Yujun Cai

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations

AutoDrive-R²: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools

From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation

ContextNav: Towards Agentic Multimodal In-Context Learning

T2G-Reasoner: Deep Reasoning for Text-to-Gloss Translation

Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models

Efficiently Disentangling CLIP for Multi-Object Perception

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering

WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning

Visual CoT Makes VLMs Smarter but More Fragile

Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory

Mitigating Coordinate Prediction Bias from Positional Encoding Failures

FrameMind: Frame-Interleaved Chain-of-Thought for Video Reasoning via Reinforcement Learning

$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement

IUT-Plug: A Plug-in tool for Interleaved Image-Text Generation

Structuring Reasoning for Complex Rules Beyond Flat Representations

Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning for Large Audio-Language Models

Beyond the Shot: Rethinking Cinematography Understanding with Foundational Skill Evaluation

Not Errors but Guardians: Understanding Sink Tokens in Multimodal LLMs

Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding

When Symbols Speak: Understanding Logo Triggered Texts in Vision-Language Models

Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion LLMs

Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation

Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs

Structured Attention Matters to Multimodal LLMs in Document Understanding

Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding

Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs

How does Watermarking Affect Visual Language Models in Document Understanding?

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models