Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 02491v2 Announce Type: replace Abstract: Language models have taken on the role of a very new type of technology, by virtue of their "human-ness" and rapid integration into users' daily lives.
arXiv:2608. 04735v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models.
arXiv:2512. 20661v2 Announce Type: replace Abstract: Transformer-based pre-trained language models (PLMs) excel in text classification but suffer from attention dilution and attention sink effects, forcing models to over-focus on task-irrelevant tokens.
arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.
arXiv:2604. 12503v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios.
arXiv:2608. 04382v1 Announce Type: new Abstract: Gradient descent has been of particular interest in modern machine learning beyond sole focus on optimization.
arXiv:2608. 04027v1 Announce Type: new Abstract: This work investigates the feasibility of augmenting traditional R-Matrix codes with a robust machine learning framework for automatically detecting neutron resonances in transmission spectra.
arXiv:2508. 04811v2 Announce Type: replace Abstract: Order dispatch systems play a vital role in ride-hailing services, which directly influence operator revenue, driver profit, and passenger experience.
arXiv:2608. 04613v1 Announce Type: new Abstract: Anomaly detection is a safety-critical machine learning problem with applications ranging from fraud detection to network intrusion prevention and industrial monitoring.
arXiv:2608. 04714v1 Announce Type: cross Abstract: Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed.
arXiv:2608. 05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer?
arXiv:2608. 04864v1 Announce Type: cross Abstract: We introduce the neural echo as a tool for understanding the behavior of neural networks.
arXiv:2608. 04479v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has recently achieved remarkable progress in synthesizing realistic audio from natural language descriptions.
arXiv:2510. 15395v2 Announce Type: replace Abstract: An AI agent will learn a desired goal more effectively if it does not resist the training process, but many partially learned goals incentivize an AI to avoid further goal updates.
arXiv:2503. 14833v2 Announce Type: replace-cross Abstract: One of the bottlenecks in robotic intelligence is the instability of neural network models.
arXiv:2510. 21084v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong potential for clinical decision support through their advanced language understanding and reasoning capabilities.
arXiv:2511. 12265v2 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) remain vulnerable to diverse adversarial perturbations, motivating multi-attack adversarial training (AT) for improved robustness.
arXiv:2512. 02567v2 Announce Type: replace-cross Abstract: The advent of strong generative AI has a considerable impact on various software engineering tasks such as code repair, test generation, or language translation.
arXiv:2608. 04173v1 Announce Type: new Abstract: Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors.
Dialectal variation remains a major challenge for multilingual language models. Perturbation-based continued pre-training (CPT) has emerged as a promising approach to improving robustness, yet existing work largely evaluates individual perturbation strategies in isolation and provides limited insight into why they work.