技术雷达TECH RADAR · GITHUB · ARXIV · HACKER NEWS

Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowled

Alexander Hickey, Joanna Knight, James Bishop

Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts

Bhanu Tokas, Rahul Nair, Rockwell Jackson

The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological expressivity refers to a family of measures particularly suited to understand

Kosio Beshkov

Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption doe

Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas

A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a schedule $U$ drawn afresh for each output, we compare the schedule-averag

Tianyi Wu

Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundle Protocol enables store-carry-forward communicati

Sajjad Baghaeea, Aimin Lib, Shanmugarajan Balasubramanian

Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical in

Daniel Szelogowski

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for ea

Joseph Lee, Yanjing Li, Bo Qiang

While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Sev

Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev

We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is

Yang Peng

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论