Peng Wang
12 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces FinBoardBench, a novel evaluation suite using financial board games to demonstrate that current LLMs, despite strong static reasoning, fail at complex, dynamic wealth management and strategic decision-making.
The paper introduces FinBoardBench, a novel evaluation suite using financial board games to demonstrate that current LLMs, despite strong static reasoning, fail at complex, dynamic wealth management and strategic decision-making.
The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.
The paper proposes Agentic ASR, a closed-loop framework that treats ASR as a multi-turn refinement task, significantly improving semantic accuracy over traditional token-level metrics.
The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.
The paper proposes Agentic ASR, a closed-loop framework that treats ASR as a multi-turn refinement task, significantly improving semantic accuracy over traditional token-level metrics.
The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.
The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.
The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.
This paper introduces RACES, a framework for recursively assembling verifiable environments to enhance Large Language Model reasoning capabilities.
The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dialects, 6 English accents, dense terminology, older adult and child speech, and human-annotated translations.
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.