Riashat Islam

@riashatislam

MTS @MicrosoftAI SuperIntelligence, Senior Researcher @ms_aifrontiers @MSFTResearch; Ex @HUMAIN @DreamFoldAI PhD @Mila_Quebec, World Models, RL Reasoning, VLMs

New York, USA

riashat.github.io

Joined November 2016

1,340 Following

1,849 Followers

Replies Reposts Media

Pinned
Riashat Islam
@riashatislam
Apr 25, 2023
Excited to share that Agent-Controller representations for offline RL in presence of rich exogenous information is now accepted at #ICML2023 (arxiv.org/abs/2211.00164) This is a follow-up of our recent work on latent state discovery (#TMLR'23) arxiv.org/abs/2207.08229
arxiv.org
Agent-Controller Representations: Principled Offline RL with Rich...
Learning to control an agent from data collected offline in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major challenge in...
1
Riashat Islam
@riashatislam
Nov 1
This is really cool!
Randall Balestriero
@randall_balestr
Oct 30
The Platonic Representation Hypothesis is now a Theorem ◼️ Train JEPAs separately, on any modalities: they provably learn the same representation up to one rotation. The result? A 109M JEPA-Text model that aligns with vision models better than 72B LLMs. w/ @ylecun 🧵
Riashat Islam
@riashatislam
Oct 29
This is a significant step forward from when we were last looking at H-Nets. Congrats for pushing this further.
Albert Gu
@_albertgu
Oct 28
I've always believed that intelligence should come from simple, general building blocks that learn their own abstractions directly from raw data; in other words, the bitter lesson. I think we're finally seeing a real step towards AI that can learn from all data. Language
Riashat Islam
@riashatislam
Oct 9
This is a really interesting piece of work. Been thinking about how to extract more signal out of the agent experience, and this work fits in nicely providing great insights on agent's affordances to learn from experience.
Anirudh Goyal
@anirudhg9119
Oct 8
How do we measure an AI agent's ability to learn, rather than just its current capability? We study agents that learn from experience without updating their weights, and measure how efficiently they improve on unseen tasks. Surprisingly, the strongest agent isn't the most
Riashat Islam
@riashatislam
Sep 25
You all will miss the amazing works that were coming out of @ms_aifrontiers!
Vaish Shrivastava
@VaishShrivas
Sep 24
ECHO is going to #NeurIPS2026 as a spotlight! 🎉 TL;DR: When an agent acts, the environment responds. ECHO learns from that signal during RL. Paper: arxiv.org/abs/2605.24517 Code: github.com/microsoft/echo…

Riashat Islam

Riashat Islam’s posts