Vahid Tarokh

STARK: Strategic Team of Agents for Refining Kernels

Beyond Worst-Case: Efficient Robust RL via In-Context Generalization

Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers

Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning

Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization

Learn2Mix: Training Neural Networks Using Adaptive Data Integration

In-Context Reinforcement Learning From Suboptimal Historical Data

Elliptic Loss Regularization

In-Context Reinforcement Learning From Suboptimal Historical Data

Learn2Mix: Training Neural Networks Using Adaptive Data Integration

TELEPORTATION WITH NULL SPACE GRADIENT PROJECTION FOR OPTIMIZATION ACCELERATION

Potential Outcome Imputation for CATE Estimation

Potential Outcomes Estimation Under Hidden Confounders