{"total":44,"rows":[{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"area":null},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2310.20208","title":"ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection","created":"2023-10-31","cited_by_count":48,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2203.14338","title":"LibMTL: A Python Library for Multi-Task Learning","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2505.06977","title":"CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging","created":"2025-05-11","cited_by_count":23,"area":null},{"id":"2308.13537","title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation","created":"2023-08-16","cited_by_count":19,"area":null},{"id":"2301.02009","title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13,"area":null},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12,"area":null},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10,"area":null},{"id":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2304.08594","title":"AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning","created":"2023-04-17","cited_by_count":5,"area":null},{"id":"2212.10066","title":"RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2305.00441","title":"Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal","created":"2023-04-30","cited_by_count":2,"area":null},{"id":"2404.15197","title":"Multi-Task Learning as enabler for General-Purpose AI-native RAN","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2503.09850","title":"TabNSA: Native Sparse Attention for Efficient Tabular Data Learning","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2512.19320","title":"MAGIC: Achieving Superior Model Merging via Magnitude Calibration","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2205.01639","title":"Dynamic and Context-Dependent Stock Price Prediction Using Attention Modules and News Sentiment","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2208.02148","title":"GPPF: A General Perception Pre-training Framework via Sparsely Activated Multi-Task Learning","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2411.02787","title":"Advancing Robust Underwater Acoustic Target Recognition through Multi-task Learning and Multi-Gate Mixture-of-Experts","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2412.12092","title":"No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2512.20420","title":"Simplifying Multi-Task Architectures Through Task-Specific Normalization","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2207.12944","title":"AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification","created":"2022-07-26","cited_by_count":0,"area":null},{"id":"2301.02494","title":"Adaptive Pattern Extraction Multi-Task Learning for Multi-Step Conversion Estimations","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2302.00003","title":"The Power of External Memory in Increasing Predictive Model Capacity","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2310.15492","title":"Robust Representation Learning for Unified Online Top-K Recommendation","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2506.23170","title":"Compositions of Variant Experts for Integrating Short-Term and Long-Term Preferences","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2602.20911","title":"From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.14540","title":"WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.22770","title":"Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.33340","title":"RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}