arXiv subjects

Aleksandar Fontana

Publications and source records attributed to Aleksandar Fontana.

5 recordsLinked to original sources

arXiv2026

DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling

Language generation research increasingly spans three paradigms: autoregressive decoding, discrete masked diffusion, and continuous flow-matching. Comparing them is difficult because each lives in a separate codebase, so measured differences often reflect implementation details rather than the paradigms themselves. We present DantinoX, an open-source JAX/Flax library in which a single modular Transformer backbone serves all three paradigms. Switching the generation paradigm, attention mechanism, or hardware topology requires only a configuration change, while the backbone architecture, tokenizer, initialization strategy, and training infrastructure remain consistent. This enables controlled cross-paradigm comparisons within one API for training, streaming inference, and benchmarking.

cs.CL↗

arXiv2026

On the Hidden Objective Biases of Group-based Reinforcement Learning

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward optimization and the underlying training objective. In this paper, we present a theoretical analysis of GRPO style methods by studying them within a unified surrogate formulation. This perspective reveals recurring properties that affect all the methods under analysis: (i) non-uniform group weighting induces systematic gradient biases on shared prefix tokens; (ii) interactions with the AdamW optimizer make training dynamics largely insensitive to reward scaling; and (iii) optimizer momentum can push policy updates beyond the intended clipping region under repeated optimization steps. We believe that these findings highlight fundamental limitations of current approaches and provide principled guidance for the design of future formulations.

cs.LG↗

arXiv2025

GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and analyze two main GRPO issues: (i) the token-level penalization, where valuable tokens shared across different responses receive contradictory feedback signals, leading to conflicting gradient updates that can reduce their likelihood; and (ii) the policy collapse, where negatively rewarded completions may penalize confident responses and shift model decisions toward unlikely tokens, destabilizing training process. To address these issues we introduce GTPO (Group-relative Trajectory-based Policy Optimization), which prevents conflicting gradients on valuable tokens by skipping negative updates while amplifying positive ones and filters out completions whose entropy exceeds a provable threshold, to prevent policy collapse. Unlike GRPO, GTPO does not rely on KL-divergence regularization, eliminating the need for a reference model during training, while still ensuring greater training stability and improved performance, as validated through multiple experiments on GSM8K, MATH, AIME 2024, AIME 2025 and AMC 2023.

cs.LG↗

arXiv2025

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence

TITAN (Threat Intelligence Through Automated Navigation) is a framework that connects natural-language cyber threat queries with executable reasoning over a structured knowledge graph. It integrates a path planner model, which predicts logical relation chains from text, and a graph executor that traverses the TITAN Ontology to retrieve factual answers and supporting evidence. Unlike traditional retrieval systems, TITAN operates on a typed, bidirectional graph derived from MITRE, allowing reasoning to move clearly and reversibly between threats, behaviors, and defenses. To support training and evaluation, we introduce the TITAN Dataset, a corpus of 88209 examples (Train: 74258; Test: 13951) pairing natural language questions with executable reasoning paths and step by step Chain of Thought explanations. Empirical evaluations show that TITAN enables models to generate syntactically valid and semantically coherent reasoning paths that can be deterministically executed on the underlying graph.

cs.AI↗

arXiv2025

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an extensive study aimed at advancing recent RL-based finetuning techniques for LLMs in the context of vulnerability detection. We start by highlighting key limitations of commonly adopted LLMs, such as their tendency to over-predict certain types of vulnerabilities while failing to detect others. To address this challenge, we explore the use of Group Relative Policy Optimization (GRPO), a recent policy-gradient method, for guiding LLM behavior through structured, rule-based rewards. We enable its application to the vulnerability detection task by redefining its advantage functions and reward signals using annotations from widely used datasets in the field, including BigVul, DiverseVul, and CleanVul. The proposed methodology enables an extensive set of experiments, addressing multiple research questions regarding the impact of GRPO on generalization, reasoning capabilities, and performance improvements over standard supervised finetuning (SFT). Our findings offer valuable insights into the potential of RL-based training to enhance both the performance and reasoning abilities of LLMs in the context of software vulnerability detection.

cs.CR↗