4 papers
Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
Jelena Markovic-Voronov, Wenhui Zhu, Bo Long +5
We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-l…
Support Tokens, Stability Margins, and a New Foundation for Robust LLMs
Deepak Agarwal, Dhyey Dharmendrakumar Mavani, Suyash Gupta +2
Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbo…
Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning
Nihal Balivada, Shrey Gupta, Shashank Shreedhar Bhatt +1
Federated Learning (FL) enables a distributed client-server architecture where multiple clients collaboratively train a global Machine Learning (ML) model without sharing sensitive…
Predictive Inference in Multi-environment Scenarios
John C. Duchi, Suyash Gupta, Kuanhao Jiang +1
We address the challenge of constructing valid confidence intervals and sets in problems of prediction across multiple environments. We investigate two types of coverage suitable f…