{"total":13,"rows":[{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711,"area":null},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2602.23823","title":"APPO: Attention-guided Perception Policy Optimization for Video Reasoning","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2603.09065","title":"Learning Adaptive LLM Decoding","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2606.15621","title":"Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2608.24300","title":"Contrastive Branch Policy Optimization","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2510.10224","title":"Text2Token: Unsupervised Text Representation Learning with Token Target Prediction","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.19739","title":"TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2607.05185","title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}