Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome.
arXiv:2608. 12593v1 Announce Type: new Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process.
arXiv:2608. 12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state.
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.
arXiv:2608. 13048v1 Announce Type: new Abstract: In this work, we introduce DMDIntel which uses dynamic mode decomposition (DMD) to make the predictions made by LLMs in a classification task interpretable.
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
arXiv:2608. 13072v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding models often generalize poorly across datasets and subjects due to domain shifts in acquisition protocols and individual neurophysiology.
arXiv:2608. 13108v1 Announce Type: new Abstract: Multi-source evidence fusion under Dempster-Shafer theory faces two persistent challenges: existing conflict measures assess inter-evidence inconsistency and intra-evidence uncertainty independently, yielding incomplete evaluations, and current fusion methods evaluate evidence sources exclusively through instantaneous comparisns without exploiting their long-term reliability across diverse decision contexts.
arXiv:2608. 12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes.
arXiv:2608. 12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group.
arXiv:2608. 12719v1 Announce Type: cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to predict model performance, creating an information-risk mismatch and a scalability bottleneck as the model pool grows.
arXiv:2608. 12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations.
arXiv:2608. 13296v1 Announce Type: cross Abstract: Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s.
arXiv:2608. 13368v1 Announce Type: cross Abstract: This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments.
arXiv:2608. 13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.
arXiv:2608. 12592v1 Announce Type: new Abstract: Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patient.
arXiv:2505. 12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets.
arXiv:2506. 17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings.
arXiv:2603. 14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones.
arXiv:2608. 13096v1 Announce Type: new Abstract: Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially.