KAIST AI

university

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

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

YuminChoi submitted a paper 3 days ago

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

VennTum submitted a paper 6 days ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

rsoohyun submitted a paper 9 days ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

View all activity

Papers

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

View all Papers

submitted a paper to Daily Papers 3 days ago

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Paper • 2609.17632 • Published 5 days ago • 33

submitted a paper to Daily Papers 6 days ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

Paper • 2608.30597 • Published 20 days ago • 27

submitted a paper to Daily Papers 9 days ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published 13 days ago • 143

submitted a paper to Daily Papers 11 days ago

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published 12 days ago • 78

submitted a paper to Daily Papers 17 days ago

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 18 days ago • 76

authored a paper 18 days ago

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

Paper • 2609.01404 • Published 19 days ago • 28

submitted a paper to Daily Papers 18 days ago

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

Paper • 2609.01404 • Published 19 days ago • 28

submitted a paper to Daily Papers 19 days ago

Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase

Paper • 2608.29310 • Published 22 days ago • 29

submitted a paper to Daily Papers 20 days ago

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

Paper • 2608.26582 • Published 24 days ago • 41

submitted a paper to Daily Papers about 1 month ago

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

Paper • 2608.19861 • Published Aug 20 • 9

submitted a paper to Daily Papers about 1 month ago

AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model

Paper • 2608.16143 • Published Aug 17 • 12

submitted a paper to Daily Papers about 1 month ago

MBA: Multimodal Benchmark and Agents for Real-World Business Ideation

Paper • 2608.11616 • Published Aug 12 • 7

submitted a paper to Daily Papers about 1 month ago

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Paper • 2608.07169 • Published Aug 7 • 51

submitted a paper to Daily Papers about 2 months ago

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published Jul 28 • 65

authored a paper 2 months ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published May 20 • 14

submitted a paper to Daily Papers 2 months ago

See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models

Paper • 2607.11498 • Published Jul 13 • 6

submitted a paper to Daily Papers 2 months ago

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

Paper • 2607.04412 • Published Jul 5 • 36

submitted a paper to Daily Papers 2 months ago

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

Paper • 2606.31329 • Published Jun 30 • 8

submitted a paper to Daily Papers 3 months ago

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Paper • 2606.29225 • Published Jun 28 • 7

submitted a paper to Daily Papers 3 months ago

MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation

Paper • 2606.26087 • Published Jun 24 • 37