💻 Category

cs

2931 papers

💻 computer science

Task-Adaptive Decoder Specialization for Unified Image Coding Toward Human Reconstruction and Machine Classification

This paper proposes a task-adaptive decoder specialization framework that utilizes a shared encoder and latent representation with dynamically reconfigured decoder-side adapters to simultaneously enhance semantic discriminability for machine classification and high-frequency texture fidelity for human perception in unified image coding, particularly at low bitrates.

Wei Zhang, Xiwu Shang, Mengyao Wang, Xiaoli Zhao, Guozhong Wang2026-07-20
💻 computer science

Predicting Visual Acuity from Fundus Photographs Using a Domain-Pretrained Vision Transformer: Anatomical Alignment of Attention Patterns

This study demonstrates that a domain-pretrained Vision Transformer (RETFound) fine-tuned on over 21,000 fundus photographs achieves substantial agreement in predicting four-class visual acuity while developing anatomically organized attention patterns—shifting from retinal vessels in low-vision eyes to the macula in normal-vision eyes—that correlate with classification correctness and offer interpretability for uncertain predictions.

Jin Hyun Kim, Yong Seop Han, Kuk Jin Jang, Seoung Jin Lee, Hyonyoung choi, Insup Lee2026-07-17
💻 computer science

Semantic Alignment, Chronological Distance, and Citation-Network Prominence in Citation Formation: Evidence from Ten Citation Corpora

By applying a rigorously leakage-mitigated framework across ten bibliographic corpora, this study demonstrates that chronological distance is the dominant predictor of citation formation, consistently outweighing the predictive power of semantic alignment and citation-network prominence under temporally strict conditions.

Moses Boudourides2026-07-17
💻 computer science

Cross-Attention Based Multi-Sensor Fusion for Robust Object Detection in ADAS: YOLOv12 with Spatiotemporal Calibration and iHOA-Tuned Temporal Fusion Transformer

This paper proposes CAMSF-ADAS, a robust object detection framework for Advanced Driver Assistance Systems that integrates camera, LiDAR, and radar data through spatiotemporal calibration and cross-attention fusion, leveraging YOLOv12 for localization and an Improved Hippopotamus Optimization Algorithm-tuned Temporal Fusion Transformer for enhanced classification.

Raghunath Mallavarapu, Kanaka Raju Pappala, Sattibabu Bhumireddi, G. Krishna Podagatlapalli, Kavitha Chandu, Durga Rao T (…)2026-07-17
💻 computer science

Retrofit or Redesign? Hardware-Validated Constant-Time Defense and Cost Analysis for the M-Step Side-Channel on TrustZone-M

This paper demonstrates through real-silicon validation on Arm TrustZone-M that redesigning cryptographic algorithms for constant-time execution is superior to retrofitting, as the latter not only incurs roughly two orders of magnitude higher cost but also risks retaining exploitable control-flow leaks that only per-instruction verification can detect.

Arash Razban2026-07-17
💻 computer science

From Infrared to Ultraviolet]{From Infrared to Ultraviolet: A Renormalization Group Approach to Frequency-Aware Progressive Training

This paper proposes a frequency-aware progressive training strategy inspired by the renormalization group that sequentially activates low-to-high frequency branches with decaying learning rates, demonstrating consistent improvements in low-dimensional, few-shot regression tasks while clarifying that its efficacy diminishes in high-dimensional or smooth-process scenarios where scale separation is less relevant.

英熙 朱2026-07-17
💻 computer science

Dual-Stage Guided Artificial Lemming Algorithm (DALA) For Solving Engineering Application Optimization Problems

This paper proposes the Dual-Stage Guided Artificial Lemming Algorithm (DALA), which enhances the traditional ALA through adaptive probability ranking, a two-stage greedy strategy combining adversarial and topological learning, and JADE mutation to effectively solve high-dimensional engineering optimization problems and hyperparameter tuning for power load forecasting.

Jiayi Gao, Yu Zhang2026-07-17
💻 computer science

Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture

This paper presents a model-agnostic, multi-turn safety governance architecture that integrates contextual risk detection, reasoning-based verification, and protocol-guided response generation to significantly improve risk management and clinician-preferred escalation in LLM-driven mental health support while maintaining conversational rapport.

Anabela C. Areias, Catarina Botelho, António Farinhas, Areti Vassilopoulos, Dora Janela, Xin Tong, Nuno M. Guerreiro, Ma (…)2026-07-17