AI Research Papers

arXiv:2605.18801v1 Announce Type: new Abstract: Data is fundamental to large language models (LLMs). However, understanding of what makes certain data useful for different stages of an LLM workflow, including training, …

arXiv:2605.18818v1 Announce Type: new Abstract: Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production…

arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex, potentially…

arXiv:2605.19008v1 Announce Type: new Abstract: Modern language-model training is increasingly exposed to instability, degraded runs, and wasted compute, especially under aggressive learning-rate, scale, and…

arXiv:2605.19010v1 Announce Type: new Abstract: Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in…

arXiv:2605.19031v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance…

arXiv:2605.19035v1 Announce Type: new Abstract: The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from…

arXiv:2605.19042v1 Announce Type: new Abstract: Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work…

arXiv:2605.19093v1 Announce Type: new Abstract: System prompts are a central control mechanism in modern AI systems, shaping behavior across conversations, tasks, and user populations. Yet they are difficult to tune…

arXiv:2605.19099v1 Announce Type: new Abstract: We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau-bench, BFCL…

arXiv:2605.19127v1 Announce Type: new Abstract: LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be …

arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function of that artifact…

arXiv:2605.19151v1 Announce Type: new Abstract: We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a…

arXiv:2605.19156v1 Announce Type: new Abstract: Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good…

arXiv:2605.19186v1 Announce Type: new Abstract: Two decades ago, the Semantic Web Services community was asked how agents with different ontological commitments could discover, compose, and invoke web services…

arXiv:2605.19192v1 Announce Type: new Abstract: Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or transfer, hallucination …

arXiv:2605.19215v1 Announce Type: new Abstract: Adaptive decision-making in biological and artificial intelligence requires balancing the exploitation of known outcomes with the exploration of uncertain alternatives.…

arXiv:2605.19219v1 Announce Type: new Abstract: A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistical significance,…

arXiv:2605.19229v1 Announce Type: new Abstract: Survey research faces mounting structural challenges: declining response rates, sample bias, block-wise missingness among at-risk respondents, and AI-assisted fraudulent…

arXiv:2605.19250v1 Announce Type: new Abstract: Modality-conflict hallucination occurs when multimodal large language models (MLLMs) prioritize erroneous textual premises over contradictory visual evidence. To…

arXiv:2605.19260v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at…

arXiv:2605.19264v1 Announce Type: new Abstract: Voting methods weighted by stakes are the fundamental governance paradigm in Proof-of-Stake (PoS) blockchains. Such a paradigm is known to be prone to power distortions:…

arXiv:2605.19330v1 Announce Type: new Abstract: LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike monolithic…

arXiv:2605.19337v1 Announce Type: new Abstract: A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason…

arXiv:2605.19376v1 Announce Type: new Abstract: How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence…

arXiv:2605.19382v1 Announce Type: new Abstract: Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluating whether…

arXiv:2605.19418v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM agents. However,…

arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be…

arXiv:2605.19457v1 Announce Type: new Abstract: Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approaches modeled…

arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution …

arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However,…

arXiv:2605.19514v1 Announce Type: new Abstract: Many works make the eye-catching claim that Transformers are Turing-complete. However, the literature often conflates two distinct settings: (i) a fixed Transformer…

arXiv:2605.19518v1 Announce Type: new Abstract: Generating Knowledge Graphs (KGs) remains one of the most time-consuming and labor-intensive tasks for knowledge engineers, as they need to identify semantic equivalences …

arXiv:2605.19521v1 Announce Type: new Abstract: We analyze the structure of the disagreement among a population of voters over a set of alternatives. Surveys typically ask either for pairwise comparisons, simple and…

arXiv:2605.19529v1 Announce Type: new Abstract: When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative…

arXiv:2605.19576v1 Announce Type: new Abstract: Self-evolving skill libraries face a silent failure mode we term \emph{library drift}: unbounded skill accumulation without outcome-driven lifecycle management causes…

arXiv:2605.19587v1 Announce Type: new Abstract: Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only what the…

arXiv:2605.19593v1 Announce Type: new Abstract: Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared,…

arXiv:2605.19604v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing…

arXiv:2605.19630v1 Announce Type: new Abstract: With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect …

arXiv:2605.19662v1 Announce Type: new Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed …

arXiv:2605.19663v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are becoming the cornerstone of high-level reasoning for robotic automation, enabling robots to parse natural language commands and perceive …

arXiv:2605.19671v1 Announce Type: new Abstract: Applying local search algorithms to combinatorial optimization problems is not an easy feat. Typically, human intervention is required to compile the constraints to input …

arXiv:2605.19674v1 Announce Type: new Abstract: Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcomes. Existing SC…

arXiv:2605.19721v1 Announce Type: new Abstract: Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinatorial explosion…

arXiv:2605.19743v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly applied to engineering design tasks, yet existing evaluation frameworks do not adequately address multi-agent systems…

arXiv:2605.19748v1 Announce Type: new Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on…

arXiv:2605.19758v1 Announce Type: new Abstract: The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models have achieved…

arXiv:2605.19762v1 Announce Type: new Abstract: Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code…

arXiv:2605.19765v1 Announce Type: new Abstract: Existing affective-computing, social-signal-processing, and meeting corpora capture important parts of human interaction, but they rarely support analysis of affect in…

arXiv:2605.19768v1 Announce Type: new Abstract: We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Existing algorithms…

arXiv:2605.19769v1 Announce Type: new Abstract: We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1)…

arXiv:2605.19779v1 Announce Type: new Abstract: We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for…

arXiv:2605.19781v1 Announce Type: new Abstract: Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle…

arXiv:2605.19782v1 Announce Type: new Abstract: LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or discovery…

arXiv:2605.19824v1 Announce Type: new Abstract: Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and Large Multimodal…

arXiv:2605.19826v1 Announce Type: new Abstract: Operators of safety-critical industrial processes increasingly rely on digital twins to screen control interventions, but such simulators rarely carry certified safety…

arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry-breaking and…

arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations,…

arXiv:2605.19940v1 Announce Type: new Abstract: Foundation models are increasingly deployed in socially sensitive domains such as education, mental health, and caregiving, where failures are often cumulative and…

arXiv:2605.19943v1 Announce Type: new Abstract: Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refining a latent state…

arXiv:2605.20006v1 Announce Type: new Abstract: Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hindered by the cost…

arXiv:2605.20023v1 Announce Type: new Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of…

arXiv:2605.20025v1 Announce Type: new Abstract: Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives,…

arXiv:2605.20072v1 Announce Type: new Abstract: Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or…

arXiv:2605.20098v1 Announce Type: new Abstract: Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting,…

arXiv:2605.20120v1 Announce Type: new Abstract: AI-assisted theorem proving can now generate substantial Lean developments for olympiad-level mathematics, but the evidential status of such developments depends on which …

arXiv:2605.20164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model…

arXiv:2605.20167v1 Announce Type: new Abstract: Flash floods in Bangladesh's haor wetlands show up with almost no warning. They wreck the annual boro rice harvest. Current setups, built for riverine floods, miss…

arXiv:2605.20173v1 Announce Type: new Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class…

arXiv:2604.19892v1 Announce Type: cross Abstract: Incremental Potential Contact (IPC) guarantees intersection-free simulation but suffers from high computational costs due to the expensive Hessian assembly and linear…

arXiv:2605.18758v1 Announce Type: cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires…

arXiv:2605.18759v1 Announce Type: cross Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance across a wide range of…

arXiv:2605.18760v1 Announce Type: cross Abstract: Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over.…

arXiv:2605.18762v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization.…

arXiv:2605.18763v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is…

arXiv:2605.18764v1 Announce Type: cross Abstract: Artificial Intelligence (AI) pipelines have become integral to modern research, supporting fields such as Medical Sciences, Agriculture, and Social Sciences, and…

arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages…

arXiv:2605.18766v1 Announce Type: cross Abstract: Retrieving relevant tables from extensive databases for a given natural language query is essential for accurately answering questions in tasks such as text-to-SQL.…

arXiv:2605.18767v1 Announce Type: cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental…

arXiv:2605.18769v1 Announce Type: cross Abstract: Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high…

arXiv:2605.18770v1 Announce Type: cross Abstract: We present a collaborative agentic GraphRAG framework for expert analysis of commercial registry data. Public registries are often formally accessible, yet difficult to …

arXiv:2605.18772v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic…

arXiv:2605.18773v1 Announce Type: cross Abstract: Traditional facility management often relies on centralized decision-making structures that limit stakeholder participation, leading to misalignment with occupant needs …

arXiv:2605.18774v1 Announce Type: cross Abstract: In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure.…

arXiv:2605.18775v1 Announce Type: cross Abstract: Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles…

arXiv:2605.18776v1 Announce Type: cross Abstract: The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely on supervised…

arXiv:2605.18780v1 Announce Type: cross Abstract: Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of their reasoning…

arXiv:2605.18781v1 Announce Type: cross Abstract: Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamics, evaluating 12…

arXiv:2605.18784v1 Announce Type: cross Abstract: The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create…

arXiv:2605.18789v1 Announce Type: cross Abstract: Features in language models have life history: they emerge, persist, and die during training, yet the importance of that history remains largely unexplored. We find…

arXiv:2605.18793v1 Announce Type: cross Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face…

arXiv:2605.18794v1 Announce Type: cross Abstract: Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear functions. A…

arXiv:2605.18795v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE)…

arXiv:2605.18797v1 Announce Type: cross Abstract: Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer…

arXiv:2605.18799v1 Announce Type: cross Abstract: Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user…

arXiv:2605.18800v1 Announce Type: cross Abstract: Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). The primary…

arXiv:2605.18802v1 Announce Type: cross Abstract: Cardiovascular stability estimation from wearable photoplethysmography (PPG) requires a principled nonlinear framework, yet major gaps persist in heuristic parameter…

arXiv:2605.18803v1 Announce Type: cross Abstract: Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate…

arXiv:2605.18804v1 Announce Type: cross Abstract: We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and…

arXiv:2605.18805v1 Announce Type: cross Abstract: LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations …

arXiv:2605.18807v1 Announce Type: cross Abstract: Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic…

arXiv:2605.18808v1 Announce Type: cross Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse…

arXiv:2605.18809v1 Announce Type: cross Abstract: General-sum multi-agent learning is often governed by a stacked update field in which each agent's policy update changes the optimization landscape faced by the others. …

arXiv:2605.18810v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel …

arXiv:2605.18813v1 Announce Type: cross Abstract: World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement learning. Yet,…

arXiv:2605.18816v1 Announce Type: cross Abstract: Neural surrogates enable orders-of-magnitude acceleration of computational fluid dynamics (CFD) simulations, with the potential to transform engineering and healthcare…

arXiv:2605.18820v1 Announce Type: cross Abstract: Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead of unrolling serial …

arXiv:2605.18822v1 Announce Type: cross Abstract: Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and …

arXiv:2605.18824v1 Announce Type: cross Abstract: Evaluation of foundation models often rely on aggregate scores from benchmarks that lack comprehensive coverage and metadata for a fine-grained evaluation. We introduce …

arXiv:2605.18826v1 Announce Type: cross Abstract: The attention interaction matrix $QK^{\top}$ contains two entangled computations: a skew-symmetric component that redistributes information between positions (routing)…

arXiv:2605.18832v1 Announce Type: cross Abstract: The Transformer is the foundational building block of modern AI, yet offers no principled handling of \emph{uncertainty}, which is prevalent in real applications:…

arXiv:2605.18833v1 Announce Type: cross Abstract: Automated data quality assessment is crucial for managing big data, but existing solutions face challenges in achieving accurate context-aware assessment. This paper…

arXiv:2605.18837v1 Announce Type: cross Abstract: Wearable devices enable continuous health monitoring from multimodal signals, but real-world deployment is hindered by limited labeled data and pervasive sensor…

arXiv:2605.18838v1 Announce Type: cross Abstract: Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base models from 16…

arXiv:2605.18839v1 Announce Type: cross Abstract: Overcrowding in emergency departments (ED) remains a persistent operational challenge worldwide, causing delays in care delivery and downstream congestion. ED boarding…

arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the frontier, this…

arXiv:2605.18844v1 Announce Type: cross Abstract: With the deep integration of the travel and energy industries, cross-industry supply chain finance has gradually become a high-risk field of hidden money laundering…

arXiv:2605.18845v1 Announce Type: cross Abstract: We give the first quantitative prediction of grokking delay under AdamW. Treating the delay as a first-passage time, we derive a closed-form law T_grok - T_mem = (1 / 2 …

arXiv:2605.18846v1 Announce Type: cross Abstract: Classical communication systems fail not only through random noise but also when transmitter and receiver use incompatible operational codebooks. Variational…

arXiv:2605.18847v1 Announce Type: cross Abstract: Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those internal…

arXiv:2605.18848v1 Announce Type: cross Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by leveraging the exact…

arXiv:2605.18849v1 Announce Type: cross Abstract: Explainability methods have progressed rapidly, but global explanations for time-series models remain underdeveloped, with most approaches focusing on local,…

arXiv:2605.18850v1 Announce Type: cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently access, aggregate,…

arXiv:2605.18852v1 Announce Type: cross Abstract: Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and evaluation signals are …

arXiv:2605.18857v1 Announce Type: cross Abstract: For most of the history of information retrieval (IR), search results were designed for human consumers who could scan, filter, and discard irrelevant information on…

arXiv:2605.18858v1 Announce Type: cross Abstract: Probabilistic prediction systems often aggregate probability estimates from multiple models into a single decision. A common assumption is that if each model is…

arXiv:2605.18859v1 Announce Type: cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many…

arXiv:2605.18862v1 Announce Type: cross Abstract: Cardiovascular disease remains the leading cause of death worldwide, and early detection of arrhythmias through continuous ECG monitoring on wearable devices can…

arXiv:2605.18864v1 Announce Type: cross Abstract: Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains …

arXiv:2605.18865v1 Announce Type: cross Abstract: Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing…

arXiv:2605.18866v1 Announce Type: cross Abstract: Reconstructing continuous flow fields from sparse surface-mounted sensors is central to aerodynamic design, flow control, and digital-twin instrumentation. Existing…

arXiv:2605.18867v1 Announce Type: cross Abstract: Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation …

arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks.…

arXiv:2605.18869v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt …

arXiv:2605.18871v1 Announce Type: cross Abstract: When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appear correct while…

arXiv:2605.18872v1 Announce Type: cross Abstract: Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive retraining for…

arXiv:2605.18873v1 Announce Type: cross Abstract: Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements are commercially…

arXiv:2605.18879v1 Announce Type: cross Abstract: Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising…

arXiv:2605.18882v1 Announce Type: cross Abstract: LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three…

arXiv:2605.18883v1 Announce Type: cross Abstract: A diffusion model trained on Hamiltonian trajectories can achieve rollout MSE near $10^{-3}$, but the standard deviation of its energy over time is between 7500 and…

arXiv:2605.18885v1 Announce Type: cross Abstract: We prove that the extremum stack of a discrete sequence is a minimal sufficient statistic for the class of all computable, causal, rate-independent functionals, in the…

arXiv:2605.18889v1 Announce Type: cross Abstract: Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical algorithms. Here we introduce Soft…

arXiv:2605.18890v1 Announce Type: cross Abstract: The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring new expressive power …

arXiv:2605.18891v1 Announce Type: cross Abstract: Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace keeps emitting the…

arXiv:2605.18892v1 Announce Type: cross Abstract: Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data across devices or…

arXiv:2605.18895v1 Announce Type: cross Abstract: Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attributable multi-vehicle …

arXiv:2605.18897v1 Announce Type: cross Abstract: Intracranial EEG (iEEG) provides high-fidelity neural recordings essential for clinical and brain-computer interface applications, but acquiring these signals requires…

arXiv:2605.18899v1 Announce Type: cross Abstract: Generative LLM-based recommenders (LLM-Rec) require continual post-deployment updates, yet deployment logs provide only policy-shaped contextual bandit feedback:…

arXiv:2605.18904v1 Announce Type: cross Abstract: Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility by selectively…

arXiv:2605.18905v1 Announce Type: cross Abstract: Neural operators have emerged as a powerful, discretization-invariant framework for solving partial differential equations (PDEs). Although established approaches like…

arXiv:2605.18907v1 Announce Type: cross Abstract: Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly…

arXiv:2605.18908v1 Announce Type: cross Abstract: Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gradients, or…

arXiv:2605.18911v1 Announce Type: cross Abstract: Wildfire prediction is important for early warning and resource allocation, yet existing Earth foundation models (Earth FMs) are pretrained for general atmospheric and…

arXiv:2605.18913v1 Announce Type: cross Abstract: The U.S. financial system processes approximately 1.3 million interbank transactions daily, yet no system in the reviewed literature models fraud propagation across the …

arXiv:2605.18915v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs,…

arXiv:2605.18916v1 Announce Type: cross Abstract: We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally…

arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web searches, retrieved …

arXiv:2605.18919v1 Announce Type: cross Abstract: Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient…

arXiv:2605.18920v1 Announce Type: cross Abstract: Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers.…

arXiv:2605.18930v1 Announce Type: cross Abstract: Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks.…

arXiv:2605.18931v1 Announce Type: cross Abstract: Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge for modern deep…

arXiv:2605.18932v1 Announce Type: cross Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language…

arXiv:2605.18971v1 Announce Type: cross Abstract: What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost entirely from…

arXiv:2605.18974v1 Announce Type: cross Abstract: Classifying artworks presents a significant challenge due to the complex interplay of fine-grained details and abstract features that condition the style or genre of an …

arXiv:2605.18988v1 Announce Type: cross Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack surface.…

arXiv:2605.18991v1 Announce Type: cross Abstract: We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and…

arXiv:2605.18993v1 Announce Type: cross Abstract: Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning through subtraction.…

arXiv:2605.19033v1 Announce Type: cross Abstract: Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent…

arXiv:2605.19043v1 Announce Type: cross Abstract: Automated grading systems have enabled scalable assessment for many response types, but handwritten mathematics remains a barrier due to the complexity of multi-step…

arXiv:2605.19049v1 Announce Type: cross Abstract: Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However,…

arXiv:2605.19060v1 Announce Type: cross Abstract: High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often …

arXiv:2605.19064v1 Announce Type: cross Abstract: Workforce transformations are difficult to forecast and costly to mismanage. In particular, the integration of artificial intelligence into knowledge work currently…

arXiv:2605.19069v1 Announce Type: cross Abstract: Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied conditions for…

arXiv:2605.19073v1 Announce Type: cross Abstract: Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention across different applications. In contrast, the manifold of…

arXiv:2605.19074v1 Announce Type: cross Abstract: The rapid global expansion of solar photovoltaic (PV) capacity-reaching a record 597 GW in 2024-highlights the urgent need for robust forecasting models to mitigate the …

arXiv:2605.19075v1 Announce Type: cross Abstract: Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video archives while…

arXiv:2605.19077v1 Announce Type: cross Abstract: Task-oriented dialogue systems -- handling transactions, reservations, and service requests -- require predictable behavior, yet the moderately-sized LLMs needed for…

arXiv:2605.19080v1 Announce Type: cross Abstract: In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay…

arXiv:2605.19092v1 Announce Type: cross Abstract: Reasoning systems increasingly separate intermediate computation into private and public channels, creating evaluation cases that look similar in transcripts:…

arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchmark problems.…

arXiv:2605.19104v1 Announce Type: cross Abstract: Continuum robots enable dexterous manipulation in constrained environments, but require accurate and efficient models for real-time manipulation and control.…

arXiv:2605.19111v1 Announce Type: cross Abstract: Existing text-to-image (T2I) evaluation metrics mainly assess whether generated images align with information explicitly stated in the prompt, but often fail to capture …

arXiv:2605.19119v1 Announce Type: cross Abstract: Existing neural combinatorial optimization solvers frame solution search as imitation of optimal decisions, inherently limiting their utility to single-objective…

arXiv:2605.19130v1 Announce Type: cross Abstract: Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent…

arXiv:2605.19133v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is now a standard way to pretrain medical image models, but performance is still mostly judged by downstream accuracy. For…

arXiv:2605.19138v1 Announce Type: cross Abstract: The scarcity of large-scale, high-quality demonstration data remains a bottleneck in scaling imitation learning for robotic manipulation. We present COBALT, a…

arXiv:2605.19141v1 Announce Type: cross Abstract: Large language models are increasingly deployed as automated judges to evaluate the strength of arguments. As this role expands, their legitimacy depends on…

arXiv:2605.19147v1 Announce Type: cross Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore,…

arXiv:2605.19150v1 Announce Type: cross Abstract: State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix.…

arXiv:2605.19172v1 Announce Type: cross Abstract: Forecasting urban delivery demand becomes substantially more challenging when newly added service regions lack historical records. Existing spatiotemporal forecasters…

arXiv:2605.19185v1 Announce Type: cross Abstract: Sparse goal-conditioned planning with few cost-to-go labels can be viewed as a graph-PDE Dirichlet extension problem: extend sparse labels on a goal-dependent boundary…

arXiv:2605.19190v1 Announce Type: cross Abstract: Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant…

arXiv:2605.19201v1 Announce Type: cross Abstract: Deep learning models detect pneumonia from chest X-rays with high accuracy, but the performance declines under domain shifts caused by differences in devices, patients, …

arXiv:2605.19202v1 Announce Type: cross Abstract: This paper addresses the problem of using a deep Reinforcement Learning (RL)-based low-level Quadrotor controller within an autonomous Quadrotor navigation stack for…

arXiv:2605.19207v1 Announce Type: cross Abstract: Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficult due to…

arXiv:2605.19218v1 Announce Type: cross Abstract: Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token…

arXiv:2605.19220v1 Announce Type: cross Abstract: Uncertainty Quantification (UQ) is widely regarded as the primary safeguard for deploying Large Language Models (LLMs) in high-stakes domains. However, we argue that…

arXiv:2605.19227v1 Announce Type: cross Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a…

arXiv:2605.19228v1 Announce Type: cross Abstract: Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step …