Unnat Jain
22 papers · 2017–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π§ Keyword Pioneer π Cross-Pollinator (11) π Conference Polyglot (9) π Academic Marathon (8) π Renaissance Researcher (8)
π
Renaissance Researcher
(8)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(38)
π₯
Mega-Team
(23)
π§¬
Topic Evolution
ποΈ
Keyword Collector
(86)
β‘
Prolific Year
(5)
π₯
Unstoppable
(9)
π
Trend Setter
π
Century Club
(21)
Conferences
CVPR (4)
NIPS (4)
ICCV (3)
CORL (2)
ECCV (2)
ICLR (2)
ICML (2)
EACL (1)
EMNLP (1)
WACV (1)
Top co-authors
Keywords
multi-agent system
(4)
visual question answering
(3)
embodied agent
(3)
embodied ai
(3)
imitation learning
(2)
egocentric vision
(2)
representation learning
(2)
reinforcement learning
(2)
object navigation
(2)
multi-object navigation
(2)
audio-visual learning
(1)
multimodal learning
(1)
question answering
(1)
action recognition
(1)
multi-agent reinforcement learning
(1)
knowledge distillation
(1)
visual dialog
(1)
attention mechanism
(1)
question generation
(1)
instruction following
(1)
Papers
Compositional Reasoning via Joint Image and Language Decomposition
EACL 2026
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
ICLR 2025
Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
ICLR 2024
MOPA: Modular Object Navigation With PointGoal Agents
WACV 2024
Pretrained Language Models as Visual Planners for Human Assistance
ICCV 2023
An Unbiased Look at Datasets for Visuo-Motor Pre-Training
CORL 2023
Adaptive Coordination in Social Embodied Rearrangement
ICML 2023
Affordances From Human Videos as a Versatile Representation for Robotics
CVPR 2023
Last-Mile Embodied Visual Navigation
CORL 2022
Learning State-Aware Visual Representations from Audible Interactions
NIPS 2022
Bridging the Imitation Gap by Adaptive Insubordination
NIPS 2021
Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
ICCV 2021
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
EMNLP 2021
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
ICML 2021
GridToPix: Training Embodied Agents With Minimal Supervision
ICCV 2021
SoundSpaces: Audio-Visual Navigation in 3D Environments
ECCV 2020
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
NIPS 2020
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
ECCV 2020
TAB-VCR: Tags and Attributes based VCR Baselines
NIPS 2019
Two Body Problem: Collaborative Visual Task Completion
CVPR 2019
Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering
CVPR 2018
Creativity: Generating Diverse Questions Using Variational Autoencoders
CVPR 2017