Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction approach can be easily adapted to other languages; we build datasets for Japanese and confirm that LLMs tuned with our data reach state-of-the-art performance. Analyses suggest that instruction-tuning in a new language allows LLMs to follow instructions, while the tuned models exhibit a notable lack of culture-specific knowledge in that language. The datasets and fine-tuned models will be publicly available. Our datasets, synthesized with open-weight LLMs, are openly distributed under permissive licenses, allowing for diverse use cases.

Nonlinear matrix decomposition (NMD) with the ReLU function, denoted ReLU-NMD, is the following problem: given a sparse, nonnegative matrix $X$ and a factorization rank $r$, identify a rank-$r$ matrix $\Theta$ such that $X\approx \max(0,\Theta)$. This decomposition finds application in data compression, matrix completion with entries missing not at random, and manifold learning. The standard ReLU-NMD model minimizes the least squares error, that is, $\|X - \max(0,\Theta)\|_F^2$. The corresponding optimization problem is nondifferentiable and highly nonconvex. This motivated Saul to propose an alternative model, Latent-ReLU-NMD, where a latent variable $Z$ is introduced and satisfies $\max(0,Z)=X$ while minimizing $\|Z - \Theta\|_F^2$ (``A nonlinear matrix decomposition for mining the zeros of sparse data'', SIAM J. Math. Data Sci., 2022). Our first contribution is to show that the two formulations may yield different low-rank solutions $\Theta$; in particular, we show that Latent-ReLU-NMD can be ill-posed when ReLU-NMD is not, meaning that there are instances in which the infimum of Latent-ReLU-NMD is not attained while that of ReLU-NMD is. We also consider another alternative model, called 3B-ReLU-NMD, which parameterizes $\Theta=WH$, where $W$ has $r$ columns and $H$ has $r$ rows, allowing one to get rid of the rank constraint in Latent-ReLU-NMD. Our second contribution is to prove the convergence of a block coordinate descent (BCD) applied to 3B-ReLU-NMD and referred to as BCD-NMD. Our third contribution is a novel extrapolated variant of BCD-NMD, dubbed eBCD-NMD, which we prove is also convergent under mild assumptions. We illustrate the significant acceleration effect of eBCD-NMD compared to BCD-NMD, and also show that eBCD-NMD performs well against the state of the art on synthetic and real-world data sets.

Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction data. Building upon this approach, we further explore the impact of prompt's robustness on the selection of high-quality instruction data. This paper proposes a pioneering framework of high-quality online instruction data mining for instruction tuning, focusing on the impact of prompt's robustness on the data mining process. Our notable innovation, is to generate the adversarial instruction data by conducting the attack for the prompt of online instruction data. Then, we introduce an Adversarial Instruction-Following Difficulty metric to measure how much help the adversarial instruction data can provide to the generation of the corresponding response. Apart from it, we propose a novel Adversarial Instruction Output Embedding Consistency approach to select high-quality online instruction data. We conduct extensive experiments on two benchmark datasets to assess the performance. The experimental results serve to underscore the effectiveness of our proposed two methods. Moreover, the results underscore the critical practical significance of considering prompt's robustness.

Since the release of ChatGPT in late 2022, generative artificial intelligence has trickled down from adults in their offices to university students in campus libraries to teenagers in high school hallways. Now it's reaching the youngest among us, and parents and teachers are grappling with the most responsible way to introduce their under-13s to a new technology that may fundamentally reshape the future. Though the terms of service for ChatGPT, Google's Gemini and other AI models specify that the tools are only meant for those over 13, parents and teachers are taking the matter of AI education into their own hands. Inspired by a story we published on parents who are teaching their children to use AI to set them up for success in school and at work, we asked Guardian readers how and why – or why not – others are doing the same. Though our original story only concerned parents, we have also included teachers in the responses published below, as preparing children for future studies and jobs is one of educators' responsibilities as well.

Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. In this work, we present ViT-Linearizer, a cross-architecture distillation framework that transfers rich ViT representations into a linear-time, recurrent-style model. Our approach leverages 1) activation matching, an intermediate constraint that encourages student to align its token-wise dependencies with those produced by the teacher, and 2) masked prediction, a contextual reconstruction objective that requires the student to predict the teacher's representations for unseen (masked) tokens, to effectively distill the quadratic self-attention knowledge into the student while maintaining efficient complexity. Empirically, our method provides notable speedups particularly for high-resolution tasks, significantly addressing the hardware challenges in inference. Additionally, it also elevates Mamba-based architectures' performance on standard vision benchmarks, achieving a competitive 84.3% top-1 accuracy on ImageNet with a base-sized model. Our results underscore the good potential of RNN-based solutions for large-scale visual tasks, bridging the gap between theoretical efficiency and real-world practice.

Real-time reinforcement learning (RL) introduces several challenges. First, policies are constrained to a fixed number of actions per second due to hardware limitations. Second, the environment may change while the network is still computing an action, leading to observational delay. The first issue can partly be addressed with pipelining, leading to higher throughput and potentially better policies. However, the second issue remains: if each neuron operates in parallel with an execution time of $\tau$, an $N$-layer feed-forward network experiences observation delay of $\tau N$. Reducing the number of layers can decrease this delay, but at the cost of the network's expressivity. In this work, we explore the trade-off between minimizing delay and network's expressivity. We present a theoretically motivated solution that leverages temporal skip connections combined with history-augmented observations. We evaluate several architectures and show that those incorporating temporal skip connections achieve strong performance across various neuron execution times, reinforcement learning algorithms, and environments, including four Mujoco tasks and all MinAtar games. Moreover, we demonstrate parallel neuron computation can accelerate inference by 6-350% on standard hardware. Our investigation into temporal skip connections and parallel computations paves the way for more efficient RL agents in real-time setting.

We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with another human participant and one of these systems before judging which conversational partner they thought was human. When prompted to adopt a humanlike persona, GPT-4.5 was judged to be the human 73% of the time: significantly more often than interrogators selected the real human participant. LLaMa-3.1, with the same prompt, was judged to be the human 56% of the time -- not significantly more or less often than the humans they were being compared to -- while baseline models (ELIZA and GPT-4o) achieved win rates significantly below chance (23% and 21% respectively). The results constitute the first empirical evidence that any artificial system passes a standard three-party Turing test. The results have implications for debates about what kind of intelligence is exhibited by Large Language Models (LLMs), and the social and economic impacts these systems are likely to have.

ARTICLE TEMPLATE Beyond Detection: Designing AI-Resilient Assessments with Automated Feedback Tool to Foster Critical Thinking and Originality Muhammad Sajjad Akbar a a University of Sydney, Australia; ARTICLE HISTORY Compiled April 1, 2025 ABSTRACT The growing prevalence of generative AI tools such as ChatGPT has raised urgent concerns about their impact on student learning, particularly their potential to erode critical thinking and creativity in academic contexts. As students increasingly use these tools to complete assessments, foundational cognitive skills are at risk of being bypassed, challenging the integrity of higher education and the authenticity of student work. Current AI-generated text detection tools are fundamentally inadequate in addressing this challenge. They produce unreliable, unverifiable outputs and are highly susceptible to false positives and false negatives, especially when students apply obfuscation techniques such as paraphrasing, translation, or structural rewording. These tools rely on shallow statistical features rather than contextual or semantic understanding, making them unsuitable as definitive indicators of AI misuse. In response, this research proposes an AI-resilient, assessment-based solution that shifts focus from reactive detection to proactive assessment design. The solution is delivered through a web-based Python tool that integrates Bloom's Taxonomy with advanced natural language processing techniques including GPT-3.5 Turbo, BERT-based semantic similarity, and TF-IDF metrics to evaluate the AI-solvability of assignment tasks. By analyzing both surface-level and semantic features, the tool helps educators assess whether a task targets lower-order thinking (e.g., recall, summarization), which is more easily completed by AI, or higher-order skills (e.g., analysis, evaluation, creation), which are more resistant to AI automation. This framework empowers educators to intentionally design cognitively demanding AI-resistant assessments that promote originality, critical thinking, and fairness. By addressing the design of root issue assessment rather than relying on flawed detection tools, this research contributes a sustainable and pedagogically sound strategy to uphold academic standards and foster authentic learning in the era of AI. KEYWORDS Generative AI; ChatGPT; AI-resilient; Bloom's Taxonomy; Automated Assessments; AI-solvability;Automated Feedback; appendices 1. Introduction Integrating AI-technology with innovative thinking skills in higher education (HE) environment has grown more challenging due to rapid digital innovation and ubiquitous data availability. In applied education, innovative thinking is essential. It is charac-CONTACT Muhammad Sajjad Akbar. It entails thinking creatively to come up with original solutions to issues, enhance workflows, or open up new possibilities.

Large language models (LLMs) demonstrate remarkable performance on many NLP tasks, yet often exhibit order dependence: simply reordering semantically identical tokens (e.g., answer choices in multiple-choice questions) can lead to inconsistent predictions. Recent work proposes Set-Based Prompting (SBP) as a way to remove order information from designated token subsets, thereby mitigating positional biases. However, applying SBP on base models induces an out-of-distribution input format, which can degrade in-distribution performance. We introduce a fine-tuning strategy that integrates SBP into the training process, "pulling" these set-formatted prompts closer to the model's training manifold. We show that SBP can be incorporated into a model via fine-tuning. Our experiments on in-distribution (MMLU) and out-of-distribution (CSQA, ARC Challenge) multiple-choice tasks show that SBP fine-tuning significantly improves accuracy and robustness to answer-order permutations, all while preserving broader language modeling capabilities. We discuss the broader implications of order-invariant modeling and outline future directions for building fairer, more consistent LLMs.

Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped. This survey provides a comprehensive review of RL-based MoP for AD, focusing on lessons from task-specific perspectives. We first outline the fundamentals of RL methodologies, and then survey their applications in MoP, analyzing scenario-specific features and task requirements to shed light on their influence on RL design choices. Building on this analysis, we summarize key design experiences, extract insights from various driving task applications, and provide guidance for future implementations. Additionally, we examine the frontier challenges in RL-based MoP, review recent efforts to addresse these challenges, and propose strategies for overcoming unresolved issues.