Foundation models in computer vision have demonstrated exceptional performance in zero-shot and few-shot tasks by extracting multi-purpose features from large-scale datasets through self-supervised pre-training methods. However, these models often overlook the severe corruption in cryogenic electron microscopy (cryo-EM) images by high-level noises. We introduce DRACO, a Denoising-Reconstruction Autoencoder for CryO-EM, inspired by the Noise2Noise (N2N) approach. By processing cryo-EM movies into odd and even images and treating them as independent noisy observations, we apply a denoising-reconstruction hybrid training scheme. We mask both images to create denoising and reconstruction tasks. For DRACO's pre-training, the quality of the dataset is essential, we hence build a high-quality, diverse dataset from an uncurated public database, including over 270,000 movies or micrographs. After pre-training, DRACO naturally serves as a generalizable cryo-EM image denoiser and a foundation model for various cryo-EM downstream tasks. DRACO demonstrates the best performance in denoising, micrograph curation, and particle picking tasks compared to state-of-the-art baselines.

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating the model merely as a standalone generator or relying on abstract textual planning. T o this end, we propose Draft-as-CoT (DraCo), a novel interleaved reasoning paradigm that fully leverages both textual and visual contents in CoT for better planning and verification. Our method first generates a low-resolution draft image as preview, providing more concrete and structural visual planning and guidance. Then, we employ the model's inherent understanding capability to verify potential semantic misalignments between the draft and input prompt, and performs refinement through selective corrections with super-resolution. In this way, our approach addresses two fundamental challenges: the coarse-grained nature of textual planning and the difficulty in generating rare attribute combinations. T o support training, we curate DraCo-240K, aiming to enhance three atomic capabilities spanning general correction, instance manipulation, and layout reorganization. Supported by DraCo-CFG, a specialized classifier-free guidance (CFG) strategy for interleaved reasoning, DraCo achieves a tremendous increase on GenEval (+8%), Imagine-Bench (+0.91), and GenEval++ (+3%), significantly outperforming direct generation and other generation methods empowered by CoT. The project is at https://github.com/CaraJ7/DraCo.

This article presents a novel framework for real-time Light Detection and Ranging (LiDAR) data transmission that leverages rate-adaptive technologies and point cloud encoding methods to ensure low-latency, and low-loss data streaming. The proposed framework is intended for, but not limited to, robotic applications that require real-time data transmission over the internet for offloaded processing. Specifically, the Low Latency, Low Loss, Scalable Throughput L4S-enabled SCReAM v2 transmission framework is extended to incorporate the Draco geometry compression algorithm, enabling dynamic compression of high-bitrate 3D LiDAR data according to the sensed channel capacity and network load. The low-latency 3D LiDAR streaming system is designed to maintain minimal end-to-end delay while constraining encoding errors to meet the accuracy requirements of robotic applications. We demonstrate the effectiveness of the proposed method through real-world experiments conducted over a public 5G network across multi-kilometer urban environments. The low-latency and low-loss requirements are preserved, while real-time offloading and evaluation of 3D SLAM algorithms are used to validate the framework's performance in practical use cases.

Autoencoder for CryO-EM, inspired by the Noise2Noise (N2N) approach. We mask both images to create denoising and reconstruction tasks.

Autoencoder for CryO-EM, inspired by the Noise2Noise (N2N) approach. We mask both images to create denoising and reconstruction tasks.

Foundation models in computer vision have demonstrated exceptional performance in zero-shot and few-shot tasks by extracting multi-purpose features from large-scale datasets through self-supervised pre-training methods. However, these models often overlook the severe corruption in cryogenic electron microscopy (cryo-EM) images by high-level noises. We introduce DRACO, a Denoising-Reconstruction Autoencoder for CryO-EM, inspired by the Noise2Noise (N2N) approach. By processing cryo-EM movies into odd and even images and treating them as independent noisy observations, we apply a denoising-reconstruction hybrid training scheme. We mask both images to create denoising and reconstruction tasks.

Larry Niven is one of the biggest names in the history of science fiction, and it was a privilege to interview him via Zoom at his home in Los Angeles recently. His 1970 novel Ringworld is the latest pick for the New Scientist Book Club, but he has also written a whole space-fleet-load of novels and short stories over the years, including my favourite sci-fi of all time, A World Out of Time. At 87 years of age, he is very much still writing. I spoke to him about Ringworld, his start in sci-fi, his favourite work over the years, his current projects and whether he thinks humankind will ever leave this solar system. This is an edited version of our conversation.

In general, I like the question this paper asked, i.e., whether or not it is necessary to impose a large deviation from the model parameters in order to attack distributed learning. Most of the research in Byzantine tolerant distributed learning, including Krum, Bulyan, and Trimmed Mean, uses some statistically "robust aggregation" instead of simple mean at the PS to mitigate the effects of adversaries. By the nature of robust statistics, all of those methods takes positive answer to the above question as granted, which serves as a cornerstone for their correctness. Thus, the fact that this paper gives a negative answer is inspiring and may force researchers to rethink about whether or not robust aggregation is enough for Byzantine tolerant machine learning. However, the author seems not aware of DRACO (listed below), which is very different from the baselines considered in this paper.

Goal Recognition aims to infer an agent's goal from a sequence of observations. Existing approaches often rely on manually engineered domains and discrete representations. Deep Recognition using Actor-Critic Optimization (DRACO) is a novel approach based on deep reinforcement learning that overcomes these limitations by providing two key contributions. First, it is the first goal recognition algorithm that learns a set of policy networks from unstructured data and uses them for inference. Second, DRACO introduces new metrics for assessing goal hypotheses through continuous policy representations. DRACO achieves state-of-the-art performance for goal recognition in discrete settings while not using the structured inputs used by existing approaches. Moreover, it outperforms these approaches in more challenging, continuous settings at substantially reduced costs in both computing and memory. Together, these results showcase the robustness of the new algorithm, bridging traditional goal recognition and deep reinforcement learning.

Recent advancements in machine learning, networked intelligent systems, and wireless connectivity have paved the way for various innovative applications and use cases across various sectors, including the Internet of Things (IoT), consumer robotics, autonomous transportation, and edge computing. These systems increasingly rely on decentralized learning architectures for processing data where generated, minimizing latency and bandwidth usage while enhancing privacy . However, these benefits come with significant challenges, particularly in terms of ensuring efficient and reliable communication and processing within inherently unstable and diverse network environments. Addressing these challenges requires novel approaches that adapt to the unique demands of decentralized architectures, fostering robust and expandable solutions for real-time data processing and learning. In this work, we consider the problem of communication efficiency in federated learning (FL) [1] and in particular in serverless (fully decentralized) learning settings that operate without a central coordinating server [2-6]. Asynchronous learning, empowering each participant to conduct local training and data transmission at their own pace, is a standard and relevant design choice in decentralized network schemes [7-12]. Asynchronous and decentralized learning have an advantage when used separately from each other, manifesting as adaptability to limited resources and downsized communication overhead. Y et unfortunately, when these two paradigms are combined, their integration poses a greater challenge in achieving a unanimous global consensus, as required for instance in the development of sophisticated navigation algorithms [13]. Decentralized optimization studies in the literature often involve high "synchronization costs" due to the complexity of ensuring consensus.