Preprint | Dezhi Yuhttps://halfrost.me/publication_types/preprint/PreprintHugoBlox Kit (https://hugoblox.com)en-usMon, 01 Jun 2026 00:00:00 +0000https://halfrost.me/media/favicon_hu_4db6119fa52e8e17.pngPreprinthttps://halfrost.me/publication_types/preprint/Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Studyhttps://halfrost.me/publication/dpo-chatbot-finetuning/Mon, 01 Jun 2026 00:00:00 +0000https://halfrost.me/publication/dpo-chatbot-finetuning/Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approacheshttps://halfrost.me/publication/bach-style-symbolic-music-generation/Mon, 01 Jun 2026 00:00:00 +0000https://halfrost.me/publication/bach-style-symbolic-music-generation/How Far Are Video Models from True Multimodal Reasoning?https://halfrost.me/publication/video-models-multimodal-reasoning/Wed, 01 Apr 2026 00:00:00 +0000https://halfrost.me/publication/video-models-multimodal-reasoning/AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigationhttps://halfrost.me/publication/adamixup-membership-inference-defense/Wed, 01 Jan 2025 00:00:00 +0000https://halfrost.me/publication/adamixup-membership-inference-defense/KVDirect: Distributed Disaggregated LLM Inferencehttps://halfrost.me/publication/kvdirect-disaggregated-llm-inference/Wed, 01 Jan 2025 00:00:00 +0000https://halfrost.me/publication/kvdirect-disaggregated-llm-inference/