Renrui Zhang

Generative Universal Verifier as Multimodal Meta-Reasoner

Spiking Discrepancy Transformer for Point Cloud Analysis

GLEAM: Learning to Match and Explain in Cross-View Geo-Localization

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Exploring the Potential of Encoder-free Architectures in 3D LMMs

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

Evolvable Safety Benchmarking: Multi-agent Pipeline for LVLMs

HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

UniCTokens-R1: Boosting Unified Personalization via Reinforcement Learning

Can World Models Benefit VLMs for World Dynamics?

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

HybridVLA: Collaborative Autoregression and Diffusion in a Unified Vision-Language-Action Model

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

PointACL: Point Cloud Understanding via Attention-Driven Contrastive Learning

TerDiT: Ternary Diffusion Models with Transformers