计算机科学

On analog neuromorphic hardware, intrinsic device noise is normally an accuracy tax. We ask whether it can instead consolidate memories. We cast per-synapse consolidation as a Doob h-transform: condition each weight's stochastic dynamics on…

Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during the design of a deep neural network to maximize performance is…

We describe the methodology used to alias the free-text author/committer identities of the entire World of Code (WoC) collection (version V2604, ~107M distinct author strings over ~6B commits) into canonical persons, extending the…

Virtual reality (VR) nature immersion is an increasingly popular field of research due to its potential to help people who do not have access to real nature. There are many questions surrounding how virtual forests can be designed to…

Robust dynamic object detection and tracking are essential for enabling robots to operate safely and effectively alongside humans in complex environments such as construction sites. While LiDAR-based SLAM and occupancy grid methods offer…

Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive…

Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe…

Best-arm identification is a canonical model for data-driven decision-making, but in many applications each reward observation is costly. Motivated by the growing availability of cheap predictions from machine learning and large language…

Conversational LLM agents can cause real-world harm when their internal workflows fail, such as completing a transaction without confirmation. Testing these state-dependent failures is difficult because critical boundaries, such as identity…

Autonomous driving systems require reliable safety validation before real-world deployment. However, large-scale road testing is costly, difffcult to reproduce, and inefffcient for exposing rare safety-critical scenarios. Conventional…

The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems. A key aspect of this process involves editing agent states in both…

Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our…

GNSS-denied unmanned aerial vehicles require occasional absolute position fixes to bound the drift of visual-inertial odometry. Cross-view image retrieval can provide such fixes, but raw appearance is sensitive to season, illumination,…

Passive hydroacoustic monitoring often generates large volumes of continuous recordings that are only partially exploited due to the cost of manual annotation. Supervised detection methods perform well but require large labeled datasets,…

In Haskell, class instance deriving and related mechanisms are used pervasively. Their influence extends beyond Haskell: Rust adopts similar ideas in its trait system, and Java libraries such as Lombok use annotations to generate methods…

Limited flight endurance significantly restricts the operational range of unmanned aerial vehicles (UAVs) in long duration missions such as surveillance and inspection, where multiple spatially distributed Areas of Interest (AOIs) must be…

On-policy distillation is a practical post-training recipe for large language models, supplying dense teacher supervision on the student's own trajectories. In privileged-context self-distillation, teacher and student are the same model…

Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of…

Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluation. LEMUR 2 introduces a large-scale, extensible framework…

Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial markets, and wireless network optimization. In these settings, the target signals are…