Speakers
Furong Huang
University of Maryland
USA
From Perception to Action: World Model Learning for Generalist Agents
Aviral Kumar
Carnegie Mellon University (CMU)
USA
Train-Time and Test-Time Exploration in Language Models
Vivek Borkar
Indian Institute of Technology
Bombay
Nothing comes from nothing
M. Vidyasagar
Indian Institute of Technology
Hyderabad
Convergence of General Momentum-Based Optimization Algorithms with Time-Varying Parameters
Prashanth L.A
Indian Institute of Technology
Madras
Policy Evaluation for variance in risk-sensitive reinforcement learning
Dheeraj Nagraj
Google DeepMind
Bengaluru
Fine-Tuning Diffusion Models via Intermediate Distribution Shaping
Arunselvan Ramaswamy
Karlstad University
Sweden
Dealing with variance and constraints in Deep Reinforcement Learning
Pranay Sharma
Indian Institute of Technology
Bombay
Natural Policy Gradient for Reinforcement Learning in Non-stationary Environments
Raunak Bhattacharyya
Indian Institute of Technology
Delhi
Reinforcement Learning for safety-aware autonomous navigation
Swanand Khare
Indian Institute of Technology
Kharagpur
Training to Forgetting: Efficient and Compliant MLaaS Pipelines
Serdar Yüksel
Queen's University
Canada
Lift-Metrize-Quantize-Q-Learn: A General Recipe for Learning in Stochastic Control with General Information Structures
Paras Chopra
Lossfunk
Bengaluru
Meta-RL: Reviewing recent progress in learning and evolving RL algorithms
Sridharan Devarajan
Indian Institute of Science
Bengaluru
Sequential Attention-based Sampling for Histopathological Analysis
Shubhada Agrawal
Indian Institute of Science
Bengaluru
Concentration of Stochastic Approximation Under Markovian Noise
Karthik Gurumoorthy
Walmart Global Tech
Bengaluru
Reinforcement Learning for E-commerce Inventory Management
