Jaegul Choo

RL makes MLLMs see better than SFT

LiveWeb-IE: A Benchmark For Online Web Information Extraction

ExpGuard: LLM Content Moderation in Specialized Domains

PHUMA: Physically-Grounded Humanoid Locomotion Dataset

More Than What Was Chosen: LLM-based Explainable Recommendation Beyond Noisy User Preferences

Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models

Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning

One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist

When Verifiable Rewards Switch the Language: Cross-Lingual Collapse in Chain-of-Thought

Structuring Hidden Features via Clustering of Unit-Level Activation Patterns

CAMERA CONDITIONED VIDEO GENERATION WITH IMPROVED POSE FIDELITY

Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models

Delving into Large Language Models for Effective Time-Series Anomaly Detection

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

Sparse autoencoders reveal selective remapping of visual concepts during adaptation

SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars

Injecting Inductive Bias to 3D Gaussian Splatting for Geometrically Accurate Radiance Fields

Selective LoRA for Domain-Aligned Dataset Generation in Urban-Scene Segmentation

Generative Location Modeling for Spatially Aware Object Insertion

Data-driven plasma equilibrium forecasting in magnetic fusion tokamak