Xiangyu Yue

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

VideoSearch Reasoner: Boosting Multimodal Reward Models through Think with Image Reasoning

Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km

A Guide to Training Consistency Models

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

Interpreting Multi-Layer Transformers for In-Context Linear Regression with Varying Covariance

Growing Visual Generative Capacity for Pre-Trained MLLMs

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems

MCP-R1: Generalized Real-World Task Agent Mastering Dozens of Tools

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

AV-Odyssey Bench: From Fundamental Audio Perception to Audio-Visual Understanding

MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents

Towards Adapting Vision-Language Models for Semi-Supervised Domain Generalization

VideoShield: A Unified Framework for Multimodal Risk Detection and Control in Video Generative Models

$X$-Planes: Adaptive and Efficient Representation for Dynamic Reconstruction and Rendering in the Age of Large Pretrained Models

HIERARCHICAL BIO-INSPIRED COGNITIVE MEMORY SYSTEMS: A UNIFIED FRAMEWORK FOR SEQUEN- TIAL INFORMATION PROCESSING AND LONG-TERM BEHAVIORAL PREDICTION

VCoT-Pro: Advancing Visual Reasoning with a Large-scale Comprehensive Visual Chain-of-Thought Dataset

ReSim: Reliable World Simulation for Autonomous Driving

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward

Video-R1: Reinforcing Video Reasoning in MLLMs

Learning to Integrate Diffusion ODEs by Averaging the Derivatives

Native-Resolution Image Synthesis

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant

Towards Continual Domain Adaptation of Vision-language Models

Debiasing Text-to-image Diffusion Models with Self-discovering Latent Directions

MindDETR: Beyond Semantics, Exploring Positional Cues from Brain Activity

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities

Truly Safe & Truly Helpful: Achieving Harmonious Balance for Large Language Model

Mitigating Generative Privacy Risks of Diffusion Models via Mixed Self-Synthesized Data Fine-tuning

Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines

SimDiffPDE: Simple Diffusion Baselines for Solving Partial Differential Equations