arXiv:2604.21098v1 Announce Type: new Abstract: Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models’ propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes to environmental factors…
arXiv:2604.21098v1 Announce Type: new Abstract: Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models’ propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes to environmental factors…
arXiv:2510.18731v2 Announce Type: replace-cross Abstract: Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information is revealed progressively in multi-turn settings. Motivated by the current progress on Reinforcement Learning…
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often replicate societal biases, particularly in how they depict demographic groups across professions. Prompts such…
arXiv:2604.17656v2 Announce Type: replace-cross Abstract: Video-to-music (V2M) is the fundamental task of creating background music for an input video. Recent V2M models achieve audiovisual alignment by typically relying on visual conditioning alone and provide limited semantic and stylistic controllability to…
arXiv:2604.21911v1 Announce Type: cross Abstract: Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in LVLMs to factors…
arXiv:2604.21911v1 Announce Type: cross Abstract: Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in LVLMs to factors…
arXiv:2604.21911v1 Announce Type: cross Abstract: Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in LVLMs to factors…
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often replicate societal biases, particularly in how they depict demographic groups across professions. Prompts such…
arXiv:2601.09253v2 Announce Type: replace-cross Abstract: While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we propose…
