Ran He

TIP: Token Importance in On-Policy Distillation

arXiv 2026

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

arXiv 2026

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

arXiv 2026

The Trinity of Consistency as a Defining Principle for General World Models

arXiv 2026

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

arXiv 2026

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

arXiv 2026

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

arXiv 2026

FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling

arXiv 2026

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

arXiv 2026

VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting

arXiv 2025

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

arXiv 2025

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

arXiv 2025

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

arXiv 2025

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

arXiv 2025

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

arXiv 2024

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

arXiv 2024

ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation

arXiv 2024

T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs

arXiv 2024

ZePo: Zero-Shot Portrait Stylization with Faster Sampling

arXiv 2024

Breaking the Low-Rank Dilemma of Linear Attention

CVPR 2025 1

InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding

arXiv 2024

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

arXiv 2024

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

arXiv 2024

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model

arXiv 2024

RMT: Retentive Networks Meet Vision Transformers

CVPR 2024 1

ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models

arXiv 2023

Improving Zero-Shot Generalization for CLIP with Synthesized Prompts

ICCV 2023 1

Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting

arXiv 2023

Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models

arXiv 2023

AdaptGuard: Defending Against Universal Attacks for Model Adaptation

ICCV 2023 1

TALL: Thumbnail Layout for Deepfake Video Detection

ICCV 2023 1