Abstract--The Tsetlin Machine (TM) is a novel machine learning paradigm that employs finite-state automata for learning and utilizes propositional logic to represent patterns. Due to its simplistic approach, TMs are inherently more interpretable than learning algorithms based on Neural Networks. The Con-volutional TM has shown comparable performance on various datasets such as MNIST, K-MNIST, F-MNIST and CIF AR-2. In this paper, we explore the applicability of the TM architecture for large-scale multi-channel (RGB) image classification. We propose a methodology to generate both local interpretations and global class representations. The local interpretations can be used to explain the model predictions while the global class representations aggregate important patterns for each class. These interpretations summarize the knowledge captured by the convolutional clauses, which can be visualized as images. We evaluate our methods on MNIST and CelebA datasets, using models that achieve 98.5% accuracy on MNIST and 86.56% F1-score on CelebA (compared to 88.07% for ResNet50) respectively. We show that the TM performs competitively to this deep learning model while maintaining its interpretability, even in large-scale complex training environments.

Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained generation fall along a spectrum: greedy constrained decoding methods enforce validity during decoding but distort the LM's distribution, while rejection sampling (RS) preserves fidelity but wastes computation by discarding invalid outputs. Both extremes are problematic in domains such as program fuzzing, where both validity and diversity of samples are essential. We present Constrained Adaptive Rejection Sampling (CARS), an approach that strictly improves the sample-efficiency of RS without distributional distortion. CARS begins with unconstrained LM sampling and adaptively rules out constraint-violating continuations by recording them in a trie and subtracting their probability mass from future draws. This adaptive pruning ensures that prefixes proven invalid are never revisited, acceptance rates improve monotonically, and the resulting samples exactly follow the constrained distribution. In experiments on a variety of domains -- e.g., program fuzzing and molecular generation -- CARS consistently achieves higher efficiency -- measured in the number of LM forward passes per valid sample -- while also producing stronger sample diversity than both GCD and methods that approximate the LM's distribution.

Personalized Head-Related Transfer Functions (HRTFs) are starting to be introduced in many commercial immersive audio applications and are crucial for realistic spatial audio rendering. However, one of the main hesitations regarding their introduction is that creating personalized HRTFs is impractical at scale due to the complexities of the HRTF measurement process. To mitigate this drawback, HRTF spatial upsampling has been proposed with the aim of reducing measurements required. While prior work has seen success with different machine learning (ML) approaches, these models often struggle with long-range spatial consistency and generalization at high upsampling factors. In this paper, we propose a novel transformer-based architecture for HRTF upsampling, leveraging the attention mechanism to better capture spatial correlations across the HRTF sphere. Working in the spherical harmonic (SH) domain, our model learns to reconstruct high-resolution HRTFs from sparse input measurements with significantly improved accuracy. To enhance spatial coherence, we introduce a neighbor dissimilarity loss that promotes magnitude smoothness, yielding more realistic upsampling. We evaluate our method using both perceptual localization models and objective spectral distortion metrics. Experiments show that our model surpasses leading methods by a substantial margin in generating realistic, high-fidelity HRTFs.

The energy consumption and carbon footprint of Artificial Intelligence (AI) have become critical concerns due to rising costs and environmental impacts. In response, a new trend in green AI is emerging, shifting from the "bigger is better" paradigm, which prioritizes large models, to "small is sufficient", emphasizing energy sobriety through smaller, more efficient models. We explore how the AI community can adopt energy sobriety today by focusing on model selection during inference. Model selection consists of choosing the most appropriate model for a given task, a simple and readily applicable method, unlike approaches requiring new hardware or architectures. Our hypothesis is that, as in many industrial activities, marginal utility gains decrease with increasing model size. Thus, applying model selection can significantly reduce energy consumption while maintaining good utility for AI inference. We conduct a systematic study of AI tasks, analyzing their popularity, model size, and efficiency. We examine how the maturity of different tasks and model adoption patterns impact the achievable energy savings, ranging from 1% to 98% for different tasks. Our estimates indicate that applying model selection could reduce AI energy consumption by 27.8%, saving 31.9 TWh worldwide in 2025 - equivalent to the annual output of five nuclear power reactors.

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce REPAIR (Robust Editing via Progressive Adaptive Intervention and Reintegration), a lifelong editing framework designed to support precise and low-cost model updates while preserving non-target knowledge. REPAIR mitigates the instability and conflicts of large-scale sequential edits through a closed-loop feedback mechanism coupled with dynamic memory management. Furthermore, by incorporating frequent knowledge fusion and enforcing strong locality guards, REPAIR effectively addresses the shortcomings of traditional distribution-agnostic approaches that often overlook unintended ripple effects. Our experiments demonstrate that REPAIR boosts editing accuracy by 10%-30% across multiple model families and significantly reduces knowledge forgetting. This work introduces a robust framework for developing reliable, scalable, and continually evolving LLMs.

This paper leverages microscaling floating-point formats, a novel technique designed to address these challenges by reducing the storage and computational overhead associated with numerical representations in LLMs. Unlike traditional floating-point representations that allocate a dedicated scale for each value, microscaling employs a shared scale across a block of values, enabling compact one-byte floating-point representations while maintaining an extended dynamic range. We explore the application of microscaling in the context of 8-bit floating-point formats to significantly reduce memory footprint and computational costs. We tested several configurations of microscaling floats within the GPT -2 LLM architecture, demonstrating that microscaling data formats can achieve competitive accuracy during training and inference, proving its efficacy as a resource-efficient alternative for deploying LLMs at scale. The source code is publicly available at: https://github.com/

We reframe and operationalise adversarial inverse reinforcement learning (IRL) to large language model reasoning, learning a dense, token-level reward model for process supervision directly from expert demonstrations rather than imitating style via supervised fine-tuning. The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets. We demonstrate that our approach prioritises correctness over surface form, yielding scores that correlate with eventual answer validity and enabling interpretable localisation of errors within a trace. Empirically, on GSM8K with Llama3 and Qwen2.5 backbones, we demonstrate: (i) dense reasoning rewards can be used as a learning signal to elicit reasoning, and (ii) predictive performance is improved from reward-guided reranking (notably for Llama-based policies). By unifying training signals, inference-time selection, and token-level diagnostics into a single reasoning reward, this work suggests reusable process-level rewards with broad potential to enhance multi-step reasoning in language models.

Symmetry is widely applied in problems such as the design of equivariant networks and the discovery of governing equations, but in complex scenarios, it is not known in advance. Most previous symmetry discovery methods are limited to linear symmetries, and recent attempts to discover nonlinear symmetries fail to explicitly get the Lie algebra subspace. In this paper, we propose LieNLSD, which is, to our knowledge, the first method capable of determining the number of infinitesimal generators with nonlinear terms and their explicit expressions. We specify a function library for the infinitesimal group action and aim to solve for its coefficient matrix, proving that its prolongation formula for differential equations, which governs dynamic data, is also linear with respect to the coefficient matrix. By substituting the central differences of the data and the Jacobian matrix of the trained neural network into the infinitesimal criterion, we get a system of linear equations for the coefficient matrix, which can then be solved using SVD. On top quark tagging and a series of dynamic systems, LieNLSD shows qualitative advantages over existing methods and improves the long rollout accuracy of neural PDE solvers by over 20% while applying to guide data augmentation. Code and data are available at https://github.com/hulx2002/LieNLSD.

The field of AutoML has made remarkable progress in post-hoc model selection, with libraries capable of automatically identifying the most performing models for a given dataset. Nevertheless, these methods often rely on exhaustive hyperparameter searches, where methods automatically train and test different types of models on the target dataset. Contrastingly, pre-hoc prediction emerges as a promising alternative, capable of bypassing exhaustive search through intelligent pre-selection of models. Despite its potential, pre-hoc prediction remains under-explored in the literature. This paper explores the intersection of AutoML and pre-hoc model selection by leveraging traditional models and Large Language Model (LLM) agents to reduce the search space of AutoML libraries. By relying on dataset descriptions and statistical information, we reduce the AutoML search space. Our methodology is applied to the AWS AutoGluon portfolio dataset, a state-of-the-art AutoML benchmark containing 175 tabular classification datasets available on OpenML. The proposed approach offers a shift in AutoML workflows, significantly reducing computational overhead, while still selecting the best model for the given dataset.

Large language models (LLMs) have demonstrated remarkable reasoning abilities in complex tasks, often relying on Chain-of-Thought (CoT) reasoning. However, due to their autoregressive token-level generation, the reasoning process is largely constrained to local decision-making and lacks global planning. This limitation frequently results in redundant, incoherent, or inaccurate reasoning, which significantly degrades overall performance. Existing approaches, such as tree-based algorithms and reinforcement learning (RL), attempt to address this issue but suffer from high computational costs and often fail to produce optimal reasoning trajectories. To tackle this challenge, we propose Plan-Then-Action Enhanced Reasoning with Group Relative Policy Optimization PTA-GRPO, a two-stage framework designed to improve both high-level planning and fine-grained CoT reasoning. In the first stage, we leverage advanced LLMs to distill CoT into compact high-level guidance, which is then used for supervised fine-tuning (SFT). In the second stage, we introduce a guidance-aware RL method that jointly optimizes the final output and the quality of high-level guidance, thereby enhancing reasoning effectiveness. We conduct extensive experiments on multiple mathematical reasoning benchmarks, including MATH, AIME2024, AIME2025, and AMC, across diverse base models such as Qwen2.5-7B-Instruct, Qwen3-8B, Qwen3-14B, and LLaMA3.2-3B. Experimental results demonstrate that PTA-GRPO consistently achieves stable and significant improvements across different models and tasks, validating its effectiveness and generalization.