3 citations · 3 across the 8 of their papers we have counts for
4 papers · 1 filter
FastE: Readout-Triggered Token Compression for LLM Embedding Inference
Jinsong Shu, Jinyong Wen, Baokun Wang +4
In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qwen3-Embedding and Qwen3-VL-E…
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Bin Dou, Junru Zhang, Zhaoyi Yuan +6
User representation learning in real-world industrial scenarios is commonly scaled by increasing user amount, behavioral sequence length and model size. However, existing methods f…
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
Jiahao Yuan, Yike Xu, Jinyong Wen +9
Industrial-scale user representation learning requires balancing robust universality with acute task-sensitivity. However, existing paradigms primarily yield static, task-agnostic…
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
Jiahao Yuan, Yike Xu, Jinyong Wen +8
Decoder-only large language models are increasingly used as behavioral encoders for user representation learning, yet the impact of attention masking on the quality of user embeddi…