https://xitter.cf/t.co/Bd2gisj8hY
Princeton, NJ
Joined March 2023
- Tweets59
- Following2
- Followers1.8K
- Likes2
Princeton Vision & Learning Lab retweeted
Researchers are actively improving memory for LLMs/VLMs. But are we measuring it right?
A system can score 100% by rereading the input for each question. If a human did that, we’d call it terrible memory!
We test beyond accuracy with ECC: Efficiency, Compression, Calibration. 🧵
Princeton Vision & Learning Lab retweeted
We have released an initial Infinigen2-Flying-Indoors dataset! It provides 2000 stereo videos, 24 frames each, with ground truth for depth, flow, normals, segmentation, albedo and more. Each group of 4 trajectories provides random synchronized views of the same procedural dynamic 3D scene.
Code to replicate it will be released soon as infinigen2.0.0a2. See full youtube preview & huggingface link below ↓
Princeton Vision & Learning Lab retweeted
Thrilled to share that I'll be joining the University of Michigan as an Assistant Professor in Fall 2027!
My lab will work on Robot Learning, Dexterous Manipulation, Robot Foundation Models & 3D Perception. I'm looking for students to join me. Please apply and reach out.
(1/2)
Princeton Vision & Learning Lab retweeted
Stereo depth is important in robotics, and relies heavily on synthetic data. But what actually makes for good synthetic data?
In WMGStereo, we study dataset design and discover a powerful data recipe - just 500 samples of our data can match 40k Sceneflow samples! 🧵[1/7]
Princeton Vision & Learning Lab retweeted
Can Visual Language Models (VLMs) do non-local visual reasoning, i.e., piecing together scattered visual evidence? Humans do this to search images, compare objects, and trace lines. Despite recent advances, our new evaluation suggests most VLMs cannot do these consistently. 1/6
