{"total":47,"rows":[{"id":"2602.11236","title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","created":"2026-02-11","cited_by_count":103,"area":null},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89,"area":null},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32,"area":null},{"id":"2512.12812","title":"Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA","created":"2025-12-14","cited_by_count":23,"area":null},{"id":"2505.22521","title":"Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data","created":"2025-05-28","cited_by_count":20,"area":null},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2509.12446","title":"PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization","created":"2025-09-15","cited_by_count":19,"area":null},{"id":"2604.19386","title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","created":"2026-04-21","cited_by_count":18,"area":null},{"id":"2510.27486","title":"FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models","created":"2025-10-31","cited_by_count":15,"area":null},{"id":"2601.16155","title":"HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval","created":"2026-01-22","cited_by_count":14,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2507.19451","title":"GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting","created":"2025-07-25","cited_by_count":11,"area":null},{"id":"2507.04822","title":"SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions","created":"2025-07-07","cited_by_count":10,"area":null},{"id":"2509.26614","title":"Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification","created":"2025-09-30","cited_by_count":10,"area":null},{"id":"2510.03161","title":"UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.04655","title":"FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2602.23827","title":"FedNSAM:Consistency of Local and Global Flatness for Federated Learning","created":"2026-02-27","cited_by_count":7,"area":null},{"id":"2509.22756","title":"Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2506.18737","title":"USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2509.05746","title":"Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation","created":"2025-09-06","cited_by_count":4,"area":null},{"id":"2604.11103","title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2512.05442","title":"IdealTSF: Can Non-Ideal Data Contribute to Enhancing the Performance of Time Series Forecasting Models?","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2512.10305","title":"InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2603.14290","title":"RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2507.01241","title":"Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2507.07854","title":"Credit Risk Analysis for SMEs Using Graph Neural Networks in Supply Chain","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2512.19150","title":"AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2604.16878","title":"OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction","created":"2026-04-18","cited_by_count":2,"area":null},{"id":"2607.06468","title":"EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.01618","title":"Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.07198","title":"Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2603.12997","title":"Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2604.15301","title":"Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2510.12401","title":"Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2511.08399","title":"Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2601.01156","title":"DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.20409","title":"AWGformer: Adaptive Wavelet-Guided Transformer for Multi-Resolution Time Series Forecasting","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.06576","title":"BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.16459","title":"Deep Hierarchical Knowledge Loss for Fault Intensity Diagnosis","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.25423","title":"Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.08975","title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.00656","title":"Demystifying the Optimal Fair Classifier in Multi-Class Classification","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.22187","title":"BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.31135","title":"Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}