Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2603. 18334v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly assist secure software development, their ability to meet the rigorous demands of Rust program verification remains unclear.
arXiv:2604. 07084v2 Announce Type: replace-cross Abstract: Open-loop end-to-end neural motion planners have recently been proposed to improve motion planning for robotic manipulators.
arXiv:2605. 08974v2 Announce Type: replace-cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes.
arXiv:2608. 11980v2 Announce Type: replace-cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence.
arXiv:2608. 14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior.
arXiv:2608. 15239v1 Announce Type: new Abstract: Power-law anisotropy in internal representations has been observed across a wide range of biological and artificial neural systems, from state-of-the-art language models to the mouse cerebral cortex.
arXiv:2608. 15429v1 Announce Type: new Abstract: Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surface behavioral signals spanning distinct behavioral domains.
arXiv:2608. 15645v1 Announce Type: new Abstract: Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference.
arXiv:2608. 15725v1 Announce Type: new Abstract: Predictive models in clinical and regulated settings must be accurate and fully auditable.
arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.
arXiv:2608. 16005v1 Announce Type: new Abstract: This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction.
arXiv:2608. 16334v1 Announce Type: new Abstract: Keystroke dynamics (typing patterns) can be used as a behavioural biometric modality for user authentication, with applications such as fraud prevention.
arXiv:2608. 15242v1 Announce Type: new Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory.
arXiv:2608. 15639v1 Announce Type: cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients.
Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematical reasoning capabilities of large language models (LLMs). However, their application to signal processing problems remains relatively under-explored.
Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols predominantly rely on static benchmarks with fixed historical test windows.
Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks typically use mean squared error (MSE) as the evaluation metric.
Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in hist...
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images.