Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We develop a new class of black-box attack, RAG-Pull, that inserts hidden UTF characters into queries or external code repositories, redirecting retrieval toward malicious code, thereby breaking the models' safety alignment. We observe that query and code perturbations alone can shift retrieval toward attacker-controlled snippets, while combined query-and-target perturbations achieve near-perfect success. Once retrieved, these snippets introduce exploitable vulnerabilities such as remote code execution and SQL injection. RAG-Pull's minimal perturbations can alter the model's safety alignment and increase preference towards unsafe code, therefore opening up a new class of attacks on LLMs.

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a structured reasoning process. First, to bridge the preference inference gap, we introduce the DeepPref benchmark. This dataset, comprising 3000 preference-query pairs across 20 topics, is curated by simulating a multi-faceted cognitive council that produces critique-annotated reasoning chains to deconstruct query semantics and reveal latent risks. Second, to instill defensive reasoning, we introduce the Personalized Generative Process Reward Model (Pers-GenPRM), which frames reward modeling as a personalized reasoning task. It generates a critique chain to evaluate a response's alignment with user preferences before outputting a final score based on this rationale. Ultimately, this interpretable, structured reward signal guides policy model through Critique-Driven Policy Alignment, a process-level online reinforcement learning algorithm integrating both numerical and natural language feedback. Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning. Large Language Models (LLMs) are rapidly evolving from simple instruction-followers to potential collaborative partners, a transition that hinges on effective personalization (V aswani et al., 2023; Brown et al., 2020).

Deciphering the function of unseen protein sequences is a fundamental challenge with broad scientific impact, yet most existing methods depend on task-specific adapters or large-scale supervised fine-tuning. We introduce the "Protein-as-Second-Language" framework, which reformulates amino-acid sequences as sentences in a novel symbolic language that large language models can interpret through contextual exemplars. Our approach adaptively constructs sequence-question-answer triples that reveal functional cues in a zero-shot setting, without any further training. To support this process, we curate a bilingual corpus of 79,926 protein-QA instances spanning attribute prediction, descriptive understanding, and extended reasoning. Empirically, our method delivers consistent gains across diverse open-source LLMs and GPT-4, achieving up to 17.2% ROUGE-L improvement (average +7%) and even surpassing fine-tuned protein-specific language models. These results highlight that generic LLMs, when guided with protein-as-language cues, can outperform domain-specialized models, offering a scalable pathway for protein understanding in foundation models.

Deep learning is expected to aid pathologists by automating tasks such as tumour segmentation. We aimed to develop one universal tumour segmentation model for histopathological images and examine its performance in different cancer types. The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma. Performance was validated in pre-planned analyses on external cohorts with over 3 000 patients across six cancer types. Exploratory analyses included over 1 500 additional patients from The Cancer Genome Atlas. Average Dice coefficient was over 80% in all validation cohorts with en bloc resection specimens and in The Cancer Genome Atlas cohorts. No loss of performance was observed when comparing the universal model with models specialised on single cancer types. In conclusion, extensive and rigorous evaluations demonstrate that generic tumour segmentation by a single model is possible across cancer types, patient populations, sample preparations, and slide scanners.

Large output spaces, also referred to as Extreme multilabel classification (XMC), is a setting that arises, e.g., in large-scale tagging and product-to-product recommendation, and is characterized by the number of labels ranging from hundreds of thousands to millions. This means that the linear classification head, usually only a tiny fraction of the overall model, turns into the main driver for compute and memory demand. Current state-of-the-art XMC methods predominantly rely on FP16-FP32 mixed-precision training, which we show can be unstable, and inefficient in terms of memory usage and computational overhead. Meanwhile, existing low-precision methods typically retain higher precision for the classification layer. In this work, we propose ELMO, a pure low-precision training framework for XMC models using BFloat16 and Float8 data types. By leveraging Kahan summation and stochastic rounding, we demonstrate that XMC models can be effectively trained entirely in Float8, without relying on single-precision master weights or tensor scaling. Low-precision training, combined with our proposed memory optimizations -- gradient fusion and chunking -- enables significant reductions in GPU memory usage. For example, we train a 3-million-label XMC model with only 6.6 GiB of GPU memory, compared to the 39.7 GiB required by the optimized SOTA method, Renee without compromising accuracy.

Hate speech poses a serious threat to social cohesion and individual well-being, particularly on social media, where it spreads rapidly. While research on hate speech detection has progressed, it remains largely focused on English, resulting in limited resources and benchmarks for low-resource languages. Moreover, many of these languages have multiple linguistic varieties, a factor often overlooked in current approaches. At the same time, large language models require substantial amounts of data to perform reliably, a requirement that low-resource languages often cannot meet. In this work, we address these gaps by compiling a meta-collection of hate speech datasets for European Spanish, standardised with unified labels and metadata. This collection is based on a systematic analysis and integration of existing resources, aiming to bridge the data gap and support more consistent and scalable hate speech detection. We extended this collection by translating it into European Portuguese and into a Galician standard that is more convergent with Spanish and another Galician variant that is more convergent with Portuguese, creating aligned multilingual corpora. Using these resources, we establish new benchmarks for hate speech detection in Iberian languages. We evaluate state-of-the-art large language models in zero-shot, few-shot, and fine-tuning settings, providing baseline results for future research. Moreover, we perform a cross-lingual analysis with our target languages. Our findings underscore the importance of multilingual and variety-aware approaches in hate speech detection and offer a foundation for improved benchmarking in underrepresented European languages.

Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the learning paradigm itself in determining emergent dynamics remains largely unexplored. Here we demonstrate that reinforcement learning (RL) and supervised learning (SL) drive recurrent neural networks (RNNs) toward fundamentally different computational solutions when trained on identical decision-making tasks. Through systematic dynamical systems analysis, we reveal that RL spontaneously discovers hybrid attractor architectures, combining stable fixed-point attractors for decision maintenance with quasi-periodic attractors for flexible evidence integration. This contrasts sharply with SL, which converges almost exclusively to simpler fixed-point-only solutions. We further show that RL sculpts functionally balanced neural populations through a powerful form of implicit regularization -- a structural signature that enhances robustness and is conspicuously absent in the more heterogeneous solutions found by SL-trained networks. The prevalence of these complex dynamics in RL is controllably modulated by weight initialization and correlates strongly with performance gains, particularly as task complexity increases. Our results establish the learning algorithm as a primary determinant of emergent computation, revealing how reward-based optimization autonomously discovers sophisticated dynamical mechanisms that are less accessible to direct gradient-based optimization. These findings provide both mechanistic insights into neural computation and actionable principles for designing adaptive AI systems.

Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critical vulnerabilities, posing significant risks when deployed in security-sensitive or mission-critical systems. This paper introduces TypePilot, an agentic AI framework designed to enhance the security and robustness of LLM-generated code by leveraging strongly typed and verifiable languages, using Scala as a representative example. We evaluate the effectiveness of our approach in two settings: formal verification with the Stainless framework and general-purpose secure code generation. Our experiments with leading open-source LLMs reveal that while direct code generation often fails to enforce safety constraints, just as naive prompting for more secure code, our type-focused agentic pipeline substantially mitigates input validation and injection vulnerabilities. The results demonstrate the potential of structured, type-guided LLM workflows to improve the SotA of the trustworthiness of automated code generation in high-assurance domains.

Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from unseen environments or compounding action errors can still cause unpredictable and unsafe behavior, leading to task failure. Early failure prediction during runtime is therefore essential for deploying robots in human-centered and safety-critical environments. We propose FIPER, a general framework for Failure Prediction at Runtime for generative IL policies that does not require failure data. FIPER identifies two key indicators of impending failure: (i) out-of-distribution (OOD) observations detected via random network distillation in the policy's embedding space, and (ii) high uncertainty in generated actions measured by a novel action-chunk entropy score. Both failure prediction scores are calibrated using a small set of successful rollouts via conformal prediction. A failure alarm is triggered when both indicators, aggregated over short time windows, exceed their thresholds. We evaluate FIPER across five simulation and real-world environments involving diverse failure modes. Our results demonstrate that FIPER better distinguishes actual failures from benign OOD situations and predicts failures more accurately and earlier than existing methods. We thus consider this work an important step towards more interpretable and safer generative robot policies. Code, data and videos are available at https://tum-lsy.github.io/fiper_website.

Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although prior work has investigated biases in text datasets and related detection methods, these studies remain narrow in scope. They typically focus on a single content type (e.g., hate speech), cover limited demographic axes, overlook biases affecting multiple demographics simultaneously, and analyze limited techniques. Consequently, practitioners lack a holistic understanding of the strengths and limitations of recent large language models (LLMs) for automated bias detection. In this study, we present a comprehensive evaluation framework aimed at English texts to assess the ability of LLMs in detecting demographic-targeted social biases. To align with regulatory requirements, we frame bias detection as a multi-label task using a demographic-focused taxonomy. We then conduct a systematic evaluation with models across scales and techniques, including prompting, in-context learning, and fine-tuning. Using twelve datasets spanning diverse content types and demographics, our study demonstrates the promise of fine-tuned smaller models for scalable detection. However, our analyses also expose persistent gaps across demographic axes and multi-demographic targeted biases, underscoring the need for more effective and scalable auditing frameworks.