Unlocking the Working Memory of Large Language Models for Latent Reasoning Paper • 2605.30343 • Published 21 days ago • 1
On Subquadratic Architectures: From Applications to Principles Paper • 2606.12364 • Published 7 days ago • 23
Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation Paper • 2510.02279 • Published Oct 23, 2025
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents Paper • 2512.23128 • Published 14 days ago
RREDCoT: Segment-Level Reward Redistribution for Reasoning Models Paper • 2606.06475 • Published 14 days ago
On Subquadratic Architectures: From Applications to Principles Paper • 2606.12364 • Published 7 days ago • 23
GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations Paper • 2510.07314 • Published Oct 8, 2025 • 4
On Information-Theoretic Measures of Predictive Uncertainty Paper • 2410.10786 • Published Oct 14, 2024
Rethinking Uncertainty Estimation in Natural Language Generation Paper • 2412.15176 • Published Dec 19, 2024
Attacking Multimodal OS Agents with Malicious Image Patches Paper • 2503.10809 • Published Mar 13, 2025
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models Paper • 2106.13618 • Published Jun 25, 2021
Semantically Diverse Language Generation for Uncertainty Estimation in Language Models Paper • 2406.04306 • Published Jun 6, 2024
Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty Paper • 2311.08309 • Published Nov 14, 2023
Theano: A Python framework for fast computation of mathematical expressions Paper • 1605.02688 • Published May 9, 2016 • 2
Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models Paper • 2105.04651 • Published May 10, 2021