PULK!T @m_pulkit

Research @QCOMResearch, MSc @Mila_quebec / UdeM 🇨🇦 Toronto, Ontario Joined October 2018

Tweets

27
Followers

253
Following

766
Likes

147

Reza Ebrahimi @rzebrahimi

3 months ago

1/N. Modern linear RNNs miss one crucial capability from classic RNNs: state-tracking. State-tracking is the ability to dynamically maintain an internal state of a system. It's essential for complex reasoning tasks, such as: - Updating a chessboard state after a sequence of…

Roland Memisevic @RolandMemisevic

3 months ago

0 1 9 895 0

1 4 12 625 2

Download Image

Roland Memisevic @RolandMemisevic

3 months ago

Binary parity ("count the number of 1s in a bit-string") is a common task to show that transformers cannot generalize. Turns out, a random(!) RNN (train only readout) can learn the task easily, and it can do so with as few as 2 (two) training examples...: arxiv.org/pdf/2505.21749

0 1 9 895 0

VAR@CVPR2025 @VARCVPR2025

6 months ago

Call for Papers and Demos #CVPR2025: on topics such as streaming vision-language models, real-time activity understanding, grounding, ego-centric video understanding, language and robot learning. Contributions are encouraged to include a demo! Link: varworkshop.github.io/calls/

0 7 6 581 0

Download Image

Reza Ebrahimi @rzebrahimi

11 months ago

Check out our paper in @COLM_conf 🦙 on random access limitations of transformers, with @sunnypanchal93 and @RolandMemisevic: 🧵(1/n)

1 6 19 3K 3

Download Image

Apratim Bhattacharyya @apratimbh

a year ago

We are excited to release the QEVD benchmark and dataset to spur progress in the development of real-world AI assistants for live fitness coaching. Link to the benchmark and dataset: developer.qualcomm.com/software/ai-da… Paper: arxiv.org/abs/2407.08101 1/4

4 7 22 2K 1

Apratim Bhattacharyya @apratimbh

2 years ago

Excited to present our #ICLR2024 paper “Look, Remember and Reason: Grounded Reasoning in Videos with Language Models” (arxiv.org/pdf/2306.17778…). Our method: LRR, is current ranked 1st on the STAR leaderboard: eval.ai/web/challenges… 1/3

1 14 39 5K 17

Download Image

Apratim Bhattacharyya @apratimbh

2 years ago

Excited to share our new work on visual reasoning using LLMs: “Look, Remember and Reason: Visual Reasoning with Grounded Rationales” (arxiv.org/pdf/2306.17778…). To appear at: klr-icml2023.github.io #ICML2023 Thread: 1/3