paper-with-me

Papers ARC

“ARC” 태그가 달린 논문 554편 · 필터 해제

DS@GT at CheckThat! 2025: Detecting Subjectivity via Transfer-Learning and Corrective Data Augmentation

2025-07-08 · Maximilian Heil, Dionne Bang

This paper presents our submission to Task 1, Subjectivity Detection, of the CheckThat! Lab at CLEF 2025. We investigate the effectiveness of transfer-learning and stylistic data augmentation to improve classification of…

ARCData AugmentationTransfer Learning

DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media

2025-07-08 · Ayush Parikh, Hoang Thanh Thanh Truong, Jeanette Schofield, Maximilian Heil

In this paper, we, as the DS@GT team for CLEF 2025 CheckThat! Task 4a Scientific Web Discourse Detection, present the methods we explored for this task. For this multiclass classification task, we determined if a tweet c…

ARC

DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification

2025-07-08 · Maximilian Heil, Aleksandar Pramov

Numerical claims, statements involving quantities, comparisons, and temporal references, pose unique challenges for automated fact-checking systems. In this study, we evaluate modeling strategies for veracity prediction …

ARCArithmetic ReasoningFact CheckingFact Verification+1

Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification

2025-07-08 · Murilo Gustineli, Anthony Miyaguchi, Adrian Cheung, Divyansh Khattak

We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images. Our pipeline combines (i) a fine-tuned Vision Transformer ViTD2PC24All for pat…

ARC

Revisiting Z Transform Laplace Inversion: To Correct flaws in Signal and System Theory

2025-06-29 · Yuxin Yang, Hang Zhou, Chaojie Li, Xin Li 외

This paper revisits the classical formulation of the Z-transform and its relationship to the inverse Laplace transform (L-1), originally developed by Ragazzini in sampled-data theory. It identifies a longstanding mathema…

ARC

Autonomous Cyber Resilience via a Co-Evolutionary Arms Race within a Fortified Digital Twin Sandbox

2025-06-25 · Malikussaid, Sutiyo

The convergence of IT and OT has created hyper-connected ICS, exposing critical infrastructure to a new class of adaptive, intelligent adversaries that render static defenses obsolete. Existing security paradigms often f…

ARC

Physics-Guided Radiotherapy Treatment Planning with Deep Learning

2025-06-23 · Stefanos Achlatis, Efstratios Gavves, Jan-Jakob Sonke

Radiotherapy (RT) is a critical cancer treatment, with volumetric modulated arc therapy (VMAT) being a commonly used technique that enhances dose conformity by dynamically adjusting multileaf collimator (MLC) positions a…

ARCDeep Learning

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma

2025-06-18 · Bohan Yang, Gang Liu, Rirao Dao, Yujia Qian 외

Objective. Proton arc therapy (PAT) is an emerging and promising modality in radiotherapy, offering several advantages over conventional intensitymodulated proton therapy (IMPT). However, identifying the optimal energy l…

ARC

Active InSAR monitoring of building damage in Gaza during the Israel-Hamas War

2025-06-17 · Corey Scher, Jamon Van Den Hoek

Aerial bombardment of the Gaza Strip beginning October 7, 2023 is one of the most intense bombing campaigns of the twenty-first century, driving widespread urban damage. Characterizing damage over a geographically dynami…

ARCChange DetectionHumanitarian

Don't throw the baby out with the bathwater: How and why deep learning for ARC

2025-06-17 · Jack Cole, Mohamed Osman

The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for genera…

ARC

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

2025-06-17 · Wenbing Li, Zikai Song, Hang Zhou, Yunyao Zhang 외

Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-…

ARCCoLAGSM8KHumanEval+4

Limited-Angle CBCT Reconstruction via Geometry-Integrated Cycle-domain Denoising Diffusion Probabilistic Models

2025-06-16 · Yuan Gao, Shaoyan Pan, Mingzhe Hu, Huiqiao Xie 외

Cone-beam CT (CBCT) is widely used in clinical radiotherapy for image-guided treatment, improving setup accuracy, adaptive planning, and motion management. However, slow gantry rotation limits performance by introducing …

ARCDenoisingSSIM

Frequency Dynamic Convolutions for Sound Event Detection

2025-06-15 · Hyeonuk Nam

Recent research in deep learning-based Sound Event Detection (SED) has primarily focused on Convolutional Recurrent Neural Networks (CRNNs) and Transformer models. However, conventional 2D convolution-based models assume…

ARCEvent DetectionSound Event Detection

Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge

2025-06-15 · Shraddha Surana, Ashwin Srinivasan, Michael Bain

The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks ha…

ARCCode GenerationProgram Synthesis

Feedforward Ordering in Neural Connectomes via Feedback Arc Minimization

2025-06-13 · Soroush Vahidi

We present a suite of scalable algorithms for minimizing feedback arcs in large-scale weighted directed graphs, with the goal of revealing biologically meaningful feedforward structure in neural connectomes. Using the Fl…

ARC

Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop

2025-06-12 · Justin Kerr, Kush Hari, Ethan Weber, Chung Min Kim 외

Humans do not passively observe the visual world -- we actively look in order to act. Motivated by this principle, we introduce EyeRobot, a robotic system with gaze behavior that emerges from the need to complete real-wo…

ARC

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models

2025-06-08 · Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf 외

Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere video generation. We argue that the training…

ARCFew-Shot LearningPose EstimationVideo Generation

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

2025-06-07 · Kyubyung Chae, Hyunbin Jin, Taesup Kim

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods fr…

ARCMMLUSafety Alignment

Text-to-LoRA: Instant Transformer Adaption

2025-06-06 · Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange

While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of t…

ARCGSM8K

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities

2025-05-31 · Jiahui Geng, Thy Thy Tran, Preslav Nakov, Iryna Gurevych

Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual in…

ARC
1–20 / 554 다음 →