Yu Wang

The paper introduces CREBench, a comprehensive benchmark for evaluating Large Language Models (LLMs) on cryptographic binary reverse engineering, finding that while LLMs show promise, human experts still maintain a significant advantage.

GoAT-X introduces a novel framework that structures cross-chain smart contract auditing as a Graph of Auditing Thoughts, significantly improving the detection of complex, semantic vulnerabilities in multi-chain token transactions.

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to perform active cross-modal perception.

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to perform active cross-modal perception.

The paper proposes LaSR, a context-aware training paradigm that uses latent reasoning to significantly improve speech recognition, especially for specialized terminology, without adding latency.

The paper proposes LaSR, a context-aware training paradigm that uses latent reasoning to significantly improve speech recognition, especially for specialized terminology, without adding latency.

The paper introduces Claw-SWE-Bench, a benchmark and adapter protocol for evaluating heterogeneous agent harnesses in software engineering tasks.

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

The paper introduces CoRenew, an open-source platform for simulating negotiations among stakeholders in multifamily residential redevelopment using LLM-based agents, with validations against survey responses and real-life negotiation data.

AgentLoupe is a tool that accurately attributes system actions to their originating LLM interactions for security auditing.