Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.27078v1 Announce Type: new Abstract: We introduce Lookup-table (LUT)-aware Efficient Attention on FPGAs (LEAF). LEAF is the first nanosecond-scale LUT-aware transformer for FPGAs. Deployin...
arXiv:2610.27107v1 Announce Type: new Abstract: Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are...
PURE is an unlabeled post‑training refinement framework that enhances feed‑forward 3D reconstruction models by improving depth and camera estimation without ground‑truth supervision. It distills structural knowledge from state‑of‑the‑art 2D priors into 4D architectures, using relative depth constraints, affine‑invariant geometry distillation, and pose refinement via feature correspondences. Experiments on synthetic and real‑world dynamic benchmarks show consistent improvements across multiple state‑of‑the‑art models, effectively mitigating domain shifts and unlocking their architectural limits in challenging in‑the‑wild scenes.
OptionWorld is a new benchmark that tracks how large language models handle long‑term personal assistant tasks, focusing on information gathering, decision making, actions, and outcomes over simulated daily life scenarios. The study finds that in 35.5% of failed cases the key facts are still present in the model’s last input, and identifies three main failure modes: missing or uncombined information, unused action opportunities, and unnecessary restrictions imposed by the agent. Follow‑up experiments show that providing missing facts, adding action reminders, and correcting erroneous restrictions can improve task success, highlighting gaps in state maintenance, deadline adherence, and assumption handling.
NarraSpace is a multimodal framework that links words and speech times to specific picture elements in picture‑description dementia classification tasks. It retrieves utterances for predefined scene events, summarizes coverage and temporal organization, and uses a frozen language model to contrast event text between Alzheimer’s disease and healthy controls, incorporating transcript surprisal and coverage metrics. On the Alzheimer’s Dementia Recognition through Spontaneous Speech benchmark, a support vector classifier built on these features achieves about 81% accuracy and 91% AUC, while the system preserves source records that map event scores back to utterances, speech intervals, and lexical matches.
PROVISO is a controller that selects which action an LLM agent should commit after the agent proposes an action and before execution. It encodes trusted and external observations, the proposed action, and an alternative into provenance-typed memory, uses role‑specific queries to relate them, and commits the action with the highest calibrated value learned from outcomes. In four agent security tasks, PROVISO outperforms all baselines in both security and utility, improving F1 by 13.84 points on SkillsBench and 7.07 points on ToolSafe, and achieving 88–99 F1 on three additional skill detection benchmarks.
arXiv:2610.28036v1 Announce Type: new Abstract: High-quality training data are a major bottleneck in machine learning, motivating increasing use of artificially generated data. We study when a binary...
arXiv:2610.28310v1 Announce Type: new Abstract: Recommending bacterial cultivation conditions from sequence data is a challenging structured problem characterized by missing standardized benchmarks a...
arXiv:2610.27444v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) attaches small low-rank matrices to a frozen backbone, and public repositories host many LoRAs per backbone, each for a di...
arXiv:2610.27621v1 Announce Type: cross Abstract: Deep learning (DL) models are increasingly being deployed into radiation-challenging environments in spacecraft, particle accelerators, and, soon, sp...
arXiv:2610.27870v1 Announce Type: cross Abstract: Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains dif...
arXiv:2610.28294v1 Announce Type: cross Abstract: Test-time scaling allocates additional inference compute to refining existing solutions or generating new ones. This raises a fundamental question: S...
arXiv:2505.23442v2 Announce Type: replace Abstract: Knowledge graphs (KGs) provide structured representations of entities and relations, and underpin data management and Web applications such as sear...
arXiv:2512.09365v2 Announce Type: replace Abstract: Predicting molecule-protein interactions (MPIs) is a fundamental task in computational biology, with crucial applications in drug discovery and mol...
arXiv:2603.03022v2 Announce Type: replace Abstract: In recent years, multi-view multi-label learning (MVML) has attracted extensive attention due to its close alignment to real-world scenarios. Infor...
arXiv:2605.12292v2 Announce Type: replace Abstract: Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contai...
arXiv:2605.15235v2 Announce Type: replace Abstract: Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two...
arXiv:2610.24585v2 Announce Type: replace Abstract: Delirium affects a large fraction of intensive care unit (ICU) patients and foreshadows longer stays, lasting cognitive decline, and higher mortali...
arXiv:2610.26770v2 Announce Type: replace Abstract: Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI...
arXiv:2610.26380v2 Announce Type: replace-cross Abstract: This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLM...