{"total":19,"rows":[{"id":"2507.01663","title":"AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training","created":"2025-07-02","cited_by_count":41,"area":null},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2511.19413","title":"UniGame: Turning a Unified Multimodal Model Into Its Own Adversary","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2508.11086","title":"Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation","created":"2025-08-14","cited_by_count":4,"area":null},{"id":"2410.20856","title":"Strada-LLM: Graph LLM for traffic prediction","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2512.11844","title":"Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2504.09488","title":"Kongzi: A Historical Large Language Model with Fact Enhancement","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.15212","title":"Group Distributionally Robust Optimization with Flexible Sample Queries","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.06215","title":"Corrector Sampling in Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2605.12138","title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2510.21345","title":"$\\alpha$-LoRA: Effective Fine-Tuning via Base Model Rescaling","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.05286","title":"Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2608.11528","title":"Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}