Zsolt Kira — Publications

2026

ECCVC96

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

K. Yadav, Y. Ali, G. Gupta, Y. Gal, Z. Kira

European Conference on Computer Vision (ECCV) arXiv Project Code Also in NeurIPS Workshop on SPACE in Vision, Language, and Embodied AI (SpaVLE), 2025.

WorkshopW21

EVE: A Generator-Verifier System for Generative Policies

Y. Ali, G. Patlin, K. Kothuri, J. Coholich, M.Z. Irshad, W. Liang, and Z. Kira

arXiv ICRA 2026 Workshop on Semantics for Reliable Robot Autonomy: From Environment Understanding and Reasoning to Safe Interaction PDF Talk ICRA 2026 Workshop on Data to Decisions: VLA Pipelines for Real Robots. PDF

WorkshopW20

Identifying and Mitigating Reasoning Errors in VLM Verifiers via Activation Decomposition

J. Cha, M. Andrade, and Z. Kira

ICLR 2026 VerifAI Workshop. OpenReview

CVPRC95

MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization

C. Huang, M.M. Zhang, R. Azarcon, G. Chou, Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. arXiv Project Code

CVPRC94

The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models

S. Chopra, S. Halbe, C. Huang, B. Maneechotesuwan, and Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. arXiv ★ Highlight

CVPRC93

Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective

B. Lai, X. Wang, S.S. Rambhatla, J.M. Rehg, Z. Kira, R. Girdhar, and I. Misra

Conference on Computer Vision and Pattern Recognition (CVPR), 2026. arXiv

ICRAC92

Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets

J. Coholich, J. Wit, R. Azarcon, and Z. Kira

International Conference on Robotics and Automation (ICRA). arXiv Project Code Also appeared in CVPR Embodied AI Workshop, 2026.

FindingsW19

EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction

X. Zhang, M.Z. Irshad, A. Yezzi, Y. Tsai, and Z. Kira

CVPR Findings, 2026 Also in CVPR Workshop on Generative Models for Computer Vision, 2026. arXiv

ICLRC91

Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

M. Andrade, J. Cha, B. Ho, V. Srihari, K. Yadav, and Z. Kira

International Conference on Learning Representations (ICLR) Also appeared in NeurIPS Workshop on Multi-Turn Interactions in Large Language Models (MT-LLM), 2026. arXiv

ConferenceC90

Grounding Descriptions in Images informs Zero-Shot Visual Recognition

S. Halbe, J. Tian, K.J. Joseph, J.S. Smith, K. Stevo, V.N. Balasubramanian, and Z. Kira

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026. arXiv

2025

NeurIPSC89

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

G. Gupta, K. Yadav, Z. Kira, Y. Gal, and R. Aljundi

International Conference on Neural Information Processing Systems (NeurIPS), 2025. arXiv

ICCVC88

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device

G. Chhablani, X. Ye, R. Grover, M.Z. Irshad, and Z. Kira

International Conference on Computer Vision (ICCV), 2025. Also apppeared in CVPR Embodied AI Workshop, 2025. arXiv Video

CVPRC87

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

A. Szot, B. Mazoure, O. Attia, A. Timofeev, H. Agrawal, D. Hjelm, Z. Gan, Z. Kira, and A.T. Toshev

Conference on Computer Vision and Pattern Recognition, 2025. arXiv ★ Oral presentation

CVPRC86

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

C. Huang*, B. Maneechotesuwan*, S. Chopra, and Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2025. arXiv Code

CVPRC85

When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach

V. Rathore, S. B, S. Dutta, S. Mehrotra, Z. Kira, B. Banerjee

Conference on Computer Vision and Pattern Recognition, 2025. arXiv

IJCAIC84

Adversarial Attacks Using Differentiable Rendering: A Survey

M. Hull, H. Wang, M. Lau, A. Helbling, M. Phute, C. Zhang, Z. Kira, W. Lunardi, M. Andreoni, W. Lee, and D.H. Chau

International Joint Conference on Artificial Intelligence (IJCAI) Survey Track, 2025. arXiv

ICLRC83

Directional Gradient Projection for Robust Fine-tuning of Foundation Models

C. Huang, J. Tian, B. Maneechotesuwan, S. Chopra, and Z. Kira

International Conference on Learning Representations (ICLR), 2025. arXiv

ICLRC82

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

A. Kumar, Z. Kira, and R.S. Rawat

International Conference on Learning Representations (ICLR), 2025. arXiv

ConferenceC81

Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion

J. Coholich, M.A. Murtaza, S. Hutchinson, and Z. Kira

American Control Conference (ACC), 2025. [arXiv coming soon]

2024

PreprintP5

ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI

A. Elawady, G. Chhablani, R. Ramrakhya, K. Yadav, D. Batra, Z. Kira, and A. Szot

arXiv:2410.02751 arXiv

PreprintP4

Neural Fields in Robotics: A Survey

M.Z. Irshad, M. Comi, Y.C. Lin, N. Heppert, A. Valada, R. Ambrus, Z. Kira, and J. Tremblay

arXiv:2410.20220 arXiv

NeurIPSC80

Grounding Multimodal Large Language Models in Actions

A. Szot, B. Mazoure, H. Agrawal, D. Hjelm, Z. Kira, and A. Toshev

Conference on Neural Information Processing Systems (NeurIPS) arXiv

NeurIPSC79

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control

G. Gupta, K. Yadav, Y. Gal, D. Batra, Z. Kira, C. Lu, and T.G.J. Rudner

Conference on Neural Information Processing Systems (NeurIPS) arXiv Also in CVPR Workshops 2024: Workshop on Reliable and Responsible Foundation Models and ICRA 2024 VLMNM Workshop, ICLR 2024 Workshop on Reliable and Responsible Foundation Models.

NeurIPSC78

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models

J. Tian, C. Huang, and Z. Kira

Conference on Neural Information Processing Systems (NeurIPS) arXiv

TMLRJ8

Continual Adaptation of Vision Transformers for Federated Learning

S. Halbe, J.S. Smith, J. Tian, and Z. Kira

Transactions on Machine Learning Research (TMLR) arXiv Code Also in NeurIPS Workshops 2023: Federated Learning in the Age of Foundation Models (Oral) as "HePCo: Data-Free Heterogeneous Prompt Consolidation for Continual Federated Learning".

ECCVC77

Reinforcement Learning via Auxiliary Task Distillation

A.N. Harish, L. Heck, J.P. Hanna, Z. Kira, and A. Szot

European Conference on Computer Vision (ECCV) arXiv

ECCVC76

NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

M.Z. Irshad, S. Zakahrov, V. Guizilini, A. Gaidon, Z. Kira, and R. Ambrus

European Conference on Computer Vision (ECCV) arXiv Project Code

TMLRJ7

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA

J.S. Smith, Y.C. Hsu, L. Zhang, T. Hua, Z. Kira, Y. Shen, and H. Jin

Transactions on Machine Learning (TMLR) arXiv

WorkshopW18

Adaptive Memory Replay for Continual Learning

J.S. Smith, L. Valkov, S. Halbe, V. Gutta, R. Feris, Z. Kira, and L. Karlinsky

CVPR Workshops 2024: Efficient Large Vision Models (Spotlight) arXiv

WorkshopW17

Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters

J.S. Smith, Y.C. Hsu, Z. Kira, Y. Shen, and H. Jin

CVPR Workshops 2024: 2nd Workshop on What is Next in Multimodal Foundation Models arXiv

CVPRC75

Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

J. Tian, L. Aggarwal, A. Colaco, Z. Kira, and M. Gonzalez-Franco

Conference on Computer Vision and Pattern Recognition (CVPR) arXiv Code

CVPRC74

Seeing the Unseen: Visual Common Sense for Semantic Placement

R. Ramrakhya, A. Kembhavi, D. Batra, Z. Kira, K.H. Zeng, and L. Weihs

Conference on Computer Vision and Pattern Recognition (CVPR). arXiv Code Also appeared in ICRA 2024 First Workshop on Vision-Language Models for Navigation and Manipulation.

CVPRC73

GOAT-Bench: A Benchmark for Multi-modal Lifelong Navigation

M. Khanna, R. Ramrakhya, G. Chhablani, S. Yenamandra, T. Gervet, M. Chang, Z. Kira, D.S. Chaplot, D. Batra, R. Mottaghi

Conference on Computer Vision and Pattern Recognition (CVPR). arXiv Project Code

WorkshopW19

ICE-G: Image Conditional Editing of 3D Gaussian Splats

V. Jaganathan, H.H. Huang, M.Z. Irshad, and Z. Kira

CVPR 2024 Workshops: AI for Content Creation Workshop, 2024. arXiv

ICRAC72

FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects

M. Lunayach, S. Zakharov, D. Chen, R. Ambrus, Z. Kira, and M.Z. Irshad

International Conference on Robotics and Automation (ICRA) arXiv Project

ICRAC71

N-QR: Natural Quick Response Codes for Multi-Robot Instance Correspondence

N. Glaser and Z. Kira

International Conference on Robotics and Automation (ICRA) arXiv

ICLRC70

Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots

X. Puig, E. Undersander, A. Szot, M.D. Cote, T.Y. Yang, R. Partsey, R. Desai, A. Clegg, M. Hlavac, S.Y. Min, V. Vondruš, T. Gervet, V.P. Berges, J.M. Turner, O. Maksymets, Z. Kira, M. Kalakrishnan, J. Malik, D.S. Chaplot, U. Jain, D. Batra, A. Rai, and R. Mottaghi

International Conference on Learning Representations (ICLR) arXiv Project

2023

PreprintP3

Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

Y. Hu, Q. Xie, V. Jain, J. Francis, J. Patrikar, N. Keetha, S. Kim, Y. Xie, T. Zhang, S. Zhao, Y. Chong, C. Wang, K. Sycara, M. Johnson-Roberson, D. Batra, X. Wang, S. Scherer, Z. Kira, F. Xia, and Y. Bisk

arXiv:2312.08782 [github (paper list)] arXiv Project

ConferenceC69

Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation

H. Maheshwari, Y.C. Liu, and Z. Kira

Winter Conference on Applications of Computer Vision (WACV) arXiv Project Code

ConferenceC68

LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration

R. Liu, S. Khose, J. Xiao, L. Sathidevi, K. Ramnath, Z. Kira, and E. Dyer

Winter Conference on Applications of Computer Vision (WACV) arXiv

NeurIPSC67

Fast Trainable Projection for Robust Fine-tuning

J. Tian, Y. Liu, J. Smith, Z. Kira

Conference on Neural Information Processing Systems (NeurIPS) arXiv Code

NeurIPSC66

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Y. Jain, H. Behl, Z. Kira, V. Vineet

Conference on Neural Information Processing Systems (NeurIPS) arXiv Code

NeurIPSC65

Training Energy-Based Normalizing Flow with Score-Matching Objectives

C.H. Chao, W.F. Sun, Y.C. Hsu, Z. Kira, C.Y. Lee

Conference on Neural Information Processing Systems (NeurIPS) arXiv Code

CoRLC64

HomeRobot: Open-Vocabulary Mobile Manipulation

S. Yenamandra, A. Ramachandran, K. Yadav, A.S. Wang, M. Khanna, T. Gervet, T.Y. Yang, V. Jain, A. Clegg, J.M. Turner, Z. Kira, M. Savva, A.X. Chang, D.S. Chaplot, D. Batra, R. Mottaghi, Y. Bisk, and C. Paxton

Conference on Robot Learning (CoRL). arXiv Code

PreprintP2

CLIP-GCD: Simple Language Guided Generalized Category Discovery

R. Ouldnoughi, C.W. Kuo, and Z. Kira

arXiv:2305.10420. arXiv

ICCVC63

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

M.Z. Irshad, S. Zakharov, K. Liu, V. Guizilini, T. Kollar, A. Gaidon, R. Ambrus, and Z. Kira

International Conference on Computer Vision (ICCV), 2023. arXiv Project Code

WorkshopW15

We Need to Talk: Identifying and Overcoming Communication-Critical Scenarios for Self-Driving

N. Glaser, Z. Kira

ICRA CoPerception: Collaborative Perception and Learning Workshop, 2023. arXiv ★ Second place for Best Paper Award!

ICMLC62

Adaptive Coordination in Social Embodied Rearrangement

A. Szot, U. Jain, Z. Kira, D. Batra, R. Desa, and A. Rai

International Conference on Machine Learning (ICML), 2023. arXiv

ConferenceC61

ConstraintMatch for Semi-Constrained Clustering

J. Goschenhofer, B. Bischl, and Z. Kira

International Conference on Neural Networks (IJCNN), 2023. ieee

WorkshopW14

A Closer Look at Rehearsal-Free Continual Learning

J. Smith, J. Tian, S. Halbe, Y.C. Hsu, and Z. Kira

CVPR Workshop on Continual Learning in Computer Vision (CLVISION), 2023. arXiv

CVPRC60

Trainable Projected Gradient Method for Robust Fine-tuning

J. Tian, X. Dai, C.Y. Ma, Z. He, Y.C. Liu, and Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2023. arXiv Code

CVPRC59

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

J. Smith, L. Karlinsky, V. Gutta, P. Cascante-Bonilla, D. Kim, A. Arbelle, R. Panda, R. Feris, and Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2023. arXiv Code

CVPRC58

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

C. Kuo and Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2023. arXiv Project Code Video

CVPRC57

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

J. Smith, P. Cascante-Bonilla, A. Arbelle, D. Kim, R. Panda, D. Cox, D. Yang, Z. Kira, R. Feris, and L. Karlinsky

Conference on Computer Vision and Pattern Recognition (CVPR), 2023. arXiv Code

ICLRC56

BC-IRL: Learning Generalizable Reward Functions from Demonstrations

A. Szot, A. Zhang, D. Batra, Z. Kira, and F. Meier

International Conference on Learning Representations (ICLR), 2023. arXiv OpenReview

ICRAC55

Communication-Critical Planning via Multi-Agent Trajectory Exchange

N. Glaser, Z. Kira

International Conference on Robotics and Automation (ICRA), 2023. arXiv

2022

RA-LJ6

Safe Reinforcement Learning using Robust Control Barrier Functions

Y. Emam, G. Notomista, P. Glotfelter, Z. Kira, and M. Egerstedt

IEEE Robotics and Automation Letters, 2022. arXiv

WorkshopW13

On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition

F. Rahman, O. Mubarek, and Z. Kira

NeurIPS Workshop on Vision Transformers: Theory and applications, 2022. arXiv

NeurIPSC54

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

Y.C. Liu, C.Y. Ma, Z. He, and Z. Kira

Neural Information Processing Systems (NeurIPS), 2022. arXiv Project

ConferenceC53

System Design for an Integrated Lifelong Reinforcement Learning Agent For Real-Time Strategy Games

S. Indranil, Z. Daniels, A. Raghavan, J. Hostetler, A. Rahman, M. Placentino, A. Divakaran, R. Corizzo, K. Faber, N. Japkowicz, M. Baron, J. Smith, S. Joshi, Z. Kira, T. Hayes, C. Kanan, and G. Gallardo

International Conference on AI-ML Systems, 2022. arXiv

ConferenceC52

Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation

C.W. Kuo, J. Hoffman, and Z. Kira

Winter Conference on Applications of Computer Vision (WACV), 2022. arXiv

ECCVC51

ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization

M.Z. Irshad, S. Zakharov, R. Ambrus, T. Kollar, Z. Kira, and A. Gaidon

European Conference on Computer Vision (ECCV), 2022. arXiv projec Code Video

ECCVC50

Open-Set Semi-Supervised Object Detection

Y.C. Liu, C.Y. Ma, X. Dai, J. Tian, P. Vajda, Z. He, and Z. Kira

European Conference on Computer Vision (ECCV), 2022. arXiv Project ★ Oral presentation

WorkshopW12

Lifelong Wandering: A realistic few-shot online continual learning setting

M. Lunayach, J. Smith, and Z. Kira

CVPR Workshop on Continual Learning (CLVISION), 2022. arXiv

Nature MIJ5

Biological underpinnings for lifelong learning machines

D. Kudithipudi, M. Aguilar-Simon, J. Babb, M. Bazhenov, D. Blackiston, J. Bongard, A.P. Brna, S.C. Raja, N. Cheney, J. Clune, A. Daram, S. Fusi, P. Helfer, L. Kay, N. Ketz, Z. Kira, S. Kolouri, J.L. Krichmar, S. Kriegman, M. Levin, S. Madireddy, S. Manicka, A. Marjaninejad, B. McNaughton, R. Miikkulainen, Z. Navratilova, T. Pandit, A. Parker, P.K. Pilly, S. Risi, T.J. Sejnowski, A. Soltoggio, N. Soures, A.S. Tolias, D. Urbina-Meléndez, F.J. Valero-Cuevas, G.M. van de Ven, J.T. Vogelstein, F. Wang, R. Weiss, A. Yanguas-Gil, X. Zou, H. Siegelmann

Nature Machine Intelligence, 2022. Nature

CVPRC49

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

C.W. Kuo, Z. Kira

Conference on Computer Vision and Pattern Recognition (CVPR), 2022. arXiv Project Code

CVPRC48

Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors

Y.C. Liu, C.Y. Ma, Z. Kira

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. arXiv Project Code

ICRAC47

Striking the Right Balance: Recall Loss for Semantic Segmentation

J. Tian, N.C. Mithun, Z. Seymour, H.P. Chiu, Z. Kira

International Conference on Robotics and Automation (ICRA), 2022. arXiv Code

ICRAC46

CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation

M.Z. Irshad, T. Kollar, M. Laskey, K. Stone, Z. Kira

International Conference on Robotics and Automation (ICRA), 2022. arXiv Project Code

2021

NeurIPSC45

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

J. Tian, D. Yung, Y.C. Hsu, Z. Kira

Neural Information Processing Systems (NeurIPS), 2021. arXiv Code Talk ★ Spotlight Paper (<3% accept) Also see follow-on preprint.

NeurIPSC44

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

A. Szot, A. Clegg, E. Undersander, E. Wijmans, Y. Zhao, J. Turner, N. Maestre, M. Mukadam, D. Chaplot, O. Maksymets, A. Gokaslan, V. Vondrus, S. Dharur, F. Meier, W. Galuba, A. Chang, Z. Kira, V. Koltun, J. Malik, M. Savva, D. Batra

Neural Information Processing Systems (NeurIPS). arXiv Project Video ★ Spotlight Paper (<3% accept) Also appears as an oral paper in the EcoRL NeurIPS workshop. Press: CNET | TechCrunch | VentureBeat | Wired (ME) | Ynet

ICCVC43

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

J. Smith, Y.C. Hsu, J. Balloch, Y. Shen, H. Jin, Z. Kira

International Conference on Computer Vision (ICCV), 2021. arXiv Project Code Talk

IROSC42

Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking

N. Glaser, Y.C.Liu, Z. Kira

International Conference on Intelligent Robots and Systems (IROS), 2021. arXiv Talk

PreprintP2

Striking the Right Balance: Recall Loss for Semantic Segmentation

J. Tian, N. Mithun, Z. Seymour, H.P. Chiu, Z. Kira

arXiv:2106.14917. arXiv

IJCNNC41

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

J. Smith, J. Balloch, Y.C. Hsu, and Z. Kira

International Conference on Neural Networks (IJCNN), 2021. arXiv Code Talk

ICRAC40

Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

M.Z. Irshad, C.Y. Ma, and Z. Kira

International Conference on Robotics and Automation (ICRA), 2021. arXiv Code Talk

ICRA
RA-LJ4, C39

LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation

J. Chen, Z. Kira, and Y. Cho

Robotics and Automation Letters (RA-L) (also accepted to ICRA), 2021. arXiv IEEE Code

ICLRC38

Unbiased Teacher for Semi-Supervised Object Detection

Y.C. Liu, C.Y. Ma, Z. He, C.W. Kuo, K. Chen, P. Zhang, B. Wu, Z. Kira, and P. Vajda

International Conference on Learning Representations (ICLR), 2021. arXiv Project Code Talk

2020

NeurIPSC37

Posterior Re-calibration for Imbalanced Datasets

J. Tian, Y.C. Liu, N. Glaser, Y.C. Hsu, Z. Kira

Neural Information Processing Systems (NeurIPS), 2020. arXiv Code

PreprintP1

Frustratingly Simple Domain Generalization via Image Stylization

N. Somavarapu, C.Y. Ma, and Z. Kira

arXiv 2006.11207, 2020. arXiv Talk

ECCVC36

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

C.W. Kuo, C.Y Ma, J.B. Huang, and Z. Kira

European Conference on Computer Vision (ECCV), 2020. arXiv Project Code Talk

ECCVC35

Learning to Generate Grounded Image Captions without Localization Supervision

C.Y. Ma, Y. Kalantidis, G. AlRegib, P. Vajda, M. Rohrbach, and Z. Kira

European Conference on Computer Vision (ECCV), 2020. arXiv Project Code

WorkshopW11

Enhancing Multi-Robot Perception via Learned Data Association

N. Glaser, Yen-Cheng Liu, Junjiao Tian, and Z. Kira

Emerging Learning & Algorithmic Methods for Data Association in Robotics Workshop, ICRA 2020. PDF Talk

CVPRC34

When2com: Multi-agent perception via Communication Graph Grouping

Y.C. Liu, J. Tian, N. Glaser, and Z. Kira

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. arXiv Code

CVPRC33

Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

Y.C. Hsu, Y. Shen, H. Jin, and Z. Kira

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. arXiv

CVPRC32

Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation

M.H. Chen, B. Li, Y. Bao, G. AlRegib, and Z. Kira

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [github] arXiv

ICRAC31

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

J. Tian, W. Cheung, N. Glaser, Y.C. Liu, and Z. Kira

IEEE International Conference on Robotics and Automation (ICRA), 2020. Also in IROS Workshop on the Importance of Uncertainty in Deep Learning for Robotics, 2019. arXiv Code

ICRAC30

Who2com: Collaborative Perception via Learnable Handshake communication

Y.C. Liu, J. Tian, C.Y. Ma, N. Glaser, C.W. Kuo, and Z. Kira

IEEE International Conference on Robotics and Automation (ICRA), 2020. arXiv

AAAIC29

Path Ranking with Attention to Type Hierarchies

W. Liu, A. Daruna, Z. Kira, and Sonia Chernova

Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2019. arXiv ★ Oral presentation

2019

WorkshopW10

Sub-Task Discovery with Limited Supervision: A Constrained Clustering Approach

P. Odom, A. Keech, and Z. Kira

2nd Learning from Limited Labeled Data (LLD) Workshop ICLR 2019. OpenReview

WorkshopW9

Adaptation to Dangerous Environments Through Automated Reward Shaping

J. Schlosser, P. Odom, A. Keech, and Z. Kira

Safe Machine Learning Workshop, ICLR 2019. PDF

ICCVC28

Temporal Attentive Alignment for Large-Scale Video Domain Adaptation

M.H. Chen, Z. Kira, G. AlRegib, J. Yoo, R. Chen, and J. Zheng

International Conference in Computer Vision (ICCV), 2019. arXiv Code Also appeared in CVPR Workshop on Learning From Unlabeled Videos (LUV). ★ Oral presentation

ReportR5

Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification

C.W. Kuo, C.Y. Ma, J.B. Huang, and Z. Kira

arXiv 1906.05202, 2019. arXiv Project

CVPRC27

The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation

C.Y. Ma, Z. Wu, G. AlRegib, C. Xiong, and Z. Kira

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. arXiv Project Code ★ Oral presentation (5.6% Acceptance)

ICRAC26

RoboCSE: Robot Common Sense Embedding

A. Daruna, Z. Kira, and S. Chernova

IEEE International Conference on Robotics and Auomation (ICRA), 2019. arXiv

RA-LJ3

Multi-view Incremental Segmentation of 3D Point Clouds for Mobile Robots

J. Chen, Y. Cho, and Z. Kira

IEEE Robotics and Automation Letters (RA-L), 2019. arXiv IEEE

JournalJ2

Deep Learning Approach to Point Cloud Scene Understanding for Automated Scan to 3D Reconstruction

J. Chen, Z. Kira, and Y. Cho

ASCE Journal of Computing in Civil Engineering. 2019. ASCE

ICLRC25

Multi-class classification without multi-class labels "

Y.C. Hsu, Z. Lv, J. Schlosser, P. Odom, and Z. Kira

International Conference on Learning Representations (ICLR), 2019. arXiv OpenReview Code

ICLRC24

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation"

C.Y. Ma, J. Lu, Z. Wu, G. AlRegib, Z. Kira, R. Socher, and C. Xiong

International Conference on Learning Representations (ICLR), 2019. arXiv OpenReview Code ★ Top 7% of reviews

ICLRC23

A Closer Look at Few-shot Classification

W. Chen, Y.C. Liu, Z. Kira, Y.C. Wang, J. Huang

International Conference on Learning Representations (ICLR), 2019. OpenReview Project Code

WACVC22

Data-Efficient Graph Embedding Learning for PCB Component Detection

C.W. Kuo, J. Ashmore, D. Huggins, and Z. Kira

IEEE Winter Conf. on Applications of Computer Vision (WACV), 2019. arXiv Project Data

JournalJ1

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

C.Y., Ma M.H. Chen, Z. Kira, and G. AlRegib

Journal of Signal Processing: Image Communication, 2019. arXiv Journal link Code

2018

WorkshopW8

Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines

Y.C. Hsu, Y.C. Liu , and Z. Kira

NeurIPS Workshop on Continual Learning, 2018. arXiv Code

WorkshopW7

A probabilistic constrained clustering for transfer learning and image category discovery

Y.C. Hsu, Z. Lv, J. Schlosser, P. Odom, Z. Kira

CVPR Deep-Vision Workshop, 2018. arXiv Code

ConferenceC21

Learning to Cluster for Proposal-Free Instance Segmentation

Y.C. Hsu, Z. Xu, Z. Kira, and J. Huang

International Conference on Neural Networks (IJCNN), 2018. arXiv ★ Won 2nd place in CVPR lane detection challenge

CVPRC20

Attend and Interact: Higher-Order Object Interactions for Video Understanding

C.Y. Ma, A. Kadav, I. Melvin, Z. Kira, G. AlRegib, and H. Peter Graf

IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2018. arXiv blog FIVER CVPR Workshop version

ICLRC19

Learning to Cluster in order to Transfer Across Domains and Tasks

Y.C. Hsu, Z. Lv, Z. Kira

International Conference on Learning Representations (ICLR), 2018. arXiv Code ★ Top 7% of reviews

2017

ReportR4

How to Train Your DRAGAN

N. Kodali, J. Abernethy, J. Hays, and Z. Kira

(note:retitled) arXiv Code

WorkshopW6

Grounded Objects and Interactions for Video Captioning

C.Y. Ma, A. Kadav, I. Melvin, Z. Kira, G. AlRegib, and H. Peter Graf

NeurIPS Workshop on Visually-Grounded Interaction and Language (ViGIL), 2017. arXiv

2016

ECCVC18

A Continuous Optimization Approach for Efficient and Accurate Scene Flow

Lv, Z., Beall, C., Alcantarilla, P.F., Li, F., Kira, Z., and Dellaert, F.

European Conference on Computer Vision (ECCV), 2016. arXiv KITTI Benchmark Project

WorkshopW5

Neural network-based clustering using pairwise constraints

Hsu, Y.C. and Kira, Z.

International Conference on Learning Representations Workshop Track (ICLR), 2016. arXiv (extended paper) PDF Project Code

ICRAC17

Fusing LIDAR and Images for Pedestrian Detection using Convolutional Neural Networks

Schlosser, J., Chow, C., and Kira, Z.

IEEE International Conference on Robotics and Automation (ICRA), 2016.

2015

ConferenceC16

From Deep Learning to Episodic Memories: Creating Categories of Visual Experiences

Doshi, J., Kira, Z., and Wagner, A.R.

in proceedings of the Third Annual Conference on Advances in Cognitive Systems (ACS), 2015. (Based on previous work here.)

ICRAC15

An Evaluation of Features for Classifier Transfer during Target Handoff Across Aerial and Ground Robots

Kira, Z.

in proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2015.

WorkshopW4

STAC: a new fusion model for complex scene characterization and semantic mapping

Kira, Z., Wagner, A.R, Kennedy, C., Zutty, J., Tuell, G.

SPIE conference on Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications, 2015.

2014

BMVCC14

Mining Structure Fragments for Smart Bundle Adjustment

Carlone, L., Alcantarilla, P., Chiu, H., Kira, Z., and Dellaert, F.

, in proceedings of the British Machine Vision Conference (BMVC), 2014. PDF ★ Oral presentation (7.7% acceptance)

ReportR3

Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning

Doshi, J., Mason, C., Wagner, A.R., Kira, Z.

Georgia Tech technical report, GT-CS-14-07, 2014. PDF

IROSC13

Transfer of Sparse Coding Representations And Object Classifiers Across Heterogeneous Robots

Kira, Z., "

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2014. PDF

ICRAC12

Eliminating Conditionally Independent Sets in Factor Graphs: A Unifying Perspective based on Smart Factors

L. Carlone, Z. Kira, C. Beall, V. Indelman, F. Dellaert

in proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2014. PDF

2012

IROSC11

Long-Range Pedestrian Detection using Stereo and a Cascade of Convolutional Network Classifiers

Kira, Z., Hadsell, R., Salgian, G., and Samarasekera, S.

IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012. PDF

WorkshopW3

Multi-Sensor Fusion for Pedestrian Detection on the Move

Kira, Z., Southall, B., Kuthirummal, S., and Eledath, J.

IEEE International Conference on Technologies for Practical Robot Applications (poster), 2012.

ConferenceC10

Unsupervised Topic Modeling for Leader Detection in Spoken Discourse

Hadsell, R., Kira, Z., Wang, W., Precoda, K.

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2012.

ConferenceC9

Detecting Leadership and Cohesion in Spoken Interactions

Wang, W., Precoda, K., Hadsell, R., Kira, Z., Richey, C., Jiva, G.

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2012.

2010

ThesisPh.D.

Kira, Z., Communication and Alignment of Grounded Symbolic Knowledge Among Heterogeneous Robots, Ph.D. Dissertation, College of Computing, Georgia Institute of Technology, May 2010. PDF

AAMASC8

Inter-Robot Transfer Learning for Perceptual Classification

Kira, Z.

9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2010. PDF ★ CoTeSys Best Robotics Paper (also nominated for Best Student/Best Paper awards)

WorkshopW2

A Design Process for Robot Capabilities and Missions Applied to Microautonomous Platforms

Kira, Z., Collins, T., and Arkin, R.C.

SPIE Conference on Micro- and Nanotechnology Sensors, Systems, and Applications II, 2010.

WorkshopW1

Mission Specification and Control for Unmanned Aerial and Ground Vehicles for Indoor Target Discovery and Tracking

Ulam, P., Kira, Z., Collins, T., and Arkin, R.C.

SPIE Conference on Ground/Air Multi-Sensor Interoperability, Integration, and Networking for Persistent ISR, 2010.

2009

IROSC7

Transferring Embodied Concepts between Perceptually Heterogeneous Robots

Kira, Z.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4650-4656, 2009. PDF

ConferenceC6

Mapping Grounded Object Properties across Perceptually Heterogeneous Embodiments

Kira, Z.

Proceedings of the 22nd International FLAIRS Conference, pp. 57-62, 2009. PDF ★ Best Student Paper award

ConferenceC5

Exerting Human Control Over Decentralized Robot Swarms

Kira, Z., Potter, M.A.

4th International Conference on Autonomous Robots and Agents, 2009. PDF

2007

ConferenceC4

Modeling Robot Differences by Leveraging a Physically Shared Context

Kira, Z., Long, K.

in L. Berthouze, C.G. Prince, M. Littman, H. Kozima, & C. Balkenius (Eds.), Proceedings of the Seventh International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, pp. 53-59, 2007. Sweden: Lund University Cognitive Studies. PDF

IROSC3

Modeling Cross-Sensory and Sensorimotor Correlations to Detect and Localize Faults in Mobile Robots

Kira, Z.

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1520-1550, 2007. San Diego, CA, USA. PDF

2006

IROSC2

Continuous and Embedded Learning for Multi-Agent Systems

Kira, Z., and Schultz, A.C.,

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3184-3190, 2006. PDF

2004

ReportR2

Spatio-Temporal Case Based Reasoning for Efficient Reactive Robot Navigation

Likhachev, M., Kaess, M., Kira, Z., and R.C. Arkin

PDF

IROSC1

Forgetting Bad Behavior: Memory Management for Case-Based Navigation

Kira, Z. and Arkin, R.C.

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3145-3152, 2004. PDF Earlier Tech report

ReportR1

Self Organization in Artificial Intelligence and the Brain

Kira, Z., and Ranganathan, A.

PDF