Jenq-Neng Hwang

8

Papers

503

Total Citations

Papers (8)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

NeurIPS 2025arXiv

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

Human Motion Instruction Tuning