activity
20242026
collaborators

7 papers

cs.CV2026

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…

cs.LG2026

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…

cs.IT2026

Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels

Vishnu Teja Kunde, Jean-Francois Chamberland, Krishna R. Narayanan +1

Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that s…

eess.SP2026

Complex Approximate Message Passing with Non-separable Denoising

Vishnu Teja Kunde, Alessandro Mirri, Jean-Francois Chamberland +1

Approximate Message Passing (AMP) is a general framework for iterative algorithms, originally developed for compressed sensing and later extended to a wide range of high-dimensiona…

eess.SP2025

Approximate Message Passing for Multi-Preamble Detection in OTFS Random Access

Alessandro Mirri, Vishnu Teja Kunde, Enrico Paolini +1

This article addresses the problem of multiple preamble detection in random access systems based on orthogonal time frequency space (OTFS) signaling. This challenge is formulated a…

eess.SP2025

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…