Weitai Kang

weitaikang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 14 days ago

weitaikang/RL-Qwen2.5VL-lora-7B-ckpt500

Updated 14 days ago • 261

published a model 16 days ago

weitaikang/RL-Qwen2.5VL-lora-7B-ckpt500

Updated 14 days ago • 261

upvoted a paper 7 months ago

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

Paper • 2410.00255 • Published Sep 30, 2024 • 5

commented a paper 7 months ago

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

Paper • 2410.00255 • Published Sep 30, 2024 • 5 •

2

authored 8 papers 7 months ago

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Paper • 2409.12963 • Published Sep 19, 2024

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

Paper • 2410.00255 • Published Sep 30, 2024 • 5

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

Paper • 2407.03200 • Published Jul 3, 2024

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

Paper • 2405.18295 • Published May 28, 2024

ACTRESS: Active Retraining for Semi-supervised Visual Grounding

Paper • 2407.03251 • Published Jul 3, 2024

Visual Grounding with Attention-Driven Constraint Balancing

Paper • 2407.03243 • Published Jul 3, 2024

On the Faithfulness of Vision Transformer Explanations

Paper • 2404.01415 • Published Apr 1, 2024

Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer

Paper • 2403.14552 • Published Mar 21, 2024