Log inSign up
Ranjay Krishna
2,099 posts
Ranjay Krishna profile banner
@RanjayKrishna

Ranjay Krishna

@RanjayKrishna
Assistant Professor @ University of Washington, Co-Director of RAIVN lab (raivn.cs.washington.edu), Director of PRIOR team (prior.allenai.org)
California, USA
ranjaykrishna.com
Joined August 2011
436
Following
6,227
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @RanjayKrishna
    Ranjay Krishna
    @RanjayKrishna
    Jul 1
    📣 Call for Papers — 1st Workshop on Multimodal Digital Agents (MDA) @ ECCV 2026 How should AI agents see and act across web, desktop, and mobile interfaces? We're bringing together work on vision-centric digital agents — perception, reasoning, benchmarks, safety, and more. 🗓️
    1
  • @RanjayKrishna
    Ranjay Krishna
    @RanjayKrishna
    Jun 4
    My students and I will be doing real robot demos at my talk at the Embodied Reasoning workshop #CVPR2026 today at Room 605 from 9:30-10:20am. Come by!
  • @RanjayKrishna
    Ranjay Krishna
    @RanjayKrishna
    Mar 24
    We believe agents for the open web should be built in the open! We are releasing MolmoWeb, a completely reproducible SOTA Web Agent! Open Data, Open Weights, Open Code!
    @allen_ai
    Ai2
    @allen_ai
    Mar 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. 🧵
    Image
  • @RanjayKrishna
    Ranjay Krishna
    @RanjayKrishna
    Mar 11
    We are releasing MolmoBot! We challenge the assumption that sim-to-real requires real-world finetuning. Our robot models beat strong baselines with no real world data. With enough diversity and scale in simulation, zero-shot transfer can actually work—across both static and
    @allen_ai
    Ai2
    @allen_ai
    Mar 11
    Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵
    Image
    00:00
  • @RanjayKrishna
    Ranjay Krishna
    @RanjayKrishna
    Feb 12
    The amount and diversity of robot data we need is much higher than what we can scale. We are betting on simulation! MolmoSpaces allows you to generate seemingly unlimited amounts of robot data in large diverse environments across multiple simulators.
    @allen_ai
    Ai2
    @allen_ai
    Feb 11
    Introducing MolmoSpaces, a large-scale, fully open platform + benchmark for embodied AI research. 🤖 230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.
    Image
    00:00
    5
Advertisement
Advertisement