{"total":328,"rows":[{"id":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2407.05000","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","created":"2024-07-06","cited_by_count":141,"area":null},{"id":"2502.07374","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","created":"2025-02-11","cited_by_count":132,"area":"lr"},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","cited_by_count":41,"area":null},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2506.02221","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","created":"2025-06-02","cited_by_count":29,"area":"diffusion"},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2410.08405","title":"AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning","created":"2024-10-10","cited_by_count":24,"area":"mllm"},{"id":"2412.04077","title":"SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning","created":"2024-12-05","cited_by_count":24,"area":null},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2406.17245","title":"Unlocking Continual Learning Abilities in Language Models","created":"2024-06-25","cited_by_count":23,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2502.16894","title":"Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment","created":"2025-02-24","cited_by_count":23,"area":"moe"},{"id":"2503.14118","title":"PET-MAD, a lightweight universal interatomic potential for advanced materials modeling","created":"2025-03-18","cited_by_count":23,"area":null},{"id":"2505.18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping","created":"2025-05-24","cited_by_count":23,"area":null},{"id":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","cited_by_count":22,"area":"mllm"},{"id":"2510.13003","title":"OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning","created":"2025-10-14","cited_by_count":21,"area":null},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19,"area":"moe"},{"id":"2506.09800","title":"Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving","created":"2025-06-11","cited_by_count":19,"area":"driving"},{"id":"2405.16350","title":"A Second-Order Perspective on Model Compositionality and Incremental Learning","created":"2024-05-25","cited_by_count":18,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"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":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2412.03512","title":"Distillation of Diffusion Features for Semantic Correspondence","created":"2024-12-04","cited_by_count":17,"area":null},{"id":"2603.11653","title":"Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning","created":"2026-03-12","cited_by_count":17,"area":"vla"},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2502.02797","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","created":"2025-02-05","cited_by_count":16,"area":null},{"id":"2503.02659","title":"Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge","created":"2025-03-04","cited_by_count":16,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2507.05964","title":"T-LoRA: Single Image Diffusion Model Customization Without Overfitting","created":"2025-07-08","cited_by_count":15,"area":"diffusion"},{"id":"2405.15586","title":"DAGER: Exact Gradient Inversion for Large Language Models","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2412.16524","title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation","created":"2024-12-21","cited_by_count":14,"area":null},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2505.21289","title":"LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning","created":"2025-05-27","cited_by_count":14,"area":null},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2409.17912","title":"Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2410.08305","title":"Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2408.06740","title":"DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with Diffusion","created":"2024-08-13","cited_by_count":12,"area":"diffusion"},{"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":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2603.21011","title":"ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods","created":"2026-01-08","cited_by_count":12,"area":"agents"},{"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":"2504.10146","title":"GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions","created":"2025-04-14","cited_by_count":11,"area":null},{"id":"2507.02503","title":"Continual Gradient Low-Rank Projection Fine-Tuning for LLMs","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2509.23106","title":"Effective Quantization of Muon Optimizer States","created":"2025-09-27","cited_by_count":11,"area":null},{"id":"2510.08564","title":"How to Teach Large Multimodal Models New Skills","created":"2025-10-09","cited_by_count":11,"area":"mllm"},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2412.06289","title":"S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2503.18225","title":"DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation","created":"2025-03-23","cited_by_count":10,"area":null},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2505.20355","title":"GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2510.19546","title":"Conditions for Catastrophic Forgetting in Multilingual Translation","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2512.18248","title":"On the Convergence Rate of LoRA Gradient Descent","created":"2025-12-20","cited_by_count":10,"area":null},{"id":"2601.20280","title":"The Forecast After the Forecast: A Post-Processing Shift in Time Series","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2410.16801","title":"Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models","created":"2024-10-22","cited_by_count":9,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2606.14222","title":"Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models","created":"2026-06-12","cited_by_count":9,"area":null},{"id":"2405.15525","title":"Sparse Matrix in Large Language Model Fine-tuning","created":"2024-05-24","cited_by_count":8,"area":null},{"id":"2405.18380","title":"Outlier-weighed Layerwise Sampling for LLM Fine-tuning","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2503.05919","title":"From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning","created":"2025-03-07","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":"2409.15371","title":"MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2412.10906","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","created":"2024-12-14","cited_by_count":7,"area":null},{"id":"2502.06619","title":"Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification","created":"2025-02-10","cited_by_count":7,"area":"diffusion"},{"id":"2503.00703","title":"Towards hyperparameter-free optimization with differential privacy","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2507.06558","title":"The Primacy of Magnitude in Low-Rank Adaptation","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2603.04949","title":"TimeWarp: Evaluating Web Agents by Revisiting the Past","created":"2026-03-05","cited_by_count":7,"area":"agents"},{"id":"2604.15574","title":"Why Fine-Tuning Encourages Hallucinations and How to Fix It","created":"2026-04-16","cited_by_count":7,"area":"distill"},{"id":"2604.23994","title":"When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models","created":"2026-04-27","cited_by_count":7,"area":"diffusion"},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6,"area":"alignment"},{"id":"2410.02330","title":"Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2411.04358","title":"Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2501.15377","title":"Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation","created":"2025-01-26","cited_by_count":6,"area":null},{"id":"2502.12663","title":"Demystifying Multilingual Chain-of-Thought in Process Reward Modeling","created":"2025-02-18","cited_by_count":6,"area":"lr"},{"id":"2502.20420","title":"Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.12576","title":"RaSA: Rank-Sharing Low-Rank Adaptation","created":"2025-03-16","cited_by_count":6,"area":null}],"next_cursor":"100"}