LiMin Wang

RIVER: A Real-Time Interaction Benchmark for Video LLMs

arXiv 2026

Towards Pixel-Level VLM Perception via Simple Points Prediction

arXiv 2026

Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

arXiv 2026

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

arXiv 2025

InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

arXiv 2025

DDT: Decoupled Diffusion Transformer

ddt-decoupled-diffusion-transformer

Make Your Training Flexible: Towards Deployment-Efficient Video Models

ICCV 2025

SORCE: Small Object Retrieval in Complex Environments

arXiv 2025

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

arXiv 2025

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

arXiv 2025

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

arXiv 2025

Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment

arXiv 2025

PixNerd: Pixel Neural Field Diffusion

arXiv 2025

MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

arXiv 2025

VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos

ICCV 2025

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning

arXiv 2025

Differentiable Solver Search for Fast Diffusion Sampling

arXiv 2025

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

arXiv 2025

VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

arXiv 2025

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging

arXiv 2025

History-Aware Transformation of ReID Features for Multiple Object Tracking

arXiv 2025

MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving

arXiv 2025

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs

arXiv 2025

Multiple Object Tracking as ID Prediction

CVPR 2025 1

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

CVPR 2025 1

VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model

arXiv 2024

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

CVPR 2025 1

VFIMamba: Video Frame Interpolation with State Space Models

arXiv 2024

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

arXiv 2024

VideoMamba: State Space Model for Efficient Video Understanding

arXiv 2024

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

arXiv 2024

Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model

arXiv 2024

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

arXiv 2024

Taming Scalable Visual Tokenizer for Autoregressive Image Generation

ICCV 2025

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

arXiv 2024

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay

arXiv 2024

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

arXiv 2024

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

arXiv 2024

Accelerating Image Generation with Sub-path Linear Approximation Model

arXiv 2024

Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training

arXiv 2024

SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos

CVPR 2024 1

Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

CVPR 2024 1

VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

CVPR 2023 1

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

CVPR 2024 1

MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

ICCV 2023 1

SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

ICCV 2023 1

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

CVPR 2023 1

Deep Equilibrium Object Detection

ICCV 2023 1

SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes

ICCV 2023 1

Memory-and-Anticipation Transformer for Online Action Understanding

ICCV 2023 1

Unmasked Teacher: Towards Training-Efficient Video Foundation Models

ICCV 2023 1

Efficient Video Action Detection with Token Dropout and Context Refinement

ICCV 2023 1

StageInteractor: Query-based Object Detector with Cross-stage Interaction

ICCV 2023 1

MGMAE: Motion Guided Masking for Video Masked Autoencoding

ICCV 2023 1

ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video

arXiv 2023

Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation

arXiv 2023

UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

arXiv 2022

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

videomae-masked-autoencoders-are-data

MixFormer: End-to-End Tracking with Iterative Mixed Attention

mixformer-end-to-end-tracking-with-iterative

Recovering 3D Human Mesh from Monocular Images: A Survey

arXiv 2022