{"total":260,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2310.00656","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","created":"2023-10-01","cited_by_count":109,"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":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"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":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90,"area":null},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88,"area":null},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"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":"2405.17604","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","created":"2024-05-27","cited_by_count":76,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2505.04481","title":"CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation","created":"2025-05-07","cited_by_count":67,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2405.15179","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","created":"2024-05-24","cited_by_count":52,"area":null},{"id":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"area":null},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48,"area":null},{"id":"2404.02893","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","created":"2024-04-03","cited_by_count":47,"area":null},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2401.13979","title":"Routoo: Learning to Route to Large Language Models Effectively","created":"2024-01-25","cited_by_count":34,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2309.15806","title":"Lyra: Orchestrating Dual Correction in Automated Theorem Proving","created":"2023-09-27","cited_by_count":25,"area":null},{"id":"2501.15427","title":"OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas","created":"2025-01-26","cited_by_count":25,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2407.21075","title":"Apple Intelligence Foundation Language Models","created":"2024-07-29","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":"2405.14804","title":"Can LLMs Solve longer Math Word Problems Better?","created":"2024-05-23","cited_by_count":22,"area":null},{"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":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2410.07170","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","created":"2024-10-09","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":"2406.10368","title":"A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2410.09432","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","created":"2024-10-12","cited_by_count":18,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2504.09602","title":"Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations","created":"2025-04-13","cited_by_count":18,"area":null},{"id":"2406.08903","title":"Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models","created":"2024-06-13","cited_by_count":17,"area":null},{"id":"2505.00662","title":"DeepCritic: Deliberate Critique with Large Language Models","created":"2025-05-01","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2311.11482","title":"Meta Prompting for AI Systems","created":"2023-11-20","cited_by_count":16,"area":null},{"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":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2512.14051","title":"OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value","created":"2025-12-16","cited_by_count":15,"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":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2506.20629","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","created":"2025-06-25","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":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2409.17972","title":"BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2409.14254","title":"Instruction Following without Instruction Tuning","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2410.13502","title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs","created":"2024-10-17","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":"2402.13572","title":"AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2404.08679","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","created":"2024-04-07","cited_by_count":11,"area":null},{"id":"2404.13082","title":"Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning","created":"2024-04-17","cited_by_count":11,"area":null},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2410.01727","title":"Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2310.13021","title":"AI for Mathematics: A Cognitive Science Perspective","created":"2023-10-19","cited_by_count":10,"area":null},{"id":"2406.14036","title":"Towards Infinite-Long Prefix in Transformer","created":"2024-06-20","cited_by_count":10,"area":null},{"id":"2410.09344","title":"DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models","created":"2024-10-12","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":"2509.22738","title":"Enabling Approximate Joint Sampling in Diffusion LMs","created":"2025-09-25","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":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2401.16818","title":"H2O-Danube-1.8B Technical Report","created":"2024-01-30","cited_by_count":9,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2410.05357","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"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":"2505.21439","title":"Towards Better Instruction Following Retrieval Models","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2602.05879","title":"EuroLLM-22B: Technical Report","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2410.01870","title":"PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2502.06572","title":"LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2505.21505","title":"How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective","created":"2025-05-27","cited_by_count":8,"area":null}],"next_cursor":"100"}