Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.
arXiv:2607. 27069v2 Announce Type: cross Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts.
arXiv:2512. 00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation.
arXiv:2601. 11178v3 Announce Type: replace Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues.
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
arXiv:2508. 07044v2 Announce Type: replace-cross Abstract: Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or used to train generative models.
arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.
arXiv:2603. 15684v2 Announce Type: replace-cross Abstract: Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn.
arXiv:2508. 02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets.
arXiv:2602. 16111v2 Announce Type: replace-cross Abstract: Online media platforms track the share of impressions associated with content attributes, or prevalence, to evaluate trade-offs and set guardrails in A/B experiments.
arXiv:2602. 23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts.
arXiv:2603. 07131v4 Announce Type: replace-cross Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis.
arXiv:2607. 26651v1 Announce Type: cross Abstract: With the promising performance of deep neural networks on image-based tasks, different real-world applications such as autonomous driving and motion detection have become increasingly mature and relevant to human lives.
arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.
arXiv:2607. 28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy.
arXiv:2607. 28191v1 Announce Type: cross Abstract: Federated learning enables multiple institutions to train shared models without exchanging raw clinical EEG data, but it does not fully prevent privacy leakage from individual model updates.
arXiv:2607. 27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing.
arXiv:2607. 27290v1 Announce Type: new Abstract: Modern telecommunication, cloud, and microservice systems emit correlated alarm cascades when components fail.
arXiv:2607. 27370v1 Announce Type: new Abstract: Sybil attackers are Blockchain actors that adopt the characteristics of regular users to exploit airdrops or influence governance.
arXiv:2607. 27418v1 Announce Type: new Abstract: Long-term ship trajectory prediction is a fundamental capability for maritime safety and autonomous navigation.