Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2603.27101v2 Announce Type: replace-cross Abstract: Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based f...
arXiv:2610.07563v1 Announce Type: new Abstract: Large language models (LLMs) have the potential to meet a key goal in economics: a quantitative model of household decision making, across a variety of...
arXiv:2610.07774v1 Announce Type: new Abstract: Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As m...
arXiv:2610.07847v1 Announce Type: new Abstract: As LLMs increasingly assist in moral reasoning, omission bias, the tendency to prefer inaction even when equivalent framings reverse substantive outcom...
arXiv:2610.08026v1 Announce Type: new Abstract: In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked w...
arXiv:2610.08303v1 Announce Type: new Abstract: Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures...
arXiv:2507.02115v3 Announce Type: cross Abstract: Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L...
The paper introduces CASTLE, a framework for fully decentralized multi‑agent reinforcement learning that uses two offline‑trained world models to provide in‑context guidance to independent agents. A Local Dynamics World Model captures each agent’s trajectory dynamics, while a Semantic‑Social World Model predicts short‑horizon task and social outcomes for candidate actions based on counterfactual simulator rollouts. During online learning, these frozen models supply prediction logits to an independent PPO policy, enabling agents to compare potential actions prospectively rather than relying solely on scalar rewards. CASTLE outperforms existing baselines on several multi‑particle benchmark tasks, achieving the highest mean final scores across 30 seeds.
The study evaluates probabilistic machine‑learning models for forecasting German grid redispatch volumes under data‑delay constraints. Using 48,242 records from 2021‑2024, boosted‑tree LightGBM with rolling calibration achieved the best performance (nWIS 0.7767), outperforming autoregressive and seasonal baselines. Neural models with zero‑censored outputs performed similarly but revealed undercoverage during high‑volume events.
Nord-Parl-TTS is an open text‑to‑speech dataset for Finnish and Swedish created from recordings of Nordic parliamentary proceedings. It contains 900 hours of Finnish and 5 090 hours of Swedish speech, processed with an adapted Emilia pipeline and accompanied by unified evaluation sets for model development and benchmarking. The dataset aims to reduce the resource gap in TTS between high‑ and lower‑resourced languages.
The study introduces MedQADE, a German open‑response clinical benchmark with 3,800 question‑answer pairs and physician reference annotations. It evaluates large language models (LLMs) as judges, finding that while some LLMs (e.g., Gemini 3 Flash) achieve physician‑level agreement on correctness, they exhibit self‑bias and low abstention rates. Physicians showed moderate agreement on correctness but limited agreement on difficulty, and their abstention increased with perceived difficulty.
arXiv:2610.06973v1 Announce Type: new Abstract: Melt-pool monitoring is central to qualifying metal additive manufacturing (AM), yet no public event-camera benchmark exists for this domain. Event cam...
arXiv:2610.07117v1 Announce Type: new Abstract: Understanding and modeling interactions between autonomous agents is a fundamental challenge in robotics, with broad implications for collaborative sys...
arXiv:2610.07903v1 Announce Type: new Abstract: Adapting vision-language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing...
arXiv:2610.08109v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while prese...
arXiv:2610.08398v1 Announce Type: new Abstract: On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this...
arXiv:2610.08418v1 Announce Type: new Abstract: Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision. We develop C...
arXiv:2610.08539v1 Announce Type: new Abstract: Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradig...
arXiv:2610.08639v1 Announce Type: new Abstract: As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existi...
arXiv:2610.08684v1 Announce Type: new Abstract: Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, an...