Direct Preference Optimization (DPO) is an effective approach for aligning protein language models with experimental design goals. However, DPO faces a scalability bottleneck: the number of possible training pairs grows quadratically with the number of labeled sequences, leading to prohibitive training times even for modestly sized datasets. We introduce g-DPO, a framework that (i) uses sequence space clustering to prune redundant pairs while preserving training signal, and (ii) amortizes likelihood computations with group-based approximations. Across three protein engineering tasks, g-DPO maintains in silico and in vitro performance that is statistically indistinguishable from standard DPO, while converging 1.7x to 5.4x times faster, with speedups that scale with dataset size and the structure of the underlying mutational landscape.

In humans and other animals, category learning enhances discrimination between stimuli close to the category boundary. This phenomenon, called categorical perception, was also empirically observed in artificial neural networks trained on classification tasks. In previous modeling works based on neuroscience data, we show that this expansion/compression is a necessary outcome of efficient learning. Here we extend our theoretical framework to artificial networks. We show that minimizing the Bayes cost (mean of the cross-entropy loss) implies maximizing the mutual information between the set of categories and the neural activities prior to the decision layer. Considering structured data with an underlying feature space of small dimension, we show that maximizing the mutual information implies (i) finding an appropriate projection space, and, (ii) building a neural representation with the appropriate metric. The latter is based on a Fisher information matrix measuring the sensitivity of the neural activity to changes in the projection space. Optimal learning makes this neural Fisher information follow a category-specific Fisher information, measuring the sensitivity of the category membership. Category learning thus induces an expansion of neural space near decision boundaries. We characterize the properties of the categorical Fisher information, showing that its eigenvectors give the most discriminant directions at each point of the projection space. We find that, unexpectedly, its maxima are in general not exactly at, but near, the class boundaries. Considering toy models and the MNIST dataset, we numerically illustrate how after learning the two Fisher information matrices match, and essentially align with the category boundaries. Finally, we relate our approach to the Information Bottleneck one, and we exhibit a bias-variance decomposition of the Bayes cost, of interest on its own.

Large Language Models (LLMs), such as ChatGPT, are increasingly leveraged for generating both traditional software code and spreadsheet logic. Despite their impressive generative capabilities, these models frequently exhibit critical issues such as hallucinations, subtle logical inconsistencies, and syntactic errors, risks particularly acute in high stakes domains like financial modelling and scientific computations, where accuracy and reliability are paramount. This position paper proposes a structured research framework that integrates the proven software engineering practice of Test-Driven Development (TDD) with Large Language Model (LLM) driven generation to enhance the correctness of, reliability of, and user confidence in generated outputs. We hypothesise that a "test first" methodology provides both technical constraints and cognitive scaffolding, guiding LLM outputs towards more accurate, verifiable, and comprehensible solutions. Our framework, applicable across diverse programming contexts, from spreadsheet formula generation to scripting languages such as Python and strongly typed languages like Rust, includes an explicitly outlined experimental design with clearly defined participant groups, evaluation metrics, and illustrative TDD based prompting examples. By emphasising test driven thinking, we aim to improve computational thinking, prompt engineering skills, and user engagement, particularly benefiting spreadsheet users who often lack formal programming training yet face serious consequences from logical errors. We invite collaboration to refine and empirically evaluate this approach, ultimately aiming to establish responsible and reliable LLM integration in both educational and professional development practices.

We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large population of homogeneous followers. The objective can be formulated as a structured bi-level optimization problem, in which the leader needs to learn a policy maximizing its reward, anticipating the response of the followers. Existing methods for solving these (and related) problems often rely on restrictive independence assumptions between the leader's and followers' objectives, use samples inefficiently due to nested-loop algorithm structure, and lack finite-time convergence guarantees. To address these limitations, we propose AC-SMFG, a single-loop actor-critic algorithm that operates on continuously generated Markovian samples. The algorithm alternates between (semi-)gradient updates for the leader, a representative follower, and the mean field, and is simple to implement in practice. We establish the finite-time and finite-sample convergence of the algorithm to a stationary point of the Stackelberg objective. To our knowledge, this is the first Stackelberg MFG algorithm with non-asymptotic convergence guarantees. Our key assumption is a "gradient alignment" condition, which requires that the full policy gradient of the leader can be approximated by a partial component of it, relaxing the existing leader-follower independence assumption. Simulation results in a range of well-established economics environments demonstrate that AC-SMFG outperforms existing multi-agent and MFG learning baselines in policy quality and convergence speed.

Efficient nutrient management is critical for crop growth and sustainable resource consumption (e.g., nitrogen, energy). Current approaches require lengthy analyses, preventing real-time optimization; similarly, imaging facilitates rapid phenotyping but can be computationally intensive, preventing deployment under resource constraints. This study proposes a flexible, tiered pipeline for anomaly detection and status estimation (fresh weight, dry mass, and tissue nutrients), including a comprehensive energy analysis of approaches that span the efficiency-accuracy spectrum. Using a nutrient depletion experiment with three treatments (T1-100%, T2-50%, and T3-25% fertilizer strength) and multispectral imaging (MSI), we developed a hierarchical pipeline using an autoencoder (AE) for early warning. Further, we compared two status estimation modules of different complexity for more detailed analysis: vegetation index (VI) features with machine learning (Random Forest, RF) and raw whole-image deep learning (Vision Transformer, ViT). Results demonstrated high-efficiency anomaly detection (73% net detection of T3 samples 9 days after transplanting) at substantially lower energy than embodied energy in wasted nitrogen. The state estimation modules show trade-offs, with ViT outperforming RF on phosphorus and calcium estimation (R2 0.61 vs. 0.58, 0.48 vs. 0.35) at higher energy cost. With our modular pipeline, this work opens opportunities for edge diagnostics and practical opportunities for agricultural sustainability.

News recommendation systems play a critical role in alleviating information overload by delivering personalized content. A key challenge lies in jointly modeling multi-view representations of news articles and capturing the dynamic, dual-scale nature of user interests-encompassing both short- and long-term preferences. Prior methods often rely on single-view features or insufficiently model user behavior across time. In this work, we introduce Co-NAML-LSTUR, a hybrid news recommendation framework that integrates NAML for attentive multi-view news encoding and LSTUR for hierarchical user modeling, designed for training on limited data resources. Our approach leverages BERT-based embeddings to enhance semantic representation. We evaluate Co-NAML-LSTUR on two widely used benchmarks, MIND-small and MIND-large. Results show that our model significantly outperforms strong baselines, achieving improvements over NRMS by 1.55% in AUC and 1.15% in MRR, and over NAML by 2.45% in AUC and 1.71% in MRR. These findings highlight the effectiveness of our efficiency-focused hybrid model, which combines multi-view news modeling with dual-scale user representations for practical, resource-limited resources rather than a claim to absolute state-of-the-art (SOTA). The implementation of our model is publicly available at https://github.com/MinhNguyenDS/Co-NAML-LSTUR

Understanding the plausible upper bounds of extreme weather events is essential for risk assessment in a warming climate. Existing methods, based on large ensembles of physics-based models, are often computationally expensive or lack the fidelity needed to simulate rare, high-impact extremes. Here, we present a novel framework that leverages a differentiable hybrid climate model, NeuralGCM, to optimize initial conditions and generate physically consistent worst-case heatwave trajectories. Applied to the 2021 Pacific Northwest heatwave, our method produces heatwave intensity up to 3.7 $^\circ$C above the most extreme member of a 75-member ensemble. These trajectories feature intensified atmospheric blocking and amplified Rossby wave patterns-hallmarks of severe heat events. Our results demonstrate that differentiable climate models can efficiently explore the upper tails of event likelihoods, providing a powerful new approach for constructing targeted storylines of extreme weather under climate change.

-- Type 1 Diabetes (T1D) affects millions worldwide, requiring continuous monitoring to prevent severe hypo-and hyperglycemic events. While continuous glucose monitoring has improved blood glucose management, deploying predictive models on wearable devices remains challenging due to computational and memory constraints. T o address this, we propose a novel Lightweight Sequential Transformer model designed for blood glucose prediction in T1D. The model is optimized for deployment on resource-constrained edge devices and incorporates a balanced loss function to handle the inherent data imbalance in hypo-and hyperglycemic events. Experiments on two benchmark datasets, OhioT1DM and DiaTrend, demonstrate that the proposed model outperforms state-of-the-art methods in predicting glucose levels and detecting adverse events. This work fills the gap between high-performance modeling and practical deployment, providing a reliable and efficient T1D management solution. Type 1 Diabetes (T1D) [1] is a chronic autoimmune condition requiring lifelong blood glucose concentration (BGC) monitoring to prevent life-threatening complications such as hypoglycemia (BGC below 70 mg/dL [2]) and hyperglycemia (BGC above 180 mg/dL [3]).

We study the problem of computing an optimal large language model (LLM) policy for the constrained alignment problem, where the goal is to maximize a primary reward objective while satisfying constraints on secondary utilities. Despite the popularity of Lagrangian-based LLM policy search in constrained alignment, iterative primal-dual methods often fail to converge, and non-iterative dual-based methods do not achieve optimality in the LLM parameter space. To address these challenges, we employ Lagrangian duality to develop an iterative dual-based alignment method that alternates between updating the LLM policy via Lagrangian maximization and updating the dual variable via dual descent. In theory, we characterize the primal-dual gap between the primal value in the distribution space and the dual value in the LLM parameter space. We further quantify the optimality gap of the learned LLM policies at near-optimal dual variables with respect to both the objective and the constraint functions. These results prove that dual-based alignment methods can find an optimal constrained LLM policy, up to an LLM parametrization gap. We demonstrate the effectiveness and merits of our approach through extensive experiments conducted on the PKU-SafeRLHF and Anthropic HH-RLHF datasets.

Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments. While navigation has been well-explored, physically meaningful interactions that mimic real-world forces remain largely understudied. In this work, we investigate using physical forces as a control signal for video generation and propose force prompts which enable users to interact with images through both localized point forces, such as poking a plant, and global wind force fields, such as wind blowing on fabric. We demonstrate that these force prompts can enable videos to respond realistically to physical control signals by leveraging the visual and motion prior in the original pretrained model, without using any 3D asset or physics simulator at inference. The primary challenge of force prompting is the difficulty in obtaining high quality paired force-video training data, both in the real world due to the difficulty of obtaining force signals, and in synthetic data due to limitations in the visual quality and domain diversity of physics simulators. Our key finding is that video generation models can generalize remarkably well when adapted to follow physical force conditioning from videos synthesized by Blender, even with limited demonstrations of few objects. Our method can generate videos which simulate forces across diverse geometries, settings, and materials. We also try to understand the source of this generalization and perform ablations that reveal two key elements: visual diversity and the use of specific text keywords during training. Our approach is trained on only around 15k training examples for a single day on four A100 GPUs, and outperforms existing methods on force adherence and physics realism, bringing world models closer to real-world physics interactions. We release all datasets, code, weights, and interactive video demos at our project page.