arXiv:2603.11331v2 Announce Type: replace Abstract: Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that strong adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed without injection to exponential…
arXiv:2604.15409v1 Announce Type: new Abstract: KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation. This assumption fails under standard FP16 precision: cache-ON and cache-OFF execution paths employ different floating-point accumulation…
arXiv:2507.18756v2 Announce Type: replace Abstract: Multi-Armed Bandit (MAB) algorithms are widely used in recommender systems that require continuous, incremental learning. A core aspect of MABs is the exploration-exploitation trade-off: choosing between exploiting items likely to be enjoyed and exploring new…
arXiv:2604.15411v1 Announce Type: new Abstract: The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the…
arXiv:2512.05722v2 Announce Type: replace Abstract: Chemical reaction mechanisms are the foundation of how chemists evaluate reactivity and feasibility, yet current Computer-Assisted Synthesis Planning (CASP) systems operate without this mechanistic reasoning. We introduce a computational framework that teaches language models to…
arXiv:2604.16138v1 Announce Type: cross Abstract: We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels of valence (negative, neutral, positive) on German fairy tales text…
arXiv:2604.15414v1 Announce Type: new Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is…
arXiv:2604.15488v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing methods often fail to be…
arXiv:2502.19312v2 Announce Type: replace Abstract: Effective personalization of LLMs is critical for a broad range of user-interfacing applications such as virtual assistants and content curation. Inspired by the strong in-context capabilities of LLMs, we propose few-shot preference optimization (FSPO), an…
arXiv:2604.15494v1 Announce Type: new Abstract: Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical domains such as healthcare.…
