Vish Sangale
Staff Machine Learning Researcher @ Meta
My research is focused on large-scale AI architectures and Recommendation Systems. While my core work centers on the research and engineering challenges of modern recommendation systems, LLMs, and the intersection between them, I am driven by a long-term fascination with how computational models can eventually mirror the robustness and efficiency of biological systems.
Recent Thinking
-
Beyond the Click: Slate-Q for Sequential Recommendation
Most recommendation systems are designed to maximize immediate engagement—the “next click.” However, true user value is built over entire sessions. In this project, RL-RECSYS, I explored how Reinfo...
-
Animating Intelligence: Visualizing AI with Manim-AI
Neural networks are often treated as “black boxes,” full of abstract matrices and hidden weights. To bridge the gap between theory and intuition, I developed MANIM-AI, an extension for the Manim an...
-
Bonsai-LLM: The 'Small LLMs Lab' Philosophy
In an era of trillion-parameter models and massive compute clusters, it’s easy to forget that capacity matters, constraints are the point, and craft beats brute force.
-
Modernizing GPT-2: A 3.1x Throughput Leap with 2025 Optimizations
The original GPT-2 architecture, released in 2019, remains the bedrock of modern NLP. However, the “standard” recipe for training Transformers has shifted dramatically. In this project, I rebuilt t...
-
Causal-Informed Hybrid Online Adaptive Optimization for Ad Load Personalization in Large-Scale Social Networks
This paper presents CTRCBO (Cohort-Based Trust Region Contextual Bayesian Optimization), a hybrid framework designed for personalizing ad load in large-scale social networks like Meta.