Stories tagged science & research.
arXiv
arXiv:2609.26547v1 Announce Type: cross Abstract: Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additive manufacturing, and fusion energy systems. Although generative modeling has…
arXiv
arXiv:2609.26711v1 Announce Type: cross Abstract: Software vulnerabilities are often discovered long after they are introduced, making it difficult to identify the vulnerability-inducing commit (VIC) responsible for introducing the underlying vulnerable condition. Existing VIC identification…
arXiv
arXiv:2606.04111v2 Announce Type: replace-cross Abstract: Vision-based UAV navigation becomes challenging when navigation targets are distributed across complementary camera views and cannot be reliably observed from a single viewpoint. We propose AgenticDiffusion, an agentic multi-view UAV…
arXiv
arXiv:2507.14077v2 Announce Type: replace Abstract: Artificial intelligence (AI) algorithms are a critical part of state-of-the-art digital health technology for diabetes management. Yet, access to large high-quality datasets is creating barriers that impede development of robust AI solutions. To…
arXiv
arXiv:2604.02947v2 Announce Type: replace Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete…
arXiv
arXiv:2606.13591v2 Announce Type: replace Abstract: Multiagent language model systems, such as collaborative reasoning and debate, produce multiple correlated candidate answers and confidence signals. However, these signals are usually calibrated only at the individual agent level, and provide no…
arXiv
arXiv:2609.26512v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge at a specific point in network depth is unclear. We compared six CNNs and two vision transformers…
arXiv
arXiv:2609.26480v1 Announce Type: cross Abstract: Recent code generation research has moved from isolated function completion toward repository-level generation in existing codebases. To implement a target function correctly, an LLM must identify reusable repository dependencies such as existing…
arXiv
arXiv:2609.23735v2 Announce Type: replace Abstract: Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim assessment. Most existing systems, however, are organized around individual tasks: the same papers…
arXiv
arXiv:2412.02520v5 Announce Type: replace-cross Abstract: Connected automated vehicles (CAVs) equipped with adaptive cruise control (ACC) create new opportunities for highway congestion mitigation. Traditional practice relies on Eulerian variable speed limits (VSL) which regulate traffic through…
arXiv
arXiv:2504.20106v4 Announce Type: replace-cross Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches, such…
arXiv
arXiv:2509.05500v2 Announce Type: replace-cross Abstract: Autonomous microrobots could enable minimally invasive interventions in confined biological environments, but their operation requires real-time navigation among moving obstacles and environmental disturbances. Here we present a closed-loop…
arXiv
arXiv:2510.25890v4 Announce Type: replace-cross Abstract: Large language models (LLMs) enable natural-language interaction in engineering modeling, but generated models may violate structural constraints, domain rules, or task requirements. We propose a metamodel-guided model generation method that…
arXiv
arXiv:2602.01163v2 Announce Type: replace-cross Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporary structures) invisible to traditional geometric sensors. In this paper, we propose a novel…
arXiv
arXiv:2609.26550v1 Announce Type: new Abstract: LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is…
arXiv
arXiv:2604.25031v3 Announce Type: replace-cross Abstract: When an LLM formalizes natural language, how do we know the output is faithful? We propose a roundtrip verification approach which does not require ground-truth annotations: formalize a statement, translate the result back to natural…
arXiv
arXiv:2605.10698v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic ``Bystander Effect,'' inducing severe…
arXiv
arXiv:2608.26480v2 Announce Type: replace-cross Abstract: Frontier coding performance is typically attained with large, costly proprietary models. We introduce ledger-based zero-shot self-orchestration (GVS5H), a training-free method in which fresh instances of one model decompose problems and…
arXiv
arXiv:2609.03467v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than…
arXiv
arXiv:2609.11873v3 Announce Type: replace-cross Abstract: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal…
arXiv
arXiv:2609.24814v2 Announce Type: replace-cross Abstract: Advances in processing power, camera technologies, and mobile image analysis have made smartphones and other mobile devices, such as laptops, increasingly suitable for medical diagnosis and healthcare applications. Researchers have developed…
arXiv
arXiv:2609.25537v1 Announce Type: cross Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latency, energy consumption, and GPU memory demand as context length scales. Existing soft-compression…
arXiv
arXiv:2609.26389v1 Announce Type: cross Abstract: Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inherently static. They either receive complete sequences for offline processing or…
arXiv
arXiv:2609.26347v2 Announce Type: cross Abstract: The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP) tools. We present TransBERT, a novel framework for pre-training language models using exclusively…
arXiv
arXiv:2609.26419v1 Announce Type: new Abstract: Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic…
arXiv
arXiv:2609.19399v2 Announce Type: replace-cross Abstract: Game-theoretic analyses of cyber defence often compute equilibria of games whose payoffs exist only as the output of a simulator. Iterative equilibrium-finding methods grow a set of attacker and defender policies and need the payoff of every…
arXiv
arXiv:2609.26023v1 Announce Type: cross Abstract: The need for collaboration between diverse fields of research is increasingly recognised as important by research funding agencies. A significant driver of this need is the current revolution in artificial intelligence (AI) and related technologies…
arXiv
arXiv:2609.26229v1 Announce Type: cross Abstract: Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification, and knowledge retrieval. Still, they are prone to produce hallucinations…
arXiv
arXiv:2609.26314v1 Announce Type: cross Abstract: Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views reveal local…
arXiv
arXiv:2609.26377v1 Announce Type: cross Abstract: Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing a fairness--robustness conflict. We propose FairMean to manage this conflict…