| 1 | ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification | Qisheng Liao, Youngah Do | cs.CL | 2026-09-21 |
| 2 | Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models | Kevin David Hayes, Arka Pal, Haosong Zhang +2 | cs.AI | 2026-09-21 |
| 3 | DTKDP: A Dual Teacher Knowledge Distillation and Pruning Framework for Lightweight Oriented SAR Ship Detection | Yuming Li, Fan Zhang, Alin M. Achim | cs.CV | 2026-09-21 |
| #4 | NPU Accelerator: Quantized Real-Time Vehicle Detection on PYNQ-Z1 Using FINN | Daniel Gutierrez, Antonio Cuesta, Jorge Fe +2 | cs.AR | 2026-09-21 |
| #5 | Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models | Xiaoqiang Wang, Mengyang Xiong, Jun Dai +1 | quant-ph | 2026-09-21 |
| #6 | Custom Named Entity Recognition and Topic Classification for Global Health Publications | Genis Skura, Antoine Geissbühler, Jean-Luc Falcone | cs.AI | 2026-09-21 |
| #7 | 0.5\%>100\%: Bidirectional Reciprocal Learning for Referring Image Segmentation | Xiaoqiang Lu, Licheng Jiao, Lingling Li +5 | cs.CV | 2026-09-21 |
| #8 | MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting | Xinying Cai, Junkai Lu, Yuhan Zhu +3 | cs.LG | 2026-09-21 |
| #9 | DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding | Xiaoqiang Lu, Licheng Jiao, Long Sun +5 | cs.CV | 2026-09-21 |
| #10 | NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge Hardware | Leonidas Delimpasis, Panagiota Moraiti, Antonis Porichis +2 | cs.LG | 2026-09-21 |
| #11 | A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes | Shahir Abdullah | cs.CV | 2026-09-21 |
| #12 | Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity | Gautam Ranka, Shubham Santosh Pandere, Aiden Dsouza | cs.CV | 2026-09-21 |
| #13 | A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach | Andreas Martin, Sandro Schwander | cs.SE | 2026-09-21 |
| #14 | Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion | Uday Allu, Abhivanth Sivaprakash, Pratik Singh +1 | cs.CV | 2026-09-21 |
| #15 | SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentation | Anja Delić, Jurica Runtas, Marin Oršić +2 | cs.CV | 2026-09-21 |
| #16 | SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models | Ali Athar, Imran Ahsan, Joon-Yong Jung | cs.AI | 2026-09-21 |
| #17 | H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache | Weifan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn +6 | cs.LG | 2026-09-21 |
| #18 | Lightweight Pedestrian Head-Orientation Recognition Network for Safe Pedestrian-Vehicle Interaction | Yuanzhe Li, Yidi Huang, Xiaotong Chang +1 | cs.CV | 2026-09-21 |
| #19 | Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses | Jiankuo Zhao, Xiangyu Zhu, Jijie Li +3 | cs.CV | 2026-09-21 |
| #20 | Acceptance-Aware Draft Model Training for Speculative Decoding | Tianhua Xia, Mugilan Ganesan, Yifei Feng +3 | cs.LG | 2026-09-21 |
| #21 | SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations | Muhammad Sudipto Siam Dip, Ali Etemad | cs.LG | 2026-09-21 |
| #22 | The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study | Jayakumar Manoharan | eess.SY | 2026-09-21 |
| #23 | Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents | Dongming Jiang, Yi Li, Bingzhe Li | cs.AI | 2026-09-21 |
| #24 | LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning | Boxun Hu, Jiawei Ge, Axel Krieger +2 | cs.AI | 2026-09-21 |
| #25 | Learning-Based 3D Reconstruction of Power Networks from Aerial Point Clouds | Rishabh Jain, Anuja Saini, Vishal Jain | eess.IV | 2026-09-20 |
| #26 | Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval | Soyeon Kim, Hyunjin Kim, JinYeong Bak +1 | cs.CL | 2026-09-20 |
| #27 | PROSE: A Theory of Optimal Stopping with Perishable Evidence for Peer Selection in Intermittently Connected Decentralised Learning | Christos Anagnostopoulos | cs.LG | 2026-09-20 |
| #28 | Comparative Performance and Parameter-Efficient Adaptation of DINOv2 for Active Trachoma Classification | Kibrom Gebremedhin, Hadush Hailu, Bruk Gebregziabher +1 | cs.CV | 2026-09-20 |
| #29 | FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model | Jingxuan Xu, Gang Wu, Yanan Wu +13 | cs.CL | 2026-09-20 |
| #30 | VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers | Abteen Arab, Guile Wu, Chengjie Huang +1 | cs.CV | 2026-09-20 |
| #31 | GRACE: Grounded Adversarial Reasoning over Canadian Law | Jiakang Xu, Wantong Huo, Udom Silparcha +1 | cs.CL | 2026-09-20 |
| #32 | One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting? | Ziang Li, Yue Huang, Guoxu Zhou +4 | cs.LG | 2026-09-20 |
| #33 | Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms | Yueyan Li, Haibo Wang, Caixia Yuan +1 | cs.CV | 2026-09-20 |
| #34 | Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields | Jianqiang Wang, Junhui Hou, Siyu Ren +2 | cs.CV | 2026-09-20 |
| #35 | PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models | Qi Qin, Erbo Li, Ting Wei +4 | stat.ML | 2026-09-20 |
| #36 | Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transport | Xiangyu Wang, Shuo Wang, Ruiyi Fang +1 | cs.LG | 2026-09-20 |
| #37 | Towards robust multimodal 3D object detection via visual foundation models | Ziying Song, Lin Liu, Hongyu Pan +4 | cs.CV | 2026-09-20 |
| #38 | PosEviLoc: Position-Conditioned Spatial Evidence for Language-Based 3D Localization | Tianyi Shang, Yike Shi, Zhenyu Li | cs.CV | 2026-09-20 |
| #39 | CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning | Hongwei Yan, Kanglei Zhou, Yuchen Liu +3 | cs.CV | 2026-09-20 |
| #40 | HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection | Junwen Chen, Keiji Yanai | cs.CV | 2026-09-20 |
| #41 | LiteTex-GS: Fast and Lightweight Texturing for Gaussian Splatting | Zhiwei Li, Yijia Guo, Yishi Lu +4 | cs.CV | 2026-09-20 |
| #42 | Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States | Yifan Wang, Dejing Dou | cs.CL | 2026-09-20 |
| #43 | CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era | Yipeng Qian, Pengjie Zhao, Chaoxi Niu | cs.LG | 2026-09-20 |
| #44 | CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning | Minkyoung Kim, Daeun Ji, Yohan Lee +2 | cs.LG | 2026-09-20 |
| #45 | Signal-Informed Temporal Routing for Vinyl Defect Regime Detection | Yi-Hung Kan, Homayoon Beigi | eess.AS | 2026-09-19 |
| #46 | Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics | Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden | cs.SD | 2026-09-19 |
| #47 | Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring | Xudong Wang, Jiacheng Cui, Junyu Xue +2 | cs.LG | 2026-09-19 |
| #48 | QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation | Le Thien Phuc Nguyen, Thien Nguyen, Thanh-Huy Nguyen +3 | cs.CV | 2026-09-19 |
| #49 | AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows | Rudrendu Kumar Paul, Sourav Nandy | cs.AI | 2026-09-19 |
| #50 | Joint Domain-Class Modeling for Federated Learning Under Feature Skew | Sina Najafi, Mostafa Tavassolipour, Seyed Pooya Shariatpanahi | cs.LG | 2026-09-19 |