2026
| Jun | After 6 wonderful years at Ai2, I am joining Hark to build the next generation of computer-use agents! ↗ | |
| Mar | Launching MolmoWeb: An open visual web agent and open data for the open web ↗ | |
| Jan | New blog post on rediscovering Makefile in the era of Python and AI ↗ | |
| Jan | The New Year issue of The Batch is out with takes from myself and a handful of other researchers on where AI research needs to go in 2026 ↗ |
2025
| Dec | Serving as an Area Chair for CVPR 2026 | |
| Dec | New work on long-horizon video reasoning agents called SAGE out on arxiv ↗ | |
| Oct | Many thanks to all participants of the ICCV 2025 Doctoral Consortium for a fun event and to NSF and ICCV conference for providing financial support to the participating students! | |
| Oct | Participated in a fun debate at the ICCV 2025 AC workshop on whether "Computer vision researchers will be obsolete in 5 years due to VLMs" ↗ | |
| Jul | Serving as Doctoral Consortium Chair for ICCV 2025 ↗ | |
| Jun | Talk at Seattle's AI House titled "chmod 007 - Agents with license to execute (your codebase)" ↗ | |
| Mar | I became a dad! On parental leave for a few weeks | |
| Feb | MutaGrep out on arxiv - work on planning for code-use with neural tree search. ↗ |
2024
| Jun | Distinguished guest lecture at IIT Kanpur's "Seminar on AI, ML, and Deep Learning" | |
| May | Serving as an Area Chair for NeurIPS 2024 | |
| Feb | Presented SPOC & ReCOVERR at UW ↗ | |
| Jan | Presented SPOC at UCSD ↗ | |
| Jan | Gave a talk on "The slow & steady march for generality in vision" at USC ↗ |
2023
| Dec | Invited talk at Adobe on VisProg ↗ | |
| Nov | Serving as an Area Chair for CVPR 2024 | |
| Oct | Invited talk at Mitsubishi Electric Research Labs (MERL) Seminal Series on VisProg ↗ | |
| Sep | Recognized as Outstanding Reviewer at ICCV 2023! | |
| Aug | Serving as an Area Chair for NeurIPS 2023 | |
| Jun | VisProg received the Best Paper Award at CVPR 2023! ↗ | |
| Jun | Hosted GRIT Challenge at CVPR 2023 as part of VPLOW Workshop ↗ | |
| Jan | Invited talk in DNOW workshop at WACV 2023 on "Novelty in the Open World - A generalist & multimodal perspective" ↗ |
2022
| Nov | Checkout VisProg - a neuro-symbolic system using GPT3 for generating programs for solving complex visual tasks described in natural language. No backprop required! ↗ | |
| Sep | Serving as an Area Chair for CVPR 2023 | |
| Sep | My thoughts on Meta's new text-to-video model (Make-A-Video) in an MIT Tech Review article ↗ | |
| May | GRIT Benchmark is ready to test generality, robustness, and calibration of your models for 7 diverse vision and vision-language tasks! ↗ | |
| Mar | GPV-1 accepted to CVPR 2022! | |
| Feb | GPV-2, a stronger GPV model that learned 10,000 concepts from the web across 5 skills, released on arXiv. ↗ | |
| Feb | Invited guest speaker at IIT Kanpur ML School ↗ |
2021
| May | Recognized as an "Outstanding Reviewer" for CVPR 2021! | |
| May | Striving towards General Purpose Vision! Checkout the GPV-1 demo. ↗ | |
| May | Create learning curves to analyze deep classifiers using our ICML 2021 work. ↗ | |
| Apr | The VidSitu dataset and the VidSRL challenge at CVPR 2021 are now live. ↗ |
2020
| Aug | Contrastive learning approach to weakly supervised phrase grounding presented at ECCV 2020. | |
| Aug | Recognized as an "Outstanding Reviewer" for ECCV 2020! | |
| Jul | Joined PRIOR @ AI2 as a Research Scientist. ↗ | |
| May | Defended my thesis! Thesis & Slides ↗ |
2019
| Sep | Lecture material for guest lecture at CS 598RK - HCI for ML (Fall 2019). ↗ | |
| Sep | Code and data released for ICCV 2019 papers - ViCo and No-Frills Human-Object Interaction Detection |