Yun Fu

GmNet: Revisiting Gating Mechanisms From A Frequency View

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

Seeing Through Words: Controlling Visual Retrieval Quality with Language Models

Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks

ARGen-Dexion: Autoregressive Image Generation Made Stronger by Vision Decoder

On Computation and Generalization of Group Relative Policy Optimization

CompSRT: Quantization and Pruning for Image Super Resolution Transformers

Boosting Large Language Models with Mask Fine-Tuning

CoT Referring: Improving Localization with Grounded Reasoning in Referring Expression Tasks

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

SSTP: Efficient Sample Selection for Trajectory Prediction

Multimodal Generative Composition Recommendation

Dense Video Understanding with Gated Residual Tokenization

DiffuPhyGS: Text-to-Video Generation with 3D Gaussians and Learnable Physical Properties via Diffusion Priors

I$^2$BQ: Quantizing LLMs via Intra- and Inter-Block Optimization

Accessing Vision Foundation Models via ImageNet-1K

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

The Indra Representation Hypothesis

Scale-Free Graph-Language Models

VaQuitA: Enhancing Alignment in LLM-Assisted Zero-Shot Video Understanding

Understanding, Abstracting and Checking: Evoking Complicated Multimodal Reasoning in LMMs

Seeing is Knowing: Advancing Semantic Understanding with MLLMs in Grounding Tasks

Improve Code Generation with Feedback

improve weakly supervised visual grounding by learning where to focus on