Rohit Jayanti

Geometry-Enabled Models for Robot Intelligence 🦾📐 | Graduate Researcher at @iiit_hyderabad

[Gabriele Berton @gabriberton]

Finally someone citing proper sources!

Thanks @_rjayanti @sourav_garg_

The paper is a NeurIPS spotlight btw

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

SegMASt3R: Geometry Grounded Segment Matching

@_rjayanti Swayam Agrawal, Vansh Garg, Siddharth Tourani, Muhammad Haris Khan, @sourav_garg_ Madhava Krishna

tl;dr: match SAM2 masks with MASt3R descriptors, SuperGlue-style.
https://t.co/k9vrdd2kdn

[Sourav Garg @sourav_garg_]

Our #NeurIPS2025 *spotlight* paper #SegMASt3R establishes image segment matching as a benchmark task & enables high performance downstream on 3D Instance Mapping & Object-Relative Navigation
https://t.co/asDjl4w8xD

Huge effort by @_rjayanti @Swayam_421 @vanshg1729
@RRCLab_IIITH

[Sourav Garg @sourav_garg_]

Not so often one gets to read such remarks from AC:

"The paper's key strength is its compelling scientific insight
...
The authors' rebuttal was exemplary, thoroughly addressing all reviewer concerns"

🏆Accepted as Spotlight #NeurIPS2025

More details coming soon!

[Rohit Jayanti @_rjayanti]

Thrilled to share that our work was accepted to NeurIPS'25 main conf as a ✨Spotlight✨! Super collab with @Swayam_421, @vanshg1729, @SidTourani1, Prof. Muhammad Haris Khan, @sourav_garg_, and advisor Prof. Madhav Krishna. Details to follow soon!

@RRCLab_IIITH @TheAIML @mbzuai

[Rohit Jayanti @_rjayanti]

@francoisfleuret And sadly GD only ever explores this surface with a single ball in any given experiment.

[Xiaomeng Xu @XiaomengXu11]

3) A whole-body visuomotor policy that learns complex manipulation skills directly from human demonstrations, efficiently aggregating information from the camera system while maintaining resilience to sensor failures.

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Sometimes reading Hamming makes me sad, because I recognize myself in this quote.

[David van Dijk @david_van_dijk]

How does complexity shape intelligence? 🤔

In our new paper Intelligence at the Edge of Chaos, we explore the relationship between complex systems and the emergence of intelligence in AI models. Can complexity alone unlock smarter systems? 🌌🧠 #AI #complexity
https://t.co/nnLMDkzwtx

[Rohit Jayanti @_rjayanti]

8/8 Credits - Used Meta's (surprisingly snappy) web demo. Video sources below.
[YT]
- https://t.co/mDEYWUsNeo
- https://t.co/2QStsVM96S
- https://t.co/iGpFWAVdVe
[Pexels]
- https://t.co/eAUflbocSO
- https://t.co/WKcrZ81pAp
- https://t.co/0iH2fEzsMK

[Rohit Jayanti @_rjayanti]

1/8 Meta's SAM2 has some really fun capabilities. Coolest one I found ? Tracking through a pretty wacky transition. All this with just a single point prompt on frame 0. Frame-by-frame breakdown and more examples in the 🧵 below!

[Rohit Jayanti @_rjayanti]

7/8 Finally, had to try Transformers (wink-wink)! Several point prompts but all before the transition through the underpass! Roughly - Point prompts for Bumblebee on frame 050, on the Decepticon on frame 089 (before it disintegrates!), a couple on the bridge on frame 175.