Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific contextualization. However, it also introduces new attack surfaces such as corpus poisoning at the same time. Most of the existing defense methods rely on the internal knowledge of the model, which conflicts with the design concept of RAG. To bridge the gap, EcoSafeRAG uses sentence-level processing and bait-guided context diversity detection to identify malicious content by analyzing the context diversity of candidate documents without relying on LLM internal knowledge. Experiments show EcoSafeRAG delivers state-of-the-art security with plug-and-play deployment, simultaneously improving clean-scenario RAG performance while maintaining practical operational costs (relatively 1.2$\times$ latency, 48\%-80\% token reduction versus Vanilla RAG).

Large Language Models (LLMs) are transformative not only for daily activities but also for engineering tasks. However, current evaluations of LLMs in engineering exhibit two critical shortcomings: (i) the reliance on simplified use cases, often adapted from examination materials where correctness is easily verifiable, and (ii) the use of ad hoc scenarios that insufficiently capture critical engineering competencies. Consequently, the assessment of LLMs on complex, real-world engineering problems remains largely unexplored. This paper addresses this gap by introducing a curated database comprising over 100 questions derived from authentic, production-oriented engineering scenarios, systematically designed to cover core competencies such as product design, prognosis, and diagnosis. Using this dataset, we evaluate four state-of-the-art LLMs, including both cloud-based and locally hosted instances, to systematically investigate their performance on complex engineering tasks. Our results show that LLMs demonstrate strengths in basic temporal and structural reasoning but struggle significantly with abstract reasoning, formal modeling, and context-sensitive engineering logic.

The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training data. In this study, we propose a speaker privacy-preserving representation learning method through the Universal Speech Codec (USC), a computationally efficient encoder-decoder model that disentangles speech into: ( i) privacy-preserving semantically rich representations, capturing content and speech paralinguistics, and ( ii) residual acoustic and speaker representations that enables high-fidelity reconstruction. Extensive evaluations presented show that USC's semantic representation preserves content, prosody, and sentiment, while removing potentially identifiable speaker attributes. Combining both representations, USC achieves state-of-the-art speech reconstruction. Additionally, we introduce an evaluation methodology for measuring privacy-preserving properties, aligning with perceptual tests. We compare USC against other codecs in the literature and demonstrate its effectiveness on privacy-preserving representation learning, illustrating the trade-offs of speaker anonymization, paralinguistics retention and content preservation in the learned semantic representations. Audio samples are shared in https://www.amazon.science/usc-samples . Latest foundational Generative AI (GenAI) revolve around multimodality (Achiam et al., 2023; Anil et al., 2023; Dubey et al., 2024). The extraordinary capabilities of Large Language Models (LLMs) as multimodal learning machines have ushered in a new paradigm for what GenAI can offer to our world (Team, 2025). These foundational LLMs are data-hungry, requiring massive amounts of multimodal training data. Speech and audio are essential modalities for many applications, and mul-timodal models require exposure to them during their training process (Borsos et al., 2023). Speech is a form of individual information (Nautsch et al., 2019), and the development of new foundational speech-aware models demands access to massive amounts of speech data to fully unlock their potential. The research community has collected and curated public data over the past decades, which has been used for specialized speech models (Łajszczak et al., 2024). However, in the realm of Responsible AI, every individual and organization must make proper use of individuals' data when training foundational models, regardless of its public availability. Hence, privacy-preserving methods must be developed to advance foundational speech research while safeguarding individual privacy. Foundational LLMs trained on language modeling tasks model the likelihood of generating coherent text sequences from a distribution of discrete tokens (Touvron et al., 2023). This allows them to produce expressive and varied responses during generation.

Large language models (LLMs) achieve impressive abilities in numerous domains, but exhibit inconsistent performance in response to minor input changes. Rather than view this as a drawback, in this paper we introduce a novel method for leveraging models' inconsistency to boost Pass@k performance. Specifically, we present a "Variator" agent that generates k variants of a given task and submits one candidate solution for each one. Our variant generation approach is applicable to a wide range of domains as it is task agnostic and compatible with free-form inputs. We demonstrate the efficacy of our agent theoretically using a probabilistic model of the inconsistency effect, and show empirically that it outperforms the baseline on the APPS dataset. Furthermore, we establish that inconsistency persists even in frontier reasoning models across coding and cybersecurity domains, suggesting our method is likely to remain relevant for future model generations.

Doctors and patients alike increasingly use Large Language Models (LLMs) to diagnose clinical cases. However, unlike domains such as math or coding, where correctness can be objectively defined by the final answer, medical diagnosis requires both the outcome and the reasoning process to be accurate. Currently, widely used medical benchmarks like MedQA and MMLU assess only accuracy in the final answer, overlooking the quality and faithfulness of the clinical reasoning process. To address this limitation, we introduce MedCaseReasoning, the first open-access dataset for evaluating LLMs on their ability to align with clinician-authored diagnostic reasoning. The dataset includes 14,489 diagnostic question-and-answer cases, each paired with detailed reasoning statements derived from open-access medical case reports. We evaluate state-of-the-art reasoning LLMs on MedCaseReasoning and find significant shortcomings in their diagnoses and reasoning: for instance, the top-performing open-source model, DeepSeek-R1, achieves only 48% 10-shot diagnostic accuracy and mentions only 64% of the clinician reasoning statements (recall). However, we demonstrate that fine-tuning LLMs on the reasoning traces derived from MedCaseReasoning significantly improves diagnostic accuracy and clinical reasoning recall by an average relative gain of 29% and 41%, respectively. The open-source dataset, code, and models are available at https://github.com/kevinwu23/Stanford-MedCaseReasoning.

Roaming in Wireless LAN (Wi-Fi) is a critical yet challenging task for maintaining seamless connectivity in dynamic mobile environments. Conventional threshold-based or heuristic schemes often fail, leading to either sticky or excessive handovers. We introduce the first cross-layer use of an on-device large language model (LLM): high-level reasoning in the application layer that issues real-time actions executed in the PHY/MAC stack. The LLM addresses two tasks: (i) context-aware AP selection, where structured prompts fuse environmental cues (e.g., location, time) to choose the best BSSID; and (ii) dynamic threshold adjustment, where the model adaptively decides when to roam. To satisfy the tight latency and resource budgets of edge hardware, we apply a suite of optimizations-chain-of-thought prompting, parameter-efficient fine-tuning, and quantization. Experiments on indoor and outdoor datasets show that our approach surpasses legacy heuristics and DRL baselines, achieving a strong balance between roaming stability and signal quality. These findings underscore the promise of application-layer LLM reasoning for lower-layer wireless control in future edge systems.

Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggregated over a diverse set of users, resulting in fine-tuned models that are aligned to the ``average-user'' preference. Nevertheless, current models are used by individual users in very specific contexts and situations, emphasizing the need for user-dependent preference control. In this work we address the problem of personalizing LLM outputs to their users. We aim to generate customized responses tailored to specific individuals instead of generic outputs that emulate the collective voices of diverse populations. We propose HyPerAlign, an interpretable and sample-efficient hypothesis-driven personalization approach for LLM models. Given few-shot examples written by a particular user, we first infer hypotheses about their communication strategies, personality, and writing style, then prompt LLM models with these hypotheses and user-specific attributes to generate customized outputs. We conduct experiments on two different personalization tasks, namely authorship attribution and deliberative alignment, with datasets from diverse domains (news articles, blog posts, emails, jailbreaking benchmarks). Results demonstrate the superiority of hypothesis-driven LLM personalization compared to preference-based fine-tuning methods. For authorship attribution, HyPerAlign generations have consistently high win-rates (commonly $> 90\%$) against state-of-the-art preference fine-tuning approaches across diverse user profiles and LLM models. For deliberative alignment, the helpfulness of LLM models is improved by up to $70\%$ on average. Overall, HyPerAlign represents an interpretable and sample-efficient strategy for the personalization of LLM models to individual users.

Abstract--Despite recent advances in applying large language models (LLMs) and machine learning (ML) techniques to open radio access network (O-RAN), critical challenges remain, such as insufficient cooperation between radio access network (R AN) intelligent controllers (RICs), high computational deman ds hindering real-time decisions, and the lack of domain-specific fine-tuning. Therefore, this article introduces the LLM-empowe red hierarchical RIC (LLM-hRIC) framework to improve the collaboration between RICs in O-RAN. The RL-empowered near-RT RIC acts as an implementer, combining this guidance with local real-time data to make near-RT decisions. We evaluate the feasibility and performance of the LLM-hRIC framework in an integrated access and backhaul (IAB) network setting, and finally, disc uss the open challenges of the LLM-hRIC framework for O-RAN. The open radio access network (O-RAN) has recently gained significant attention for its ability to prompt inter op-erability and flexibility.

Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and predominantly feature videos rooted in Western cultural contexts. In this paper, we present VideoVista-CulturalLingo, the first video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension. Our work differs from existing benchmarks in the following ways: 1) Cultural diversity, incorporating cultures from China, North America, and Europe; 2) Multi-linguistics, with questions presented in Chinese and English-two of the most widely spoken languages; and 3) Broad domain, featuring videos sourced from hundreds of human-created domains. VideoVista-CulturalLingo contains 1,389 videos and 3,134 QA pairs, and we have evaluated 24 recent open-source or proprietary video large models. From the experiment results, we observe that: 1) Existing models perform worse on Chinese-centric questions than Western-centric ones, particularly those related to Chinese history; 2) Current open-source models still exhibit limitations in temporal understanding, especially in the Event Localization task, achieving a maximum score of only 45.2%; 3) Mainstream models demonstrate strong performance in general scientific questions, while open-source models demonstrate weak performance in mathematics.

App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle with long-horizon planning, failing to find the optimal actions for complex tasks with longer steps. To address this, world models are used to predict the next GUI observation based on user actions, enabling more effective agent planning. However, existing world models primarily focus on generating only textual descriptions, lacking essential visual details. To fill this gap, we propose ViMo, the first visual world model designed to generate future App observations as images. For the challenge of generating text in image patches, where even minor pixel errors can distort readability, we decompose GUI generation into graphic and text content generation. We propose a novel data representation, the Symbolic Text Representation~(STR) to overlay text content with symbolic placeholders while preserving graphics. With this design, ViMo employs a STR Predictor to predict future GUIs' graphics and a GUI-text Predictor for generating the corresponding text. Moreover, we deploy ViMo to enhance agent-focused tasks by predicting the outcome of different action options. Experiments show ViMo's ability to generate visually plausible and functionally effective GUIs that enable App agents to make more informed decisions.