Wei Wu

The paper introduces LogicEval, a systematic framework and dataset (LogicDS) to evaluate automated repair techniques for logical software vulnerabilities, finding that prompt sensitivity and context loss are major failure drivers.

The paper analyzes Ethereum builder transactions to show that builder centralization is an emergent property of the Proposer-Builder Separation (PBS) architecture, driven by specific order flow and MEV patterns.

The paper introduces SafeRx-Agent, a knowledge-grounded multi-agent framework that improves medication recommendation accuracy and safety by incorporating fine-grained ATC codes and rigorous safety verification.

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training and rollout.

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identification regardless of geometric variations.

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages and that direct audio processing is superior to cascaded ASR+LLM systems.

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-side conditioning.

This paper introduces an open-source framework for evaluating the efficacy of AI agents powered by open-weight large language models on data preparation tasks in research using locally deployable models.