Publications

CodeNav: Beyond tool-use to using real-world codebases with LLM agents
Tanmay Gupta*   Luca Weihs*   Aniruddha Kembhavi
arXiv 2024

 
 

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
Zixian Ma   Weikai Huang   Jieyu Zhang   Tanmay Gupta   Ranjay Krishna
arXiv 2024

 
 

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
Tanmay Gupta*   Kiana Ehsani*   Luca Weihs*   Rose Hendrix*   Jordi Salvador*   Kuo-Hao Zeng*   Kunal Pratap Singh   Yejin Kim   Winson Han   Alvaro Herrasti   Ranjay Krishna   Dustin Schwenk   Eli VanderBilt   Aniruddha Kembhavi
CVPR 2024

 
 

Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
Tejas Srinivasan   Jack Hessel   Tanmay Gupta   Bill Yuchen Lin   Yejin Choi   Jesse Thomason   Khyathi Raghavi Chandu
ACL Findings 2024

 
 

OBJECT 3DIT: Language-guided 3D-aware Image Editing
Oscar Michael   Anand Bhattad   Ranjay Krishna   Aniruddha Kembhavi   Tanmay Gupta
NeurIPS 2023

 
 

Visual Programming: Compositional visual reasoning without training
Tanmay Gupta   Aniruddha Kembhavi
CVPR 2023

 
 

GRIT: General Robust Image Task Benchmark
Tanmay Gupta   Ryan Marten   Aniruddha Kembhavi   Derek Hoiem
arXiv 2022

 
 

Webly Supervised Concept Expansion for General Purpose Vision Models
Amita Kamath*   Christopher Clark*   Tanmay Gupta*   Aniruddha Kembhavi   Derek Hoiem
ECCV 2022

 
 

Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture
Tanmay Gupta   Amita Kamath   Aniruddha Kembhavi   Derek Hoiem
CVPR 2022 (Oral)

 
 

Learning Curves for Analysis of Deep Networks
Derek Hoiem   Tanmay Gupta   Zhizhong Li   Michal M. Shlapentokh-Rothman
ICML 2021

 
 

Visual Semantic Role Labeling for Video Understanding
Arka Sadhu   Tanmay Gupta   Mark Yatskar   Aniruddha Kembhavi
CVPR 2021

 
 

Contrastive Learning for Weakly Supervised Phrase Grounding
Tanmay Gupta   Arash Vahdat   Gal Chechik   Xiaodong Yang   Jan Kautz   Derek Hoiem
ECCV 2020 (Spotlight)

 
 

PhD Thesis: Representations from Vision and Language
Tanmay Gupta
Thomas M. Siebel Center for Computer Science
University of Illinois Urbana-Champaign
May 2020

 
 

ViCo: Word Embeddings from Visual Co-occurrences
Tanmay Gupta   Alexander Schwing   Derek Hoiem
ICCV 2019

 
 

No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques
Tanmay Gupta   Alexander Schwing   Derek Hoiem
ICCV 2019

 
 

Imagine This! Scripts to Compositions to Videos
Tanmay Gupta   Dustin Schwenk   Ali Farhadi   Derek Hoiem Aniruddha Kembhavi
ECCV 2018

 
 

Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
Tanmay Gupta   Kevin Shih   Saurabh Singh   Derek Hoiem
ICCV 2017

 
 

3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Tanmay Gupta   Daeyun Shin   Naren Sivagnanadasan   Derek Hoiem
arXiv 2016

 
 

Completing 3D Object Shape from One Depth Image
Jason Rock   Tanmay Gupta   Justin Thorsen   JunYoung Gwak   Daeyun Shin   Derek Hoiem
CVPR 2015

 
 

Face Tracking and Recognition with Orientation, Pose and Illumination Variations
Tanmay Gupta   Shubham Gupta   Aditya K. Jagannatham
Undergraduate Thesis, Department of Electrical Engineeging, IIT Kanpur. 2014