oh sehun

sehun's activity

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

upvoted an article about 3 hours ago

view article

Article

Ulysses Sequence Parallelism: Training with Million-Token Contexts

• 
• 

4 days ago

•

15

upvoted a paper about 4 hours ago

In-Context Reinforcement Learning for Tool Use in Large Language Models

Paper • 2603.08068 • Published 4 days ago • 20

upvoted a paper about 20 hours ago

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

Paper • 2603.10160 • Published 3 days ago • 20

upvoted 2 papers about 21 hours ago

Scale Space Diffusion

Paper • 2603.08709 • Published 4 days ago • 14

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 3 days ago • 57

upvoted a paper 1 day ago

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 3 days ago • 37

upvoted 2 papers 2 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 3 days ago • 41

AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery

Paper • 2603.07300 • Published 6 days ago • 14

upvoted an article 2 days ago

view article

Article

Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge

• 

4 days ago

•

8

upvoted 2 papers 3 days ago

Dynamic Chunking Diffusion Transformer

Paper • 2603.06351 • Published 7 days ago • 12

π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Paper • 2603.02083 • Published 11 days ago • 9

upvoted a collection 4 days ago

Agentic RL Hackathon (SF) 2026

Collection

158 items • Updated 1 day ago • 5

upvoted 2 papers 4 days ago

Progressive Residual Warmup for Language Model Pretraining

Paper • 2603.05369 • Published 8 days ago • 32

Reasoning Models Struggle to Control their Chains of Thought

Paper • 2603.05706 • Published 7 days ago • 26

upvoted a paper 5 days ago

Distribution-Conditioned Transport

Paper • 2603.04736 • Published 8 days ago • 3

upvoted 2 papers 6 days ago

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

Paper • 2603.04743 • Published 8 days ago • 47

Large Multimodal Models as General In-Context Classifiers

Paper • 2602.23229 • Published 15 days ago • 22

upvoted an article 6 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

8 days ago

•

90

upvoted 2 papers 7 days ago

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Paper • 2603.04791 • Published 8 days ago • 16

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 9 days ago • 160