3D shape generation has greatly flourished through the development of so-called "native" 3D diffusion, particularly through the Vecset Diffusion Model (VDM). While recent advancements have shown promising results in generating high-resolution 3D shapes, VDM still struggles with high-speed generation. Challenges exist because of difficulties not only in accelerating diffusion sampling but also VAE decoding in VDM, areas under-explored in previous works. To address these challenges, we present FlashVDM, a systematic framework for accelerating both VAE and DiT in VDM. For DiT, FlashVDM enables flexible diffusion sampling with as few as 5 inference steps and comparable quality, which is made possible by stabilizing consistency distillation with our newly introduced Progressive Flow Distillation. For VAE, we introduce a lightning vecset decoder equipped with Adaptive KV Selection, Hierarchical Volume Decoding, and Efficient Network Design. By exploiting the locality of the vecset and the sparsity of shape surface in the volume, our decoder drastically lowers FLOPs, minimizing the overall decoding overhead. We apply FlashVDM to Hunyuan3D-2 to obtain Hunyuan3D-2 Turbo. Through systematic evaluation, we show that our model significantly outperforms existing fast 3D generation methods, achieving comparable performance to the state-of-the-art while reducing inference time by over 45x for reconstruction and 32x for generation. Code and models are available at https://github.com/Tencent/FlashVDM.

This paper presents a capacitively-coupled chopper instrumentation amplifier designed for the analog front end (AFE) of Electrocardiogram monitoring. It employs an embedded DC-servo loop to reduce the input-referred noise (IRN). Additionally, a digital calibration unit is employed to realize large electrode DC offset (EDO) cancellation ability. To prevent the second harmonic ripple, a three-state ripple reduction loop is proposed here. The proposed AFE is implemented in a 180 nm CMOS process and consumes 1.37 μW from a 1.2 V supply with ±95 mV EDO cancellation range. Besides, the IRN from 1 Hz to 200 Hz is 1.68 μVrmswith a noise efficiency factor of 4.87.

Visual patterns are basic elements in images and represent the discernible regularity in the visual world. Thus, mining visual patterns is a fundamental task in computer vision. Most previous studies consider that only one visual pattern exists in a category, and then builds up a one-to-one mapping using category label. In reality, however, many categories include multiple patterns, which are many-to-one mappings. Without knowing the information of patterns, few existing pattern mining methods can discover and distinguish varied patterns in a category. To tackle this problem, we propose a novel framework, PaclMap, which learns medium-grained features to represent patterns. It includes an unsupervised pattern-level contrastive learning and a multipattern activation map. Their joint optimization encourages the network to mine both discriminative and frequent patterns in a category. Extensive experiments conducted on four benchmark datasets (Place-20, imagenet large scale visual recognition challenge (ILSVRC)-20, visual object classes (VOC), and Travel) demonstrate that PaclMap outperforms six state-of-the-art methods with average improvements of 2.9% on accuracy and 12.3% on frequency, respectively.