7 papers
WaterGen: Decoupling Scene and Medium in Underwater Image Generation
Jiayi Wu, Tianfu Wang, Tianyi Xiong +6
Underwater computer vision tasks, such as detection, restoration, and segmentation, are limited by the scarcity of large-scale and diverse training data. We introduce WaterGen, a m…
Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate
Chenxi Liu, Yanshuo Chen, Ruibo Chen +3
The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reaso…
PhyCritic: Multimodal Critic Models for Physical AI
Tianyi Xiong, Shihao Wang, Guilin Liu +5
With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise…
Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
Chenxi Liu, Tianyi Xiong, Yanshuo Chen +5
The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimizatio…
Understanding Catastrophic Interference: On the Identifibility of Latent Representations
Yuke Li, Yujia Zheng, Tianyi Xiong +2
Catastrophic interference, also known as catastrophic forgetting, is a fundamental challenge in machine learning, where a trained learning model progressively loses performance on…
LLaVA-Critic: Learning to Evaluate Multimodal Models
Tianyi Xiong, Xiyao Wang, Dong Guo +5
We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks. LLaV…