satyabratsingh's profile picture. Interest in Software, ML, Quant Research, MSc in ML from UCL, MSc Maths from IIT

Satyabrat Singh

@satyabratsingh

Interest in Software, ML, Quant Research, MSc in ML from UCL, MSc Maths from IIT

Satyabrat Singh reposted

Glad to introduce our new work "Game-Theoretic Regularized Self-Play Alignment of Large Language Models". arxiv.org/abs/2503.00030 🎉 We introduce RSPO, a general, provably convergent framework to bring different regularization strategies into self-play alignment. 🧵👇

xiaohang_tang's tweet image. Glad to introduce our new work "Game-Theoretic Regularized Self-Play Alignment of Large Language Models". arxiv.org/abs/2503.00030 🎉

We introduce RSPO, a general, provably convergent framework to bring different regularization strategies into self-play alignment. 🧵👇

Satyabrat Singh reposted

Thrilled to introduce our test-time algorithm for robust multi-objective alignment! Huge kudos to my incredible collaborators for making this happen!

❓No clue about the priorities of the objectives? ❗️ Focus on robustness at test-time! 🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.

seongho_son_ml's tweet image. ❓No clue about the priorities of the objectives?
❗️ Focus on robustness at test-time!
🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.
seongho_son_ml's tweet image. ❓No clue about the priorities of the objectives?
❗️ Focus on robustness at test-time!
🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.


Satyabrat Singh reposted

❓No clue about the priorities of the objectives? ❗️ Focus on robustness at test-time! 🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.

seongho_son_ml's tweet image. ❓No clue about the priorities of the objectives?
❗️ Focus on robustness at test-time!
🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.
seongho_son_ml's tweet image. ❓No clue about the priorities of the objectives?
❗️ Focus on robustness at test-time!
🚀Robust Multi-Objective Decoding (RMOD) is a novel inference-time alignment algorithm that produces robust responses under multiple objectives to consider.

Satyabrat Singh reposted

🚀Sampling = Reinforcement Learning🤖 This means you can train a neural sampler using RL! We introduce the Value Gradient Sampler (VGS)—a novel diffusion sampler that leverages value functions to generate samples from an unnormalized density. 📄 Paper: arxiv.org/abs/2502.13280

WoongSSang's tweet image. 🚀Sampling = Reinforcement Learning🤖
This means you can train a neural sampler using RL!

We introduce the Value Gradient Sampler (VGS)—a novel diffusion sampler that leverages value functions to generate samples from an unnormalized density.
📄 Paper: arxiv.org/abs/2502.13280

Satyabrat Singh reposted

(1/9) Flying to #NeurIPS2024 ? Our paper arxiv.org/abs/2405.20304 and blog shorturl.at/aIShm might be an interesting read on ur long flight to Vancouver! Accepted at #NeurIPS2024 and excited to present it as a poster on 13th December (1-4pm)!


Satyabrat Singh reposted

On my way to #NeurIPS2024 ✈️ We are presenting several papers this year, including REDUCER, ARDT, GR-DPO/IPO, invariant BO. I’d love to connect and chat about topics like Alignment, RL/RLHF, LLM deception, robustness, and reasoning!


Satyabrat Singh reposted

🚀🚀🚀 Introducing Adversarially Robust Decision Transformer (ARDT) 🚀🚀🚀 The first Decision Transformer for adversarial game-solving and robust decision-making, accepted to #NeurIPS #NeurIPS2024 🚨Change slightly : Replacing returns-to-go with minimax return. 🚨 Improve…

xiaohang_tang's tweet image. 🚀🚀🚀 Introducing Adversarially Robust Decision Transformer (ARDT) 🚀🚀🚀

The first Decision Transformer for adversarial game-solving and robust decision-making, accepted to #NeurIPS #NeurIPS2024  

🚨Change slightly : Replacing returns-to-go with minimax return.
🚨 Improve…

15 years ago today, I got a second chance at life… never realized how close death could be #MumbaiTerrorAttack #GratefulForLife


Satyabrat Singh reposted

📣 If you've got an objective that exhibits symmetries, you should be using invariant kernel BO 📣 🚀 More sample efficient than constrained/naive BO! 🚀 More compute efficient than data augmentation! 🧵 1/4 #NeurIPS2024 #BayesianOptimisation #ai


This book is an absolute gem for understanding the intricacies of neural nets. Huge thanks to @SimonScardapane #MachineLearning #DeepLearning #AI

satyabratsingh's tweet image. This book is an absolute gem for understanding the intricacies of neural nets. Huge thanks to @SimonScardapane #MachineLearning #DeepLearning #AI
satyabratsingh's tweet image. This book is an absolute gem for understanding the intricacies of neural nets. Huge thanks to @SimonScardapane #MachineLearning #DeepLearning #AI

DeepSets are useful where we need permutation invariance. Imagine a batch of data with shape (n,m) —we split this batch into k sets, each of size (k,m) feed them through a neural network, and aggregate the outputs as: f(X) = ∑(i=1 to k) g(x_i). This method captures the essence…


Satyabrat Singh reposted

The 2nd edition of my #ReinforcementLearning 477-page textbook for my course at ASU has just been published and is freely available at the book's website web.mit.edu/dimitrib/www/R… which also contains slides, videolectures, and supporting material


Satyabrat Singh reposted

Competition Launch Alert! Realtime Marketdata hosted by @JaneStreetGroup 🎯 Challenge: Develop an ML forecasting model using real-world data derived from production systems 💰 Prize Pool: $120,000 ⏰ Entry Deadline: 12/30/2024 Explore the difficult dynamics that shape financial…


Satyabrat Singh reposted

Detailed Thread on Option Pricing with Deep Learning Original paper link -cs230.stanford.edu/projects_fall_… Like, Retweet and comment "OPDL", to receive the code for the Deep Learning for Option Pricing

QuantINsider_IQ's tweet image. Detailed Thread on Option Pricing with Deep Learning

Original paper link -cs230.stanford.edu/projects_fall_…  

Like, Retweet and comment "OPDL", to receive the code for the Deep Learning for Option Pricing

Human mind is complex network, inadvertently saw some gross pictures of accident and feel really disturbed, shouldnt @X sensor them ?


Satyabrat Singh reposted

🔒 Discover the hidden risks of AI-driven devices with Dr Anna Maria Mandalari. Gain essential insights on security & privacy from the session at the Festival of Research 2024. 🎥 Watch now: buff.ly/3AdtpBD #CyberSecurity #FOR24

ucleeenews's tweet image. 🔒 Discover the hidden risks of AI-driven devices with Dr Anna Maria Mandalari.
 
Gain essential insights on security & privacy from the session at the Festival of Research 2024.  

🎥 Watch now: buff.ly/3AdtpBD

#CyberSecurity #FOR24

Satyabrat Singh reposted

🚀 Exciting PhD opportunity in IoT, edge devices, security & privacy at UCL! I have a fully-funded 4-year studentship available. More info: ucl.ac.uk/electronic-ele… #PhDOpportunity #IoT @UCL_ICCS


Wonder how many times #AI is mentioned in town-hall meetings these days, captures merely 99.99% of the time :) #AI #MachineLearning


United States Trends

Loading...

Something went wrong.


Something went wrong.