Research Scientist at Meta. I did a postdoc at Stanford and PhD at CMU. I work on computer vision and machine learning.

Redmond, WA
Joined August 2020
Introducing VOTSp2026 — a new point tracking challenge! 50 hand-picked videos including animals, robots, cells, egocentric capture, and more, with clean annotations and standardized evaluation. Submit your tracker and compete: votchallenge.net/vots2026/
5
1
34
8,898
Adam W. Harley retweeted
We released the code and model weights here: github.com/ayushjain1144/tra…. Have fun! 🙂
1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames). Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video. trackeverything.github.io
6
128
3
1,197
48,673
Our team is hiring PhD interns now for 2027. Ping me if you are interested and qualified, especially if you work on similar problems as me.
5
15
178
13,404
Adam W. Harley retweeted
Check out TrackEverything from CMU Robotics. 💡 TrackEverything is a Long-term 3D point tracking method (1000+ frames), using depth and camera pose to see the world in a stable coordinate system. TrackEverything is especially effective for egocentric capture setups like Project Aria glasses. Amazing work by @ayushjain1144 while interning with @AdamWHarley at Meta. 🚀
1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames). Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video. trackeverything.github.io
1
7
52
5,327
Adam W. Harley retweeted
1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames). Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video. trackeverything.github.io
25
183
14
1,662
139,546
Adam W. Harley retweeted
The deadline for participating in the VOTSp2026 point tracking is this Sunday, June 28! Preparing a submission should take a couple hours max (especially with a coding agent involved). Give it a shot! The results of the challenge will be presented at ECCV 2026.
Introducing VOTSp2026 — a new point tracking challenge! 50 hand-picked videos including animals, robots, cells, egocentric capture, and more, with clean annotations and standardized evaluation. Submit your tracker and compete: votchallenge.net/vots2026/
3
9
3,590
The deadline for participating in the VOTSp2026 point tracking is this Sunday, June 28! Preparing a submission should take a couple hours max (especially with a coding agent involved). Give it a shot! The results of the challenge will be presented at ECCV 2026.
Introducing VOTSp2026 — a new point tracking challenge! 50 hand-picked videos including animals, robots, cells, egocentric capture, and more, with clean annotations and standardized evaluation. Submit your tracker and compete: votchallenge.net/vots2026/
3
9
3,590
Very fun: Our paper for Insect Science is one of the journal's most-viewed articles of 2025! Yay for point tracking + vibrational signal analysis (with @JPolajnar)! BTW the underlying point tracker here is basically "PIPs+++" -- a simple method tuned well can do a lot!
1
1
1
37
9,787
Adam W. Harley retweeted
The Project Aria team is excited to be part of the Third Joint Egocentric Vision (EgoVis) Workshop at #CVPR2026! 👓✨ Don’t miss the latest Project Aria updates as we dive into the future of egocentric perception. Check out the full program of invited speakers below! 📅 June 3, 2026 📍 Colorado Convention Center | Room 704/706 🔗 egovis.github.io/cvpr26/ ⚡️@liuziwei7 , @mapo1 , @doughty_hazel
5
19
3,184
Adam W. Harley retweeted
Dynamic 3D from monocular video 🎥 Static pre-scan + video = richer reconstruction ✨ As image-to-3D improves, static pre-scans become increasingly practical! Kudos to @tnarek99 and team! drops-dynamics.github.io
Excited to present DRoPS! A novel method for dynamic 3D reconstruction from monocular videos, accompanied by a static-prescan of the dynamic object. 🌐 Project: drops-dynamics.github.io 📄 Paper: arxiv.org/abs/2603.24770 🧵 [1/7]
2
8
49
5,466
Adam W. Harley retweeted
Excited to present DRoPS! A novel method for dynamic 3D reconstruction from monocular videos, accompanied by a static-prescan of the dynamic object. 🌐 Project: drops-dynamics.github.io 📄 Paper: arxiv.org/abs/2603.24770 🧵 [1/7]
7
32
4
221
35,040
Adam W. Harley retweeted
New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 research.nvidia.com/labs/sil… 1/10
12
125
10
642
145,761
Adam W. Harley retweeted
Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: facebookresearch.github.io/S… Paper: arxiv.org/abs/2601.11514 Links to code and huggingface below ⬇️
17
145
8
1,007
71,107
Adam W. Harley retweeted
📢 New Paper PointSt3R: Point Tracking through 3D Grounded Correspondence Can point tracking be re-formulated as pairwise frame correspondence solely? We fine-tuning MASt3R with dynamic correspondences and a visibility loss and achieve competitive point tracking results 1/3
3
21
1
122
10,502
Adam W. Harley retweeted
Generative Point Tracking with Flow Matching My latest project with @AdamWHarley @CSProfKGD @DerekRenderling @chrisjpal Project page: mtesfaldet.net/genpt_projpag… Paper: arxiv.org/abs/2510.20951 Code: github.com/tesfaldet/genpt
2
25
2
132
10,477
Adam W. Harley retweeted
Happy 80th birthday to the legend Takeo Kanade! 🐐 Thanks @katerinafrag for sharing!
3
9
1
124
13,892
Yup! But I wouldn't say "single shot" -- AllTracker, inheriting from CoTracker and PIPs and RAFT, is an iterative approach. In practice, we iterate 4x to get the final answer (and this sums to 11 FPS at 576x1024).
AllTracker. Hi-res, dense point tracking across long video ranges in a single shot. Tracks every pixel. Fast, lightweight (16M params). Sparse tracking is obsolete. alltracker.github.io/
9
1,269
The visualizer in the AllTracker repo is now GPU-based (much faster), with new options to improve clarity. Very satisfying to see 3D shape "pop out" from the tracking. github.com/aharley/alltracke…
3
40
2
321
20,572
Alternate sampling rates.
8
835
We made a @gradio demo for AllTracker! AllTracker is the current state-of-the-art for general-purpose point tracking. The demo gives a good sense of the accuracy---try your own videos and see for yourself! 🔗 Demo: huggingface.co/spaces/aharle… 💻 Code: github.com/aharley/alltracke…
9
63
3
362
41,643