{"total":65,"rows":[{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"area":null},{"id":"2508.02087","title":"When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models","created":"2025-08-04","cited_by_count":50,"area":null},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44,"area":null},{"id":"2502.12170","title":"MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections","created":"2025-02-13","cited_by_count":31,"area":null},{"id":"2504.07096","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","created":"2025-04-09","cited_by_count":27,"area":null},{"id":"2503.04722","title":"Enough Coin Flips Can Make LLMs Act Bayesian","created":"2025-03-06","cited_by_count":22,"area":null},{"id":"2412.12004","title":"The Open Source Advantage in Large Language Models (LLMs)","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2507.03014","title":"Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!","created":"2025-07-02","cited_by_count":18,"area":null},{"id":"2503.04598","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2412.10424","title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","created":"2024-12-10","cited_by_count":13,"area":null},{"id":"2410.13184","title":"Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"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":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2510.07739","title":"MeSH: Memory-as-State-Highways for Recursive Transformers","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2410.13456","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2509.00454","title":"Universal Properties of Activation Sparsity in Modern Large Language Models","created":"2025-08-30","cited_by_count":7,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2505.18497","title":"The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models","created":"2025-05-24","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":"2601.19723","title":"Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2412.13377","title":"DateLogicQA: Benchmarking Temporal Biases in Large Language Models","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2506.17671","title":"TPTT: Transforming Pretrained Transformers into Titans","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2512.07612","title":"PCMind-2.1-Kaiyuan-2B Technical Report","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2605.17849","title":"Generating Pretraining Tokens from Organic Data for Data-Bound Scaling","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2503.05840","title":"Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2506.07731","title":"NeurIPS 2025 E2LM Competition : Early Training Evaluation of Language Models","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2510.15893","title":"Accelerating Frontier MoE Training with 3D Integrated Optics","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2511.04981","title":"Scaling depth capacity via zero/one-layer model expansion","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.14490","title":"Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.19363","title":"AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.27402","title":"How Language Models Organize and Structure Moral Knowledge","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2410.01818","title":"Integrating AI's Carbon Footprint into Risk Management Frameworks: Strategies and Tools for Sustainable Compliance in Banking Sector","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2410.19128","title":"Retrieving Implicit and Explicit Emotional Events Using Large Language Models","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2502.06635","title":"Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2502.12928","title":"Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2506.16289","title":"The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2512.12744","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.26603","title":"Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.03598","title":"Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.10655","title":"BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.03080","title":"Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.05858","title":"ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.02940","title":"When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.09160","title":"SwiftQK: Fast and Communication-Efficient Tensor Parallelism for Query-Key Normalization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.11034","title":"SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.18539","title":"Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.26621","title":"Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34449","title":"CORTEX: Learning to Share and Specialize in Dense Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.17495","title":"A Sense of Proprioception in Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19113","title":"From Copying to Composition: How Language Models Develop In-Context Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}