Shuicheng YAN

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking

UniF$^2$ace: A $\underline{Uni}$fied $\underline{F}$ine-grained $\underline{Face}$ Understanding and Generation Model

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

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

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Libra-Emo: A Large Dataset for Multimodal Fine-grained Negative Emotion Detection

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward Supervision

Interpreting Any Condition to Caption for Controllable Video Generation

Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement

Demystifying Reinforcement Learning in Agentic Reasoning

MMRC: Measuring Massive-Computational Math Reasoning with Code in LLMs

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

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

Poison-splat: Computation Cost Attack on 3D Gaussian Splatting

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

EasyInv: Toward Fast and Better DDIM Inversion

Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy

AgentStudio: A Toolkit for Building General Virtual Agents

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

Cradle: Empowering Foundation Agents towards General Computer Control

MoH: Multi-Head Attention as Mixture-of-Head Attention

Towards Semantic Equivalence of Tokenization in Multimodal LLM

VR-Sampling: Accelerating Flow Generative Model Training with Variance Reduction Sampling

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

MoH: Multi-Head Attention as Mixture-of-Head Attention

Hierarchy-Aided Sparse Attention For Fast LLMs Prefilling Inference

Two Are Better than One: Context Window Extension with Multi-Grained Self-Injection

Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation

Geo-3DGS: Multi-view Geometry Consistency for 3D Gaussian Splatting and Surface Reconstruction

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

SOLOS: Sparse Optimization For Long Sequence In Context Compression Enhanced LLMs

ASOR: Anchor State Oriented Regularization for Policy Optimization under Dynamics Shift

Cradle: Empowering Foundation Agents towards General Computer Control

MEMO: Memory-Guided and Emotion-Aware Talking Video Generation

Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning

MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes

DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On

MOEfication by Experts as Masks