{"total":254,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2409.16167","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","created":"2024-09-24","cited_by_count":59,"area":null},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2501.01230","title":"Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent","created":"2025-01-02","cited_by_count":39,"area":null},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2506.17219","title":"No Free Lunch: Rethinking Internal Feedback for LLM Reasoning","created":"2025-06-20","cited_by_count":37,"area":"lr"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2509.17786","title":"Accurate and Efficient Low-Rank Model Merging in Core Space","created":"2025-09-22","cited_by_count":29,"area":null},{"id":"2409.15250","title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","created":"2024-09-23","cited_by_count":27,"area":null},{"id":"2502.17159","title":"RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness","created":"2025-02-24","cited_by_count":26,"area":null},{"id":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2412.05148","title":"LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2505.15875","title":"Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging","created":"2025-05-21","cited_by_count":18,"area":null},{"id":"2511.18810","title":"MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent","created":"2025-11-24","cited_by_count":18,"area":"mllm"},{"id":"2502.12420","title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models","created":"2025-02-18","cited_by_count":16,"area":null},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2504.14662","title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning","created":"2025-04-20","cited_by_count":16,"area":null},{"id":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14,"area":null},{"id":"2511.06876","title":"Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions","created":"2025-11-10","cited_by_count":14,"area":null},{"id":"2411.16815","title":"FREE-Merging: Fourier Transform for Efficient Model Merging","created":"2024-11-25","cited_by_count":13,"area":null},{"id":"2505.19892","title":"OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging","created":"2025-05-26","cited_by_count":13,"area":"mllm"},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2411.16746","title":"LoBAM: LoRA-Based Backdoor Attack on Model Merging","created":"2024-11-23","cited_by_count":12,"area":null},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12,"area":"mllm"},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2502.10339","title":"STAR: Spectral Truncation and Rescale for Model Merging","created":"2025-02-14","cited_by_count":11,"area":null},{"id":"2503.01372","title":"SwiLTra-Bench: The Swiss Legal Translation Benchmark","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2503.07661","title":"Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy","created":"2025-03-08","cited_by_count":11,"area":null},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2502.10436","title":"MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs","created":"2025-02-09","cited_by_count":10,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2503.16549","title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","created":"2025-03-19","cited_by_count":10,"area":"mllm"},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2510.10977","title":"Revisiting Model Interpolation for Efficient Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2511.07970","title":"Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective","created":"2025-11-11","cited_by_count":10,"area":"diffusion"},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2411.09263","title":"Rethinking Weight-Averaged Model-merging","created":"2024-11-14","cited_by_count":8,"area":null},{"id":"2503.20240","title":"Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models","created":"2025-03-26","cited_by_count":8,"area":"diffusion"},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2410.06664","title":"Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning","created":"2024-10-09","cited_by_count":7,"area":"diffusion"},{"id":"2410.08604","title":"MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2505.22389","title":"Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2505.23561","title":"Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2602.05495","title":"Transport and Merge: Cross-Architecture Merging for Large Language Models","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"id":"2605.19095","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2412.19819","title":"ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation","created":"2024-12-15","cited_by_count":6,"area":null},{"id":"2502.04484","title":"An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Face","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2502.17380","title":"Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2505.21226","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2509.01548","title":"Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing","created":"2025-09-01","cited_by_count":6,"area":null},{"id":"2602.13273","title":"MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2411.00553","title":"Is Multiple Object Tracking a Matter of Specialization?","created":"2024-11-01","cited_by_count":5,"area":null},{"id":"2502.05784","title":"Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble","created":"2025-02-09","cited_by_count":5,"area":null},{"id":"2502.10743","title":"1bit-Merging: Dynamic Quantized Merging for Large Language Models","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2505.11427","title":"Mergenetic: a Simple Evolutionary Model Merging Library","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2505.17110","title":"Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling","created":"2025-05-21","cited_by_count":5,"area":"mllm"},{"id":"2507.04790","title":"Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2507.06782","title":"Temporal Information Retrieval via Time-Specifier Model Merging","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2508.03140","title":"RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior","created":"2025-08-05","cited_by_count":5,"area":"lr"},{"id":"2511.21437","title":"A Systematic Study of In-the-Wild Model Merging for Large Language Models","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2512.04695","title":"TRINITY: An Evolved LLM Coordinator","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2504.06768","title":"FedMerge: Federated Personalization via Model Merging","created":"2025-04-09","cited_by_count":4,"area":"moe"},{"id":"2504.10902","title":"Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs","created":"2025-04-15","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":"2506.14126","title":"From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2510.23891","title":"PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2603.09463","title":"An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse","created":"2026-03-10","cited_by_count":4,"area":null},{"id":"2603.26317","title":"Label-Free Cross-Task LoRA Merging with Null-Space Compression","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2604.05502","title":"AttnDiff: Attention-based Differential Fingerprinting for Large Language Models","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null}],"next_cursor":"100"}