Autonomous vehicles must react in milliseconds while reasoning about road geometry and traffic intent to navigate complex situations. We introduce NovaDrive, a single-branch vision-language architecture that processes front-camera images, HD-map tiles, LiDAR depth, and textual waypoints in a single branch. A lightweight, two-stage cross-attention block first aligns waypoint tokens with the HD map, then refines attention over fine-grained image and depth patches. Coupled with a novel smoothness loss that discourages abrupt steering and speed changes, this design eliminates the need for recurrent memory. We fine-tune the top 15 layers of an 11B LLaMA-3.2 vision-language backbone, enabling real-time inference. On the nuScenes / Waymo subset of the MD-NEX Outdoor benchmark, NovaDrive raises success rate to 84% (+4%), boosts path-efficiency (SPL) to 0.66 (+0.11), and reduces collision frequency from 2.6% to 1.2% (-1.4%) relative to the previous state-of-the-art. Our ablations confirm that waypoint tokens, partial VLM fine-tuning, and the cross-attention fusion each contribute the most to these gains. Beyond safety, NovaDrive's shorter routes (resulting from the novel smoothness loss) translate to lower fuel or battery usage, pointing toward leaner, more easily updated driving stacks. NovaDrive can be extended to other embodied-AI domains as well.

Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In this work, the MoE-specific safety risk of positional vulnerability-that safety-aligned behaviors rely on specific expert modules-is formalized and systematically analyzed. An analytical framework, SAFEx, is presented to robustly identify, characterize, and validate safety-critical experts via a stability-based expert selection procedure, and to decompose them into two functional groups: the Harmful Content Detection Group (HCDG), which specializes in identifying and recognizing harmful content within user inputs, and the Harmful Response Control Group (HRCG), which specializes in controlling and enforcing model behaviors to generate appropriate safety responses. Expert-level interventions are conducted to probe causality and to test mitigation. Targeted masking of SAFEx-selected experts reveals that safety behavior is highly concentrated. On Qwen3-30B-A3B, configured with 48 MoE-FFN layers and 128 experts per layer under top-8 routing (48x128=6,144 experts in total), disabling 12 selected experts reduces the refusal rate by 22%. In addition, lightweight adaptation is performed using LoRA under three configurations-the HRCG, the union of HCDG and HRCG, and all experts-and the resulting updates are composed through negative weight merging targeted at the HRCG, leading to improved refusal under adversarial prompts without full-model retraining. These results establish positional vulnerability as a distinct MoE-specific safety challenge and provide a practical, compute-efficient pathway for expert-level safety interventions within routed architectures.

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety degradation when user data includes harmful prompts, a threat known as harmful finetuning attacks. Prior works attempt to mitigate this issue by first constructing safety-aligned model and then finetuning the model on user data. However, we observe that the safety-aligned weights provide weak initialization for downstream task learning, leading to suboptimal safety-alignment and downstream task performance. To address this, we propose a Refusal-T eacher (Ref-T eacher)-guided finetuning framework. Instead of finetuning a safety-aligned model on user data, our approach directly finetunes the base model under the guidance of a safety-aligned Ref-Teacher, which filters harmful prompts from user data and distills safety-alignment knowledge into the base model. Extensive experiments demonstrate that our Ref-Teacher-guided finetuning strategy effectively minimizes harmful outputs and enhances finetuning accuracy for user-specific tasks, offering a practical solution for secure and reliable deployment of LLMs in FaaS. Recent advancements in Large Language Models (LLMs) (Touvron et al. (2023); Jiang et al. (2023); Team et al. (2024); Team (2024); Hurst et al. (2024); Guo et al. (2025); Research et al. (2025)) have achieved remarkable performance across a wide range of natural language processing tasks. LLMs are typically pretrained on massive and diverse corpora, resulting in strong generalization ability and broad applicability across domains. To further facilitate LLMs for individual and domain-specific purposes, major AI service providers such as Google and OpenAI offer not only access to pretrained LLMs but also Finetuning-as-a-Service (FaaS). This service enables users to upload custom datasets and adapt LLMs to more specific tasks and domains depending on their unique requirements. However, FaaS must prevent the malicious use of LLMs through safety-alignment, even when users attempt to jailbreak the models via customization. These types of attacks, which inject harmful prompts into user data for finetuning, are called harmful finetuning attacks. Several studies (Qi et al. (2023); Lermen et al. (2023); Rosati et al. (2024); Huang et al. (2024b;c;d); Li et al. (2025); Huang et al. (2025)) have shown that finetuning on user data containing harmful content compromises the safety-alignment, despite the LLMs being safety-aligned before finetuning.

Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with many choices, LLMs suffer from under-confidence in correct predictions and over-confidence in incorrect ones, leading to a substantially degraded performance. To solve this problem, we propose Self-ensemble in this work. Our method splits the choices into several groups and ensembles LLM predictions across these groups to reach a final decision. The advantage of Self-ensemble is its plug-and-play nature, where it can be integrated into existing LLM architecture based on a designed attention mask and positional encoding, without requiring labeled datasets for parameter tuning. Experimental results on three LLMs and datasets demonstrate that Self-ensemble comprehensively addresses the confidence distortion problem of LLMs, outperforming standard inference as well as baseline methods.

We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conventional RAG methods that rely on end-to-end fine-tuning or isolated component enhancements, MA-RAG orchestrates a collaborative set of specialized AI agents: Planner, Step Definer, Extractor, and QA Agents, each responsible for a distinct stage of the RAG pipeline. By decomposing tasks into subtasks such as query disambiguation, evidence extraction, and answer synthesis, and enabling agents to communicate intermediate reasoning via chain-of-thought prompting, MA-RAG progressively refines retrieval and synthesis while maintaining modular interpretability. Extensive experiments on multi-hop and ambiguous QA benchmarks, including NQ, HotpotQA, 2WikimQA, and TriviaQA, demonstrate that MA-RAG significantly outperforms standalone LLMs and existing RAG methods across all model scales. Notably, even a small LLaMA3-8B model equipped with MA-RAG surpasses larger standalone LLMs, while larger variants (LLaMA3-70B and GPT-4o-mini) set new state-of-the-art results on challenging multi-hop datasets. Ablation studies reveal that both the planner and extractor agents are critical for multi-hop reasoning, and that high-capacity models are especially important for the QA agent to synthesize answers effectively. Beyond general-domain QA, MA-RAG generalizes to specialized domains such as medical QA, achieving competitive performance against domain-specific models without any domain-specific fine-tuning. Our results highlight the effectiveness of collaborative, modular reasoning in retrieval-augmented systems: MA-RAG not only improves answer accuracy and robustness but also provides interpretable intermediate reasoning steps, establishing a new paradigm for efficient and reliable multi-agent RAG.

Retrieval-Augmented Generation (RAG) leverages large language models (LLMs) combined with external contexts to enhance the accuracy and reliability of generated responses. However, reliably attributing generated content to specific context segments, context attribution, remains challenging due to the computationally intensive nature of current methods, which often require extensive fine-tuning or human annotation. In this work, we introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD), enabling efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling. Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements compared to the previous surrogate-based method. Furthermore, our mechanistic analysis reveals specific attention heads and multilayer perceptron (MLP) layers responsible for context attribution, providing valuable insights into the internal workings of RAG models and how they affect RAG behaviours. Our code is available at https://github.com/ruizheliUOA/ARC_JSD.

Macro-aligned micro-records are crucial for credible simulations in social science and urban studies. For example, epidemic models are only reliable when individual-level mobility and contacts mirror real behavior, while aggregates match real-world statistics like case counts or travel flows. However, collecting such fine-grained data at scale is impractical, leaving researchers with only macro-level data. LLMSynthor addresses this by turning a pretrained LLM into a macro-aware simulator that generates realistic micro-records consistent with target macro-statistics. It iteratively builds synthetic datasets: in each step, the LLM generates batches of records to minimize discrepancies between synthetic and target aggregates. Treating the LLM as a nonparametric copula allows the model to capture realistic joint dependencies among variables. To improve efficiency, LLM Proposal Sampling guides the LLM to propose targeted record batches, specifying variable ranges and counts, to efficiently correct discrepancies while preserving realism grounded in the model's priors. Evaluations across domains (mobility, e-commerce, population) show that LLMSynthor achieves strong realism, statistical fidelity, and practical utility, making it broadly applicable to economics, social science, and urban studies.

Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minority samples to rebalance the dataset. Most existing methods, such as SMOTE, require converting categorical variables into numerical vectors, which often leads to information loss. Recently, large language model (LLM)-based methods have been introduced to overcome this limitation. However, current LLM-based approaches typically generate minority samples with limited diversity, reducing robustness and generalizability in downstream classification tasks. To address this gap, we propose a novel LLM-based oversampling method designed to enhance diversity. First, we introduce a sampling strategy that conditions synthetic sample generation on both minority labels and features. Second, we develop a new permutation strategy for fine-tuning pre-trained LLMs. Third, we fine-tune the LLM not only on minority samples but also on interpolated samples to further enrich variability. Extensive experiments on 10 tabular datasets demonstrate that our method significantly outperforms eight SOTA baselines. The generated synthetic samples are both realistic and diverse. Moreover, we provide theoretical analysis through an entropy-based perspective, proving that our method encourages diversity in the generated samples.

Whether your chip is running a vintage computer game or the latest DeepSeek model, it'll reward you for speaking its native language. But if you took a look beneath the pixels--the rickety rides, the crowds of hungry, thirsty, barfing people (and the janitors mopping in their wake)--deep down at the level of the code, you saw craftsmanship so obsessive that it bordered on insane. Chris Sawyer, the game's sole developer, wrote the whole thing in assembly. Because if/when the machines take over, we should at least speak their language. Certain programming languages, like Python or Go or C++, are called "high-level" because they work sort of like human language, written in commands and idioms that might fit in at a poetry slam.

Why we should be skeptical of the hasty global push to test 15-year-olds' AI literacy in 2029 If 2022 was the year OpenAI knocked our world off course with the launch of ChatGPT, 2025 will be remembered for the frenzied embrace of AI as the solution to everything. And, yes, this includes teaching and schoolwork. In today's breakneck AI innovation race, the Organization for Economic Co-operation and Development (OECD), along with the European Commission, have called for the development of unified AI literacy strategies in kindergarten to Grade 12 education. They have done this through an AI Literacy Framework developed with Code.org, and a range of experts in computational thinking, neuroscience, AI, educational technology and innovation -- and with "valuable insights" from the "TeachAI community ." The "TeachAI community" refers to a larger umbrella project providing web resources targeting teachers, education leaders and "solution providers" .