Fine-Tuning Language Models with Just Forward Passes
零阶优化 & 收敛理论
LLM
User Behavior Simulation with Large Language Model based Agents
基于认知科学实现推荐用户模拟, 并以此探究信息茧房、从众心理等现象
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
在知识图谱上实现 LLM, KG 的交替推理
HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
利用 LLM 高效生成个性化广告语
Distilling LLM Agent into Small Models with Retrieval and Code Tools
Agent Distillation
Structured Agent Distillation for Large Language Model
Agent 的 Reasoning & Action 蒸馏
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
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
LC-Rec, LLM + RQ-VAE + 丰富的多任务训练
Base of RoPE Bounds Context Length
讨论 RoPE base 对于相似 Tokens 感知能力的影响
Round and Round We Go! What makes Rotary Positional Encodings useful?
理解 RoPE 的高低频