arXiv:2602.02280v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and lacks systematic criteria to evaluate test suite quality and adequacy. While coverage criteria have…
arXiv:2605.10983v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse…
arXiv:2605.11373v1 Announce Type: cross Abstract: The trustworthiness of AI decision-making systems is increasingly important. A key feature of such systems is the ability to provide recommendations for how an individual may reverse a negative decision, a problem known as algorithmic…
arXiv:2605.10985v1 Announce Type: new Abstract: Protein language models such as ESM-2 learn rich residue representations that achieve strong performance on protein function prediction, but their features remain difficult to interpret as structural $&$ evolutionary signals are encoded in dense latent…
arXiv:2605.11784v1 Announce Type: cross Abstract: Full-vehicle crash simulations are computationally expensive, limiting their use in iterative design exploration. This work investigates learned hybrid surrogate models (MeshTransolver, MeshGeoTransolver, and MeshGeoFLARE) for predicting time-resolved structural deformation fields in an industrial lateral pole-impact…
arXiv:2605.10987v1 Announce Type: new Abstract: Modern machine learning deployments increasingly compose specialized models into dynamic inference pipelines, where upstream components produce intermediate predictions that determine the workload and inputs of downstream components. The cost of processing an input is therefore…
arXiv:2605.12281v1 Announce Type: cross Abstract: What makes a word difficult to learn, and how does the difficulty depend on the learner’s native language? We computationally model vocabulary difficulty for English learners whose first language is Spanish, German, or Chinese with…
arXiv:2605.10988v1 Announce Type: new Abstract: Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instance-level annotations are prohibitively expensive, posing great difficulties…
arXiv:2503.16072v4 Announce Type: replace Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as an intrinsic property of isolated text. This position paper argues that toxicity…
arXiv:2605.10989v1 Announce Type: new Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted…
