arXiv:2605.00639v1 Announce Type: cross Abstract: Autonomous science is transforming how we discover materials and chemical systems for advanced energy technologies. However, many initially promising systems never reach deployment. This “valley of death” stems from optimization that prioritizes laboratory metrics over industrial viability. We propose a new strategy: “born-qualified” autonomous development, which embeds manufacturability, cost, and […]
AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
arXiv:2604.27855v2 Announce Type: replace-cross Abstract: AI inference is becoming a persistent and geographically distributed source of electricity demand. Unlike many traditional electrical loads, inference workloads can sometimes be executed away from the user-facing service location, provided that latency, state locality, capacity, and regulatory constraints remain acceptable. This paper studies when such digital relocation of computation […]
Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision
arXiv:2605.00644v1 Announce Type: cross Abstract: Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. However, learning multimodal EBM by maximum likelihood requires Markov Chain Monte Carlo (MCMC) sampling in the joint data space, where noise-initialized Langevin dynamics often mixes poorly and fails to […]
BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
arXiv:2605.00632v1 Announce Type: cross Abstract: Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically […]
DeGenTWeb: A First Look at LLM-dominant Websites
arXiv:2605.00087v1 Announce Type: cross Abstract: Many recent news reports have claimed that content generated by large language models (LLMs) is taking over the web. However, these claims are typically not based on a representative sample of the web and the methodology underlying them is often opaque. Moreover, when aiming to minimize the chances of falsely […]
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
arXiv:2605.00225v1 Announce Type: cross Abstract: We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the embedding model. This result is of practical importance because annotated bioacoustic data are scarce and costly to obtain, leaving conventional supervised approaches prone to overfitting and […]
The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor
arXiv:2601.09896v4 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed “aesthetic” is inextricably linked to personal taste and cultural values, raising the question of whose taste is represented in visual generative AI models. In this work, we study an aesthetic evaluation model–LAION-Aesthetics Predictor […]
SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning
arXiv:2604.19098v2 Announce Type: replace-cross Abstract: English financial NLP has advanced rapidly through benchmarks targeting earnings analysis, market sentiment, tabular reasoning, and financial question answering, yet Arabic financial NLP remains virtually nonexistent, despite 422 million speakers, $4.9 trillion in Gulf sovereign wealth, and a $4-5 trillion Islamic finance industry requiring specialized Shari’ah compliance over instruments like […]
Fairness of Classifiers in the Presence of Constraints between Features
arXiv:2605.00592v1 Announce Type: cross Abstract: In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when constraints exist between features, such dependencies can be obscured by the constraints. To avoid this problem, we propose that a decision […]
Bridging the Experimental Last Mile: Digitizing Laboratory Know-How for Safe AI-Assisted Support
arXiv:2604.16345v2 Announce Type: replace-cross Abstract: While advances in materials informatics have accelerated the development of Self-Driving Laboratories (SDLs), human-led experiments remain standard in many educational and exploratory research laboratories. In specific lab settings, formal documentation alone is often insufficient for safe and reliable operation. We refer to the gap between formal documentation and reliable execution […]
Jailbreaking Vision-Language Models Through the Visual Modality
arXiv:2605.00583v1 Announce Type: cross Abstract: The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting […]
A First Guess is Rarely the Final Answer: Learning to Search in the Traveling Salesperson Problem
arXiv:2604.06940v2 Announce Type: replace-cross Abstract: Most neural solvers for the Traveling Salesperson Problem (TSP) are trained to output a single solution, even though practitioners rarely stop there: at test time, they routinely spend extra compute on sampling or post-hoc search. This raises a natural question: can the search procedure itself be learned? Neural improvement methods […]