Cheng Wang
9 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes a novel CRT-based asymptotically perfect Disjunctive Hierarchical Secret Sharing (DHSS) scheme that overcomes security and information rate limitations of existing methods.
The paper proposes two new asymptotically ideal and secure Hierarchical Secret Sharing (HSS) schemes, disjunctive and conjunctive, utilizing the Chinese Remainder Theorem (CRT) over an integer ring and one-way functions.
The paper introduces a novel, asymptotically ideal Conjunctive Hierarchical Secret Sharing (CHSS) scheme using the Chinese Remainder Theorem (CRT) for polynomial rings, achieving high security and an optimal information rate.
The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.
The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.
This paper investigates the thermal constraints of deploying AI compute infrastructure in space, comparing GPUs and compute-in-memory (CIM) accelerators using a co-design methodology.
This paper investigates the thermal constraints of deploying AI compute infrastructure in space, comparing GPUs and compute-in-memory (CIM) accelerators using a co-design methodology.
This paper investigates the thermal constraints of deploying AI compute infrastructure in space, comparing GPUs and compute-in-memory (CIM) accelerators using a co-design methodology.
This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.
Papers
Multimodal Graph RAG for Long-range Visually Rich Document Understanding
This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.