Chen Zhao

The paper introduces ClawTrap, a MITM-based red-teaming framework, to evaluate the security robustness of web agents like OpenClaw against dynamic, real-world network attacks, finding that model strength correlates with resistance to tampered observations.

Mind-Omni introduces a unified multi-task framework that models the interplay between brain, vision, and language signals using a discrete diffusion paradigm, achieving state-of-the-art performance across multiple tasks.

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.

The paper proposes a novel multimodal learning approach to predict the properties of new bilayer 2D materials formed by stacking dissimilar functional layers.

The paper introduces VHDLSuite, an infrastructure for evaluating Large Language Models in VHDL, including a data pipeline, benchmark, and evaluation framework.

JoyNexus is a multi-tenant service for VLA model supervised fine-tuning, reinforcement learning, and evaluation, which decouples services, introduces group batching, and improves training efficiency.