{"total":30,"rows":[{"id":"2509.23024","title":"Tracing the Representation Geometry of Language Models from Pretraining to Post-training","created":"2025-09-27","cited_by_count":35,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2505.12306","title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2602.05717","title":"Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.16279","title":"Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design","created":"2026-04-17","cited_by_count":4,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2508.20230","title":"Coresets from Trajectories: Selecting Data via Correlation of Loss Differences","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2504.13125","title":"LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2506.00175","title":"Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2605.03373","title":"Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.27774","title":"Fine-Tuning Dynamics of In-Context Factual Recall in Transformers","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2606.26857","title":"LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.30699","title":"Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.23260","title":"Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31214","title":"Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33620","title":"Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.09164","title":"Training Language Models To Be Coherent Decision-Makers","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}