← Search

Hai Victor Habi

7 accepted papers

2026

Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors

ICML 2026poster

Commercial Microwave Links (CMLs) offer dense spatial coverage for rainfall sensing but produce path-integrated measurements that make accurate ground-level reconstruction challenging. Existing methods typically oversimplify CMLs as point sensors and neglect the physical power-law relating rainfall …

Cited by 0SourceScholar
2026

LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs

ICML 2026poster

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly improve quantization robustness by reducing activation outliers; h…

Cited by 0SourceScholar
2025

Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo

ICML 2025poster

In image processing, solving inverse problems is the task of finding plausible reconstructions of an image that was corrupted by some (usually known) degradation operator. Commonly, this process is done using a generative image model that can guide the reconstruction towards solutions that appear na…

Cited by 1SourcePDFScholar
2020

HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs

ECCV 2020poster

Recent work in network quantization produced state-of-the-art results using mixed precision quantization. An imperative requirement for many efficient edge device hardware implementations is that their quantizers are uniform and with power-of-two thresholds. In this work, we introduce the Hardware F…