{"total":199,"rows":[{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"id":"2406.16437","title":"Theory on Mixture-of-Experts in Continual Learning","created":"2024-06-24","cited_by_count":54,"area":"moe"},{"id":"2403.18886","title":"Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning","created":"2024-03-27","cited_by_count":53,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43,"area":"moe"},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39,"area":null},{"id":"2412.01427","title":"FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration","created":"2024-12-02","cited_by_count":39,"area":null},{"id":"2511.11007","title":"VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models","created":"2025-11-14","cited_by_count":37,"area":"mllm"},{"id":"2503.10324","title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2506.11672","title":"Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning","created":"2025-06-13","cited_by_count":27,"area":"mllm"},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2503.04229","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models","created":"2025-03-06","cited_by_count":21,"area":"mllm"},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2508.04227","title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","created":"2025-08-06","cited_by_count":18,"area":"mllm"},{"id":"2407.15793","title":"CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning","created":"2024-07-22","cited_by_count":17,"area":"mllm"},{"id":"2406.18868","title":"Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models","created":"2024-06-27","cited_by_count":15,"area":"mllm"},{"id":"2505.11883","title":"MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging","created":"2025-05-17","cited_by_count":14,"area":null},{"id":"2409.14983","title":"Dynamic Integration of Task-Specific Adapters for Class Incremental Learning","created":"2024-09-23","cited_by_count":13,"area":null},{"id":"2507.07100","title":"Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2405.11530","title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts","created":"2024-05-19","cited_by_count":12,"area":"moe"},{"id":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2503.10111","title":"Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2503.08510","title":"External Knowledge Injection for CLIP-Based Class-Incremental Learning","created":"2025-03-11","cited_by_count":11,"area":null},{"id":"2503.16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models","created":"2025-03-21","cited_by_count":11,"area":"mllm"},{"id":"2504.13822","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2505.23271","title":"LADA: Scalable Label-Specific CLIP Adapter for Continual Learning","created":"2025-05-29","cited_by_count":11,"area":"mllm"},{"id":"2510.08564","title":"How to Teach Large Multimodal Models New Skills","created":"2025-10-09","cited_by_count":11,"area":"mllm"},{"id":"2510.16877","title":"Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning","created":"2025-10-19","cited_by_count":11,"area":null},{"id":"2403.19979","title":"Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning","created":"2024-03-29","cited_by_count":10,"area":null},{"id":"2409.18860","title":"LW2G: Learning Whether to Grow for Prompt-based Continual Learning","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2412.08929","title":"CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental Learning","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2506.03189","title":"Continual Learning in Vision-Language Models via Aligned Model Merging","created":"2025-05-30","cited_by_count":8,"area":"mllm"},{"id":"2509.21413","title":"Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity","created":"2025-09-25","cited_by_count":8,"area":null},{"id":"2503.20612","title":"IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting","created":"2025-03-26","cited_by_count":7,"area":"mllm"},{"id":"2505.13997","title":"StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning","created":"2025-05-20","cited_by_count":7,"area":"moe"},{"id":"2404.18311","title":"Towards Incremental Learning in Large Language Models: A Critical Review","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2408.01076","title":"Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2410.05899","title":"Brain-inspired continual pre-trained learner via silent synaptic consolidation","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2411.02210","title":"One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering","created":"2024-11-04","cited_by_count":6,"area":"mllm"},{"id":"2412.02503","title":"VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting","created":"2024-12-03","cited_by_count":6,"area":"moe"},{"id":"2502.00843","title":"VLM-Assisted Continual learning for Visual Question Answering in Self-Driving","created":"2025-02-02","cited_by_count":6,"area":"mllm"},{"id":"2503.07663","title":"Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs","created":"2025-03-08","cited_by_count":6,"area":"mllm"},{"id":"2505.20680","title":"Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.12351","title":"EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2510.15280","title":"Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2511.11421","title":"BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning","created":"2025-11-14","cited_by_count":6,"area":null},{"id":"2512.03125","title":"Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models","created":"2025-12-02","cited_by_count":6,"area":null},{"id":"2411.00553","title":"Is Multiple Object Tracking a Matter of Specialization?","created":"2024-11-01","cited_by_count":5,"area":null},{"id":"2506.21035","title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","created":"2025-06-26","cited_by_count":5,"area":"moe"},{"id":"2602.00722","title":"Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2408.09984","title":"Boosting Open-Domain Continual Learning via Leveraging Intra-domain Category-aware Prototype","created":"2024-08-19","cited_by_count":4,"area":"mllm"},{"id":"2409.19954","title":"Domain Consistency Representation Learning for Lifelong Person Re-Identification","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2411.06764","title":"Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning","created":"2024-11-11","cited_by_count":4,"area":"mllm"},{"id":"2411.19154","title":"DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning","created":"2024-11-28","cited_by_count":4,"area":null},{"id":"2503.14129","title":"SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2505.12512","title":"Scalable Strategies for Continual Learning with Replay","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2507.09924","title":"MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora","created":"2025-07-14","cited_by_count":4,"area":null},{"id":"2508.00260","title":"Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models","created":"2025-08-01","cited_by_count":4,"area":"mllm"},{"id":"2512.00694","title":"Affordance-First Decomposition for Continual Learning in Video-Language Understanding","created":"2025-11-30","cited_by_count":4,"area":null},{"id":"2601.13020","title":"PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning","created":"2026-01-19","cited_by_count":4,"area":"moe"},{"id":"2603.19145","title":"Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2405.19005","title":"Auto-selected Knowledge Adapters for Lifelong Person Re-identification","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2410.15858","title":"Towards Optimal Adapter Placement for Efficient Transfer Learning","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2502.17920","title":"C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2503.10705","title":"Enhanced Continual Learning of Vision-Language Models with Model Fusion","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"id":"2505.07690","title":"Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models","created":"2025-05-12","cited_by_count":3,"area":"mllm"},{"id":"2506.12409","title":"Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models","created":"2025-06-14","cited_by_count":3,"area":"mllm"},{"id":"2508.16463","title":"Modular Embedding Recomposition for Incremental Learning","created":"2025-08-22","cited_by_count":3,"area":"mllm"},{"id":"2509.19230","title":"DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2509.22645","title":"HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.26311","title":"Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2511.15633","title":"Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2601.22828","title":"Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA","created":"2026-01-30","cited_by_count":3,"area":"mllm"},{"id":"2602.03473","title":"Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts","created":"2026-02-03","cited_by_count":3,"area":"moe"},{"id":"2412.01004","title":"Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning","created":"2024-12-01","cited_by_count":2,"area":null},{"id":"2502.00618","title":"DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition","created":"2025-02-02","cited_by_count":2,"area":"mllm"},{"id":"2503.21227","title":"LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models","created":"2025-03-27","cited_by_count":2,"area":"mllm"},{"id":"2504.15041","title":"Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification","created":"2025-04-21","cited_by_count":2,"area":"distill"},{"id":"2506.11038","title":"MoTE: Mixture of Task-specific Experts for Pre-Trained ModelBased Class-incremental Learning","created":"2025-05-21","cited_by_count":2,"area":"moe"},{"id":"2507.13568","title":"LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2508.05993","title":"Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts","created":"2025-08-08","cited_by_count":2,"area":"moe"},{"id":"2508.11673","title":"Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2511.09853","title":"ConSurv: Multimodal Continual Learning for Survival Analysis","created":"2025-11-13","cited_by_count":2,"area":"moe"},{"id":"2511.11460","title":"Rethinking Efficient Mixture-of-Experts for Remote Sensing Modality-Missing Classification","created":"2025-11-14","cited_by_count":2,"area":"moe"},{"id":"2512.19551","title":"Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2602.04411","title":"Self-evolving Embodied AI","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2602.06043","title":"Shared LoRA Subspaces for almost Strict Continual Learning","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.27481","title":"On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.18610","title":"CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic","created":"2026-05-18","cited_by_count":2,"area":"mllm"},{"id":"2605.20247","title":"CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning","created":"2026-05-18","cited_by_count":2,"area":"moe"},{"id":"2606.01379","title":"Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2607.14852","title":"Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation","created":"2026-07-16","cited_by_count":2,"area":"vla"},{"id":"2608.09572","title":"Hyperbolic Multimodal Continual Learning","created":"2026-08-10","cited_by_count":2,"area":null}],"next_cursor":"100"}