{"total":144,"rows":[{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240,"area":"lr"},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2407.20311","title":"Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process","created":"2024-07-29","cited_by_count":108,"area":"lr"},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2412.06538","title":"Understanding Factual Recall in Transformers via Associative Memories","created":"2024-12-09","cited_by_count":51,"area":null},{"id":"2408.16293","title":"Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems","created":"2024-08-29","cited_by_count":50,"area":"lr"},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2509.26030","title":"Muon Outperforms Adam in Tail-End Associative Memory Learning","created":"2025-09-30","cited_by_count":46,"area":null},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2503.21676","title":"How do language models learn facts? Dynamics, curricula and hallucinations","created":"2025-03-27","cited_by_count":37,"area":null},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33,"area":null},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2505.18761","title":"How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark","created":"2025-05-24","cited_by_count":28,"area":"lr"},{"id":"2503.22165","title":"Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models","created":"2025-03-28","cited_by_count":25,"area":"lr"},{"id":"2412.06540","title":"Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2405.09220","title":"ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models","created":"2024-05-15","cited_by_count":18,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2410.01380","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2503.05212","title":"Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning","created":"2025-03-07","cited_by_count":16,"area":"lr"},{"id":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2406.18400","title":"Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers","created":"2024-06-26","cited_by_count":15,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2501.05078","title":"Analyzing Memorization in Large Language Models through the Lens of Model Attribution","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2603.26554","title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","created":"2026-03-27","cited_by_count":14,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2411.04920","title":"Enabling LLM Knowledge Analysis via Extensive Materialization","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.15962","title":"Pre-training Limited Memory Language Models with Internal and External Knowledge","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2605.10923","title":"Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2405.13209","title":"Investigating Symbolic Capabilities of Large Language Models","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2603.17435","title":"ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression","created":"2026-03-18","cited_by_count":8,"area":"inference"},{"id":"2605.19407","title":"A Bitter Lesson for Data Filtering","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2606.26387","title":"Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs","created":"2026-06-24","cited_by_count":8,"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":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2604.15574","title":"Why Fine-Tuning Encourages Hallucinations and How to Fix It","created":"2026-04-16","cited_by_count":7,"area":"distill"},{"id":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"area":"synth"},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2505.20993","title":"Who Reasons in the Large Language Models?","created":"2025-05-27","cited_by_count":5,"area":"lr"},{"id":"2602.01605","title":"Universal Redundancies in Time Series Foundation Models","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2502.04066","title":"Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training","created":"2025-02-06","cited_by_count":4,"area":null},{"id":"2506.18233","title":"Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2508.20755","title":"Provable Benefits of In-Tool Learning for Large Language Models","created":"2025-08-28","cited_by_count":4,"area":"agents"},{"id":"2510.10964","title":"Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2602.15156","title":"Panini: Continual Learning in Token Space via Structured Memory","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2605.09724","title":"Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2502.01717","title":"Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2504.03635","title":"Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models","created":"2025-04-04","cited_by_count":3,"area":"lr"},{"id":"2504.17562","title":"When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2605.05189","title":"Sharp Capacity Thresholds in Linear Associative Memory: From Top-1 Retrieval to Tail-Average Learning","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2605.10129","title":"Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.09730","title":"SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research","created":"2026-06-08","cited_by_count":3,"area":"agents"},{"id":"2606.19172","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2408.06087","title":"Building Decision Making Models Through Language Model Regime","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2409.13421","title":"State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2409.15825","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2502.05159","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.12899","title":"A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2504.01450","title":"CASCADE Your Datasets for Cross-Mode Knowledge Retrieval of Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2505.04528","title":"Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2505.14070","title":"Enhancing LLMs via High-Knowledge Data Selection","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.12312","title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2507.02529","title":"RetrySQL: text-to-SQL training with retry data for self-correcting query generation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2407.15425","title":"Empirical Capacity Model for Self-Attention Neural Networks","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2501.05787","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2502.14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2504.06823","title":"Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.16570","title":"URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.18369","title":"Small Models, Smarter Learning: The Power of Joint Task Training","created":"2025-05-23","cited_by_count":1,"area":null}],"next_cursor":"100"}