Yanwei Li

OpenReview

papers

3,355

total citations

papers (17)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

CVPR 2025arXiv

917

citations

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

ICML 2025arXiv

citations

Multi-Scale Aligned Distillation for Low-Resolution Detection

CVPR 2021arXiv

citations

Scale-Aware Automatic Augmentation for Object Detection

CVPR 2021arXiv

citations

Fine-Grained Dynamic Head for Object Detection

NEURIPS 2020arXiv

citations

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

ICCV 2025arXiv

citations

Rethinking Learnable Tree Filter for Generic Feature Transform

NEURIPS 2020arXiv

citations

Aligning Effective Tokens with Video Anomaly in Large Language Models

ICCV 2025arXiv

citations

End-to-end 3D Tracking with Decoupled Queries

ICCV 2023

citations

Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines

ECCV 2022

citations

Yanwei Li

papers (17)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

LISA: Reasoning Segmentation via Large Language Model

Unifying Voxel-based Representation with Transformer for 3D Object Detection

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Focal Sparse Convolutional Networks for 3D Object Detection

Fully Convolutional Networks for Panoptic Segmentation

Learning Dynamic Routing for Semantic Segmentation

Voxel Field Fusion for 3D Object Detection

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

Multi-Scale Aligned Distillation for Low-Resolution Detection

Scale-Aware Automatic Augmentation for Object Detection

Fine-Grained Dynamic Head for Object Detection

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Rethinking Learnable Tree Filter for Generic Feature Transform

Aligning Effective Tokens with Video Anomaly in Large Language Models

End-to-end 3D Tracking with Decoupled Queries

Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines

papers (17)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

LISA: Reasoning Segmentation via Large Language Model

Unifying Voxel-based Representation with Transformer for 3D Object Detection

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Focal Sparse Convolutional Networks for 3D Object Detection

Fully Convolutional Networks for Panoptic Segmentation

Learning Dynamic Routing for Semantic Segmentation

Voxel Field Fusion for 3D Object Detection

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

Multi-Scale Aligned Distillation for Low-Resolution Detection

Scale-Aware Automatic Augmentation for Object Detection

Fine-Grained Dynamic Head for Object Detection

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Rethinking Learnable Tree Filter for Generic Feature Transform

Aligning Effective Tokens with Video Anomaly in Large Language Models

End-to-end 3D Tracking with Decoupled Queries

Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines