Siliang Tang

Full Professor@Zhejiang University·中国·OpenReview

研究方向

graph neural network in computer vision · information extraction · natural language processing · vision and language · mulitmodal learning · topic models

Siliang Tang

Towards Physically Executable 3D Gaussian for Embodied Navigation

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL

Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for LLMs

FAST THINKING FOR LARGE LANGUAGE MODELS

HILDA: Hessian-Implicit Langevin with Damping and Adaptation for Diffusion Sampling

On Path to Multimodal Generalist: General-Level and General-Bench

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark

Robust Video Moment Retrieval with Introspective Knowledge Distillation

HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models

Benchmarking and Rethinking Multiplex Graphs