The growth of Massive Open Online Courses (MOOCs) presents significant challenges for personalized learning, where concept recommendation is crucial. Existing approaches typically rely on heterogeneous information networks or knowledge graphs to capture conceptual relationships, combined with knowledge tracing models to assess learners' cognitive states. However, these methods face significant limitations due to their dependence on high-quality structured knowledge graphs, which are often scarce in real-world educational scenarios. To address this fundamental challenge, this paper proposes CLLMRec, a novel framework that leverages Large Language Models through two synergistic technical pillars: Semantic Alignment and Prerequisite Knowledge Distillation. The Semantic Alignment component constructs a unified representation space by encoding unstructured textual descriptions of learners and concepts. The Prerequisite Knowledge Distillation paradigm employs a teacher-student architecture, where a large teacher LLM (implemented as the Prior Knowledge Aware Component) extracts conceptual prerequisite relationships from its internalized world knowledge and distills them into soft labels to train an efficient student ranker. Building upon these foundations, our framework incorporates a fine-ranking mechanism that explicitly models learners' real-time cognitive states through deep knowledge tracing, ensuring recommendations are both structurally sound and cognitively appropriate. Extensive experiments on two real-world MOOC datasets demonstrate that CLLMRec significantly outperforms existing baseline methods across multiple evaluation metrics, validating its effectiveness in generating truly cognitive-aware and personalized concept recommendations without relying on explicit structural priors.

Large language model (LLM) agents show promise in automating machine learning (ML) engineering. However, existing agents typically operate in isolation on a given research problem, without engaging with the broader research community, where human researchers often gain insights and contribute by sharing knowledge. To bridge this gap, we introduce MLE-Live, a live evaluation framework designed to assess an agent's ability to communicate with and leverage collective knowledge from a simulated Kaggle research community. Building on this framework, we propose CoMind, an multi-agent system designed to actively integrate external knowledge. CoMind employs an iterative parallel exploration mechanism, developing multiple solutions simultaneously to balance exploratory breadth with implementation depth. On 75 past Kaggle competitions within our MLE-Live framework, CoMind achieves a 36% medal rate, establishing a new state of the art. Critically, when deployed in eight live, ongoing competitions, CoMind outperforms 92.6% of human competitors on average, placing in the top 5% on three official leaderboards and the top 1% on one.

Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workload such as chain-of-throught, complex reasoning, agent services significantly increase the inference cost by invoke the model repeatedly. Optimization methods such as parallelism, compression, and caching have been adopted to reduce costs, but the diverse service requirements make it hard to select the right method. Recently, specialized LLM inference engines have emerged as a key component for integrating the optimization methods into service-oriented infrastructures. However, a systematic study on inference engines is still lacking.This paper provides a comprehensive evaluation of 25 open-source and commercial inference engines. We examine each inference engine in terms of ease-of-use, ease-of-deployment, general-purpose support, scalability, and suitability for throughput- and latency-aware computation. Furthermore, we explore the design goals of each inference engine by investigating the optimization techniques it supports. In addition, we assess the ecosystem maturity of open source inference engines and handle the performance and cost policy of commercial solutions.We outline future research directions that include support for complex LLM-based services, support of various hardware, and enhanced security, offering practical guidance to researchers and developers in selecting and designing optimized LLM inference engines. We also provide a public repository to continually track developments in this fast-evolving field: \href{https://github.com/sihyeong/Awesome-LLM-Inference-Engine}{https://github.com/sihyeong/Awesome-LLM-Inference-Engine}.

In the era of data-driven intelligence, the paradox of data abundance and annotation scarcity has emerged as a critical bottleneck in the advancement of machine learning. This paper gives a detailed overview of Active Learning (AL), which is a strategy in machine learning that helps models achieve better performance using fewer labeled examples. It introduces the basic concepts of AL and discusses how it is used in various fields such as computer vision, natural language processing, transfer learning, and real-world applications. The paper focuses on important research topics such as uncertainty estimation, handling of class imbalance, domain adaptation, fairness, and the creation of strong evaluation metrics and benchmarks. It also shows that learning methods inspired by humans and guided by questions can improve data efficiency and help models learn more effectively. In addition, this paper talks about current challenges in the field, including the need to rebuild trust, ensure reproducibility, and deal with inconsistent methodologies. It points out that AL often gives better results than passive learning, especially when good evaluation measures are used. This work aims to be useful for both researchers and practitioners by providing key insights and proposing directions for future progress in active learning.

Chicago's top prosecutor turns on woke judge who freed 72-time arrestee accused of setting devout Christian woman, 26, on fire on train What HAS happened to Beyoncé? Suddenly so desperate, I know what's really going on... and it's ugly: CAROLINE BULLOCK LIZ JONES: Sorry, but it's now time for Kate to stop making excuses Fani Willis' election interference case against Trump thrown out by Georgia prosecutor Teenager dragged from car'by migrant gang' and raped in front of her fiancé describes her night of hell and reveals they warned her'if you scream we'll kill you' Trump slams'ugly' female reporter behind NYT'hit piece' after'creepy' health rumors Joy Reid suggests JD Vance may dump'brown Hindu' wife Usha for'white queen' Erika Kirk to win 2028 election during vile chat with podcaster who laughed at Charlie's murder Here's the proof of a Democrat plot to make our troops pawns in their petty political war on Trump: LT COL DANIEL DAVIS Meghan Markle slammed for unsanitary mistake while preparing Thanksgiving turkey: 'It's basic knowledge' Karoline Leavitt's sister-in-law wrote VERY provocative Instagram post about stepson, 11, whose Brazilian mother has now been seized by ICE Marlo Thomas gives rare comment on how she's coping after loss of husband Phil Donahue a year after his death Troubled 350lb son of Hollywood icon is forced to humiliating new low... as his movie star brother luxuriates in $7m Montecito mansion Shocking reason brother of Anna Kepler'murder' suspect jumped out of moving car before Carnival cruise death horror Sir Richard Branson reveals his wife Joan died'quickly and painlessly' while in hospital for a back injury - as he says'life will never be the same' without his'shining star' The disgusting sex claims and'explicit videos' that allegedly expose World's Strongest Woman as'biological male' Human remains confirmed to be missing rodeo star, 25, who vanished in 2019 after argument with wife's family Calorie labels are a SHAM! Calorie labels on menus are pointless unless you're actively trying to lose weight, a study has found. Researchers have discovered that being told your beef pie is 1,362 calories or your cheeseburger is 2,133 calories makes no difference to what you order unless you're watching what you eat. It casts further doubt on the effectiveness of the government's policy, introduced in 2022, that ordered the use of calorie labels by all food outlets with more than 250 employees.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Your morning catch-up: Mayor Lurie has SF feeling better, California's job market is taking a hit and more big stories Why outrage is erupting over Trump plan to exclude nursing from'professional' designation This is read by an automated voice. Please report any issues or inconsistencies here . Trump administration proposes excluding nursing and other fields from "professional" designation, capping graduate student loans. Nursing leaders warn the policy will worsen California's severe nurse shortage by discouraging graduate degrees required for teaching and specialized patient care.

Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where a single algorithm can simultaneously attain $\mathcal{O}(\sqrt{T})$ regret for convex functions, $\mathcal{O}(d \log T)$ for exp-concave functions, and $\mathcal{O}(\log T)$ for strongly convex functions, where $T$ is the number of rounds and $d$ is the dimension of the feasible domain. However, these methods still lack problem-dependent adaptivity. In particular, no universal method provides regret bounds that scale with the gradient variation $V_T$, a key quantity that plays a crucial role in applications such as stochastic optimization and fast-rate convergence in games. In this work, we introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman. Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $\mathcal{O}(\log V_T)$ regret for strongly convex functions and $\mathcal{O}(d \log V_T)$ regret for exp-concave functions. For convex functions, the regret bounds differ: UniGrad.Correct achieves an $\mathcal{O}(\sqrt{V_T \log V_T})$ bound while preserving the RVU property that is crucial for fast convergence in online games, whereas UniGrad.Bregman achieves the optimal $\mathcal{O}(\sqrt{V_T})$ regret bound through a novel design. Both methods employ a meta algorithm with $\mathcal{O}(\log T)$ base learners, which naturally requires $\mathcal{O}(\log T)$ gradient queries per round. To enhance computational efficiency, we introduce UniGrad++, which retains the regret while reducing the gradient query to just $1$ per round via surrogate optimization. We further provide various implications.

Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning constrained by this unavailability an active area of research. Existing techniques typically require gradients or ground-truth labels, rendering them infeasible in settings with limited computational resources. In this work, we investigate the fundamental question of identifying components that are critical to the model's predictive performance, without access to either gradients or the loss function, and with only distributional access such as synthetic data. We theoretically demonstrate that the global reconstruction error is linearly bounded by local reconstruction errors for Lipschitz-continuous networks such as CNNs and well-trained Transformers (which, contrary to existing literature, we find exhibit Lipschitz continuity). This motivates using the locally reconstructive behavior of component subsets to quantify their global importance, via a metric that we term Subset Fidelity. In the uncorrelated features setting, selecting individual components via their Subset Fidelity scores is optimal, which we use to propose ModHiFi, an algorithm for model modification that requires no training data or loss function access. ModHiFi-P, for structured pruning, achieves an 11% speedup over the current state of the art on ImageNet models and competitive performance on language models. ModHiFi-U, for classwise unlearning, achieves complete unlearning on CIFAR-10 without fine-tuning and demonstrates competitive performance on Swin Transformers.

Abstract--Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail classes. Recent efforts have leveraged pre-trained vision-language models, such as CLIP, alongside long-tailed learning techniques to exploit rich visual-textual priors for improved performance. However, existing methods often derive semantic inter-class relationships directly from imbalanced datasets, resulting in unreliable correlations for tail classes due to data scarcity . Moreover, CLIP's zero-shot paradigm is optimized for single-label image-text matching, making it suboptimal for multi-label tasks. The framework incorporates a graph convolutional network for label-aware propagation and learnable soft prompts for refined embeddings. Moreover, it improves generalization through test-time ensembling and realigns visual-textual modalities using parameter-efficient fine-tuning to avert overfitting on tail classes without compromising head class performance. Recent progress in long-tailed visual recognition has mainly centered on the single-label multi-class setting. However, real-world images often encompass multiple objects and concepts, giving rise to long-tailed multi-label visual recognition (LTML), where each image is associated with multiple labels exhibiting long-tailed distributions [5], [6], [7], [8], [9], [10]. LTML introduces additional intricacies compared to its single-label multi-class counterpart, including label co-occurrences, which create interdependencies among classes, and intra-class imbalances between positive and negative instances. Existing LTML methods have primarily relied on strategies like class re-sampling, loss re-weighting, and specialized architectures, typically built upon ImageNet-pre-trained convolutional neural networks (CNNs) as backbones [5], [6], [7]. Wei Tang is with the School of Computer Science and Engineering, Southeast University, Nanjing 210096, China, the Key Laboratory of Computer Network and Information Integration (Southeast University), MoE, China, and with the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE (e-mail: tangw@seu.edu.cn).

The rapid proliferation of Large Language Models (LLMs) has revolutionized AI-assisted code generation. This rapid development of LLMs has outpaced our ability to properly benchmark them. Prevailing benchmarks emphasize unit-test pass rates and syntactic correctness. Such metrics understate the difficulty of many real-world problems that require planning, optimization, and strategic interaction. We introduce a multi-agent reasoning-driven benchmark based on a real-world logistics optimization problem (Auction, Pickup, and Delivery Problem) that couples competitive auctions with capacity-constrained routing. The benchmark requires building agents that can (i) bid strategically under uncertainty and (ii) optimize planners that deliver tasks while maximizing profit. We evaluate 40 LLM-coded agents (by a wide range of state-of-the-art LLMs under multiple prompting methodologies, including vibe coding) against 17 human-coded agents developed before the advent of LLMs. Our results over 12 double all-play-all tournaments and $\sim 40$k matches demonstrate (i) a clear superiority of human(graduate students)-coded agents: the top 5 spots are consistently won by human-coded agents, (ii) the majority of LLM-coded agents (33 out of 40) are beaten by very simple baselines, and (iii) given the best human solution as an input and prompted to improve upon, the best performing LLM makes the solution significantly worse instead of improving it. Our results highlight a gap in LLMs' ability to produce code that works competitively in the real-world, and motivate new evaluations that emphasize reasoning-driven code synthesis in real-world scenarios.