Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in cold-start scenarios and long-term personalization due to their inherently static and shallow designs. In this work, we introduce the Reinforcement Learning for Personalized Alignment (RLPA) framework, in which an LLM interacts with a simulated user model to iteratively infer and refine user profiles through dialogue. The training process is guided by a dual-level reward structure: the Profile Reward encourages accurate construction of user representations, while the Response Reward incentivizes generation of responses consistent with the inferred profile. We instantiate RLPA by fine-tuning Qwen-2.5-3B-Instruct, resulting in Qwen-RLPA, which achieves state-of-the-art performance in personalized dialogue. Empirical evaluations demonstrate that Qwen-RLPA consistently outperforms prompting and offline fine-tuning baselines, and even surpasses advanced commercial models such as Claude-3.5 and GPT-4o. Further analysis highlights Qwen-RLPA's robustness in reconciling conflicting user preferences, sustaining long-term personalization and delivering more efficient inference compared to recent reasoning-focused LLMs. These results emphasize the potential of dynamic profile inference as a more effective paradigm for building personalized dialogue systems.

Online class-incremental learning (OCIL) focuses on gradually learning new classes (called plasticity) from a stream of data in a single-pass, while concurrently preserving knowledge of previously learned classes (called stability). The primary challenge in OCIL lies in maintaining a good balance between the knowledge of old and new classes within the continually updated model. Most existing methods rely on explicit knowledge interaction through experience replay, and often employ exclusive training separation to address bias problems. Nevertheless, it still remains a big challenge to achieve a well-balanced learner, as these methods often exhibit either reduced plasticity or limited stability due to difficulties in continually integrating knowledge in the OCIL setting. In this paper, we propose a novel replay-based method, called Balanced Inclusive Separation for Online iNcremental learning (BISON), which can achieve both high plasticity and stability, thus ensuring more balanced performance in OCIL. Our BISON method proposes an inclusive training separation strategy using dual classifiers so that knowledge from both old and new classes can effectively be integrated into the model, while introducing implicit approaches for transferring knowledge across the two classifiers. Extensive experimental evaluations over three widely-used OCIL benchmark datasets demonstrate the superiority of BISON, showing more balanced yet better performance compared to state-of-the-art replay-based OCIL methods.

Composite federated learning offers a general framework for solving machine learning problems with additional regularization terms. However, existing methods often face significant limitations: many require clients to perform computationally expensive proximal operations, and their performance is frequently vulnerable to data heterogeneity. To overcome these challenges, we propose a novel composite federated learning algorithm called \textbf{FedCanon}, designed to solve the optimization problems comprising a possibly non-convex loss function and a weakly convex, potentially non-smooth regularization term. By decoupling proximal mappings from local updates, FedCanon requires only a single proximal evaluation on the server per iteration, thereby reducing the overall proximal computation cost. Concurrently, it integrates control variables into local updates to mitigate the client drift arising from data heterogeneity. The entire architecture avoids the complex subproblems of primal-dual alternatives. The theoretical analysis provides the first rigorous convergence guarantees for this proximal-skipping framework in the general non-convex setting. It establishes that FedCanon achieves a sublinear convergence rate, and a linear rate under the Polyak-Łojasiewicz condition, without the restrictive bounded heterogeneity assumption. Extensive experiments demonstrate that FedCanon outperforms the state-of-the-art methods in terms of both accuracy and computational efficiency, particularly under heterogeneous data distributions.

Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering (QA) tasks by leveraging relevant passages retrieved from corpora. In multilingual RAG (mRAG), the retrieved passages can be written in languages other than that of the query entered by the user, making it challenging for LLMs to effectively utilize the provided information. Recent research suggests that retrieving passages from multilingual corpora can improve RAG performance, particularly for low-resource languages. However, the extent to which LLMs can leverage different kinds of multilingual contexts to generate accurate answers, *independently from retrieval quality*, remains understudied. In this paper, we conduct an extensive assessment of LLMs' ability to (i) make consistent use of a relevant passage regardless of its language, (ii) respond in the expected language, and (iii) focus on the relevant passage even when multiple `distracting' passages in different languages are provided in the context. Our experiments with four LLMs across three QA datasets covering a total of 48 languages reveal a surprising ability of LLMs to extract the relevant information from passages in a different language than the query, but a much weaker ability to formulate a full answer in the correct language. Our analysis, based on both accuracy and feature attribution techniques, further shows that distracting passages negatively impact answer quality regardless of their language. However, distractors in the query language exert a slightly stronger influence. Taken together, our findings deepen the understanding of how LLMs utilize context in mRAG systems, providing directions for future improvements.

Large language models (LLMs) have shown strong performance in data-rich domains such as programming, but their reliability in engineering tasks remains limited. Circuit analysis -- requiring multimodal understanding and precise mathematical reasoning -- highlights these challenges. Although Gemini 2.5 Pro improves diagram interpretation and analog-circuit reasoning, it still struggles to consistently produce correct solutions when given both text and circuit diagrams. At the same time, engineering education needs scalable AI tools capable of generating accurate solutions for tasks such as automated homework feedback and question-answering. This paper presents an enhanced, end-to-end circuit problem solver built on Gemini 2.5 Pro. We first benchmark Gemini on a representative set of undergraduate circuit problems and identify two major failure modes: 1) circuit-recognition hallucinations, particularly incorrect source polarity detection, and 2) reasoning-process hallucinations, such as incorrect current directions. To address recognition errors, we integrate a fine-tuned YOLO detector and OpenCV processing to isolate voltage and current sources, enabling Gemini to re-identify source polarities from cropped images with near-perfect accuracy. To reduce reasoning errors, we introduce an ngspice-based verification loop in which Gemini generates a .cir file, ngspice simulates the circuit, and discrepancies trigger iterative regeneration with optional human-in-the-loop review. Across 83 problems, the proposed pipeline achieves a 97.59% success rate (81 correct solutions), substantially outperforming Gemini 2.5 Pro's original 79.52% accuracy. This system extends LLM capabilities for multimodal engineering problem-solving and supports the creation of high-quality educational datasets and AI-powered instructional tools.

In the unsupervised pre-training for reinforcement learning, the agent aims to learn a prior policy for downstream tasks without relying on task-specific reward functions. We focus on state entropy maximization (SEM), where the goal is to learn a policy that maximizes the entropy of the state stationary distribution. In this paper, we introduce SEMDICE, a principled off-policy algorithm that computes an SEM policy from an arbitrary off-policy dataset, which optimizes the policy directly within the space of stationary distributions. SEMDICE computes a single, stationary Markov state-entropy-maximizing policy from an arbitrary off-policy dataset. Experimental results demonstrate that SEMDICE outperforms baseline algorithms in maximizing state entropy while achieving the best adaptation efficiency for downstream tasks among SEM-based unsupervised RL pre-training methods.

Learning is most effective when it's connected to relevant, relatable examples that resonate with learners on a personal level. However, existing educational AI tools don't focus on generating examples or adapting to learners' changing understanding, struggles, or growing skills. We've developed ExaCraft, an AI system that generates personalized examples by adapting to the learner's dynamic context. Through the Google Gemini AI and Python Flask API, accessible via a Chrome extension, ExaCraft combines user-defined profiles (including location, education, profession, and complexity preferences) with real-time analysis of learner behavior. This ensures examples are both culturally relevant and tailored to individual learning needs. The system's core innovation is its ability to adapt to five key aspects of the learning context: indicators of struggle, mastery patterns, topic progression history, session boundaries, and learning progression signals. Our demonstration will show how ExaCraft's examples evolve from basic concepts to advanced technical implementations, responding to topic repetition, regeneration requests, and topic progression patterns in different use cases.

Elon Musk attends the Saudi Investment Forum at the Kennedy Center, on 19 November, in Washington DC. Elon Musk attends the Saudi Investment Forum at the Kennedy Center, on 19 November, in Washington DC. President Nayib Bukele entrusting chatbot known for calling itself'MechaHitler' to create'AI-powered' curricula Elon Musk is partnering with the government of El Salvador to bring his artificial intelligence company's chatbot, Grok, to more than 1 million students across the country, according to a Thursday announcement by xAI. Over the next two years, the plan is to "deploy" the chatbot to more than 5,000 public schools in an "AI-powered education program". Over the past year, the chatbot has spewed various antisemitic content, decried "white genocide" and claimed Donald Trump won the 2020 election .

AI has entered the classroom - but is it the solution for overworked teachers? Schools across the UK are trialling the use of deepfake teachers and even employing remote staff to deliver lessons hundreds of miles away from the classroom. It comes as the use of AI is becoming increasingly prevalent in schools. The government says AI has the power to transform education, and improve teacher workload, particularly around admin for teachers. The BBC has spoken to teachers, school leaders and unions who seem divided on what the future of the UK's classrooms should look like.

Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework to address these challenges in dedicated NMT architectures. We first demonstrate that LoRA-based fine-tuning adapts NMT models to new languages and domains with performance on par with full-parameter techniques, while utilizing only a fraction of the parameter space. Second, we propose an interactive adaptation method using a calibrated linear combination of LoRA modules. This approach functions as a gate-free mixture of experts, enabling real-time, user-controllable adjustments to domain and style without retraining. Finally, to mitigate catastrophic forgetting, we introduce a novel gradient-based regularization strategy specifically designed for low-rank decomposition matrices. Unlike methods that regularize the full parameter set, our approach weights the penalty on the low-rank updates using historical gradient information. Experimental results indicate that this strategy efficiently preserves prior domain knowledge while facilitating the acquisition of new tasks, offering a scalable paradigm for interactive and continual NMT.