RL4VLA @ RSS 2026

2 papers

Top Research Directions

The 2 research directions with RL4VLA @ RSS 2026 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Resolving Superposition with Sparse Autoencoders150.0%
2Step Level Feedback for Long Horizon Reinforcement Learning150.0%

Download all directions as CSV

Institutions

Institutions credited by RL4VLA @ RSS 2026 papers: a paper credits every institution named in its affiliations, once. 2 institutions share 1 credited papers.

#InstitutionPapersShare
1University of California, Berkeley 1100.0%
2University of Oxford 1100.0%

Download all institutions as CSV

About this data

Papers. RL4VLA @ RSS 2026 lists 2 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 1 of 2 papers (50.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “RL4VLA @ RSS 2026”, https://lacuna.tiptreesystems.com/venue/rl4vla-rss/2026.

Top Authors

AuthorPapers
Joy Zheyun Yang2
Socrates Osorio2

Papers

Title
Sparse Progress and Risk Features in OpenVLA: Fragile Under Task-Family Shift
The Reward Is Already Inside the Policy: Internal-Activation Progress and Safety Signals for Vision-Language-Action Reinforcement Learning