Mo Zhao

Haochen Zhu, Gang Cao, Mo Zhao

With the widespread use of powerful image editing tools, image tampering becomes easy and realistic. Existing image forensic methods still face challenges of low generalization performance and robustness. In this letter, we propose an effective image tampering localization scheme based on ConvNeXt network and multi-scale feature fusion. Stacked ConvNeXt blocks are used as an encoder to capture hierarchical multi-scale features, which are then fused in decoder for locating tampered pixels accurately. Combined loss and effective data augmentation are adopted to further improve the model performance. Extensive experimental results show that localization performance of our proposed scheme outperforms other state-of-the-art ones. The source code will be available at https://github.com/ZhuHC98/ITL-SSN.

Annan Li, Chufan Wu, Zengle Ge et al.

Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic combination of LLM-based reasoning and large-scale evolutionary search to address complex real-world challenges. The core of FM Agent integrates several key innovations: 1) a cold-start initialization phase incorporating expert guidance, 2) a novel evolutionary sampling strategy for iterative optimization, 3) domain-specific evaluators that combine correctness, effectiveness, and LLM-supervised feedback, and 4) a distributed, asynchronous execution infrastructure built on Ray. Demonstrating broad applicability, our system has been evaluated across diverse domains, including operations research, machine learning, GPU kernel optimization, and classical mathematical problems. FM Agent reaches state-of-the-art results autonomously, without human interpretation or tuning -- 1976.3 on ALE-Bench (+5.2\%), 43.56\% on MLE-Bench (+4.0pp), up to 20x speedups on KernelBench, and establishes new state-of-the-art(SOTA) results on several classical mathematical problems. Beyond academic benchmarks, FM Agent shows considerable promise for both large-scale enterprise R\&D workflows and fundamental scientific research, where it can accelerate innovation, automate complex discovery processes, and deliver substantial engineering and scientific advances with broader societal impact.

Mo Zhao, Robert H. Blick

An advanced system of sensors/actuators should allow the direct feedback of a sensed signal into an actuation, e.g., an action potential propagation through an axon or a special cell activity might be sensed and suppressed by an actuator through voltage stimulation or chemical delivery. Such a complex procedure of sensing and stimulation calls for direct communication among these sensors and actuators. In addition, minimizing the sensor/actuator to the size of a biological cell can enable the cell-level automatic therapy. For this objective, we propose such an approach to form a peer-to-peer network of \emph{in vivo} sensors/actuators (S/As) that can be deployed with or even inside biological cells. The S/As can communicate with each other via electromagnetic waves of optical frequencies. In comparison with the comparable techniques including the radio-frequency identification (RFID) and the wireless sensor network (WSN), this technique is well adapted for the cell-level sensing-actuating tasks considering the requirements on size, actuation speed, signal-collision avoidance, etc.