Shen Yan

17

Papers

96

Total Citations

Papers (17)

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

CompCap: Improving Multimodal Large Language Models with Composite Captions

NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics

Pixel-Aligned Language Model

VideoPrism: A Foundational Visual Encoder for Video Understanding

Multiview Transformers for Video Recognition

Long-Term Visual Localization With Mobile Sensors

Soft Augmentation for Image Classification

Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks

UnLoc: A Unified Framework for Video Localization Tasks

Deep Active Contours for Real-time 6-DoF Object Tracking

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation

LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment

Streaming Dense Video Captioning

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?

NAS-Bench-x11 and the Power of Learning Curves