Learning Progressions (LPs) can help adjust instruction to individual learners needs if the LPs reflect diverse ways of thinking about a construct being measured, and if the LP-aligned assessments meaningfully measure this diversity. The process of doing science is inherently multi-modal with scientists utilizing drawings, writing and other modalities to explain phenomena. Thus, fostering deep science understanding requires supporting students in using multiple modalities when explaining phenomena. We build on a validated NGSS-aligned multi-modal LP reflecting diverse ways of modeling and explaining electrostatic phenomena and associated assessments. We focus on students modeling, an essential practice for building a deep science understanding. Supporting culturally and linguistically diverse students in building modeling skills provides them with an alternative mode of communicating their understanding, essential for equitable science assessment. Machine learning (ML) has been used to score open-ended modeling tasks (e.g., drawings), and short text-based constructed scientific explanations, both of which are time-consuming to score. We use ML to evaluate LP-aligned scientific models and the accompanying short text-based explanations reflecting multi-modal understanding of electrical interactions in high school Physical Science. We show how LP guides the design of personalized ML-driven feedback grounded in the diversity of student thinking on both assessment modes.

The rapid adoption of LLM-based conversational systems is already transforming the landscape of educational technology. However, the current state-of-the-art learning models do not take into account the student's affective states. Multiple studies in educational psychology support the claim that positive or negative emotional states can impact a student's learning capabilities. To bridge this gap, we present MathBuddy, an emotionally aware LLM-powered Math Tutor, which dynamically models the student's emotions and maps them to relevant pedagogical strategies, making the tutor-student conversation a more empathetic one. The student's emotions are captured from the conversational text as well as from their facial expressions. The student's emotions are aggregated from both modalities to confidently prompt our LLM Tutor for an emotionally-aware response. We have evaluated our model using automatic evaluation metrics across eight pedagogical dimensions and user studies. We report a massive 23 point performance gain using the win rate and a 3 point gain at an overall level using DAMR scores which strongly supports our hypothesis of improving LLM-based tutor's pedagogical abilities by modeling students' emotions. Our dataset and code are available at: https://github.com/ITU-NLP/MathBuddy .

Empirical scaling laws have driven the evolution of large language models (LLMs), yet their coefficients shift whenever the model architecture or data pipeline changes. Mixture-of-Experts (MoE) models, now standard in state-of-the-art systems, introduce a new sparsity dimension that current dense-model frontiers overlook. We investigate how MoE sparsity influences two distinct capability regimes: memorization skills and reasoning skills. By training MoE families that vary total parameters, active parameters, and top-k routing under fixed compute budgets, we disentangle pre-training loss from downstream accuracy. Our results reveal two principles. First, Active FLOPs: models with identical training loss but greater active compute achieve higher reasoning accuracy. Second, T otal tokens per parameter (TPP): memorization tasks improve with more parameters, while reasoning tasks benefit from optimal TPP, indicating that reasoning is data-hungry. Neither reinforcement learning post-training (GRPO) nor increased test-time compute alters these trends. We therefore argue that optimal MoE sparsity must be determined jointly by active FLOPs and TPP, revising the classical picture of compute-optimal scaling. The recent evolution of large language models (LLMs) has been driven by empirical scaling laws (Hestness et al., 2017) that link training loss to model size, dataset size, and compute budget. Kaplan et al. (2020) showed that these laws hold across seven orders of magnitude, establishing them as a reliable extrapolation tool for dense Transformers. Subsequent work by Hoffmann et al. (2022) demonstrated that scaling curves can be inverted to choose the compute-optimal combination of parameters and tokens for a fixed budget. Together, these results have made scaling analysis a cornerstone of model planning at both academic and industrial labs.

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between DRO and current DL practices. Modern DL optimizers require adaptivity and the ability to handle stochastic gradients, as these methods demonstrate superior performance. Additionally, for practical applications, a method should allow weight assignment not only to individual samples, but also to groups of objects (for example, all samples of the same class). This paper aims to bridge this gap by introducing ALSO $\unicode{x2013}$ Adaptive Loss Scaling Optimizer $\unicode{x2013}$ an adaptive algorithm for a modified DRO objective that can handle weight assignment to sample groups. We prove the convergence of our proposed algorithm for non-convex objectives, which is the typical case for DL models. Empirical evaluation across diverse Deep Learning tasks, from Tabular DL to Split Learning tasks, demonstrates that ALSO outperforms both traditional optimizers and existing DRO methods.

Fast and reliable validation of novel designs in complex physical systems such as batteries is critical to accelerating technological innovation. However, battery research and development remain bottlenecked by the prohibitively high time and energy costs required to evaluate numerous new design candidates, particularly in battery prototyping and life testing. Despite recent progress in data-driven battery lifetime prediction, existing methods require labeled data of target designs to improve accuracy and cannot make reliable predictions until after prototyping, thus falling far short of the efficiency needed to enable rapid feedback for battery design. Here, we introduce Discovery Learning (DL), a scientific machine-learning paradigm that integrates active learning, physics-guided learning, and zero-shot learning into a human-like reasoning loop, drawing inspiration from learning theories in educational psychology. DL can learn from historical battery designs and actively reduce the need for prototyping, thus enabling rapid lifetime evaluation for unobserved material-design combinations without requiring additional data labeling. To test DL, we present 123 industrial-grade large-format lithium-ion pouch cells, spanning eight material-design combinations and diverse cycling protocols. Trained solely on public datasets of small-capacity cylindrical cells, DL achieves 7.2% test error in predicting the average cycle life under unknown device variability. This results in savings of 98% in time and 95% in energy compared to industrial practices. This work highlights the potential of uncovering insights from historical designs to inform and accelerate the development of next-generation battery technologies. DL represents a key advance toward efficient data-driven modeling and helps realize the promise of machine learning for accelerating scientific discovery and engineering innovation.

Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle inputs from unknown classes that a closed-set model would misclassify. Recent works address both issues by (i)~training multi-head models using the task-incremental learning framework, and (ii) predicting the task identity employing out-of-distribution (OOD) detectors. While effective, the latter mainly relies on joint training with a memory buffer of past data, raising concerns around privacy, scalability, and increased training time. In this paper, we present an in-depth analysis of post-hoc OOD detection methods and investigate their potential to eliminate the need for a memory buffer. We uncover that these methods, when applied appropriately at inference time, can serve as a strong substitute for buffer-based OOD detection. We show that this buffer-free approach achieves comparable or superior performance to buffer-based methods both in terms of class-incremental learning and the rejection of unknown samples. Experimental results on CIFAR-10, CIFAR-100 and Tiny ImageNet datasets support our findings, offering new insights into the design of efficient and privacy-preserving CIL systems for open-world settings.

Large reasoning models such as OpenAI o1 and DeepSeek-R1 have achieved remarkable performance in the domain of reasoning. A key component of their training is the incorporation of verifiable rewards within reinforcement learning (RL). However, existing reward benchmarks do not evaluate reference-based reward systems, leaving researchers with limited understanding of the accuracy of verifiers used in RL. In this paper, we introduce two benchmarks, VerifyBench and VerifyBench-Hard, designed to assess the performance of reference-based reward systems. These benchmarks are constructed through meticulous data collection and curation, followed by careful human annotation to ensure high quality. Current models still show considerable room for improvement on both VerifyBench and VerifyBench-Hard, especially smaller-scale models. Furthermore, we conduct a thorough and comprehensive analysis of evaluation results, offering insights for understanding and developing reference-based reward systems. Our proposed benchmarks serve as effective tools for guiding the development of verifier accuracy and the reasoning capabilities of models trained via RL in reasoning tasks.

Teachers' visual attention and its distribution across the students in classrooms can constitute important implications for student engagement, achievement, and professional teacher training. Despite that, inferring the information about where and which student teachers focus on is not trivial. Mobile eye tracking can provide vital help to solve this issue; however, the use of mobile eye tracking alone requires a significant amount of manual annotations. To address this limitation, we present an automated processing pipeline concept that requires minimal manually annotated data to recognize which student the teachers focus on. To this end, we utilize state-of-the-art face detection models and face recognition feature embeddings to train face recognition models with transfer learning in the classroom context and combine these models with the teachers' gaze from mobile eye trackers. We evaluated our approach with data collected from four different classrooms, and our results show that while it is possible to estimate the visually focused students with reasonable performance in all of our classroom setups, U-shaped and small classrooms led to the best results with accuracies of approximately 0.7 and 0.9, respectively. While we did not evaluate our method for teacher-student interactions and focused on the validity of the technical approach, as our methodology does not require a vast amount of manually annotated data and offers a non-intrusive way of handling teachers' visual attention, it could help improve instructional strategies, enhance classroom management, and provide feedback for professional teacher development.

When reading, we often have specific information that interests us in a text. For example, you might be reading this paper because you are curious about LLMs for eye movements in reading, the experimental design, or perhaps you wonder ``This sounds like science fiction. Does it actually work?''. More broadly, in daily life, people approach texts with any number of text-specific goals that guide their reading behavior. In this work, we ask, for the first time, whether open-ended reading goals can be automatically decoded solely from eye movements in reading. To address this question, we introduce goal decoding tasks and evaluation frameworks using large-scale eye tracking for reading data in English with hundreds of text-specific information seeking tasks. We develop and compare several discriminative and generative multimodal text and eye movements LLMs for these tasks. Our experiments show considerable success on the task of selecting the correct goal among several options, and even progress towards free-form textual reconstruction of the precise goal formulation. These results open the door for further scientific investigation of goal driven reading, as well as the development of educational and assistive technologies that will rely on real-time decoding of reader goals from their eye movements.

Large artificial intelligence (AI) models have garnered significant attention for their remarkable, often "superhuman", performance on standardized benchmarks. However, when these models are deployed in high-stakes verticals such as healthcare, education, and law, they often reveal notable limitations. For instance, they exhibit brittleness to minor variations in input data, present contextually uninformed decisions in critical settings, and undermine user trust by confidently producing or reproducing inaccuracies. These challenges in applying large models necessitate cross-disciplinary innovations to align the models' capabilities with the needs of real-world applications. We introduce a framework that addresses this gap through a layer-wise abstraction of innovations aimed at meeting users' requirements with large models. Through multiple case studies, we illustrate how researchers and practitioners across various fields can operationalize this framework. Beyond modularizing the pipeline of transforming large models into useful "vertical systems", we also highlight the dynamism that exists within different layers of the framework. Finally, we discuss how our framework can guide researchers and practitioners to (i) optimally situate their innovations (e.g., when vertical-specific insights can empower broadly impactful vertical-agnostic innovations), (ii) uncover overlooked opportunities (e.g., spotting recurring problems across verticals to develop practically useful foundation models instead of chasing benchmarks), and (iii) facilitate cross-disciplinary communication of critical challenges (e.g., enabling a shared vocabulary for AI developers, domain experts, and human-computer interaction scholars).