Formal Sciences

100 papers

Every entry carries a structured overview and the reproduction evidence collected so far. A paper is listed here when it carries the category as its primary field or as a secondary classification. Both are shown on the paper page.

Latest in Formal Sciences

Showing 21–40 of 100

Apr 22, 2026Formal Sciences260423.0021

Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

Pascal Archambault, Houari Sahraoui, Eugene Syriani

This paper applies Generative Flow Networks (GFlowNets) to adapt digital twin models of natural systems by learning to sample simulator parameters proportional to their agreement with observations. The approach handles the fundamental challenge that sparse observations often leave multiple plausible parameter configurations, preserving uncertainty rather than finding a single optimal solution.

Apr 22, 2026Formal Sciences260423.0022

Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing

Abhijit Talluri

This paper provides a comprehensive structured analysis of adversarial robustness literature and introduces Auto-ART, an open-source framework that standardizes robustness evaluation across 50+ attacks, detects gradient masking, and maps compliance to regulatory frameworks. It addresses fragmentation in the field by combining meta-scientific synthesis with practical engineering tools.

Apr 22, 2026Formal Sciences260423.0023

MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment

Andor Vári-Kakas, Ji Won Park, Natasa Tagasovska

MGDA-Decoupled is a geometry-based multi-objective optimization algorithm for aligning LLMs that balances conflicting objectives like helpfulness and truthfulness without requiring reinforcement learning or explicit reward models. It operates within the Direct Preference Optimization framework and achieves higher win rates than existing methods by accounting for each objective's convergence dynamics.

Apr 22, 2026Formal Sciences260423.0024

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales

Samuel Salfati

This paper systematically studies transformer compression across GPT-2 and Mistral 7B, identifying five structural properties that explain why certain compression techniques fail, particularly showing that high-variance activations are not predictively important and that block-level approximations suffer from distribution shift. The findings suggest fundamental limits to static compression and motivate adaptive, per-token approaches instead.

Apr 22, 2026Formal Sciences260423.0025

Improving clinical interpretability of linear neuroimaging models through feature whitening

Sara Petiton, Antoine Grigis, Raphaël Vock, Edouard Duchesnay

This paper proposes a feature whitening approach that decorrelates anatomically grouped brain regions to improve the interpretability of linear neuroimaging models while maintaining predictive performance. The method helps disentangle overlapping information across correlated brain measures, making model weights more clinically meaningful for identifying biomarkers in psychiatric disorders.

Apr 22, 2026Formal Sciences260423.0026

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Jingyi Wang, Lei Zhu, Tengjin Weng, Song-Li Wu +7 more

This paper introduces GRPO-VPS, which enhances Group Relative Policy Optimization by adding verifiable process supervision that tracks the model's confidence in correct answers throughout reasoning steps. This enables more targeted credit assignment and sample-efficient policy updates without requiring critic models or auxiliary supervision.

Apr 22, 2026Formal Sciences260423.0027

A weighted angle distance on strings

Grant Molnar

The paper introduces a multi-scale metric for strings that combines angle distances between n-gram count vectors at different scales using exponential weights. It provides algorithms, theoretical guarantees, and empirical validation for clustering applications.

Apr 22, 2026Formal Sciences260423.0028

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

Aravind Venugopal, Jiayu Chen, Xudong Wu, Chongyi Zheng +2 more

This paper proposes Occupancy Reward Shaping (ORS), a method that extracts temporal and geometric information from learned world models to create reward functions that improve credit assignment in offline goal-conditioned reinforcement learning. The approach uses optimal transport on occupancy measures and demonstrates 2.2x performance improvements across diverse tasks including real-world Tokamak control.

Apr 22, 2026Formal Sciences260423.0029

pAI/MSc: ML Theory Research with Humans on the Loop

Mahmoud Abdelmoneum, Pierfrancesco Beneventano, Tomaso Poggio

pAI/MSc is an open-source multi-agent system designed to assist researchers in ML theory by automating the conversion of hypotheses into manuscript drafts, significantly reducing manual steering effort. The system emphasizes human-in-the-loop collaboration rather than fully autonomous research.

Apr 22, 2026Formal Sciences260423.0030

Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

Naizhong Xu

SmartVector augments vector embeddings with temporal awareness, confidence decay, and relational properties to improve retrieval-augmented generation accuracy on versioned knowledge. The framework doubles accuracy on versioned queries and reduces stale answers by 62% compared to standard cosine similarity retrieval.

Apr 22, 2026Formal Sciences260423.0031

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

Jie Xu, Haaris Mehmood, Rogier Van Dalen, Karthikeyan Saravanan +1 more

PINA is a differentially private clustered federated learning framework that uses low-rank adapters and compressed sketches for privacy-preserving initialization, followed by normality-driven aggregation to improve convergence. It achieves 2.9% higher accuracy than state-of-the-art DP-FL methods while maintaining formal privacy guarantees.

Apr 22, 2026Formal Sciences260423.0032

An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling

Anif N. Shikder, Ramit Dey, Sayantan Auddy, Luisa Liboni +5 more

This paper establishes a mathematical correspondence between state space models (like S4) and nonlinear oscillator networks, deriving an exact operator expression for S4D's forward pass. This provides analytical interpretability for modern sequence models by revealing how information propagates as waves in a ring network topology.

Apr 22, 2026Formal Sciences260423.0033

A Hierarchical MARL-Based Approach for Coordinated Retail P2P Trading and Wholesale Market Participation of DERs

Patrick Wilk, Ethan Cantor, Yikui Liu, Jie Li

This paper proposes a hierarchical multi-agent deep reinforcement learning framework that enables distributed energy resources to participate in both peer-to-peer retail trading and wholesale electricity markets through coordinated prosumer aggregation. The approach uses a Stackelberg game to optimize market performance and grid flexibility.

Apr 22, 2026Formal Sciences260423.0034

Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis

Fariz Ikhwantri, Dusica Marijan

This paper proposes a graph neural network framework to analyze assurance cases (structured safety argument documents) for link prediction between argument elements and detection of LLM-generated versus human-authored cases. The work reveals that LLM-generated assurance cases have distinct structural patterns and highlights limitations in GNN explanation methods.

Apr 22, 2026Formal Sciences260423.0035

Amortized Vine Copulas for High-Dimensional Density and Information Estimation

Houman Safaai

This paper proposes Vine Denoising Copula (VDC), an amortized approach to vine copulas that trains a single bivariate denoising model and reuses it across all vine edges, enabling fast and tractable high-dimensional density and information estimation. The method combines neural flexibility with classical copula interpretability while achieving significant computational speedups.

Apr 22, 2026Formal Sciences260423.0036

On Bayesian Softmax-Gated Mixture-of-Experts Models

Nicola Bariletto, Huy Nguyen, Nhat Ho, Alessandro Rinaldo

This paper provides the first systematic theoretical analysis of Bayesian mixture-of-experts models with softmax gating, establishing posterior contraction rates for density estimation, convergence guarantees for parameter estimation, and strategies for selecting the number of experts.

Apr 22, 2026Formal Sciences260423.0037

Efficient Symbolic Computations for Identifying Causal Effects

Benjamin Hollering, Pratik Misra, Nils Sturma

This paper presents an efficient symbolic computation algorithm for determining whether causal effects can be identified from observational data with latent confounders in linear structural causal models. The algorithm finds the lowest-degree identifying formulas in quasi-polynomial time, making causal identifiability analysis practical for larger problems.

Apr 22, 2026Formal Sciences260423.0038

CHASM: Unveiling Covert Advertisements on Chinese Social Media

Jingyi Zheng, Tianyi Hu, Yule Liu, Zhen Sun +4 more

This paper introduces CHASM, a dataset of 4,992 annotated instances from Chinese social media for detecting covert advertisements disguised as regular posts. The study reveals that current multimodal large language models fail to reliably identify these deceptive advertisements, highlighting a critical gap in content moderation capabilities.

Apr 22, 2026Formal Sciences260423.0039

Explicit Dropout: Deterministic Regularization for Transformer Architectures

Vidhi Agrawal, Illia Oleksiienko, Alexandros Iosifidis

This paper reformulates dropout as a deterministic regularization term added directly to the training loss instead of using stochastic masking, providing fine-grained control over regularization in Transformers. Experiments show the approach matches or outperforms standard dropout across image, video, and audio tasks.

Apr 22, 2026Formal Sciences260423.0040

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Xueyan Li, Johannes Zenn, Ekaterina Fadeeva, Guinan Su +2 more

DLE is a deterministic decoding method that systematically explores distinct reasoning paths in a truncated decoding tree instead of sampling with replacement, improving inference efficiency and performance on math, coding, and reasoning tasks.