Robo-3Dvlm @ CVPR 2025

4 papers

Top Research Directions

The 8 research directions with Robo-3Dvlm @ CVPR 2025 papers, ranked by paper count, next to 2024. Share is the fraction of the edition’s papers in the direction.

#Direction20252024Share 2025Share 20242024 rank
1Bootstrapping Reinforcement Learning with Expert Demonstrations1125.0%100.0%1
2Bridging the Embodiment Gap in Robot Learning1025.0%0.0%—
3Generalizing Robotic Policies Across Diverse Hardware Embodiments1125.0%100.0%2
4Lifting Vision Language Embeddings to 3D Representations1025.0%0.0%—
5Overcoming the Reality Gap in Robotic Control1025.0%0.0%—
6The Limitations of Open Loop Robotic Execution1025.0%0.0%—
7Zero-Shot Generalization from Simulation to Reality1025.0%0.0%—
8Zero-Shot Sim-to-Real Transfer for Robotic Control1125.0%100.0%5

Download all directions as CSV

Institutions

Institutions credited by Robo-3Dvlm @ CVPR 2025 papers: a paper credits every institution named in its affiliations, once. 11 institutions share 3 credited papers.

#InstitutionPapersShare20242024 rank
105knpdt07 133.3%0—
2Allen Institute for Artificial Intelligence 133.3%12
3National University of Singapore 133.3%0—
4Peking University 133.3%0—
5Robert Bosch (Germany) 133.3%0—
6Sichuan University 133.3%0—
7Technical University of Munich 133.3%0—
8University of Delaware 133.3%0—
9University of Toronto 133.3%0—
10University of Washington 133.3%11
11Zhejiang University 133.3%0—

Download all institutions as CSV

About this data

Papers. Robo-3Dvlm @ CVPR 2025 lists 4 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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. Comparisons with 2024 use shares, since the edition went from 1 to 4 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 3 of 4 papers (75.0%) 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 2026-11-17 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Robo-3Dvlm @ CVPR 2025”, https://lacuna.tiptreesystems.com/venue/robo-3dvlm-cvpr/2025.

Top Authors

AuthorPapers
Ainaz Eftekhar1
Ali Farhadi1
Alvaro Herrasti1
Aniruddha Kembhavi1
Chenrui Tie1
Cho-Ying Wu1
Ege Caglar1
Eli VanderBilt1
Guoquan Huang1
Haonan Chen1
Jaimyn Drake1
Jingxiang Guo1
Jinxuan Zhu1
Jordi Salvador1
Junting Chen1
Kiana Ehsani1
Kuo-Hao Zeng1
Lin Shao1
Liu Ren1
Luca Weihs1

Papers

Title
Agentic Language-Grounded Adaptive Robotic Assembly
Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
Online Language Splatting
The One RING: a Robotic Indoor Navigation Generalist