arXiv:2510.05580v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA, a unified, backbone-agnostic post-training framework for efficient and scalable alignment. MetaVLA introduces Context-Aware Meta Co-Training, which consolidates diverse target […]
Noise-induced excitability: bloom, bust and extirpation in autotoxic population dynamics
arXiv:2601.20670v1 Announce Type: new Abstract: Species populations often modify their environment as they grow. When environmental feedback operates more slowly than population growth, the system can undergo boom-bust dynamics, where the population overshoots its carrying capacity and subsequently collapses. In extreme cases, this collapse leads to total extinction. While deterministic models typically fail to capture […]
SimpleMem: Efficient Lifelong Memory for LLM Agents
arXiv:2601.02553v2 Announce Type: replace Abstract: To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, […]
Enterprise Resource Planning Using Multi-type Transformers in Ferro-Titanium Industry
arXiv:2601.20696v1 Announce Type: new Abstract: Combinatorial optimization problems such as the Job-Shop Scheduling Problem (JSP) and Knapsack Problem (KP) are fundamental challenges in operations research, logistics, and eterprise resource planning (ERP). These problems often require sophisticated algorithms to achieve near-optimal solutions within practical time constraints. Recent advances in deep learning have introduced transformer-based architectures as […]
UDEEP: Edge-based Computer Vision for In-Situ Underwater Crayfish and Plastic Detection
arXiv:2401.06157v2 Announce Type: replace-cross Abstract: Invasive signal crayfish have a detrimental impact on ecosystems. They spread the fungal-type crayfish plague disease (Aphanomyces astaci) that is lethal to the native white clawed crayfish, the only native crayfish species in Britain. Invasive signal crayfish extensively burrow, causing habitat destruction, erosion of river banks and adverse changes in […]
Implementing Metric Temporal Answer Set Programming
arXiv:2601.20735v1 Announce Type: new Abstract: We develop a computational approach to Metric Answer Set Programming (ASP) to allow for expressing quantitative temporal constraints, like durations and deadlines. A central challenge is to maintain scalability when dealing with fine-grained timing constraints, which can significantly exacerbate ASP’s grounding bottleneck. To address this issue, we leverage extensions of […]
Randomly Wrong Signals: Bayesian Auction Design with ML Predictions
arXiv:2502.08792v3 Announce Type: replace-cross Abstract: We study auction design when a seller relies on machine-learning predictions of bidders’ valuations that may be unreliable. Motivated by modern ML systems that are often accurate but occasionally fail in a way that is essentially uninformative, we model predictions as randomly wrong: with high probability the signal equals the […]
Cross-Country Learning for National Infectious Disease Forecasting Using European Data
arXiv:2601.20771v1 Announce Type: new Abstract: Accurate forecasting of infectious disease incidence is critical for public health planning and timely intervention. While most data-driven forecasting approaches rely primarily on historical data from a single country, such data are often limited in length and variability, restricting the performance of machine learning (ML) models. In this work, we […]
Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
arXiv:2506.10912v3 Announce Type: replace Abstract: Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark […]
From Specialist to Generalist: Unlocking SAM’s Learning Potential on Unlabeled Medical Images
arXiv:2601.17934v2 Announce Type: replace-cross Abstract: Foundation models like the Segment Anything Model (SAM) show strong generalization, yet adapting them to medical images remains difficult due to domain shift, scarce labels, and the inability of Parameter-Efficient Fine-Tuning (PEFT) to exploit unlabeled data. While conventional models like U-Net excel in semi-supervised medical learning, their potential to assist […]
Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
arXiv:2601.20642v1 Announce Type: cross Abstract: Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization, where they unintentionally reproduce exact copies or parts of training images. Recent memorization detection methods are primarily based on the norm of score difference as indicators of memorization. We prove that such norm-based metrics are […]
VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing
arXiv:2601.07315v3 Announce Type: replace-cross Abstract: Analog mixed-signal circuit sizing involves complex trade-offs within high-dimensional design spaces. Existing automatic analog circuit sizing approaches rely solely on netlists, ignoring the circuit schematic, which hinders the cognitive link between the schematic and its performance. Furthermore, the black-box nature of machine learning methods and hallucination risks in large language […]