27 citations · 206 across the 63 of their papers we have counts for
73 papers
TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents
Debajoy Mukherjee, Jeremy Carleton, Sushil Vemuri +2
Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and unhelpful decisions undifferen…
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…
ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies
Tzu-Hsiang Lin, Srinivas Shakkottai, Dileep Kalathil +1
Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing metho…
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
Xingyu Su, Jacob Helwig, Shubham Parashar +6
We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention i…
Learnability-Informed Fine-Tuning of Diffusion Language Models
Shubham Parashar, Atharv Chagi, Jacob Helwig +5
We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces chall…
Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
Vishnu Saj, Sushil Vemuri, Dileep Kalathil +1
Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in overly conservative policies tha…
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…
Optimistic World Models: Efficient Exploration in Model-Based Deep Reinforcement Learning
Akshay Mete, Shahid Aamir Sheikh, Tzu-Hsiang Lin +2
Efficient exploration remains a central challenge in reinforcement learning (RL), particularly in sparse-reward environments. We introduce Optimistic World Models (OWMs), a princip…
ReFuzz: Reusing Tests for Processor Fuzzing with Contextual Bandits
Chen Chen, Zaiyan Xu, Mohamadreza Rostami +4
Processor designs rely on iterative modifications and reuse well-established designs. However, this reuse of prior designs also leads to similar vulnerabilities across multiple pro…
GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels
Bhavya Sai Nukapotula, Rishabh Tripathi, Seth Pregler +3
Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant over…
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…
MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection
Jeremy Carleton, Debajoy Mukherjee, Srinivas Shakkottai +1
Large Language Models (LLMs) are increasingly deployed across diverse applications that demand balancing multiple, often conflicting, objectives -- such as helpfulness, harmlessnes…
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…
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
Shubham Parashar, Shurui Gui, Xiner Li +8
We aim to improve the reasoning capabilities of language models via reinforcement learning (RL). Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilitie…
Abstractions-of-Thought: Intermediate Representations for LLM Reasoning in Hardware Design
Matthew DeLorenzo, Kevin Tieu, Prithwish Jana +4
Large language models (LLMs) have achieved impressive proficiency on logic and programming tasks, often rivaling expert-level performance. However, generating functionally correct…
Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models
Min Cheng, Fatemeh Doudi, Dileep Kalathil +2
Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tun…
Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
Zaiyan Xu, Sushil Vemuri, Kishan Panaganti +3
A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, a…
Risk-Averse Finetuning of Large Language Models
Sapana Chaudhary, Ujwal Dinesha, Dileep Kalathil +1
We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-…
PowerMamba: A Deep State Space Model and Comprehensive Benchmark for Time Series Prediction in Electric Power Systems
Ali Menati, Fatemeh Doudi, Dileep Kalathil +1
The electricity sector is undergoing substantial transformations due to the rising electrification of demand, enhanced integration of renewable energy resources, and the emergence…
Structured Reinforcement Learning for Media Streaming at the Wireless Edge
Archana Bura, Sarat Chandra Bobbili, Shreyas Rameshkumar +3
Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein…
AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning
Vasudev Gohil, Satwik Patnaik, Dileep Kalathil +1
Machine learning has shown great promise in addressing several critical hardware security problems. In particular, researchers have developed novel graph neural network (GNN)-based…
Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems
Amit Jena, Dileep Kalathil, Le Xie
This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. The state-of-the-art methods, such as Neural Lyapunov Function…
Transformers are Provably Optimal In-context Estimators for Wireless Communications
Vishnu Teja Kunde, Vicram Rajagopalan, Chandra Shekhara Kaushik Valmeekam +4
Pre-trained transformers exhibit the capability of adapting to new tasks through in-context learning (ICL), where they efficiently utilize a limited set of prompts without explicit…
Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage
Kishan Panaganti, Zaiyan Xu, Dileep Kalathil +1
The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration.…