Yu-Gang Jiang

AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL

WithAnyone: Toward Controllable and ID Consistent Image Generation

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow

RoboOmni: Proactive Robot Manipulation in Omni-modal Context

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

TrajTok: What makes for a good trajectory tokenizer in behavior generation?

EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark

CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design

HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision–Language–Action Policies

Unleashing 2D Rewards for Human Preference Aligned Text-to-3D Generation via Preference Score Distillation

TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot Control

WorldPM: Understanding Scaling Patterns in Human Preference Modeling

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

FlashPlanner: Accelerating Diffusion-based Planner for Autonomous Driving via Globally Consistent Velocity Field and Redundancy Reduction

Unraveling Hallucination in Large Reasoning Models: A Topological Perspective

AgenticPA: Toward Automated and Large-Scale Prompt Attacks on LLMs

PointARSim: Point-cloud–enhanced Generative Auto-Regressive Simulation for Closed-loop End-to-end Autonomous Driving Evaluation

ReGen4AD: Retrieval Based Online Video Generation for Reactive Autonomous Driving Simulation

Mitigating Gaslighting by Relocating Text-induced Visual Attention Bias

CoSMo-RL: Towards Trustworthy LMRMs via Joint Safety and Stability

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models

Model Utility Law: Evaluating LLMs beyond Performance via Mechanistically Interpretable Metric

OmniSVG: A Unified Scalable Vector Graphics Generation Model

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

OmniGen-AR: AutoRegressive Any-to-Image Generation

Adaptive Retention & Correction: Test-Time Training for Continual Learning

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning

ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

AgentGym: Evaluating and Evolving Large Language Model-based Agents across Diverse Envronments

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers

Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example

Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words

IDEATOR: Jailbreaking VLMs Using VLMs

Towards a Theoretical Understanding of Memorization in Diffusion Models

GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting