5 papers
AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding
Mahdi Farahbakhsh, Ilan Sela, Fatemeh Doudi +4
Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the mo…
Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
Yu-Shin Huang, Chao Tian, Krishna Narayanan
This paper considers the problem of multi-bit generative watermarking for large language models under a worst-case false-alarm constraint. Prior work established a lower bound on t…
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Vishnu Teja Kunde, Fatemeh Doudi, Mahdi Farahbakhsh +3
Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging…
Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
Mahdi Farahbakhsh, Vishnu Teja Kunde, Dileep Kalathil +2
Diffusion models have been used as priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruc…
In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory
Matteo Zecchin, Tomer Raviv, Dileep Kalathil +3
In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. L…