11 papers
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
Yuntian Tang, Bohan Jia, Wenxuan Huang +7
Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. E…
CompBench: Benchmarking Complex Instruction-guided Image Editing
Bohan Jia, Wenxuan Huang, Yuntian Tang +14
While real-world applications increasingly demand intricate scene manipulation, existing instruction-guided image editing benchmarks often oversimplify task complexity and lack com…
ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation
Jingzhong Lin, Xinru Li, Yuanyuan Qi +8
Reactive dance generation (RDG), the task of generating a dance conditioned on a lead dancer's motion, holds significant promise for enhancing human-robot interaction and immersive…
MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation
Qin Dong, Yuntian Tang, Heming Jia +7
Low-Rank Adaptation (LoRA) has emerged as a dominant method in Parameter-Efficient Fine-Tuning (PEFT) for large language models, which augments the transformer layer with one down-…
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Wenxuan Huang, Bohan Jia, Zijie Zhai +7
DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). Inspired by this breakthrough, we explore…
CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression
Kangjie Zhang, Wenxuan Huang, Xin Zhou +9
Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image cap…