5 papers
When Noise Lowers The Loss: Rethinking Likelihood-Based Evaluation in Music Large Language Models
Xiaosha Li, Chun Liu, Ziyu Wang
The rise of music large language models (LLMs) demands robust methods of evaluating output quality, especially in distinguishing high-quality compositions from "garbage music". Cur…
Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
Ziyue Wang, Sheng Jin, Zhongrong Zuo +5
Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequen…
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
Weihang Wang, Xinhao Li, Ziyue Wang +5
Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual infor…
Synthetic Video Enhances Physical Fidelity in Video Synthesis
Qi Zhao, Xingyu Ni, Ziyu Wang +4
We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respec…
Multimodal Generalized Category Discovery
Yuchang Su, Renping Zhou, Siyu Huang +4
Generalized Category Discovery (GCD) aims to classify inputs into both known and novel categories, a task crucial for open-world scientific discoveries. However, current GCD method…