Youngjae Yu

TIPO: Text to Image with Text Pre-sampling for Prompt Optimization

v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought

What MLLMs Learn about When they Learn about Multimodal Reasoning: Perception, Reasoning, or their Integration?

Teaching Metric Distance to Discrete Autoregressive Language Models

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

A11YN: Aligning LLMs for Accessible Web UI Code Generation

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

When AI Co‑Scientists Fail: SPOT—a Benchmark for Automated Verification of Scientific Research

DUSK: Do Not Unlearn Shared Knowledge

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

KL Penalty Control via Perturbation for Direct Preference Optimization

G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

HIPPO-VIDEO : Simulating Watch Histories with Large Language Models for History-Driven Video Highlighting

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation