arXiv subjects

Marius Dragoi

Publications and source records attributed to Marius Dragoi.

6 recordsLinked to original sources

arXiv2026

TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed reference frame to learn a low-rank update applied to the singular value matrix. A soft spectral penalty discourages updates aligned with dominant singular directions, reducing interference while routing fine-grained adaptation into the highly flexible, long-tail spectral coordinates.

cs.LG↗

arXiv2026

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.

cs.LG↗

arXiv2026

Closing the gap on tabular data with Fourier and Implicit Categorical Features

While Deep Learning has demonstrated impressive results in applications on various data types, it continues to lag behind tree-based methods when applied to tabular data, often referred to as the last "unconquered castle" for neural networks. We hypothesize that a significant advantage of tree-based methods lies in their intrinsic capability to model and exploit non-linear interactions induced by features with categorical characteristics. In contrast, neural-based methods exhibit biases toward uniform numerical processing of features and smooth solutions, making it challenging for them to effectively leverage such patterns. We address this performance gap by using statistical-based feature processing techniques to identify features that are strongly correlated with the target once discretized. We further mitigate the bias of deep models for overly-smooth solutions, a bias that does not align with the inherent properties of the data, using Learned Fourier. We show that our proposed feature preprocessing significantly boosts the performance of deep learning models and enables them to achieve a performance that closely matches or surpasses XGBoost on a comprehensive tabular data benchmark.

cs.LG↗

arXiv2025

C-ing Clearly: Enhanced Binary Code Explanations using C code

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly, which leverages the corresponding C code to enhance an LLM's understanding of assembly. By fine-tuning on data generated through our method, we demonstrate improved LLM performance for binary code summarization and vulnerability detection. Our approach demonstrates consistent gains across different LLM families and model sizes.

cs.CL↗

arXiv2025

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm to improve Large Language Models on reasoning tasks such as coding, math or logic. To assess the reasoning boundary (the fraction of problems a model can solve) researchers often report Pass@k at large sampling budgets. Recent results reveal a crossover phenomenon: while RLVR models outperform the base model at small k values, the base model usually outperforms them when sampling a very large number of completions. This has been interpreted as evidence that base models have a larger reasoning boundary. We argue that on tasks with discrete answer spaces, such as math with numeric outputs, Pass@k at large k reflects the increasingly higher chance of success in the limit of the number of trials rather than genuine reasoning, and can therefore be misleading. We propose Cover@tau, which measures the fraction of problems that a model can solve for which at least a tau proportion of completions are correct. Unlike Pass@k, Cover@tau captures reasoning under an explicit reliability threshold: models that rely on random guessing degrade rapidly as tau increases. We evaluate several RLVR models using Cover@tau-based metrics and illustrate how the relative rankings of popular algorithms change compared to Pass@1, offering a different perspective on reasoning boundaries.

cs.AI↗

arXiv2023

AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection

Analyzing the distribution shift of data is a growing research direction in nowadays Machine Learning (ML), leading to emerging new benchmarks that focus on providing a suitable scenario for studying the generalization properties of ML models. The existing benchmarks are focused on supervised learning, and to the best of our knowledge, there is none for unsupervised learning. Therefore, we introduce an unsupervised anomaly detection benchmark with data that shifts over time, built over Kyoto-2006+, a traffic dataset for network intrusion detection. This type of data meets the premise of shifting the input distribution: it covers a large time span ($10$ years), with naturally occurring changes over time (eg users modifying their behavior patterns, and software updates). We first highlight the non-stationary nature of the data, using a basic per-feature analysis, t-SNE, and an Optimal Transport approach for measuring the overall distribution distances between years. Next, we propose AnoShift, a protocol splitting the data in IID, NEAR, and FAR testing splits. We validate the performance degradation over time with diverse models, ranging from classical approaches to deep learning. Finally, we show that by acknowledging the distribution shift problem and properly addressing it, the performance can be improved compared to the classical training which assumes independent and identically distributed data (on average, by up to $3\%$ for our approach). Dataset and code are available at https://github.com/bit-ml/AnoShift/.

cs.LG↗