11 papers
Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation
Xudong Zou, Siyu Wu, Zunlei Feng +4
Deep learning has shown strong potential for massive multiple-input multiple-output (Massive MIMO) physical-layer tasks, including channel state information (CSI) feedback and chan…
Sampling-Aware Quantization for Diffusion Models
Qian Zeng, Jie Song, Yuanyu Wan +2
Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation…
Rethinking Token Reduction for Large Vision-Language Models
Yi Wang, Haofei Zhang, Qihan Huang +7
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction meth…
HuggingR: A Progressive Reasoning Framework for Discovering Optimal Model Companions
Shaoyin Ma, Chenggong Hu, Huiqiong Wang +3
Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (e.g., HuggingFace with > 2M models) based on natural lang…
Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
Yi Wang, Mushui Liu, Wanggui He +13
Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. Howe…
Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
Qihan Huang, Haofei Zhang, Rong Wei +4
RL (reinforcement learning) methods (e.g., GRPO) for MLLM (Multimodal LLM) perception ability has attracted wide research interest owing to its remarkable generalization ability. N…