arXiv:2512.00349v1 Announce Type: new Abstract: Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidious and destructive safety risks, namely deception. Unlike…
arXiv:2512.01316v1 Announce Type: cross Abstract: Minimum Bayes risk (MBR) decoding generates high-quality translations by maximizing the expected utility of output candidates, but it evaluates all pairwise scores over the candidate set; hence, it takes quadratic time with respect to the…
arXiv:2512.00406v1 Announce Type: new Abstract: Building design directly affects human well-being and carbon emissions, yet generating spatial-functional and energy-compliant floorplans remains manual, costly, and non-scalable. Existing methods produce visually plausible layouts but frequently violate key constraints, yielding invalid results due…
arXiv:2512.01707v1 Announce Type: cross Abstract: Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realistic applications like AR glasses. While prior streaming benchmarks evaluate temporal reasoning, none measure whether MLLMs…
arXiv:2512.00479v1 Announce Type: new Abstract: Data collection often reflects human decisions. In healthcare, for instance, a referral for a diagnostic test is influenced by the patient’s health, their preferences, available resources, and the practitioner’s recommendations. Despite the extensive literature on…
arXiv:2502.07663v3 Announce Type: replace Abstract: AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users’ cognitive biases and emotional vulnerabilities to…
arXiv:2512.00601v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as Grouped Relative Policy Optimization (GRPO), mainly reward…
arXiv:2305.14299v2 Announce Type: replace-cross Abstract: Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost. Annotating and gathering utterance relationships in conversations are difficult,…
arXiv:2512.00670v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete. We propose EDIT (Early Diffusion Inference Termination), an inference-time criterion that adaptively stops denoising once sufficient…
arXiv:2504.13908v3 Announce Type: replace-cross Abstract: Standardized surveys scale efficiently but sacrifice depth, while conversational interviews improve response quality at the cost of scalability and consistency. This study bridges the gap between these methods by introducing a framework for AI-assisted conversational…
