YiFan Zhang

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Thyme: Think Beyond Images

BaseReward: A Strong Baseline for Multimodal Reward Model

VITA-E: A Dual-Model Framework for Real-Time, Interruptible, and Concurrent Human-Robot Interaction

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models

OmniEarth-Bench: Probing Cognitive Abilities of MLLMs for Earth's Multi-sphere Observation Data

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

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

InstructEngine: Instruction-driven Text-to-Image Alignment

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

DAMA: Data- and Model-aware Alignment of Multi-modal LLMs

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting