{"total":21,"rows":[{"id":"2408.07055","title":"LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs","created":"2024-08-13","cited_by_count":144,"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":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2506.07725","title":"ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2411.16454","title":"Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2502.01677","title":"Position: AI Scaling: From Up to Down and Out","created":"2025-02-02","cited_by_count":5,"area":null},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2505.18557","title":"TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2501.13779","title":"Not Every AI Problem is a Data Problem: We Should Be Intentional About Data Scaling","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2506.01474","title":"Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.22621","title":"IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2606.20937","title":"Learning through Internalization","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2510.26683","title":"Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2608.14290","title":"Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.31688","title":"Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.35290","title":"EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01118","title":"Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02516","title":"Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04810","title":"Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.15501","title":"Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}