Jay Karhade
@JayKarhade
Followers
397
Following
292
Media
5
Statuses
143
PhD Robotics @CMU_Robotics, Computer Vision, Robotics.
Joined September 2022
Summer Update: Had an incredible research internship at @theworldlabs 🌎working towards #SpatialAI 🚀🚀. Next Up: PhD @CMU_Robotics !
Hello, world! We are World Labs, a spatial intelligence company building Large World Models (LWMs) to perceive, generate, and interact with the 3D world. Read more:
2
11
156
RT @Haoyu_Xiong_: Your bimanual manipulators might need a Robot Neck 🤖🦒. Introducing Vision in Action: Learning Active Perception from Huma….
0
84
0
RT @zhenjun_zhao: UFM: A Simple Path towards Unified Dense Correspondence with Flow. @YuchenZhan54250, @Nik__V__, Chenwei Lyu, @robo2902, Y….
0
7
0
UFM is a step forward towards solving the top 3 problems of computer vision: Correspondence, Correspondence and Correspondence 🙃. Exciting colab which was led by @YuchenZhan54250! 1 year in the making, and lots of engineering and insights uncovered!.
Introducing UFM, a Unified Flow & Matching model, which for the first time shows that the unification of optical flow and image matching tasks is mutually beneficial and achieves SOTA. Check out UFM’s matching in action below! 👇. 🌐 Website: 🧵👇
0
0
11
RT @drfeifei: Check out this shiny new, fast and dynamic web renderer for 3D Gaussian Splats! The things one could do are just mind bogglin….
0
40
0
RT @AjdDavison: All researchers should fight against this. Every week I try to persuade my students that top papers often have few quantita….
0
95
0
RT @akashshrm02: Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tact….
0
47
0
RT @mihirp98: Excited to share our work: Maximizing Confidence Alone Improves Reasoning. Humans rely on confidence to learn when answer key….
0
37
0
RT @akashshrm02: Last week I passed my thesis proposal, and I'm now officially a Ph.D. candidate! .My proposed thesis "Self supervised perc….
0
1
0
RT @jcjohnss: Compute increases in the last ~decade are insane. The B200 is 1000x faster than the K40 that was state-of-the-art when I sta….
0
39
0
RT @hanwenjiang1: Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D….
0
70
0
RT @gan_chuang: What a fun collaboration with Zhiqiu on this summer internship project!. Understanding camera motion in videos is extremely….
0
4
0
Super cool project to have been involved in! Camera motion understanding is far from solved — even top SLAM/SfM and VLM models struggle in the wild. CameraBench pushes the frontier with high-quality annotations and cinematographer-designed taxonomy. VLMs 🤝 SFM next ?😉.
📷 Can AI understand camera motion like a cinematographer?. Meet CameraBench: a large-scale, expert-annotated dataset for understanding camera motion geometry (e.g., trajectories) and semantics (e.g., scene contexts) in any video – films, games, drone shots, vlogs, etc. Links
1
0
12
RT @_crockwell: Ever wish YouTube had 3D labels?. 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with….
0
39
0
RT @i_ikhatri: Just over a month left to submit to this year's Argoverse 2 challenges! Returning from previous years, are our motion foreca….
0
9
0
RT @ZhiqiuLin: Fresh GPT‑o3 results on our vision‑centric #NaturalBench (NeurIPS’24) benchmark! 🎯 Its new visual chain‑of‑thought—by “zoomi….
0
23
0
RT @kvuongdev: [1/6] Recent models like DUSt3R generalize well across viewpoints, but performance drops on aerial-ground pairs. At #CVPR20….
0
103
0
RT @Koven_Yu: 🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introd….
0
94
0
RT @tarashakhurana: Reminder that the deadline to submit your cool work to the Workshop on 4D vision @ CVPR 2025 is in about a week!!!.
0
2
0
RT @KyleSargentAI: Modern generative models of images and videos rely on tokenizers. Can we build a state-of-the-art discrete image tokeniz….
0
142
0