KAIST AI

university

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

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

harryjo97 submitted a paper about 10 hours ago

Future Representation Distillation for Imagination-free World Action Models

junbrro submitted a paper 1 day ago

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

WJ0830 submitted a paper 2 days ago

Factorized MLLM Embeddings for Composed Image Retrieval

View all activity

Papers

Future Representation Distillation for Imagination-free World Action Models

RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

View all Papers

submitted a paper to Daily Papers about 10 hours ago

Future Representation Distillation for Imagination-free World Action Models

Paper • 2611.04527 • Published 3 days ago • 6

submitted a paper to Daily Papers 1 day ago

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

Paper • 2611.04391 • Published 4 days ago • 14

submitted a paper to Daily Papers 2 days ago

Factorized MLLM Embeddings for Composed Image Retrieval

Paper • 2611.05193 • Published 4 days ago • 47

submitted a paper to Daily Papers 2 days ago

DreamX: Video Diffusion Model is a Universal Latent Action Learner

Paper • 2611.05377 • Published 4 days ago • 58

submitted a paper to Daily Papers 2 days ago

RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

Paper • 2611.05163 • Published 4 days ago • 7

submitted a paper to Daily Papers 4 days ago

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

Paper • 2610.27954 • Published 18 days ago • 36

submitted a paper to Daily Papers 4 days ago

Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling

Paper • 2610.37393 • Published 11 days ago • 8

submitted a paper to Daily Papers 4 days ago

Latent Reasoning in Continuous Space for Unified Multimodal Models

Paper • 2610.42149 • Published 8 days ago • 45

submitted a paper to Daily Papers 7 days ago

L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory

Paper • 2610.40614 • Published 9 days ago • 48

submitted a paper to Daily Papers 7 days ago

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

Paper • 2610.36671 • Published 11 days ago • 117

submitted a paper to Daily Papers 9 days ago

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 12 days ago • 60

submitted a paper to Daily Papers 11 days ago

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

Paper • 2610.32195 • Published 15 days ago • 27

submitted a paper to Daily Papers 14 days ago

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 17 days ago • 37

authored a paper 18 days ago

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

Paper • 2610.19159 • Published 25 days ago • 56

submitted a paper to Daily Papers 19 days ago

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

Paper • 2610.19159 • Published 25 days ago • 56

authored 5 papers 22 days ago

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

Paper • 2610.02202 • Published Oct 1 • 12

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 • 48

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 • 42