Yukang Chen

25

Papers

763

Total Citations

Papers (25)

LISA: Reasoning Segmentation via Large Language Model

WorldModelBench: Judging Video Generation Models As World Models

SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs

RENAS: Reinforced Evolutionary Neural Architecture Search

Learning Dynamic Routing for Semantic Segmentation

Multi-Scale Aligned Distillation for Low-Resolution Detection

Scale-Aware Automatic Augmentation for Object Detection

Voxel Field Fusion for 3D Object Detection

Focal Sparse Convolutional Networks for 3D Object Detection

Spherical Transformer for LiDAR-Based 3D Recognition

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs

Mask-Attention-Free Transformer for 3D Instance Segmentation

IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

VisionZip: Longer is Better but Not Necessary in Vision Language Models

NVILA: Efficient Frontier Visual Language Models

Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code

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

DetNAS: Backbone Search for Object Detection

Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

Data Pruning via Moving-one-Sample-out