collaborators

7 papers

cond-mat.soft2026

Benchmarking the flow of epithelial cell monolayer with self-aligning deformable active membranes

Marcos Pasa, Carine P. Beatrici, François Graner +2

Collective cell migration emerges from the interplay between motility, deformability and mechanical interactions, yet incorporating these ingredients into computationally efficient…

cs.AI2026

From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents

Myeongseob Ko, Jihyun Jeong, Sumiran Singh Thakur +2

Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required specialized expertise, tailored algorit…

cs.LG2026

Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver

Jonathan Patsenker, Henry Li, Myeongseob Ko +2

Diffusion models have been firmly established as principled zero-shot solvers for linear and nonlinear inverse problems, owing to their powerful image prior and iterative sampling…

cs.LG2026

The Signal is in the Steps: Local Scoring for Reasoning Data Selection

Hoang Anh Just, Myeongseob Ko, Ruoxi Jia

Distilling long-form reasoning from teacher models into smaller students requires selecting which candidate solutions to train on. Recent work argues that one should select respons…

cs.CV2025

More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models

Hoang Anh Just, Yifei Fan, Handong Zhao +6

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. How…

cs.CL2025

Retracing the Past: LLMs Emit Training Data When They Get Lost

Myeongseob Ko, Nikhil Reddy Billa, Adam Nguyen +3

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based d…