Ling Yang

Generative Universal Verifier as Multimodal Meta-Reasoner

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

LAION-Comp: Unlocking Controllable and Compositional Generation with Structural Annotations

UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers

DIVA: Discrete Diffusion Vision-Language-Action Models for Parallelized Action Generation

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Demystifying Reinforcement Learning in Agentic Reasoning

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

MMaDA: Multimodal Large Diffusion Language Models

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

Semantic Score Distillation Sampling for Compositional Text-to-3D Generation

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation

Multi-Agent Collaborative Data Selection for Efficient Language Model Pretraining

IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts

Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis