Motivated by recursive self-improvement (RSI), we study how LLM agents can learn through external memory without updating model parameters. Extracting useful experience from a single attempt is difficult: flawed reasoning can produce success, while poor execution can obscure a sound strategy. Preserving its value over...
Yu-Tong Song, Jiang Wu, Yu-Xin Ren et al.· 0 citations
DuoLM is introduced, a framework for fast and effective personalized recommendation that integrates a compact recommendation model with an efficient serving runtime that accelerates inference through virtual token IDs for embedding access, shared history computation, and CUDA Graph replay.
Jiang Wu, Yu-Tong Song, Hong-Bo Wang et al.· 0 citations
PsPLUG is proposed, a lightweight plug-in that learns a user-specific residual after accounting for the requested style, and better preserves user preferences while providing precise control over the balance between personalization and style adherence.
Yutong Song, Jiang Wu, Shaofan Yuan et al.· 1 citation
This work presents CARD, a hierarchical framework that achieves effective personalization through progressive refinement that first clusters users according to shared stylistic patterns and learns group-specific LoRA adapters, enabling robust generalization and strong low-resource performance.
The Evidence Package Benchmark is introduced, integrating 1,870 packages across six heterogeneous sources with explicit modality masks and evidence permissions, and EviBound, a protocol-aware evidence control framework is proposed, a protocol-aware evidence control framework for safer clinical NLP research.
Cheng-Yuan Gao, Jiang Wu, Tao Lu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
