Pai 的 AI 雷达
2026-08-22：2.1.239；More than just code review；llm 0.32.1
Longitudinal electronic health records (EHRs) document patients' sequences of clinical visits over time, preserving the temporal evolution of disease progression and care delivery. However, real longitudinal EHRs are dif
Vector sketches remain one of the most concise and immediate mediums for abstract human expression. However, generating high-quality vector strokes that exhibit human-like drawing styles remains an open challenge due to
Black-box VR and 3D applications are difficult to regression test because observable failures depend on where a tester moves, what objects are visible, and which views are captured. Manual exploratory testing can find su
LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory represe
Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training data and stress-test tutoring systems. However, common prompt-based a
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, whic
Robotic systems are traditionally designed and deployed in static configurations, with assumptions made at design-time becoming immutable constraints during runtime. This design-then-deploy paradigm produces performant s
This article presents a novel 3D reconstruction and mapping of the interior of the International Space Station (ISS) using 3D Gaussian Splatting (3DGS). Using existing grayscale images from the Astrobee free-flying robot
Current work in modeling symbolic music primarily relies on representations extracted from MIDI-like data. While such formats allow for modeling symbolic music as sequences of notes, they omit the large space of symbolic
Recent mesh-based simulation advances have, in no small part, relied on neural surrogates of two distinct families: global models that route information through a small set of latent tokens, and local models that perform
Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially when evaluation-aware models exhibit scheming or deception. However
The topic of explanation in recommender systems has seen steady research attention since the earliest days of the field. With some exceptions, this work has focused on the explanation of single items in a recommendation
When discrete-time optimizers operate at the edge of stability, they exhibit near-two-periodic behavior. These oscillatory dynamics are reminiscent of conservative systems, such as the dynamics generated by symplectic in
Multi-task learning often combines losses that span several orders of magnitude, causing homoscedastic uncertainty weighting to degrade severely. We propose Bounded Precision-Geometry Scaling (BPGS), a method that maps e
Neural-network surrogate models are increasingly used to accelerate scientific simulations, but their deployment in extrapolative and autoregressive settings requires input-dependent estimates of prediction error. In thi
TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper presents a systematic performance and power characterization of diverse
Motivated by equivariant neural networks, we study piecewise linear equivariant maps between finite-dimensional real representations of compact groups. We show that all genuinely non-linear piecewise linear behaviour is
Accurate and reliable collection of electricity consumption data through Advanced Metering Infrastructure (AMI) is of great importance for the operation of smart grids, especially for the detection of non-technical losse
Video Object-Centric Learning (OCL) has traditionally focused on refining the encoder architecture to ensure temporal consistency. In this paper, we argue that the primary bottleneck lies in the decoder. We show that tra
Trajectory optimization computes dynamically feasible motions that enable autonomous systems to accomplish complex tasks while satisfying operational and environmental constraints. This tutorial presents OpenSCvx, an ope
Cheque fraud is a material risk in after-hours business deposit operations because funds may be released within one business day, while cheque clearing takes several days. This timing gap creates a fraud exposure window
Semantic communication shifts the objective of communication systems from accurate symbol reconstruction toward meaning preservation, task accomplishment, and efficient information exchange. However, its evaluation remai
In on-device NLP tasks, limited resources of embedded hardware, such as the Raspberry Pi 5, require efficient inference strategies. This paper introduces FrugalSOT (Frugal Search Over The Models), a resource-aware model
This paper investigates wearable-based recognition of human activities and gestures to support Human-Robot Interaction (HRI) in object-handover and assembly-like scenarios. Electromyography (EMG) and Inertial Measurement