Taeyun Roh

txxnrd's activity

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

upvoted a paper 6 days ago

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Paper • 2610.01762 • Published 25 days ago • 240

upvoted an article 9 days ago

view article

Article

UltraBERT: One Encoder for Classification and Retrieval

• 

dmis-lab

•

12 days ago

• 65

liked a model 9 days ago

nlpai-lab/MixLID

Token Classification • 0.1B • Updated 12 days ago • 262 • 22

liked a model 10 days ago

dmis-lab/UltraBERT-150M

Fill-Mask • 0.2B • Updated 9 days ago • 8.27k • 59

upvoted a paper 10 days ago

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Paper • 2610.19366 • Published 12 days ago • 56

authored a paper 12 days ago

Learning How to Remember: Memory Modality Selection for GUI Agents

Paper • 2610.17928 • Published 13 days ago • 42

upvoted a paper 12 days ago

Learning How to Remember: Memory Modality Selection for GUI Agents

Paper • 2610.17928 • Published 13 days ago • 42

submitted a paper to Daily Papers 12 days ago

Learning How to Remember: Memory Modality Selection for GUI Agents

Paper • 2610.17928 • Published 13 days ago • 42

upvoted a paper 12 days ago

UltraBERT: Beyond the Limit of BERT Pre-Training

Paper • 2610.15028 • Published 16 days ago • 72

upvoted a paper about 2 months ago

Reason Through the Latent! Making Latent Visual Reasoning Necessary

Paper • 2609.06746 • Published Sep 6 • 37

upvoted a paper 4 months ago

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval

Paper • 2607.04605 • Published Jul 6 • 22

authored a paper 4 months ago

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Paper • 2606.31825 • Published Jun 30 • 26

upvoted 4 papers 4 months ago

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Paper • 2606.31825 • Published Jun 30 • 26

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

Paper • 2606.27595 • Published Jun 25 • 9

OpenThoughts-Agent: Data Recipes for Agentic Models

Paper • 2606.24855 • Published Jun 23 • 49

Geometric Action Model for Robot Policy Learning

Paper • 2606.17046 • Published Jun 15 • 118

authored a paper 5 months ago

When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA

Paper • 2603.28026 • Published Mar 30 • 1

upvoted 3 papers 5 months ago

When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA

Paper • 2603.28026 • Published Mar 30 • 1

ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?

Paper • 2606.05553 • Published Jun 4 • 50

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Paper • 2606.04743 • Published Jun 3 • 47