EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
通过减小 KV cache size 加速 LLMRec 的推理
Blogs
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
COBRA, 链接离散编码和稠密表示的尝试
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
LC-Rec, LLM + RQ-VAE + 丰富的多任务训练
Sinkhorn Distance and Sinkhorn-Knopp Algorithm
关于利用 Sinkhorn 距离求解离散最优传输问题的记录
OneRec: Unifying Retrieve and Rank with Generative Recommender and Preference Alignment
OneRec, 端到端的推荐模型
Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
SimVQ, 坐标变换替代可学习 Codebook
Restructuring Vector Quantization with The Rotation Trick
一种利用 Rotation Trick 来替代 STE 的方案
Is Every Item Worth An Embedding?
是否每个 Item 都值得一个可学习的 Embedding 呢
Let’s Verify Step by Step
来自 OpenAI 的 process supervision
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
来自 DeepSeek 的 process supervision