6 papers
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with oppo…
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
He Du, Qiming Ge, Jiakai Hu +18
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented…
Semantic-guided Diverse Decoding for Large Language Model
Weijie Shi, Yue Cui, Yaguang Wu +7
Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than…
DIDS: Domain Impact-aware Data Sampling for Large Language Model Training
Weijie Shi, Jipeng Zhang, Yaguang Wu +8
Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance…
Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications
Huichao Zhang, Pengyu Wang, Manyi Li +2
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space plann…
LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation
Fan Deng, Yaguang Wu, Xinyang Yu +4
Recently, text-to-image models based on diffusion have achieved remarkable success in generating high-quality images. However, the challenge of personalized, controllable generatio…