{"total":69,"rows":[{"id":"2505.11792","title":"Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling","created":"2025-05-17","cited_by_count":45,"area":null},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2506.09991","title":"Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation","created":"2025-06-11","cited_by_count":30,"area":null},{"id":"2512.23333","title":"CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2512.14051","title":"OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value","created":"2025-12-16","cited_by_count":15,"area":null},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2506.16393","title":"From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling","created":"2025-06-19","cited_by_count":8,"area":null},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2602.07909","title":"SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization","created":"2026-02-08","cited_by_count":8,"area":null},{"id":"2506.19794","title":"Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study","created":"2025-06-24","cited_by_count":7,"area":null},{"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":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2503.09499","title":"MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?","created":"2025-03-12","cited_by_count":6,"area":null},{"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":"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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2601.04611","title":"Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2602.02099","title":"Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2510.08203","title":"Memory Retrieval and Consolidation in Large Language Models through Function Tokens","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.17715","title":"QueST: Incentivizing LLMs to Generate Difficult Problems","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2512.01210","title":"Knowledge Graph Augmented Large Language Models for Disease Prediction","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2509.21091","title":"Best-of-$\\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2509.26376","title":"ScalingAR: Scaling Confidence for Autoregressive Image Generation","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2606.04465","title":"SePO: Self-Evolving Prompt Agent for System Prompt Optimization","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2502.12669","title":"Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2506.03077","title":"StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2509.06524","title":"LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.23595","title":"Timber: Training-free Instruct Model Refining with Base via Effective Rank","created":"2025-09-28","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":"2607.26253","title":"Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2511.07940","title":"ISExplore:Informative Segment Selection for Efficient Personalized 3D Talking Face Generation","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2601.23006","title":"InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.13773","title":"On Representation Redundancy in Large-Scale Instruction Tuning Data Selection","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2605.19285","title":"Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.32029","title":"When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors","created":"2026-06-30","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":"2609.07183","title":"CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2505.24500","title":"TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.06127","title":"PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2510.01427","title":"A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.09709","title":"The Idola Tribus of AI: Large Language Models tend to perceive order where none exists","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2601.03672","title":"Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2603.27164","title":"daVinci-LLM:Towards the Science of Pretraining","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.17614","title":"Characterizing Model-Native Skills","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.12906","title":"Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.30442","title":"The FIL Hypothesis: Inductive Biases Help with Kernel Engineering","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.02118","title":"Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.04322","title":"DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.05439","title":"CriticGen: Generation-Aware Evaluation as Actionable Feedback","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.24186","title":"LIMIT: Less Is More for Instruction Tuning in Text-to-SQL","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36246","title":"Learning from Teacher Continuations at Student States","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.10536","title":"Decoupling Exploration from Optimization in RLVR","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.16531","title":"Support or Magnitude? Characterizing Neuron Relevance for Instruction Data Selection","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18634","title":"Geometric Calibration of Supervised Fine-Tuning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}