meetings across different languages…
Adaptive parallel decoding (APD) enhances the throughput of diffusion large language models (dLLMs) by dynamically adjusting parallel token generation without…
A unified large recommender model with intrinsic reasoning capabilities is proposed, facilitating interleaved reasoning and recommendation using a reinforcement learning…
Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system…