{"total":115,"rows":[{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2402.05120","title":"More Agents Is All You Need","created":"2024-02-03","cited_by_count":180,"area":"agents"},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67,"area":null},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"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":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41,"area":"distill"},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"area":null},{"id":"2410.03777","title":"Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling","created":"2024-10-03","cited_by_count":28,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"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":"2411.18729","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","created":"2024-11-27","cited_by_count":22,"area":null},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2406.02224","title":"FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models","created":"2024-06-04","cited_by_count":19,"area":null},{"id":"2406.16330","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2410.09303","title":"Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles","created":"2024-10-11","cited_by_count":15,"area":null},{"id":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14,"area":null},{"id":"2510.24695","title":"AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis","created":"2025-10-28","cited_by_count":14,"area":"agents"},{"id":"2404.09170","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","created":"2024-04-14","cited_by_count":13,"area":"lr"},{"id":"2406.03280","title":"FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","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":"2412.07448","title":"Efficient Dynamic Ensembling for Multiple LLM Experts","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2502.08020","title":"Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8,"area":"distill"},{"id":"2505.12570","title":"Batched Self-Consistency Improves LLM Relevance Assessment and Ranking","created":"2025-05-18","cited_by_count":8,"area":"lr"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2602.05495","title":"Transport and Merge: Cross-Architecture Merging for Large Language Models","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2402.16107","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2510.00931","title":"Making, not Taking, the Best of N","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2412.01289","title":"Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion","created":"2024-12-02","cited_by_count":5,"area":"mllm"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2502.19982","title":"Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models","created":"2025-02-27","cited_by_count":5,"area":"safety"},{"id":"2503.10325","title":"Collaborative Speculative Inference for Efficient LLM Inference Serving","created":"2025-03-13","cited_by_count":5,"area":"inference"},{"id":"2504.12364","title":"DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging","created":"2025-04-16","cited_by_count":5,"area":null},{"id":"2509.03956","title":"World Model Implanting for Test-time Adaptation of Embodied Agents","created":"2025-09-04","cited_by_count":5,"area":"wm"},{"id":"2512.14954","title":"Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation","created":"2025-12-16","cited_by_count":5,"area":"distill"},{"id":"2406.12527","title":"FuseGen: PLM Fusion for Data-generation based Zero-shot Learning","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.10902","title":"Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2511.00903","title":"ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval","created":"2025-11-02","cited_by_count":4,"area":"rag"},{"id":"2406.19227","title":"Aligning Teacher with Student Preferences for Tailored Training Data Generation","created":"2024-06-27","cited_by_count":3,"area":"distill"},{"id":"2410.01508","title":"Disentangling Latent Shifts of In-Context Learning with Weak Supervision","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2506.15721","title":"Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3,"area":"alignment"},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2410.12613","title":"Exploring Model Kinship for Merging Large Language Models","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2502.04492","title":"Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents","created":"2025-02-06","cited_by_count":2,"area":"agents"},{"id":"2503.06138","title":"System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2508.03329","title":"Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach","created":"2025-08-05","cited_by_count":2,"area":"agents"},{"id":"2508.17669","title":"A Taxonomy of Transcendence","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2508.20492","title":"IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2510.04682","title":"TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.08102","title":"Lossless Vocabulary Reduction for Auto-Regressive Language Models","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2601.22030","title":"Per-parameter Task Arithmetic for Unlearning in Large Language Models","created":"2026-01-29","cited_by_count":2,"area":"safety"},{"id":"2604.01674","title":"Can Heterogeneous Language Models Be Fused?","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2604.22823","title":"PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging","created":"2026-04-18","cited_by_count":2,"area":"mllm"},{"id":"2605.21699","title":"X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation","created":"2026-05-20","cited_by_count":2,"area":"distill"},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2504.06562","title":"FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion","created":"2025-04-09","cited_by_count":1,"area":"alignment"},{"id":"2505.16221","title":"LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.23844","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.04459","title":"Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2510.18321","title":"Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding","created":"2025-10-21","cited_by_count":1,"area":"mllm"},{"id":"2510.19507","title":"Teaming LLMs to Detect and Mitigate Hallucinations","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.22730","title":"ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.22056","title":"Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch","created":"2026-03-23","cited_by_count":1,"area":"distill"},{"id":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2606.30518","title":"Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts","created":"2026-06-29","cited_by_count":1,"area":"rag"},{"id":"2607.18026","title":"Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2607.20918","title":"OPOD: On-Policy Omni Distillation","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2503.22747","title":"LeForecast: Enterprise Hybrid Forecast by Time Series Intelligence","created":"2025-03-27","cited_by_count":0,"area":null}],"next_cursor":"100"}