{"total":223,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166,"area":"mllm"},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109,"area":"lr"},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2401.07324","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","created":"2024-01-14","cited_by_count":93,"area":"agents"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2406.13542","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","created":"2024-06-19","cited_by_count":73,"area":"alignment"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67,"area":null},{"id":"2401.10334","title":"DrugAssist: A Large Language Model for Molecule Optimization","created":"2023-12-28","cited_by_count":59,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"area":null},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51,"area":"lr"},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41,"area":null},{"id":"2501.15915","title":"Parametric Retrieval Augmented Generation","created":"2025-01-27","cited_by_count":38,"area":"rag"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33,"area":"lr"},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"id":"2310.11616","title":"Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2402.11893","title":"Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"area":"alignment"},{"id":"2411.15708","title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training","created":"2024-11-24","cited_by_count":26,"area":"moe"},{"id":"2506.14175","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","created":"2025-06-17","cited_by_count":25,"area":"alignment"},{"id":"2312.17653","title":"LARP: Language-Agent Role Play for Open-World Games","created":"2023-12-24","cited_by_count":24,"area":"agents"},{"id":"2310.06504","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","created":"2023-10-10","cited_by_count":23,"area":null},{"id":"2401.07004","title":"Extending LLMs' Context Window with 100 Samples","created":"2024-01-13","cited_by_count":21,"area":null},{"id":"2510.01982","title":"Fine-Grained GRPO for Precise Preference Alignment in Flow Models","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2412.11919","title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation","created":"2024-12-16","cited_by_count":20,"area":null},{"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":"2508.03700","title":"MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning","created":"2025-07-19","cited_by_count":19,"area":"agents"},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16,"area":"rag"},{"id":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2403.01197","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","created":"2024-03-02","cited_by_count":15,"area":"alignment"},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"id":"2506.23219","title":"UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding","created":"2025-06-29","cited_by_count":15,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"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":"2404.01067","title":"Exploring the Mystery of Influential Data for Mathematical Reasoning","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2409.07045","title":"Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2506.18369","title":"RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models","created":"2025-06-23","cited_by_count":13,"area":"mllm"},{"id":"2411.11027","title":"BianCang: A Traditional Chinese Medicine Large Language Model","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2502.15401","title":"Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning","created":"2025-02-21","cited_by_count":12,"area":"lr"},{"id":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","cited_by_count":12,"area":null},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"area":"lr"},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2512.19134","title":"QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation","created":"2025-12-22","cited_by_count":12,"area":"rag"},{"id":"2603.01097","title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2502.05911","title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","created":"2025-02-09","cited_by_count":11,"area":"safety"},{"id":"2512.23126","title":"InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization","created":"2025-12-29","cited_by_count":11,"area":"alignment"},{"id":"2404.16766","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10,"area":"lr"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2502.02988","title":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","created":"2025-02-05","cited_by_count":9,"area":"lr"},{"id":"2503.01887","title":"When Continue Learning Meets Multimodal Large Language Model: A Survey","created":"2025-02-27","cited_by_count":9,"area":"mllm"},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2402.08015","title":"Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets","created":"2024-02-12","cited_by_count":8,"area":null},{"id":"2409.03810","title":"How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2410.04717","title":"$\\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","cited_by_count":7,"area":"synth"},{"id":"2507.05227","title":"NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Driving","created":"2025-07-07","cited_by_count":7,"area":"mllm"},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","cited_by_count":7,"area":"synth"},{"id":"2602.21992","title":"PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2405.19265","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2406.11474","title":"How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment","created":"2024-06-17","cited_by_count":6,"area":"alignment"},{"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":"2505.21963","title":"LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents","created":"2025-05-28","cited_by_count":6,"area":"agents"},{"id":"2507.10605","title":"RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services","created":"2025-07-13","cited_by_count":6,"area":null},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","cited_by_count":6,"area":"alignment"},{"id":"2406.01392","title":"Sparsity-Accelerated Training for Large Language Models","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2408.08003","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","created":"2024-08-15","cited_by_count":5,"area":null}],"next_cursor":"100"}