Junhyeok Kim

kjunh's activity

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

upvoted a paper 1 day ago

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Paper • 2507.07990 • Published 2 days ago • 29

upvoted a paper 6 days ago

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

Paper • 2506.23918 • Published 12 days ago • 76

upvoted 4 papers about 1 month ago

Language-Image Alignment with Fixed Text Encoders

Paper • 2506.04209 • Published Jun 4 • 11

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Paper • 2506.00070 • Published May 29 • 28

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues

Paper • 2506.00958 • Published Jun 1 • 20

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

Paper • 2505.18842 • Published May 24 • 37

upvoted a paper about 2 months ago

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Paper • 2505.15277 • Published May 21 • 103

upvoted a paper 4 months ago

VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms

Paper • 2503.14427 • Published Mar 18 • 19

upvoted 2 papers 5 months ago

Kanana: Compute-efficient Bilingual Language Models

Paper • 2502.18934 • Published Feb 26 • 66

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Paper • 2502.14892 • Published Feb 17 • 6

upvoted a paper 6 months ago

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

Paper • 2501.09284 • Published Jan 16 • 10

upvoted a paper 9 months ago

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Paper • 2410.13232 • Published Oct 17, 2024 • 45