This paper addresses the problem of text classification models being vulnerable and lacking robustness under adversarial perturbations by proposing a robust text classification method based on large language model calibration. The method builds on a pretrained language model and constructs a multi-stage framework for semantic representation and confidence regulation. It achieves stable optimization of classification results through semantic embedding extraction, calibration adjustment, and consistency constraints. First, the model uses a pretrained encoder to generate context-aware semantic features and […]

Ver mais

Numbers such as π, e, log 2 or √2 have binary digits (bits) that look randomly distributed. They are very good candidates to generate randomness especially in cryptography. One way to assess their randomness is by proving that they are normal numbers. Such a proof has remained elusive for centuries. Here I focus on a different type of numbers that seem a lot easier to handle, such as (2π)-1 arccos(3/5). To test normality, the most well-known tool is […]

Ver mais

We often hear that “neurons” in DNNs are just a loose analogy for biological neurons. The consensus seems to be that while abstract ideas (like hierarchies) match, the actual architectures are fundamentally different, largely because biological mechanisms are seen as either computationally expensive or incompatible with current silicon hardware. However, as I’ve recently begun bridging the gap between my PhD in applied math and a BS in Neuroscience, I’ve started to question if we are moving away from […]

Ver mais

Knowledge graph completion via link prediction is critical for intelligent equipment maintenance systems to support accurate fault diagnosis and maintenance decision-making. However, existing approaches struggle to simultaneously capture local structural dependencies and perform effective multi-hop reasoning, due to limited receptive fields or inefficient path exploration mechanisms. Traditional path-based methods implicitly assume path symmetry, treating all reasoning chains equally without considering their task-specific relevance. To address this issue, we propose a GAT-guided semantic path reasoning framework that breaks this […]

Ver mais

We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when learning multiple tasks sequentially. This method referred to as Group and Exclusive Sparsity based Continual Learning (GESCL) avoids forgetting of previous tasks by ensuring the stability of the CNN via a stability regularization term, which prevents filters detected as important for past tasks to deviate too much when learning a new […]

Ver mais

arXiv:2601.04261v1 Announce Type: new Abstract: The widespread adoption of Large Language Model (LLM) in commercial and research settings has intensified the need for robust intellectual property protection. Backdoor-based LLM fingerprinting has emerged as a promising solution for this challenge. In practical application, the low-cost multi-model collaborative technique, LLM ensemble, combines diverse LLMs to leverage their complementary strengths, garnering significant attention and practical adoption. Unfortunately, the vulnerability of existing LLM fingerprinting for the ensemble scenario is unexplored. In order […]

Ver mais

arXiv:2601.10814v1 Announce Type: new Abstract: Localization and mapping are core perceptual capabilities for underwater robots. Stereo cameras provide a low-cost means of directly estimating metric depth to support these tasks. However, despite recent advances in stereo depth estimation on land, computing depth from image pairs in underwater scenes remains challenging. In underwater environments, images are degraded by light attenuation, visual artifacts, and dynamic lighting conditions. Furthermore, real-world underwater scenes frequently lack rich texture useful for stereo depth estimation […]

Ver mais

Market Prediction Despite the recent backlash around WLFI, political memecoins connected to the Trump family are likely to be among the most impactful assets in the next 2-3 years. After years in the crypto industry, you start recognizing patterns not just in the token charts, but also in the behavior of traders and a broader global economy. Watching the current crypto market patterns, we can expect an interesting paradox emerging soon – crypto startups with no real utility […]

Ver mais

arXiv:2601.09773v1 Announce Type: new Abstract: Deploying deep neural networks (DNNs) on resource-constrained edge devices such as FPGAs requires a careful balance among latency, power, and hardware resource usage, while maintaining high accuracy. Existing Lookup Table (LUT)-based DNNs — such as LogicNets, PolyLUT, and NeuraLUT — face two critical challenges: the exponential growth of LUT size and inefficient random sparse connectivity. This paper presents SparseLUT, a comprehensive framework that addresses these challenges through two orthogonal optimizations. First, we propose […]

Ver mais