{"total":243,"rows":[{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2408.05517","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","created":"2024-08-10","cited_by_count":355,"area":"mllm"},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2407.05000","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","created":"2024-07-06","cited_by_count":141,"area":null},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"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":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80,"area":null},{"id":"2407.18242","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","created":"2024-07-25","cited_by_count":77,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39,"area":null},{"id":"2401.05605","title":"Scaling Laws for Forgetting When Fine-Tuning Large Language Models","created":"2024-01-11","cited_by_count":38,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2410.12694","title":"VividMed: Vision Language Model with Versatile Visual Grounding for Medicine","created":"2024-10-16","cited_by_count":28,"area":"mllm"},{"id":"2410.23831","title":"FRoundation: Are Foundation Models Ready for Face Recognition?","created":"2024-10-31","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":"2411.19557","title":"Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning","created":"2024-11-29","cited_by_count":22,"area":null},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2410.07170","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","created":"2024-10-09","cited_by_count":20,"area":null},{"id":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2503.10337","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","created":"2025-03-13","cited_by_count":19,"area":"inference"},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2502.16377","title":"Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines","created":"2025-02-22","cited_by_count":18,"area":null},{"id":"2601.04025","title":"Simulated Students in Tutoring Dialogues: Substance or Illusion?","created":"2026-01-07","cited_by_count":18,"area":null},{"id":"2406.13175","title":"Sparse High Rank Adapters","created":"2024-06-19","cited_by_count":17,"area":null},{"id":"2406.08798","title":"FouRA: Fourier Low Rank Adaptation","created":"2024-06-13","cited_by_count":15,"area":"diffusion"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2501.02892","title":"FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection","created":"2025-01-06","cited_by_count":14,"area":null},{"id":"2501.03800","title":"MADation: Face Morphing Attack Detection with Foundation Models","created":"2025-01-07","cited_by_count":14,"area":null},{"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":"2510.01938","title":"StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold","created":"2025-10-02","cited_by_count":14,"area":null},{"id":"2408.10774","title":"Flexora: Flexible Low Rank Adaptation for Large Language Models","created":"2024-08-20","cited_by_count":13,"area":null},{"id":"2410.14961","title":"LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2501.13669","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2409.14057","title":"Co-occurrence is not Factual Association in Language Models","created":"2024-09-21","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":"2503.01877","title":"Starjob: Dataset for LLM-Driven Job Shop Scheduling","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2505.19819","title":"FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets","created":"2025-05-26","cited_by_count":12,"area":null},{"id":"2512.23165","title":"Evaluating Parameter Efficient Methods for RLVR","created":"2025-12-29","cited_by_count":12,"area":null},{"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":"2410.15580","title":"Language Models are Symbolic Learners in Arithmetic","created":"2024-10-21","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":"2412.19191","title":"Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models","created":"2024-12-26","cited_by_count":10,"area":null},{"id":"2502.14538","title":"LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2502.15436","title":"Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","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":"2501.04315","title":"RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation","created":"2025-01-08","cited_by_count":9,"area":null},{"id":"2502.15828","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","created":"2025-02-20","cited_by_count":9,"area":"moe"},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.18356","title":"The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"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":"2603.08823","title":"Fish Audio S2 Technical Report","created":"2026-03-09","cited_by_count":9,"area":null},{"id":"2410.04060","title":"LoRTA: Low Rank Tensor Adaptation of Large Language Models","created":"2024-10-05","cited_by_count":7,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2507.06558","title":"The Primacy of Magnitude in Low-Rank Adaptation","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2409.13931","title":"On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists","created":"2024-09-20","cited_by_count":6,"area":null},{"id":"2406.17740","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2407.16712","title":"Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters","created":"2024-07-22","cited_by_count":5,"area":null},{"id":"2410.19925","title":"Improving Multimodal Large Language Models Using Continual Learning","created":"2024-10-25","cited_by_count":5,"area":"mllm"},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.10496","title":"CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs","created":"2025-05-15","cited_by_count":5,"area":null},{"id":"2505.20237","title":"Efficient Speech Translation through Model Compression and Knowledge Distillation","created":"2025-05-26","cited_by_count":5,"area":"distill"},{"id":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2508.08730","title":"Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation","created":"2025-08-12","cited_by_count":5,"area":null},{"id":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","cited_by_count":5,"area":"alignment"},{"id":"2511.18600","title":"NeAR: Coupled Neural Asset-Renderer Stack","created":"2025-11-23","cited_by_count":5,"area":null},{"id":"2410.16088","title":"Fine-Tuning LLMs for Reliable Medical Question-Answering Services","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2502.07783","title":"Curvature Tuning: Provable Training-free Model Steering From a Single Parameter","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2505.22444","title":"On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4,"area":"lr"},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2508.06953","title":"BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2509.04884","title":"L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2511.00051","title":"Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT","created":"2025-10-28","cited_by_count":4,"area":null},{"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":"2409.17538","title":"LoRA Provides Differential Privacy by Design via Random Sketching","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2412.20891","title":"DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2501.12067","title":"EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2502.01074","title":"Omni-Mol: Multitask Molecular Model for Any-to-any Modalities","created":"2025-02-03","cited_by_count":3,"area":"mllm"},{"id":"2502.12200","title":"Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2503.08045","title":"Adapting Large Language Models for Parameter-Efficient Log Anomaly Detection","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2503.22517","title":"Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities","created":"2025-03-28","cited_by_count":3,"area":"moe"},{"id":"2504.21239","title":"Memorization and Knowledge Injection in Gated LLMs","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2505.14238","title":"ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2507.04221","title":"Context Tuning for In-Context Optimization","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2512.22827","title":"FasterPy: An LLM-based Code Execution Efficiency Optimization Framework","created":"2025-12-28","cited_by_count":3,"area":null},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2605.31484","title":"Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence","created":"2026-05-29","cited_by_count":3,"area":null}],"next_cursor":"100"}