{"total":10,"rows":[{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2602.03396","title":"Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2602.17395","title":"SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2601.21503","title":"MAR: Efficient Large Language Models via Module-aware Architecture Refinement","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.00072","title":"XekRung Technical Report","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.20749","title":"The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.28869","title":"Balancing Multimodal Learning through Label Space Reshaping","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.03091","title":"BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.23124","title":"PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.02299","title":"Dual-Selective Network for Domain-Incremental Change Detection","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":null}