Abstract Tools for automatic wood species identification are needed worldwide in order to support sustainable timber trade. This work explores the application of computer vision techniques to classify high-resolution macroscopic images of timber. The main challenge of this problem is that fine-grained patterns in timber are crucial in order to accurately identify wood species, and these patterns are not learned by convolutional neural networks (CNNs) trained on low resolution images. This work introduces the Timber Deep Learning Identification with Patch-based Inference Voting methodology, abbreviated TDLI-PIV methodology. This methodology exploits the concept of patching and the availability of high-resolution macroscopic images of timber in order to overcome the inherent challenges that CNNs face in timber identification. The TDLI-PIV methodology is able to capture fine-grained patterns in timber and, moreover, boosts robustness and prediction accuracy via a collaborative voting inference process. In this work we also introduce a new data set of marcroscopic images of timber, called GOIMAI-Phase-I, which has been obtained using optical magnification, and is openly published online in zenodo. Our experiments have assessed the performance of the TDLI-PIV methodology, including a comparison with other methodologies available in the literature, an exploration of data augmentation methods and the effect that the dataset size has on the accuracy of TDLI-PIV.

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues, hallucinations, and jailbreak vulnerabilities. Jailbreaking refers to the crafting of prompts that bypass alignment safeguards, leading to unsafe outputs that compromise the integrity of LLMs. This work specifically focuses on the challenge of jailbreak vulnerabilities and introduces a novel taxonomy of jailbreak attacks grounded in the training domains of LLMs. It characterizes alignment failures as arising from gaps in generalization, objectives, and robustness. Our primary contribution is a perspective on jailbreak, framed through the different linguistic domains that emerge during LLM training and alignment. This viewpoint highlights the limitations of existing approaches and enables us to classify jailbreak attacks in terms of the underlying model deficiencies they exploit. Unlike conventional classifications that categorize attacks based on prompt construction methods (e.g., prompt templating), our approach provides a deeper understanding of LLM behavior. We introduce a taxonomy with four categories—mismatched generalization, competing objectives, adversarial robustness, and mixed attacks— offering insights into the fundamental nature of jailbreak vulnerabilities. Finally, we present key lessons derived from this taxonomic study. • We perform an analysis on why aligned Large Language Models (LLMs) are vulnerable to jailbreaking attacks. These attacks allows an user to generate answers against the policies of a LLM company. The analysis is done from a domain perspective, where we distinguish different training domain regions. This analysis is based and extended from the Jailbroken hypothesis, a paper published at the NeurIPS conference. • Based on the previous analysis, we propose a taxonomy to classify LLMs jailbreaking attacks. Three main types of attacks are distinguished, namely mismatched generalization, competing objectives and adversarial robustness. We further categorize these types of attacks into subgroups. • We extensively review the LLM jailbreaking literature to support our taxonomy, classifying them into each of the categories we propose.

Transformers have emerged as a highly effective architecture for natural language processing and computer vision. Of late, there has been a surge in initiatives aimed at refining this architecture to enhance its applicability to long sequence time-series forecasting, yielding promising outcomes.This paper introduces Local Attention, an efficient attention mechanism tailored for time series data. This mechanism exploits the continuity properties of time series and the principle of locality in order to compute less attention scores. We provide an Θ(n log n) algorithm to implement Local Attention based on tensor algebra results, which contrasts to the Θ(n2) time and memory complexity of the original attention mechanism.Our experimental analysis shows that the vanilla transformer with Local Attention outperforms state of the art models based on probabilistic attention mechanisms. These findings affirm the effectiveness of our approach and outline a spectrum of future challenges in long sequence time series forecasting.

Significant advancements in the field of wood species recognition are needed worldwide to support sustainable timber trade. In this work we contribute to automate the identification of wood species using machine learning techniques and high-resolution macroscopic images of timber. The main challenge of this problem is that fine-grained patterns in timber are crucial in order to accurately identify wood species, and these patterns are not properly learned by traditional convolutional neural networks (CNNs) trained on low/medium resolution images.To this end, in the context of funded project GoIMAI, we have collected a Wood Species dataset to cover 37 wood species. Most of them CITES-listed and some similar species of the same genera. We propose a patch-based classification with a voting mechanism that overcomes the inherent challenges that CNNs face in timber identification. Our method is able to capture finegrained patterns in timber and boost robustness and prediction accuracy of the model. Our experiments have assessed the performance of the method, involving the comparison of several model architectures proposed in the literature, the analysis of the parameters of our proposed methodology, and the exploration of data augmentation methods.

Abstract. We give a nearly linear-time algorithm to approximately sample satisfying assignments in the random [Formula: see text]-SAT model when the density of the formula scales exponentially with [Formula: see text]. The best previously known sampling algorithm for the random [Formula: see text]-SAT model applies when the density [Formula: see text] of the formula is less than [Formula: see text] and runs in time [Formula: see text] [Galanis et al., SIAM J. Comput., 50 (2021), pp. 1701–1738]. Here [Formula: see text] is the number of variables and [Formula: see text] is the number of clauses. Our algorithm achieves a significantly faster running time of [Formula: see text] and samples satisfying assignments up to density [Formula: see text]. The main challenge in our setting is the presence of many variables with unbounded degree, which causes significant correlations within the formula and impedes the application of relevant Markov chain methods from the bounded-degree setting [Feng et al., J. ACM, 68 (2021) 40; Jain, Pham, and Vuong, On the Sampling Lovász Local Lemma for Atomic Constraint Satisfaction Problems, 2021]. Our main technical contribution is a [Formula: see text] bound of the sum of influences in the [Formula: see text]-SAT model which turns out to be robust against the presence of high-degree variables. This allows us to apply the spectral independence framework and obtain fast mixing results of a uniform-block Glauber dynamics on a carefully selected subset of the variables. The final key ingredient in our method is to take advantage of the sparsity of logarithmic-sized connected sets and the expansion properties of the random formula, and establish relevant connectivity properties of the set of satisfying assignments that enable the fast simulation of this Glauber dynamics. Our results also allow us to conclude that, with high probability, a random [Formula: see text]-CNF formula with density at most [Formula: see text] has a giant component of solutions that are connected in a graph where solutions are adjacent if they have Hamming distance [Formula: see text]. We are also able to deduce looseness results for random [Formula: see text]-CNFs in the same regime.

Abstract We study the complexity of approximating the partition function of the q-state Potts model and the closely related Tutte polynomial for complex values of the underlying parameters. Apart from the classical connections with quantum computing and phase transitions in statistical physics, recent work in approximate counting has shown that the behaviour in the complex plane, and more precisely the location of zeros, is strongly connected with the complexity of the approximation problem, even for positive real-valued parameters. Previous work in the complex plane by Goldberg and Guo focused on q = 2, which corresponds to the case of the Ising model; for q > 2, the behaviour in the complex plane is not as well understood and most work applies only to the real-valued Tutte plane. Our main result is a complete classification of the complexity of the approximation problems for all non-real values of the parameters, by establishing #P-hardness results that apply even when restricted to planar graphs. Our techniques apply to all q $$\geq$$ ≥ 2 and further complement/refine previous results both for the Ising model and the Tutte plane, answering in particular a question raised by Bordewich, Freedman, Lovász and Welsh in the context of quantum computations.

We study the complexity of approximating the partition function $Z_{\mathrm{Ising}}(G; \beta)$ of the Ising model in terms of the relation between the edge interaction $\beta$ and a parameter $\Delta$ which is an upper bound on the maximum degree of the input graph $G$. Following recent trends in both statistical physics and algorithmic research, we allow the edge interaction $\beta$ to be any complex number. Many recent partition function results focus on complex parameters, both because of physical relevance and because of the key role of the complex case in delineating the tractability/intractability phase transition of the approximation problem. In this work we establish both new tractability results and new intractability results. Our tractability results show that $Z_{\mathrm{Ising}}(-; \beta)$ has an FPTAS when $\lvert \beta - 1 \rvert / \lvert \beta + 1 \rvert < \tan(\pi / (4 \Delta - 4))$. The core of the proof is showing that there are no inputs $G$ that make the partition function $0$ when $\beta$ is in this range. Our result significantly extends the known zero-free region of the Ising model (and hence the known approximation results). Our intractability results show that it is $\mathrm{\#P}$-hard to multiplicatively approximate the norm and to additively approximate the argument of $Z_{\mathrm{Ising}}(-; \beta)$ when $\beta \in \mathbb{C}$ is an algebraic number such that $\beta \not \in \mathbb{R} \cup \{i, -i\}$ and $\lvert \beta - 1\rvert / \lvert \beta + 1 \rvert > 1 / \sqrt{\Delta - 1}$. These are the first results to show intractability of approximating $Z_{\mathrm{Ising}}(-, \beta)$ on bounded degree graphs with complex $\beta$. Moreover, we demonstrate situations in which zeros of the partition function imply hardness of approximation in the Ising model.

We study the complexity of approximating the partition function of the q-state Potts model and the closely related Tutte polynomial for complex values of the underlying parameters. Apart from the classical connections with quantum computing and phase transitions in statistical physics, recent work in approximate counting has shown that the behaviour in the complex plane, and more precisely the location of zeros, is strongly connected with the complexity of the approximation problem, even for positive real-valued parameters. Previous work in the complex plane by Goldberg and Guo focused on q = 2, which corresponds to the case of the Ising model; for q > 2, the behaviour in the complex plane is not as well understood and most work applies only to the real-valued Tutte plane. Our main result is a complete classification of the complexity of the approximation problems for all non-real values of the parameters, by establishing #P-hardness results that apply even when restricted to planar graphs. Our techniques apply to all q ≥ 2 and further complement/refine previous results both for the Ising model and the Tutte plane, answering in particular a question raised by Bordewich, Freedman, Lovász and Welsh in the context of quantum computations.