Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
TESTING

MAGPI: Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data

Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning methods have demonstrated promise in learning efficient...

Atticus Rex, Elizabeth Qian, David Peterson

2603.22050 2026-03-23
AI LLM

Dynamic analysis enhances issue resolution

Translating natural language descriptions into viable code fixes remains a fundamental challenge in software engineering. While the proliferation of agentic large language models (LLMs) has vastly ...

Mingwei Liu, Zihao Wang, Zhenxi Chen, Zheng Pei, Yanlin Wang, Zibin Zheng

2603.22048 2026-03-23
AI LLM

DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation

Text-to-Image (T2I) diffusion models have demonstrated strong generation ability, but their potential to generate unsafe content raises significant safety concerns. Existing inference-time defense ...

Binhong Tan, Zhaoxin Wang, Handing Wang

2603.22041 2026-03-23
TESTING

Set-Theoretic Types for Erlang: Theory, Implementation, and Evaluation

Erlang's dynamic typing discipline can lead to runtime errors that persist even after process restarts. Some of these runtime errors could be prevented through static type checking. While Erlang pr...

Albert Schimpf, Stefan Wehr, Annette Bieniusa

2603.22032 2026-03-23
TESTING

Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models

Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploitin...

Purui Bai, Junxian Duan, Pin Wang, Jinhua Hao, Ming Sun, Chao Zhou, Huaibo Huang

2603.22027 2026-03-23
TESTING

Identical, independent quantum weak measurements violate objective realism

We demonstrate violation of objective realism in quantum world using unconstrained weak measurements. Instead of limited Leggett-Garg approach with artificial bounds on the observed values, we assu...

Tomasz Rybotycki, Tomasz Białecki, Josep Batle, Bartłomiej Zglinicki, Adam Szereszewski, Wolfgang...

2603.22020 2026-03-23
AI LLM

On the Challenges and Opportunities of Learned Sparse Retrieval for Code

Retrieval over large codebases is a key component of modern LLM-based software engineering systems. Existing approaches predominantly rely on dense embedding models, while learned sparse retrieval ...

Simon Lupart, Maxime Louis, Thibault Formal, Hervé Déjean, Stéphane Clinchant

2603.22008 2026-03-23
AI LLM

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models

Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals. This "black-box" mapping forces a single forward pass to simul...

Zixuan Wang, Yuxin Chen, Yuqi Liu, Jinhui Ye, Pengguang Chen, Changsheng Lu, Shu Liu, Jiaya Jia

2603.22003 2026-03-23
TESTING

CRPS-Optimal Binning for Conformal Regression

We propose a method for non-parametric conditional distribution estimation based on partitioning covariate-sorted observations into contiguous bins and using the within-bin empirical CDF as the pre...

Paolo Toccaceli

2603.22000 2026-03-23
AI LLM

Surfacing and Applying Meaning: Supporting Hermeneutical Autonomy for LGBTQ+ People in Taiwan

After Taiwan's legalization of same-sex marriage in 2019, LGBTQ+ communities continue to face hostility on social media. Using the lens of hermeneutical injustice and autonomy, we examine how techn...

Yi-Tong Chen, En-Kai Chang, Nanyi Bi, Nitesh Goyal

2603.21990 2026-03-23
AI LLM

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-st...

SII-GAIR, Sand. ai, :, Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, Jia...

2603.21986 2026-03-23
AI LLM

SecureBreak -- A dataset towards safe and secure models

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Altho...

Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera

2603.21975 2026-03-23
AI LLM

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-t...

Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng

2603.21972 2026-03-23
AI LLM

Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning

Fine-tuning large language models for domain-specific tasks such as medical text summarization demands substantial computational resources. Parameter-efficient fine-tuning (PEFT) methods offer prom...

Ulugbek Shernazarov, Rostislav Svitsov, Bin Shi

2603.21970 2026-03-23
TESTING

BHDD: A Burmese Handwritten Digit Dataset

We introduce the Burmese Handwritten Digit Dataset (BHDD), a collection of 87,561 grayscale images of handwritten Burmese digits in ten classes. Each image is 28x28 pixels, following the MNIST form...

Swan Htet Aung, Hein Htet, Htoo Say Wah Khaing, Thuya Myo Nyunt

2603.21966 2026-03-23
TESTING

Structured-light propagation in a medium with uniform torsion: polarization textures, geometric birefringence, and beam-resolved optical activity

We investigate finite-width optical-beam propagation in a medium with uniform torsion described by the geometric theory of a continuous distribution of screw dislocations. Starting from the Riemann...

Edilberto O. Silva

2603.21963 2026-03-23
AI LLM

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compressi...

Junhao Du, Jialong Xue, Anqi Li, Jincheng Dai, Guo Lu

2603.21957 2026-03-23
AI LLM

You See It, They Don't: An Exploratory Study of User-to-User Variation in Instagram Comments

In March 2025, Meta announced a new AI system to rank the order of the comments shown to Instagram users. With existing research showing how feed personalization systems can lead to increased polar...

Brahmani Nutakki, Manon Lilott Kempermann, Ingmar Weber

2603.21953 2026-03-23
TESTING

Parsimonious Subset Selection for Generalized Linear Models with Biomedical Applications

High-dimensional biomedical studies require models that are simultaneously accurate, sparse, and interpretable, yet exact best subset selection for generalized linear models is computationally intr...

Anant Mathur, Benoit Liquet, Samuel Muller, Sarat Moka

2603.21952 2026-03-23
AI LLM

Look, Listen and Segment: Towards Weakly Supervised Audio-visual Semantic Segmentation

Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSA...

Chengzhi Li, Heyan Huang, Ping Jian, Yanghao Zhou

2603.21948 2026-03-23