Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students - imperfect, iterative, and stylistically diverse? We present ParaStudent, a systematic study of LLM-based "student-like" code generation in an introductory programming course setting. Using a dataset of timestamped student submissions across multiple semesters, we design low- and high-resolution experiments to model student progress and evaluate code outputs along semantic, functional, and stylistic dimensions. Our results show that fine-tuning significantly improves alignment with real student trajectories and captures error patterns, incremental improvements, and stylistic variations more faithfully. This study shows that modeling realistic student code requires capturing learning dynamics through context-aware generation, temporal modeling, and multi-dimensional evaluation. Code for experiments and evaluation is available at https://github.com/mmiroyan/ParaStudent.

The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applicability in real-world scenarios. In this paper, we introduce two Korean expert-level benchmarks. KMMLU-Redux, reconstructed from the existing KMMLU, consists of questions from the Korean National Technical Qualification exams, with critical errors removed to enhance reliability. KMMLU-Pro is based on Korean National Professional Licensure exams to reflect professional knowledge in Korea. Our experiments demonstrate that these benchmarks comprehensively represent industrial knowledge in Korea. We release our dataset publicly available.

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences across multiple clients, harming the model's convergence and performance. In this paper, we first introduce powerful diffusion models into the federated learning paradigm and show that diffusion representations are effective steers during federated training. T o explore the possibility of using diffusion representations in handling data heterogeneity, we propose a novel diffusion-inspired F ederated paradigm with Diffusion Representation Collaboration, termed FedDifRC, leveraging meaningful guidance of diffusion models to mitigate data heterogeneity. The key idea is to construct text-driven diffusion contrasting and noise-driven diffusion regularization, aiming to provide abundant class-related semantic information and consistent convergence signals. On the one hand, we exploit the conditional feedback from the diffusion model for different text prompts to build a text-driven contrastive learning strategy. On the other hand, we introduce a noise-driven consistency regularization to align local instances with diffusion denois-ing representations, constraining the optimization region in the feature space. In addition, FedDifRC can be extended to a self-supervised scheme without relying on any labeled data. W e also provide a theoretical analysis for FedDifRC to ensure convergence under non-convex objectives.

Traditional agent-based urban mobility simulations often rely on rigid rule-based systems that struggle to capture the complexity, adaptability, and behavioral diversity inherent in human travel decision making. Recent advancements in large language models and AI agent technologies present new opportunities to develop agents with enhanced reasoning capabilities, persistent memory, and adaptive learning. We introduce GATSim (Generative-Agent Transport Simulation), a novel framework that leverages these advancements to simulate urban mobility using generative agents with rich, human-like behaviors. Unlike conventional approaches, GATSim agents are characterized by diverse socioeconomic profiles, individual lifestyles, and evolving preferences shaped through psychologically informed memory systems, tool usage, and lifelong learning. The main contributions of this work are: (1) a comprehensive architecture that integrates an urban mobility foundation model with agent cognitive systems and a transport simulation environment; (2) a hierarchical memory designed for efficient retrieval of contextually relevant information, incorporating spatial and temporal associations, keyword matching, and semantic relevance; (3) innovative planning and reactive mechanisms for modeling adaptive mobility behaviors which integrate a multi-scale reflection process to transform specific travel experiences into generalized behavioral insights. We implement a prototype system and conduct systematic validation, demonstrating that generative agents produce believable and coherent travel behaviors. Experimental results indicate that generative agents perform at least as well as human annotators with 92\% posterior probability, while naturally producing realistic macroscopic traffic patterns. The code for the prototype implementation is publicly available at https://github.com/qiliuchn/gatsim.

We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSeek-V3 to decompose complex problems into a series of subgoals. The proofs of resolved subgoals are synthesized into a chain-of-thought process, combined with DeepSeek-V3's step-by-step reasoning, to create an initial cold start for reinforcement learning. This process enables us to integrate both informal and formal mathematical reasoning into a unified model. The resulting model, DeepSeek-Prover-V2-671B, achieves state-of-the-art performance in neural theorem proving, reaching 88.9% pass ratio on the MiniF2F-test and solving 49 out of 658 problems from PutnamBench. In addition to standard benchmarks, we introduce ProverBench, a collection of 325 formalized problems, to enrich our evaluation, including 15 selected problems from the recent AIME competitions (years 24-25). Further evaluation on these 15 AIME problems shows that the model successfully solves 6 of them. In comparison, DeepSeek-V3 solves 8 of these problems using majority voting, highlighting that the gap between formal and informal mathematical reasoning in large language models is substantially narrowing.

Philosophy professor Dr. Susan Schneider joins'Fox & Friends First' to discuss the impact of artificial intelligence on students' performance in the classroom. Across America, education is changing at a pace few could have imagined even a decade ago. Artificial intelligence is being deployed to train machines to teach our children. School systems are embedding gender ideology and political agendas into their curriculum with little regard for parental input. At the same time, traditional values are being pushed to the margins, and our students are caught in the middle.

I've long believed that the first hugely popular music you realize you hate is in many ways as important a discovery as the first music you realize you love. There's something crucial and formative about the recognition that an artist whose music is beloved by millions makes your skin crawl, not simply in the realization that said music "isn't for you," but in the fierce and irrational conviction that those millions of people are wrong, that sometimes art that's enormously successful is not, in fact, correspondingly good. As misanthropic as that sounds, it's a significant milestone in coming to learn that everyone's taste is (or at least should be) individuated and distinct, and that those distinct tastes are a large part of what makes people attractive, maddening, and above all else interesting to one another. I don't remember exactly when I discovered I hated Billy Joel's music, but it was sometime in middle school, when as a relatively proficient young piano player, I was asked, for the 10th or 100th time, to play "Piano Man." At that age I only vaguely knew the song and hadn't learned how to play it, and for reasons I probably couldn't have articulated, I promptly resolved that I never would.

While average treatment effects (ATE) and conditional average treatment effects (CATE) provide valuable population- and subgroup-level summaries, they fail to capture uncertainty at the individual level. For high-stakes decision-making, individual treatment effect (ITE) estimates must be accompanied by valid prediction intervals that reflect heterogeneity and unit-specific uncertainty. However, the fundamental unidentifiability of ITEs limits the ability to derive precise and reliable individual-level uncertainty estimates. To address this challenge, we investigate the role of a cross-world correlation parameter, $ ρ(x) = cor(Y(1), Y(0) | X = x) $, which describes the dependence between potential outcomes, given covariates, in the Neyman-Rubin super-population model with i.i.d. units. Although $ ρ$ is fundamentally unidentifiable, we argue that in most real-world applications, it is possible to impose reasonable and interpretable bounds informed by domain-expert knowledge. Given $ρ$, we design prediction intervals for ITE, achieving more stable and accurate coverage with substantially shorter widths; often less than 1/3 of those from competing methods. The resulting intervals satisfy coverage guarantees $P\big(Y(1) - Y(0) \in C_{ITE}(X)\big) \geq 1 - α$ and are asymptotically optimal under Gaussian assumptions. We provide strong theoretical and empirical arguments that cross-world assumptions can make individual uncertainty quantification both practically informative and statistically valid.

We study PAC and online learnability of hypothesis classes formed by copies of a countably infinite graph G, where each copy is induced by permuting G's vertices. This corresponds to learning a graph's labeling, knowing its structure and label set. We consider classes where permutations move only finitely many vertices. Our main result shows that PAC learnability of all such finite-support copies implies online learnability of the full isomorphism type of G, and is equivalent to the condition of automorphic triviality. We also characterize graphs where copies induced by swapping two vertices are not learnable, using a relaxation of the extension property of the infinite random graph. Finally, we show that, for all G and k>2, learnability for k-vertex permutations is equivalent to that for 2-vertex permutations, yielding a four-class partition of infinite graphs, whose complexity we also determine using tools coming from both descriptive set theory and computability theory.

The evaluation of large language models is a complex task, in which several approaches have been proposed. The most common is the use of automated benchmarks in which LLMs have to answer multiple-choice questions of different topics. However, this method has certain limitations, being the most concerning, the poor correlation with the humans. An alternative approach, is to have humans evaluate the LLMs. This poses scalability issues as there is a large and growing number of models to evaluate making it impractical (and costly) to run traditional studies based on recruiting a number of evaluators and having them rank the responses of the models. An alternative approach is the use of public arenas, such as the popular LM arena, on which any user can freely evaluate models on any question and rank the responses of two models. The results are then elaborated into a model ranking. An increasingly important aspect of LLMs is their energy consumption and, therefore, evaluating how energy awareness influences the decisions of humans in selecting a model is of interest. In this paper, we present GEA, the Generative Energy Arena, an arena that incorporates information on the energy consumption of the model in the evaluation process. Preliminary results obtained with GEA are also presented, showing that for most questions, when users are aware of the energy consumption, they favor smaller and more energy efficient models. This suggests that for most user interactions, the extra cost and energy incurred by the more complex and top-performing models do not provide an increase in the perceived quality of the responses that justifies their use.