{"total":109,"rows":[{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17,"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":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"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":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","cited_by_count":11,"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":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","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":"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":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2505.20211","title":"PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2508.02932","title":"PLoRA: Efficient Concurrent LoRA Training for Large Language Models","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2607.18293","title":"One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context","created":"2026-06-30","cited_by_count":6,"area":"distill"},{"id":"2412.20004","title":"Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices","created":"2024-12-28","cited_by_count":5,"area":null},{"id":"2501.00339","title":"GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2505.16789","title":"Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2507.07186","title":"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2512.15634","title":"How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness","created":"2025-12-17","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2511.00130","title":"A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2512.10955","title":"Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2601.06305","title":"Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models","created":"2026-01-09","cited_by_count":4,"area":"safety"},{"id":"2602.09492","title":"Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2504.08780","title":"How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2506.09093","title":"Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2509.03740","title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","created":"2025-09-03","cited_by_count":3,"area":"mllm"},{"id":"2510.05532","title":"Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation","created":"2025-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2601.21794","title":"Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models","created":"2026-01-29","cited_by_count":3,"area":"mllm"},{"id":"2603.03995","title":"Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2605.01929","title":"Exploring Data-Free LoRA Transferability for Video Diffusion Models","created":"2026-05-03","cited_by_count":3,"area":"diffusion"},{"id":"2605.20296","title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.02437","title":"On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2606.03723","title":"Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2501.19389","title":"Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2510.19155","title":"VeFA: Vector-Based Feature Space Adaptation for Robust Model Fine-Tuning","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2601.06788","title":"Artificial Entanglement in the Fine-Tuning of Large Language Models","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2601.22708","title":"A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.14493","title":"Fine-tuning MLLMs Without Forgetting Is Easier Than You Think","created":"2026-03-15","cited_by_count":2,"area":"lr"},{"id":"2605.19018","title":"LoRA vs. Full Fine-Tuning: A Theoretical Perspective","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2607.23711","title":"The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2504.05343","title":"AROMA: Autonomous Rank-one Matrix Adaptation","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2507.04487","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2509.21637","title":"BoHA: Blockwise Hadamard Product Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.10683","title":"LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2601.14051","title":"Kakugo: Distillation of Low-Resource Languages into Small Language Models","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2601.22818","title":"Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"mechinterp"},{"id":"2603.03389","title":"Towards Improved Sentence Representations using Token Graphs","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.13306","title":"Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.04516","title":"GAIN: Multiplicative Modulation for Domain Adaptation","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.18124","title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.07959","title":"Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.29498","title":"Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.01558","title":"Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.13867","title":"Muon$^p$: Muon with Fractional Spectral Powers","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.20911","title":"Latent Personal Memory: Represent personal memory as dynamic soft prompts","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.05001","title":"TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.21975","title":"On the Convergence of Stochastic Low-Rank Adaptation","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2609.23594","title":"Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2502.13474","title":"Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2505.02255","title":"Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic Dataset","created":"2025-05-04","cited_by_count":0,"area":"diffusion"},{"id":"2506.02018","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","created":"2025-05-28","cited_by_count":0,"area":"alignment"},{"id":"2507.01841","title":"Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2509.04398","title":"IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.09801","title":"HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning","created":"2025-09-11","cited_by_count":0,"area":"lr"},{"id":"2510.06982","title":"Revisiting Mixout: An Overlooked Path to Robust Finetuning","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2511.01794","title":"Random Initialization of Gated Sparse Adapters","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2512.17983","title":"Parameter-Efficient Fine-Tuning for HAR: Integrating LoRA and QLoRA into Transformer Models","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2512.19219","title":"Selective LoRA for Visual Tokens and Attention Heads","created":"2025-12-22","cited_by_count":0,"area":"mllm"},{"id":"2601.12937","title":"On the Evidentiary Limits of Membership Inference for Copyright Auditing","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.07479","title":"ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.10404","title":"Modular Multi-Task Learning for Chemical Reaction Prediction","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.24148","title":"HumanOrbit: 3D Human Reconstruction as 360{\\deg} Orbit Generation","created":"2026-02-27","cited_by_count":0,"area":"diffusion"},{"id":"2603.00720","title":"MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search","created":"2026-02-28","cited_by_count":0,"area":"mllm"},{"id":"2603.16428","title":"An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.17504","title":"Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.04440","title":"Training Transformers in Cosine Coefficient Space","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.08956","title":"Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.18740","title":"Autonomous Skeletal Landmark Localization towards Agentic C-Arm Control","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.01077","title":"Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.06330","title":"Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07111","title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08174","title":"CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.19028","title":"Learning When to Adapt","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.26292","title":"Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2605.27836","title":"Symmetry Defeats Auditing","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.06738","title":"Modular Monolingual Adaptation using Pretrained Language Models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.16244","title":"Activating Latent Security Knowledge through LLM-Guided Risk Analysis for Secure Code Generation","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.04306","title":"SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation","created":"2026-07-05","cited_by_count":0,"area":"distill"},{"id":"2607.04510","title":"Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.16637","title":"TopoTuner: Topological Finetuning of Large Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.07786","title":"Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.25677","title":"Learning New Facts with QLoRA: An Acquisition-Retention Frontier","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":"100"}