ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Ashish Sabharwal

Ashish Sabharwal

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:09 AM AMS

11

papers

2,592

total citations

papers (11)

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

The Illusion of State in State-Space Models

A Logic for Expressing Log-Precision Transformers

NEURIPS 2023arXiv

Belief Propagation Neural Networks

NEURIPS 2020arXiv

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

NEURIPS 2025arXiv

Closing the Curious Case of Neural Text Degeneration

Exact Expressive Power of Transformers with Padding

NEURIPS 2025arXiv

Understanding the Logic of Direct Preference Alignment through Logic

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

NEURIPS 2025arXiv

Position: Data-driven Discovery with Large Generative Models