Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2512. 19011v3 Announce Type: replace-cross Abstract: Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned transformers and LLM-as-a-judge pipelines.
arXiv:2407. 05370v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) algorithms often struggle to perform well when trained on imbalanced data.
arXiv:2510. 04212v4 Announce Type: replace-cross Abstract: The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models.
arXiv:2606. 15331v1 Announce Type: cross Abstract: Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective.
arXiv:2508. 00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms.
OpenAI introduces Deployment Simulation, a method to predict AI model behavior before deployment using real conversation data to improve safety and evaluation accuracy.
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored. Infrared images provide distinctive cues, including thermal intensity structures, object boundaries, and illumination-invariant scene features, which can enrich visual-language learning beyond conventional RGB observations.
Where are your agents right now?
arXiv:2606. 14060v1 Announce Type: new Abstract: Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors.
arXiv:2602. 02355v2 Announce Type: replace-cross Abstract: Hierarchical federated learning (HFL) is well suited for large-scale wireless and Internet of Things systems, where devices communicate with nearby edge servers before reaching the cloud.
arXiv:2606. 14245v1 Announce Type: new Abstract: Drug-target interaction (DTI) and affinity (DTA) predictors increasingly achieve strong benchmark scores, yet their internal use of sequence, fingerprint, and graph features often remains opaque.
arXiv:2606. 14518v1 Announce Type: new Abstract: The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU.
arXiv:2604. 18419v5 Announce Type: replace Abstract: LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses.
arXiv:2606. 14386v1 Announce Type: cross Abstract: Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large.
arXiv:2606. 13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository.
arXiv:2509. 24725v4 Announce Type: replace-cross Abstract: Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management.
arXiv:2606. 14159v1 Announce Type: new Abstract: Protein-ligand binding affinity (PLA) prediction is critical in drug discovery.
arXiv:2508. 18166v5 Announce Type: replace-cross Abstract: Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization.
arXiv:2504. 20908v3 Announce Type: replace Abstract: Current subgroup identification methods typically follow a two-step approach: first estimate conditional average treatment effects and then apply thresholding or rule-based procedures to define subgroups.
arXiv:2606. 13737v1 Announce Type: cross Abstract: Stream guardrails enable token-level safety detection before full responses are generated.
