arXiv:2603.13683v1 Announce Type: cross Abstract: Although debiased LLMs perform well on known bias patterns, they often fail to generalize to unfamiliar bias prompts, producing toxic outputs. We first validate that such high-bias prompts constitute a emphdistribution shift via OOD detection, and show static models degrade under this shift. To adapt on-the-fly, we propose textbfCAP-TTA, a […]
Separable neural architectures as a primitive for unified predictive and generative intelligence
arXiv:2603.12244v2 Announce Type: replace-cross Abstract: Intelligent systems across physics, language and perception often exhibit factorisable structure, yet are typically modelled by monolithic neural architectures that do not explicitly exploit this structure. The separable neural architecture (SNA) addresses this by formalising a representational class that unifies additive, quadratic and tensor-decomposed neural models. By constraining interaction order […]
AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
arXiv:2603.13779v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform in industrial anomaly detection (IAD). This is because MLLMs trained mostly on general web data differ significantly from industrial images. Moreover, they encode each image independently and can only compare images in the […]
ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting
arXiv:2603.14629v1 Announce Type: cross Abstract: ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv, extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware related-work section. The system combines FastAPI, Next.js, DSPy, SQLite, and Qdrant in a local-first […]
EI-Part: Explode for Completion and Implode for Refinement
arXiv:2603.14021v1 Announce Type: cross Abstract: Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often struggle to produce well-constructed parts, exhibiting poor structural coherence, geometric implausibility, inaccuracy, or inefficiency. […]
MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?
arXiv:2603.11935v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet their potential for generating kernels specifically for mobile devices remains largely unexplored. In this work, we extend the scope of automated kernel generation to the mobile domain to investigate the central question: Can LLMs write efficient kernels for […]
Controllable Accent Normalization via Discrete Diffusion
arXiv:2603.14275v1 Announce Type: cross Abstract: Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. We propose DLM-AN, a controllable accent normalization system built on masked discrete diffusion over self-supervised speech tokens. A Common Token Predictor identifies source tokens that likely encode […]
s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
arXiv:2603.14628v1 Announce Type: cross Abstract: Neurosymbolic approaches leveraging Large Language Models (LLMs) with formal methods have recently achieved strong results on mathematics-oriented theorem-proving benchmarks. However, success on competition-style mathematics does not by itself demonstrate the ability to construct proofs about real-world implementations. We address this gap with a benchmark derived from an industrial cryptographic library […]
MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization
arXiv:2603.12677v2 Announce Type: replace-cross Abstract: Knowledge editing (KE) aims to precisely rectify specific knowledge in Large Language Models (LLMs) without disrupting general capabilities. State-of-the-art methods suffer from an open-loop control mismatch. We identify a critical “Semantic-Execution Disconnect”: the semantic target is derived independently without feedback from the downstream’s feasible region. This misalignment often causes valid […]
RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
arXiv:2603.11558v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) systems have shown strong potential for language-driven robotic manipulation. However, scaling them to long-horizon tasks remains challenging. Existing pipelines typically separate data collection, policy learning, and deployment, resulting in heavy reliance on manual environment resets and brittle multi-policy execution. We present RoboClaw, an agentic robotics framework that unifies […]
TopoCL: Topological Contrastive Learning for Medical Imaging
arXiv:2603.14647v1 Announce Type: cross Abstract: Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g., connectivity patterns, boundary configurations, cavity formations) that provide valuable cues for medical image analysis. To address this limitation, we propose a […]
EcoFair-CH-MARL: Scalable Constrained Hierarchical Multi-Agent RL with Real-Time Emission Budgets and Fairness Guarantees
arXiv:2603.14625v1 Announce Type: cross Abstract: Global decarbonisation targets and tightening market pressures demand maritime logistics solutions that are simultaneously efficient, sustainable, and equitable. We introduce EcoFair-CH-MARL, a constrained hierarchical multi-agent reinforcement learning framework that unifies three innovations: (i) a primal-dual budget layer that provably bounds cumulative emissions under stochastic weather and demand; (ii) a fairness-aware […]