KAIST AI

university

https://gsai.kaist.ac.kr/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

DongkiKim submitted a paper 1 day ago

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

glory-hyeok submitted a paper 5 days ago

Self-Distilling Future Video Representations for World Action Models

seungone authored a paper 9 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

View all activity

Papers

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

View all Papers

submitted a paper to Daily Papers 1 day ago

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

Paper • 2610.32195 • Published 5 days ago • 35

submitted a paper to Daily Papers 5 days ago

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 7 days ago • 51

authored a paper 9 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 15 days ago • 160

submitted a paper to Daily Papers 9 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 15 days ago • 160

authored 5 papers 13 days ago

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

Paper • 2610.02202 • Published 27 days ago • 16

Efficient Test-Time Adaptation through Human-AI Interaction

Paper • 2609.04141 • Published Sep 3

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 61

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Paper • 2607.04412 • Published Jul 5 • 37

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 45

submitted a paper to Daily Papers 13 days ago

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Paper • 2610.14448 • Published 18 days ago • 49

submitted a paper to Daily Papers 14 days ago

Omni-Modal LLMs Know More Than They Say

Paper • 2610.16135 • Published 16 days ago • 11

submitted a paper to Daily Papers 14 days ago

Latent World Action Model for GUI Agents

Paper • 2610.14228 • Published 19 days ago • 25

submitted a paper to Daily Papers 19 days ago

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Paper • 2610.12299 • Published 20 days ago • 73

submitted a paper to Daily Papers 19 days ago

LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation

Paper • 2609.38562 • Published 29 days ago • 2

submitted a paper to Daily Papers 20 days ago

Q-Learning with Scalar Adjoint Matching

Paper • 2610.10437 • Published 21 days ago • 26

submitted a paper to Daily Papers 20 days ago

FastOPD: On-Policy Distillation for Lightweight VLA Deployment

Paper • 2610.02832 • Published 26 days ago • 3

submitted a paper to Daily Papers 20 days ago

Tetris3D: 3D Scene Generation With Objects That Fit Together

Paper • 2610.10539 • Published 21 days ago • 49

submitted a paper to Daily Papers 20 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 21 days ago • 44

submitted a paper to Daily Papers 20 days ago

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 21 days ago • 92

submitted a paper to Daily Papers 21 days ago

Harness-Aware Distillation for Small Language Model Agents

Paper • 2610.02858 • Published 26 days ago • 17