KAIST AI

university

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

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Justin4AI submitted a paper 1 day ago

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

DongkiKim submitted a paper 3 days ago

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

glory-hyeok submitted a paper 7 days ago

Self-Distilling Future Video Representations for World Action Models

View all activity

Papers

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

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

View all Papers

kaist-ai 's papers 104

Submitted by

Heejun Lee

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

kaist-ai

Submitted by

Junyeong Ahn

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

kaist-ai

Submitted by

DongkiKim

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

kaist-ai

2

Submitted by

Suhyeok Jang

Self-Distilling Future Video Representations for World Action Models

kaist-ai

Submitted by

Sihwan Park

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

kaist-ai

1

Submitted by

Hojun Choi

Latent World Action Model for GUI Agents

kaist-ai

Submitted by

HyunWook Choi

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

kaist-ai

Submitted by

jee0

GRACE: Generation-aware latent compression for efficient video generation

kaist-ai

Submitted by

Jinheon Baek

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

kaist-ai

Submitted by

Jaeyeong Kim

Tetris3D: 3D Scene Generation With Objects That Fit Together

kaist-ai

Submitted by

Yonghoon Dong

Q-Learning with Scalar Adjoint Matching

kaist-ai

Submitted by

Junhoo

RobotUse: Allocating Computation, Context, and Decisions

kaist-ai