Chen Peng
7 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper introduces a novel, efficient protocol for training Gradient Boosting Decision Trees (GBDT) on vertically partitioned data held by two mutually distrustful parties while ensuring complete anonymity by hiding record identifiers.
The paper introduces ProductWebGen, a benchmark for evaluating multimodal models' ability to generate consistent, high-fidelity product webpages from images and instructions, finding that separate editing-based workflows outperform unified models in overall webpage instruction following.
The paper introduces ProductWebGen, a benchmark for evaluating multimodal models' ability to generate consistent, high-fidelity product webpages from images and instructions, finding that separate editing-based workflows outperform unified models in overall webpage instruction following.
A new paradigm for generating personalized videos on demand from inferred user interest.
xDSM is a full-space, elastic DSM system built over CXL that transparently scales unmodified multithreaded applications by employing an OS-runtime co-design, dynamic data placement policy, and spatial locality-aware elasticity.
This paper proposes a protection framework for shared agent workflows to prevent tampered workflows from misleading downstream agents.
This paper presents ZipFusion, a method that enables attention to consume losslessly compressed key-value (KV) cache directly, improving model decode throughput and reducing memory-bandwidth bound.
Papers
ZipFusion: Fusing Lossless KV Decompression with Attention for Efficient LLM Decoding
This paper presents ZipFusion, a method that enables attention to consume losslessly compressed key-value (KV) cache directly, improving model decode throughput and reducing memory-bandwidth bound.