Jeonghwan Kim

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

Papers on Lattice

Total citations

Topics

h-index

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

Jul 15, 2026·also Handong Global Unviersity, KAIST

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

Achieving up to 60% success in robot manipulation by aligning language and action predictions without sacrificing pretrained visual representations reveals a breakthrough in VLA policy training.

Dwip Dalal, Shivansh Patel, Shivansh Patel +8

Multimodal Models Robotics & Embodied AI

Search

Jeonghwan Kim

Research focus

Frequent co-authors

Papers (1)