{"total":171,"rows":[{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998,"area":null},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"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":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2506.09477","title":"On a few pitfalls in KL divergence gradient estimation for RL","created":"2025-06-11","cited_by_count":29,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2603.16856","title":"Online Experiential Learning for Language Models","created":"2026-03-17","cited_by_count":28,"area":null},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","cited_by_count":19,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2502.07365","title":"LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2410.05165","title":"Efficient Inference for Large Language Model-based Generative Recommendation","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2602.12222","title":"Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2412.09282","title":"CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2602.20816","title":"Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2408.03561","title":"MPC-Minimized Secure LLM Inference","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2408.10691","title":"Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches","created":"2024-08-20","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2606.10581","title":"ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models","created":"2026-06-09","cited_by_count":6,"area":null},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2602.16066","title":"Improving Interactive In-Context Learning from Natural Language Feedback","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2604.27083","title":"Co-Evolving Policy Distillation","created":"2026-04-29","cited_by_count":5,"area":null},{"id":"2607.13639","title":"OvisOCR2 Technical Report","created":"2026-07-15","cited_by_count":5,"area":null},{"id":"2412.09807","title":"LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering","created":"2024-12-13","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":"2504.17421","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":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2607.18110","title":"LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks","created":"2026-07-20","cited_by_count":4,"area":null},{"id":"2408.04998","title":"ProFuser: Progressive Fusion of Large Language Models","created":"2024-08-09","cited_by_count":3,"area":null},{"id":"2409.13949","title":"Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2512.09892","title":"Provably Learning from Modern Language Models via Low Logit Rank","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2601.11667","title":"Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2605.08605","title":"Lattice Deduction Transformers","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2605.31494","title":"Consolidating Rewarded Perturbations for LLM Post-Training","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.30383","title":"Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2411.14507","title":"From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2502.14305","title":"Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2502.14910","title":"EvoP: Robust LLM Inference via Evolutionary Pruning","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2504.15300","title":"Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2505.15252","title":"An Efficient Private GPT Never Autoregressively Decodes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.09885","title":"Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2603.22479","title":"Cognitive Training for Language Models: Towards General Capabilities via Cross-Entropy Games","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.05122","title":"Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.28638","title":"Learning Stateful Predictive Knowledge From Experience","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2608.20334","title":"Exploring the Performance Frontier of Compact Unified Image Generation Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2502.14075","title":"Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2503.03225","title":"Targeted Distillation for Sentiment Analysis","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2504.02521","title":"UNDO: Understanding Distillation as Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2512.24092","title":"HY-MT1.5 Technical Report","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2601.19862","title":"Calibration without Ground Truth","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2603.26556","title":"When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.16037","title":"Stochasticity in Tokenisation Improves Robustness","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.11260","title":"Curriculum Learning-Guided Progressive Distillation in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.17531","title":"Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.20005","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.22240","title":"Unlocking Proactivity in Task-Oriented Dialogue","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.04733","title":"LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.15196","title":"Subjective Risk Decomposition: A New View for Uncertainty Quantification","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.20918","title":"OPOD: On-Policy Omni Distillation","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.27770","title":"Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.13721","title":"Capacity-Dependent Effects of Data Selection for Reasoning","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2609.26216","title":"Beyond Imitation: Auditing the Recoverability of Reasoning in Distilled Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2409.17171","title":"Cross-Domain Content Generation with Domain-Specific Small Language Models","created":"2024-09-19","cited_by_count":0,"area":null}],"next_cursor":"100"}