{"list":"other","total":60,"rows":[{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1811.02629","title":"Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge","created":"2018-11-05","cited_by_count":511},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2412.10859","title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting","created":"2024-12-14","cited_by_count":107},{"id":"2308.15126","title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models","created":"2023-08-29","cited_by_count":99},{"id":"2503.21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","created":"2025-03-27","cited_by_count":96},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83},{"id":"2405.14622","title":"Calibrated Self-Rewarding Vision Language Models","created":"2024-05-23","cited_by_count":78},{"id":"1612.07003","title":"Image biomarker standardisation initiative","created":"2016-12-21","cited_by_count":63},{"id":"2312.08733","title":"VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding","created":"2023-12-14","cited_by_count":62},{"id":"2409.00872","title":"Self-evolving Agents with reflective and memory-augmented abilities","created":"2024-09-01","cited_by_count":52},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50},{"id":"2405.15330","title":"Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model","created":"2024-05-24","cited_by_count":48},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2503.23512","title":"SCORE: Story Coherence and Retrieval Enhancement for AI Narratives","created":"2025-03-30","cited_by_count":42},{"id":"2312.08636","title":"MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning","created":"2023-12-14","cited_by_count":41},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2507.17801","title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","created":"2025-07-23","cited_by_count":37},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31},{"id":"2501.04606","title":"Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion","created":"2025-01-08","cited_by_count":28},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28},{"id":"2111.12485","title":"Understanding the Dynamics of DNNs Using Graph Modularity","created":"2021-11-24","cited_by_count":26},{"id":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26},{"id":"2404.01663","title":"CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models","created":"2024-04-02","cited_by_count":26},{"id":"2410.14720","title":"SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models","created":"2024-10-14","cited_by_count":25},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19},{"id":"2406.07929","title":"A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models","created":"2024-06-12","cited_by_count":18},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17},{"id":"2508.10523","title":"Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies","created":"2025-08-14","cited_by_count":17},{"id":"2501.08620","title":"CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting","created":"2025-01-15","cited_by_count":16},{"id":"2405.04135","title":"Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models","created":"2024-05-07","cited_by_count":15},{"id":"2506.12935","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","created":"2025-06-15","cited_by_count":15},{"id":"2303.07677","title":"SR-init: An interpretable layer pruning method","created":"2023-03-14","cited_by_count":13},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12},{"id":"2504.12574","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","created":"2025-04-17","cited_by_count":11},{"id":"2504.14868","title":"Twin Co-Adaptive Dialogue for Progressive Image Generation","created":"2025-04-21","cited_by_count":11},{"id":"2503.19474","title":"A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition","created":"2025-03-25","cited_by_count":10},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10},{"id":"2505.00941","title":"FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection","created":"2025-05-02","cited_by_count":10},{"id":"2405.12963","title":"Comprehensive Multimodal Deep Learning Survival Prediction Enabled by a Transformer Architecture: A Multicenter Study in Glioblastoma","created":"2024-05-21","cited_by_count":9},{"id":"2507.13032","title":"Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation","created":"2025-07-17","cited_by_count":9},{"id":"2504.14205","title":"Dual-channel Heterophilic Message Passing for Graph Fraud Detection","created":"2025-04-19","cited_by_count":8},{"id":"2506.16393","title":"From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling","created":"2025-06-19","cited_by_count":8},{"id":"2507.09081","title":"From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion","created":"2025-07-11","cited_by_count":8},{"id":"2507.09491","title":"GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?","created":"2025-07-13","cited_by_count":8},{"id":"2111.11165","title":"Graph-Based Similarity of Neural Network Representations","created":"2021-11-22","cited_by_count":7},{"id":"2504.14204","title":"DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection","created":"2025-04-19","cited_by_count":7},{"id":"2504.12112","title":"A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction","created":"2025-04-16","cited_by_count":6},{"id":"2505.16001","title":"Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning","created":"2025-05-21","cited_by_count":6},{"id":"2508.13378","title":"Governance-Ready Small Language Models for Medical Imaging: Prompting, Abstention, and PACS Integration","created":"2025-08-18","cited_by_count":6},{"id":"2411.10507","title":"RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively","created":"2024-11-15","cited_by_count":4},{"id":"2504.10776","title":"Rainy: Unlocking Satellite Calibration for Deep Learning in Precipitation","created":"2025-04-15","cited_by_count":4},{"id":"2504.13442","title":"SatelliteCalculator: A Multi-Task Vision Foundation Model for Quantitative Remote Sensing Inversion","created":"2025-04-18","cited_by_count":4},{"id":"2504.14785","title":"DC4CR: When Cloud Removal Meets Diffusion Control in Remote Sensing","created":"2025-04-21","cited_by_count":4},{"id":"2505.21571","title":"FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition","created":"2025-05-27","cited_by_count":4},{"id":"2506.01319","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","created":"2025-06-02","cited_by_count":4},{"id":"2506.06176","title":"SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery","created":"2025-06-06","cited_by_count":3},{"id":"2507.12011","title":"DUSE: A Data Expansion Framework for Low-resource Automatic Modulation Recognition based on Active Learning","created":"2025-07-16","cited_by_count":2}],"next_cursor":null}