Jeonghwan Kim

University of Illinois Urbana-Champaign, KAIST, Handong Global Unviersity

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Robotics & Embodied AI (1)

Frequent co-authors

Dwip Dalal (1)Shivansh Patel (1)Shivansh Patel (1)Chahit Jain (1)

Papers (1)

Jul 15, 2026

1w ago·also Handong Global Unviersity, KAIST

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

Anchor-Align boosts real-robot success rates from 28% to 54% by preventing representation drift during finetuning, revealing a critical synergy between preserving pretrained knowledge and effective action learning.

Dwip Dalal, Shivansh Patel, Shivansh Patel +8

Multimodal Models Robotics & Embodied AI

Search

Jeonghwan Kim

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)