Taekyung Kim

taekyung-k's activity

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

upvoted a paper 1 day ago

Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models

Paper • 2610.09496 • Published 15 days ago • 6

upvoted a paper 3 days ago

Omni-Modal LLMs Know More Than They Say

Paper • 2610.16135 • Published 10 days ago • 10

upvoted a paper 7 days ago

Learning Transferable World-Action Models from Task-Paired Human Videos

Paper • 2610.14351 • Published 13 days ago • 11

upvoted a paper 14 days ago

On-Policy Distillation with Negative-Policy Rollouts

Paper • 2610.07874 • Published 16 days ago • 22

upvoted a paper about 1 month ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published Sep 7 • 23

upvoted 2 papers 12 months ago

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published Oct 18, 2025 • 50

Exploring Conditions for Diffusion models in Robotic Control

Paper • 2510.15510 • Published Oct 17, 2025 • 40

upvoted a paper about 1 year ago

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published Oct 15, 2025 • 14

upvoted 2 papers over 1 year ago

Masked Image Modeling via Dynamic Token Morphing

Paper • 2401.00254 • Published Dec 30, 2023 • 2

Token Bottleneck: One Token to Remember Dynamics

Paper • 2507.06543 • Published Jul 9, 2025 • 20