SeongWan Kim

idgmatrix's activity

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

upvoted a paper 4 days ago

Can Understanding and Generation Truly Benefit Together -- or Just Coexist?

Paper • 2509.09666 • Published 8 days ago • 32

upvoted a paper 5 days ago

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Paper • 2509.09372 • Published 8 days ago • 189

upvoted 2 papers 8 days ago

Causal Attention with Lookahead Keys

Paper • 2509.07301 • Published 11 days ago • 21

3D and 4D World Modeling: A Survey

Paper • 2509.07996 • Published 15 days ago • 55

upvoted 4 papers 9 days ago

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published 9 days ago • 159

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published 10 days ago • 95

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Paper • 2509.08721 • Published 9 days ago • 581

Language Self-Play For Data-Free Training

Paper • 2509.07414 • Published 11 days ago • 26

upvoted a paper 12 days ago

Why Language Models Hallucinate

Paper • 2509.04664 • Published 15 days ago • 172

upvoted a paper 15 days ago

Towards a Unified View of Large Language Model Post-Training

Paper • 2509.04419 • Published 15 days ago • 71

upvoted 2 papers 16 days ago

FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

Paper • 2509.01052 • Published 19 days ago • 19

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published 17 days ago • 192

upvoted a paper 17 days ago

Autoregressive Universal Video Segmentation Model

Paper • 2508.19242 • Published 24 days ago • 26

upvoted 2 papers 22 days ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published 23 days ago • 36

Predicting the Order of Upcoming Tokens Improves Language Modeling

Paper • 2508.19228 • Published 24 days ago • 21

upvoted 4 papers 23 days ago

Diffusion Language Models Know the Answer Before Decoding

Paper • 2508.19982 • Published 23 days ago • 22

FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

Paper • 2508.19188 • Published 24 days ago • 15

Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

Paper • 2508.17437 • Published about 1 month ago • 35

VibeVoice Technical Report

Paper • 2508.19205 • Published 24 days ago • 122

upvoted a paper 24 days ago

Hermes 4 Technical Report

Paper • 2508.18255 • Published 25 days ago • 35