The advanced reasoning capabilities of Large Reasoning Models enable them to thoroughly understand and apply safety policies through deliberate thought processes, thereby improving the models' safety. Beyond safety, these models must also be able to reflect the diverse range of human values across various cultures. This paper presents the Cultural Norm-based Cultural Alignment (CNCA) framework, which enables models to leverage their powerful reasoning ability to align with cultural norms. Specifically, we propose three methods to automatically mine cultural norms from limited survey data and explore ways to effectively utilize these norms for improving cultural alignment. Two alignment paradigms are examined: an in-context alignment method, where cultural norms are explicitly integrated into the user context, and a fine-tuning-based method, which internalizes norms through enhanced Chain-of-Thought training data. Comprehensive experiments demonstrate the effectiveness of these methods, highlighting that models with stronger reasoning capabilities benefit more from cultural norm mining and utilization. Our findings emphasize the potential for reasoning models to better reflect diverse human values through culturally informed alignment strategies.

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks' subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the reliability of replay data, our Quality-Enhanced Pseudo Replay strategy leverages self-consistency and semantic similarity to reduce hallucinations in generated samples.

In modern software development workflows, the open-source software supply chain significantly contributes to efficient and convenient engineering practices. With increasing system complexity, it has become a common practice to use open-source software as third-party dependencies. However, due to the lack of maintenance for underlying dependencies and insufficient community auditing, ensuring the security of source code and the legitimacy of repository maintainers has become a challenge, particularly in the context of high-stealth backdoor attacks such as the XZ-Util incident. To address these problems, we propose a fine-grained project evaluation framework for backdoor risk assessment in open-source software. Our evaluation framework models highly stealthy backdoor attacks from the attacker's perspective and defines targeted metrics for each attack stage. Moreover, to overcome the limitations of static analysis in assessing the reliability of repository maintenance activities, such as irregular com-mitter privilege escalation and insufficient review participation, we employ large language models (LLMs) to perform semantic evaluation of code repositories while avoiding reliance on manually crafted patterns. The effectiveness of our framework is validated on 66 high-priority packages in the Debian ecosystem, and the experimental results reveal that the current open-source software supply chain is exposed to a series of security risks.

Generating thorough natural language explanations for threat detections remains an open problem in cybersecurity research, despite significant advances in automated malware detection systems. In this work, we present AutoMalDesc, an automated static analysis summarization framework that, following initial training on a small set of expert-curated examples, operates independently at scale. This approach leverages an iterative self-paced learning pipeline to progressively enhance output quality through synthetic data generation and validation cycles, eliminating the need for extensive manual data annotation. Evaluation across 3,600 diverse samples in five scripting languages demonstrates statistically significant improvements between iterations, showing consistent gains in both summary quality and classification accuracy. Our comprehensive validation approach combines quantitative metrics based on established malware labels with qualitative assessment from both human experts and LLM-based judges, confirming both technical precision and linguistic coherence of generated summaries. To facilitate reproducibility and advance research in this domain, we publish our complete dataset of more than 100K script samples, including annotated seed (0.9K) and test (3.6K)

Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could lead to significant economic losses for model providers. For copyright protection, existing methods inject watermark embeddings into text embeddings and use them to detect copyright infringement. However, current watermarking methods often resist only a subset of attacks and fail to provide \textit{comprehensive} protection. To this end, we present the region-triggered semantic watermarking framework called RegionMarker, which defines trigger regions within a low-dimensional space and injects watermarks into text embeddings associated with these regions. By utilizing a secret dimensionality reduction matrix to project onto this subspace and randomly selecting trigger regions, RegionMarker makes it difficult for watermark removal attacks to evade detection. Furthermore, by embedding watermarks across the entire trigger region and using the text embedding as the watermark, RegionMarker is resilient to both paraphrasing and dimension-perturbation attacks. Extensive experiments on various datasets show that RegionMarker is effective in resisting different attack methods, thereby protecting the copyright of EaaS.

Task-oriented dexterous grasping holds broad application prospects in robotic manipulation and human-object interaction. However, most existing methods still struggle to generalize across diverse objects and task instructions, as they heavily rely on costly labeled data to ensure task-specific semantic alignment. In this study, we propose \textbf{ZeroDexGrasp}, a zero-shot task-oriented dexterous grasp synthesis framework integrating Multimodal Large Language Models with grasp refinement to generate human-like grasp poses that are well aligned with specific task objectives and object affordances. Specifically, ZeroDexGrasp employs prompt-based multi-stage semantic reasoning to infer initial grasp configurations and object contact information from task and object semantics, then exploits contact-guided grasp optimization to refine these poses for physical feasibility and task alignment. Experimental results demonstrate that ZeroDexGrasp enables high-quality zero-shot dexterous grasping on diverse unseen object categories and complex task requirements, advancing toward more generalizable and intelligent robotic grasping.

Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users do not want logged, retained, or leaked. We observe this to be especially acute when users discuss friends, coworkers, or adversaries, i.e., when they spill the tea. Enterprises face the same challenge when they want to use LLMs for internal communication and decision-making. In this whitepaper, we present Whistledown, a best-effort privacy layer that modifies prompts before they are sent to the LLM. Whistledown combines pseudonymization and $ε$-local differential privacy ($ε$-LDP) with transformation caching to provide best-effort privacy protection without sacrificing conversational utility. Whistledown is designed to have low compute and memory overhead, allowing it to be deployed directly on a client's device in the case of individual users. For enterprise users, Whistledown is deployed centrally within a zero-trust gateway that runs on an enterprise's trusted infrastructure. Whistledown requires no changes to the existing APIs of popular LLM providers.

Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion models within a visuomotor policy framework that merges visual and textual inputs to generate precise robotic trajectories. By employing reference demonstrations during training, the model learns to execute manipulation tasks specified through textual commands within the robot's immediate environment. The proposed research aims to extend an existing model by leveraging improved em-beddings, and adapting techniques from diffusion models for image generation. We evaluate our methods on the CAL VIN dataset, proving enhanced performance on various manipulation tasks and an increased long-horizon success rate when multiple tasks are executed in sequence. Our approach reinforces the usefulness of diffusion models and contributes towards general multitask manipulation.

Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge. However, LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge. While retrieval-augmented generation (RAG) frameworks, such as GraphRAG and its variants, have been proposed to mitigate these issues by incorporating external knowledge, they face two key challenges in the healthcare scenario: (1) identifying the clinical necessity to activate the retrieval mechanism, and (2) achieving synergy between the retriever and the generator to craft contextually appropriate retrievals. To address these challenges, we propose GHAR, a \underline{g}enerative \underline{h}ierarchical \underline{a}gentic \underline{R}AG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare. Specifically, for the first challenge, we design a dual-agent architecture comprising Agent-Top and Agent-Low. Agent-Top acts as the primary physician, iteratively deciding whether to rely on parametric knowledge or to initiate retrieval, while Agent-Low acts as the consulting service, summarising all task-relevant knowledge once retrieval was triggered. To tackle the second challenge, we innovatively unify the optimization of both agents within a formal Markov Decision Process, designing diverse rewards to align their shared goal of accurate prediction while preserving their distinct roles. Extensive experiments on three benchmark datasets across three popular tasks demonstrate our superiority over state-of-the-art baselines, highlighting the potential of hierarchical agentic RAG in advancing healthcare systems.

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of machine-generated responses, particularly in large language models (LLMs). As these systems are increasingly embedded in ethical decision-making scenarios, it is important to understand their moral reasoning and the inherent uncertainties in building reliable AI systems. This work examines how uncertainty influences moral decisions in the classical trolley problem, analyzing responses from 32 open-source models and 9 distinct moral dimensions. We first find that variance in model confidence is greater across models than within moral dimensions, suggesting that moral uncertainty is predominantly shaped by model architecture and training method. To quantify uncertainty, we measure binary entropy as a linear combination of total entropy, conditional entropy, and mutual information. To examine its effects, we introduce stochasticity into models via "dropout" at inference time. Our findings show that our mechanism increases total entropy, mainly through a rise in mutual information, while conditional entropy remains largely unchanged. Moreover, this mechanism significantly improves human-LLM moral alignment, with correlations in mutual information and alignment score shifts. Our results highlight the potential to better align model-generated decisions and human preferences by deliberately modulating uncertainty and reducing LLMs' confidence in morally complex scenarios.