arXiv:2604.09734v4 Announce Type: replace-cross Abstract: We introduce an unsupervised visual representation learning system based entirely on local plasticity rules, without labels, backpropagation, or global error signals. The model is a VisNet-inspired hierarchical architecture combining opponent color inputs, multi-frequency Gabor and wavelet feature streams, competitive normalization with lateral inhibition, saliency modulation, associative memory, and a feedback […]
Soft-Label Governance for Distributional Safety in Multi-Agent Systems
arXiv:2604.19752v1 Announce Type: cross Abstract: Multi-agent AI systems exhibit emergent risks that no single agent produces in isolation. Existing safety frameworks rely on binary classifications of agent behavior, discarding the uncertainty inherent in proxy-based evaluation. We introduce SWARM (textbfSystem-textbfWide textbfAssessment of textbfRisk in textbfMulti-agent systems), a simulation framework that replaces binary good/bad labels with emphsoft […]
A Vision-Language-Action Model for Adaptive Ultrasound-Guided Needle Insertion and Needle Tracking
arXiv:2604.20347v1 Announce Type: cross Abstract: Ultrasound (US)-guided needle insertion is a critical yet challenging procedure due to dynamic imaging conditions and difficulties in needle visualization. Many methods have been proposed for automated needle insertion, but they often rely on hand-crafted pipelines with modular controllers, whose performance degrades in challenging cases. In this paper, a Vision-Language-Action […]
Can We Locate and Prevent Stereotypes in LLMs?
arXiv:2604.19764v1 Announce Type: cross Abstract: Stereotypes in large language models (LLMs) can perpetuate harmful societal biases. Despite the widespread use of models, little is known about where these biases reside in the neural network. This study investigates the internal mechanisms of GPT 2 Small and Llama 3.2 to locate stereotype related activations. We explore two […]
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
arXiv:2604.08570v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks, making it difficult to separate quantum reasoning from framework familiarity. We introduce QuanBench+, a unified benchmark spanning Qiskit, PennyLane, and Cirq, with 42 aligned tasks covering quantum algorithms, gate […]
CreativeGame:Toward Mechanic-Aware Creative Game Generation
arXiv:2604.19926v1 Announce Type: new Abstract: Large language models can generate plausible game code, but turning this capability into emphiterative creative improvement remains difficult. In practice, single-shot generation often produces brittle runtime behavior, weak accumulation of experience across versions, and creativity scores that are too subjective to serve as reliable optimization signals. A further limitation is […]
scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
arXiv:2604.20003v1 Announce Type: new Abstract: The integration of single-cell proteomic data is often hindered by the fragmented nature of targeted antibody panels. To address this limitation, we introduce scpFormer, a transformer-based foundation model designed for single-cell proteomics. Pre-trained on over 390 million cells, scpFormer replaces standard index-based tokenization with a continuous, sequence-anchored approach. By combining […]
Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
arXiv:2604.01577v2 Announce Type: replace-cross Abstract: We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable internal structures that evolve alongside the input. This mechanism allows the model to maintain coherent and clustered representations over […]
From Fuzzy to Formal: Scaling Hospital Quality Improvement with AI
arXiv:2604.20055v1 Announce Type: new Abstract: Hospital Quality Improvement (QI) plays a critical role in optimizing healthcare delivery by translating high-level hospital goals into actionable solutions. A critical step of QI is to identify the key modifiable contributing factors, a process we call QI factor discovery, typically through expert-driven semi-structured qualitative tools like fishbone diagrams, chart […]
Image Generators are Generalist Vision Learners
arXiv:2604.20329v1 Announce Type: cross Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining. While it has long been conjectured that the ability to create visual content implies an ability to understand it, […]
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
arXiv:2604.20140v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over dispreferred responses in their entirety and lacks the granularity to provide feedback on subsections of many-step solutions typical […]
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
arXiv:2603.29025v2 Announce Type: replace-cross Abstract: Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through a diagnose-measure-bridge-treat framework. Causal-behavioral analysis of the “car wash problem” across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the […]