10 papers
Beyond Correct Answers: How Compositional Cues Shape Visual Judgments
Xiaoyu Ma, Zheyuan Zhang, Kaiwen Shi +1
Visual question answering requires models to assign attributes and relations to the correct objects, a problem known as visual binding. Structured prompts make these assignments ex…
Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models
Zhenhong Zhou, Xuanyue Zhao, Youji Liu +4
Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually collapse in real-world environmen…
TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
Lianyu Hu, Xiaoyu Ma, Zeqin Liao +1
Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language models. However, when applied to multimodal LLMs (MLLMs), existing CoT approac…
Balancing Multimodal Learning through Label Space Reshaping
Xiaoyu Ma, Weijie Zhang, Yuanhao Gao +3
Multimodal learning often suffers from modality imbalance, where modalities that converge faster dominate optimization while others remain undertrained. Existing approaches typical…
BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
Xiaoyu Ma, Lianyu Hu, Wenbing Tang +4
Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated…
Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
Yunjian Zhang, Sudong Wang, Yang Li +5
Large language models (LLMs) have exhibited remarkable performance on complex reasoning tasks, with reinforcement learning under verifiable rewards (RLVR) emerging as a principled…
BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
Xiaoyu Ma, Zhengqing Yuan, Zheyuan Zhang +3
Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot contro…
Revisit Modality Imbalance at the Decision Layer
Xiaoyu Ma, Hao Chen
Multimodal learning integrates information from different modalities to enhance model performance, yet it often suffers from modality imbalance, where dominant modalities overshado…
Mixup Helps Understanding Multimodal Video Better
Xiaoyu Ma, Ding Ding, Hao Chen
Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, mult…
Improving Multimodal Learning Balance and Sufficiency through Data Remixing
Xiaoyu Ma, Hao Chen, Yongjian Deng
Different modalities hold considerable gaps in optimization trajectories, including speeds and paths, which lead to modality laziness and modality clash when jointly training multi…