arXiv:2605.01369v2 Announce Type: replace-cross Abstract: Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a privacy-preserving and cost-effective manner. However, DL-based models generalize poorly across environments, a challenge amplified in multi-user settings where overlapping activities cause CSI entanglement and domain shifts. Practical […]
Detecting Synthetic Political Narratives in Cross-Platform Social Media Discourse
arXiv:2605.21540v1 Announce Type: cross Abstract: The proliferation of large language models has introduced a new paradigm of synthetic political communication in which narratives may be generated, semantically coordinated, and strategically disseminated across platforms at scale. We present a cross-platform framework for detecting synthetic political narratives using four coordination signals — lexical diversity D(C), temporal burstiness […]
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
arXiv:2605.22786v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can improve efficiency and preserve richer task-relevant information. However, KV caches also encode contextual inputs, […]
HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine
arXiv:2605.21496v1 Announce Type: cross Abstract: Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmarks miss the failure modes that matter in emergency medicine: trajectory-level safety collapse, tool misuse, and capitulation under sustained clinical pressure. We present HealthCraft, the first public reinforcement-learning environment that rewards […]
Secure and Parallel Determinant Computation for Large-Scale Matrices in Edge Environments
arXiv:2605.22039v1 Announce Type: cross Abstract: The advent of edge computing has enabled resource-constrained clients to delegate intensive computational tasks to distributed edge servers, especially within Internet of Things (IoT) environments. Among such tasks, Matrix Determinant Computation (MDC) remains critical for applications in control systems, cryptography, and machine learning. However, the cubic complexity of traditional determinant […]
OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025
arXiv:2605.22200v1 Announce Type: cross Abstract: Achieving high levels of surgical skill through effective training is essential for optimal patient outcomes. Automated, data-driven skill assessment holds significant potential to improve surgical training. While machine learning-based methods are increasingly popular for assessing skills in minimally invasive surgery, their application to open surgery remains limited. We present the […]
Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging
arXiv:2605.21789v1 Announce Type: cross Abstract: Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose strict latency and accuracy constraints. While transformer architectures achieve the highest jet tagging accuracy when compute is unconstrained, […]
Thermodynamic Irreversibility of Training Algorithms
arXiv:2605.21933v1 Announce Type: cross Abstract: The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and understanding the irreversibility of these algorithms is a fundamental step towards understanding the learning dynamics of modern AI systems. In this work, we establish a general framework for defining and analyzing the irreversibility of training algorithms. We show […]
Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology
arXiv:2605.22401v1 Announce Type: cross Abstract: Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpropagation at human V1 by testing the same five learning rules against macaque electrophysiology. The rules are backpropagation (BP), feedback alignment (FA), predictive coding (PC), spike-timing-dependent plasticity (STDP), and […]
Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly
arXiv:2605.21625v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting […]
MRecover: A Conditional Generative Model for Recovering Motion-Corrupted MR images Using AI Generated Contrast
arXiv:2605.21669v1 Announce Type: cross Abstract: Hippocampal subfield segmentation requires high-resolution T2w turbo spin echo (TSE) MRI, yet this sequence is susceptible to motion artifacts, leading to substantial data loss. We developed a conditional generative model (MRecover) that synthesizes routinely acquired T1w images to create TSE images with autoregressive slice conditioning for volumetric consistency. Trained on […]
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
arXiv:2605.21856v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious model publishers who use evasive, or indirect, contamination strategies, such as paraphrasing benchmark data to evade existing detection […]