AIConfPaper
← Search

Ahsan Bilal

4 accepted papers

2026

Channel Prediction under Network Distribution Shift Using Continual Learning-based Loss Regularization

Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Ibtsaam Qadir, Muhammad Ali Jamshed, Dean Hougen, John M. Cioffi
ICASSP 2026oral

Modern wireless networks face critical challenges when mobile users traverse heterogeneous network configurations with varying antenna layouts, carrier frequencies, and scattering statistics. Traditional predictors degrade under distribution shift, with NMSE rising by 37.5\% during cross-configurati…

Cited by 0Source ↗PDF ↗Scholar ↗
2026

Conditional Prior-based Non-stationary Channel Estimation Using Accelerated Diffusion Models

Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Umer, Muhammad Ali Jamshed, Dean F. Hougen, John M. Cioffi
ICASSP 2026poster

Wireless channels in motion-rich urban microcell (UMi) settings are non-stationary; mobility and scatterer dynamics shift the distribution over time, degrading classical and deep estimators. This work proposes conditional prior diffusion for channel estimation, which learns a history-conditioned sco…

Cited by 0Source ↗PDF ↗Scholar ↗
2026

What If We Allocate Test-Time Compute Adaptively?

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Ali Subhan, Hassan Rizwan, Ayesha Mohsin +1
ICML 2026poster

Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative trajectory generation and selection. For each problem, the ag…

Cited by 0Source ↗Scholar ↗
2025

ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model

Sagnik Bhattacharya, Abhiram Rao Gorle, Ahsan Bilal, Connor Ding, Amit Kumar Singh Yadav, Tsachy Weissman
NeurIPS 2025poster

Generative modeling of non-negative, discrete data, such as symbolic music, remains challenging due to two persistent limitations in existing methods. Firstly, many approaches rely on modeling continuous embeddings, which is suboptimal for inherently discrete data distributions. Secondly, most model…

Cited by 0Source ↗Scholar ↗