@ARRay693

Research Scientist @Google | Teaching AI to complete tasks that humans need but don’t want to do.

 SF, CA
arijitray.com
Joined November 2015
  • Tweets83
  • Following823
  • Followers195
6Media
"It is by logic that we prove, but by [abstract] intuition that we discover." - Henri Poincaré. When faced with a complex problem, we pause, we think. Not exactly in words, not exactly in images — in something more abstract, something harder to name. So, for truly intelligent agents, should we not ask that they do the same? Introducing Mull-Tokens — a modality-agnostic latent thinking paradigm. Now, the model can think in space, in time, in words, in affordances — in all the things that language alone cannot easily convey. arijitray.com/multimodal_thi…
2
2
9
875
Very excited to announce Gemini 4 Argon, our new Frontier AI model, and a huge step forward across key capabilities. We’re focused on rolling it out responsibly starting with government and trusted cyber defenders through our Fairwind Program today, before wider availability soon
441
684
145
9,171
526,707
Arijit Ray retweeted
Jiafei Duan
@DJiafeiMay 8
Launching my research group, MAGIC (Manipulation and General Intelligence Control) Lab @NUSComputing, Singapore! We focus on building the next generation of human-centric models for robotic manipulation — deployable safely, reliably, and easily in the real world. Our research spans MLLM reasoning, 3D vision, robot learning, simulation, dexterous manipulation, and cross-embodiment learning. Interested in joining? Sign up here and I'll send a reminder email: forms.gle/oJPLR2pLTt8kLCxZ7
9
28
3
338
26,360
Arijit Ray retweeted
Ai2
@allen_aiMar 24
Today we're releasing MolmoWeb, an open source agent that can navigate + complete tasks in a browser on your behalf. Built on Molmo 2 in 4B & 8B sizes, it sets a new open-weight SOTA across four major web-agent benchmarks & even surpasses agents built on proprietary models. 🧵
21
112
30
801
134,740
As conversations continue around grounding visual & textual reasoning, we believe latent, modality-agnostic thinking could be a promising direction. The latents can be extended to anything - trajectories, 3D point-cloud features, audio! Paper, code, and models posted. Dive in and let us know what you build! 🚀
1
136
This work would not be possible without all my amazing collaborators: Ahmed Abdelkader, Chengzhi Mao, Bryan Plummer, @kate_saenko_ , @RanjayKrishna , Leonidas Guibas, and Vincent Chu!
2
128
🚀 Excited to share that my team at Meta just launched Segment Anything 3! SAM 3 doubles the performance of existing models on open-vocabulary instance segmentation on our new SA-Co benchmark, with 207K unique object labels. Huge congrats to the team, so proud of this work!
AI at Meta
@AIatMeta19 Nov 2025
Today we’re excited to unveil a new generation of Segment Anything Models: 1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. 🔗 Learn more about SAM 3: go.meta.me/591040 2️⃣ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. 🔗 Learn more about SAM 3D: go.meta.me/305985 These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.
4
9
90
9,368
Game your benchmark first (and de-bias it) before others do!
Ellis Brown @ COLM
@_ellisbrown10 Nov 2025
🌶️ hot take 🌶️ > we should normalize training on the test set yes, you read that right. no, I'm not joking. and, yes... I have taken ML 101 👉 here's why this is crucial for future multimodal LLM research [1/n] 🧵
1
251
SIMS-V offers free (simulated) rich accurate video annotations for object relationships, distances, and temporal tracking—capabilities often lacking in existing video training datasets. 🎞️💫 Mix it into your data and boost your model's performance on video reasoning tasks! Code and data are open! ellisbrown.github.io/sims-v/
Ellis Brown @ COLM
@_ellisbrown7 Nov 2025
MLLMs are great at understanding videos, but struggle with spatial reasoning—like estimating distances or tracking objects across time. the bottleneck? getting precise 3D spatial annotations on real videos is expensive and error-prone. introducing SIMS-V 🤖 [1/n]
2
4
428
MLLMs are great at understanding videos, but struggle with spatial reasoning—like estimating distances or tracking objects across time. the bottleneck? getting precise 3D spatial annotations on real videos is expensive and error-prone. introducing SIMS-V 🤖 [1/n]
3
47
4
229
16,516
We live, feel, and create by perceiving the world as visual spaces unfolding through time — videos. Our memories and even our language are spatial: mind-palaces, mind-maps, "taking steps in the right direction..." Super excited to see Cambrian-S pushing this frontier! And, happy to also see simulations — building on our SIMS-V and SAT — helping bootstrap the first wave of spatial supersensing in models ⚡️ Code & data are open: 🔹 SIMS-V (Videos): ellisbrown.github.io/sims-v/ 🔹 SAT (Multi-images): arijitray.com/SAT/ Dive in, explore, and let us know what you build toward video super-intelligence!! 🚀
Saining Xie
@sainingxie7 Nov 2025
Introducing Cambrian-S it’s a position, a dataset, a benchmark, and a model but above all, it represents our first steps toward exploring spatial supersensing in video. 🧶
1
2
8
925
Load more