KuaFu: Compressing Long User Behavior into Understanding at Billion Scale

arXiv:2609.31045 · cs.IR, cs.CL, cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.IR, cs.CL, cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/esbatmop/MNBVC

Terminology

• Hallucination — 21× in this paper · explained in 3 episodes
• Embeddings — 15× in this paper · explained in 2 episodes
• Generative Recommendation — 9× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Fidelity — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• AUC — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Latent Reasoning — 2× in this paper · explained in 2 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
• Language Modeling Is Compression
• GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification
• In-context Autoencoder for Context Compression in a Large Language Model
• The Llama 3 Herd of Models
• FOUNDv2: Learning Unified User Quantized Tokenizers for User Representation
• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
• 500xCompressor: Generalized Prompt Compression for Large Language Models
• REFRAG: Rethinking RAG based Decoding
• Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation
• Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
• Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
• Learning to Compress Prompts with Gist Tokens
• Qwen3-VL Technical Report
• Recommender Systems with Generative Retrieval
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• UserSumBench: A Benchmark Framework for Evaluating User Summarization Approaches
• Qwen3 Technical Report
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• An Empirical Study on Prompt Compression for Large Language Models

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG