Tao Xu

Aaron Hurst, Adam Lerer, Adam P. Goucher et al. · openai

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Josh Achiam, Steven Adler, Sandhini Agarwal et al. · berkeley, deepmind

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformer-based model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4's performance based on models trained with no more than 1/1,000th the compute of GPT-4.

Chengxi Liao, Tao Xu, Zulong Chen et al.

Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 evaluate schema generalization, large-scale databases, and realistic workflows, but largely overlook enterprise scenarios where SQL generation depends on private business knowledge, such as internal metrics, reporting conventions, and organizational rules. We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents. EntSQL contains 1,066 aligned Chinese-English semantic examples across five business domains, with most examples requiring domain knowledge beyond the question and schema and involving complex SQL structures. On English inputs, the best evaluated system reaches only 15.9\% when long-form documents are provided, highlighting the difficulty of grounding SQL generation in enterprise knowledge.

Alec Radford, Jong Wook Kim, Tao Xu et al.

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

Shiqiang Zhu, Ting Yu, Tao Xu et al.

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.

Yu-Jhe Li, Tao Xu, Ji Hou et al. · cmu

We tackle the task of text-to-3D creation with pre-trained latent-based NeRFs (NeRFs that generate 3D objects given input latent code). Recent works such as DreamFusion and Magic3D have shown great success in generating 3D content using NeRFs and text prompts, but the current approach of optimizing a NeRF for every text prompt is 1) extremely time-consuming and 2) often leads to low-resolution outputs. To address these challenges, we propose a novel method named 3D-CLFusion which leverages the pre-trained latent-based NeRFs and performs fast 3D content creation in less than a minute. In particular, we introduce a latent diffusion prior network for learning the w latent from the input CLIP text/image embeddings. This pipeline allows us to produce the w latent without further optimization during inference and the pre-trained NeRF is able to perform multi-view high-resolution 3D synthesis based on the latent. We note that the novelty of our model lies in that we introduce contrastive learning during training the diffusion prior which enables the generation of the valid view-invariant latent code. We demonstrate through experiments the effectiveness of our proposed view-invariant diffusion process for fast text-to-3D creation, e.g., 100 times faster than DreamFusion. We note that our model is able to serve as the role of a plug-and-play tool for text-to-3D with pre-trained NeRFs.

Yu-Jhe Li, Tao Xu, Bichen Wu et al. · cmu

We tackle the task of NeRF inversion for style-based neural radiance fields, (e.g., StyleNeRF). In the task, we aim to learn an inversion function to project an input image to the latent space of a NeRF generator and then synthesize novel views of the original image based on the latent code. Compared with GAN inversion for 2D generative models, NeRF inversion not only needs to 1) preserve the identity of the input image, but also 2) ensure 3D consistency in generated novel views. This requires the latent code obtained from the single-view image to be invariant across multiple views. To address this new challenge, we propose a two-stage encoder for style-based NeRF inversion. In the first stage, we introduce a base encoder that converts the input image to a latent code. To ensure the latent code is view-invariant and is able to synthesize 3D consistent novel view images, we utilize identity contrastive learning to train the base encoder. Second, to better preserve the identity of the input image, we introduce a refining encoder to refine the latent code and add finer details to the output image. Importantly note that the novelty of this model lies in the design of its first-stage encoder which produces the closest latent code lying on the latent manifold and thus the refinement in the second stage would be close to the NeRF manifold. Through extensive experiments, we demonstrate that our proposed two-stage encoder qualitatively and quantitatively exhibits superiority over the existing encoders for inversion in both image reconstruction and novel-view rendering.

Jinghui Lu, Jiayi Guan, Zhijian Huang et al.

Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. At inference, the auxiliary decoders are discarded and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering state-of-the-art accuracy at answer-only latency, and providing direct evidence that tighter compression, when guided in both language and world-model supervision, produces more generalizable representations than verbose token-by-token reasoning. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL

Tao Xu, Wang Xi, Jianping He

Deriving analytic solutions for optimal mixed strategies in zero-sum linear-quadratic differential games (ZSLQDGs) remains an open problem. In this paper, we analytically synthesize near-optimal mixed strategies for ZSLQDGs and establish rigorous performance certifications. Specifically, we construct a surrogate pure-strategy stochastic differential game (SDG) by matching the first two moments of the mixed strategies. This method achieves an $\mathcal{O}(\barπ^2)$ weak approximation of state distributions and expected costs with respect to the maximum commitment delay $\barπ$. By analytically resolving the surrogate SDG, we derive closed-form optimal control laws for the matched moments. Crucially, we reveal that the surrogate game is governed by a Generalized Riccati Differential Equation (GRDE), which explicitly dictates a dynamic energy allocation law for variance injection. Building on these solutions, we propose a robust dual-routing architecture to execute the near-optimal mixed strategies. Furthermore, we certify that both the global value approximation error and the strategy suboptimality gaps are bounded by $\mathcal{O}(\barπ^{\frac{1}{2}})$. Finally, numerical experiments on a double-integrator pursuit-evasion game illustrate the induced physical behaviors and validate the theoretical bounds.

Tianrun Chen, Chaotao Ding, Lanyun Zhu et al.

Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) have been pivotal in biomedical image segmentation, yet their ability to manage long-range dependencies remains constrained by inherent locality and computational overhead. To overcome these challenges, in this technical report, we first propose xLSTM-UNet, a UNet structured deep learning neural network that leverages Vision-LSTM (xLSTM) as its backbone for medical image segmentation. xLSTM is a recently proposed as the successor of Long Short-Term Memory (LSTM) networks and have demonstrated superior performance compared to Transformers and State Space Models (SSMs) like Mamba in Neural Language Processing (NLP) and image classification (as demonstrated in Vision-LSTM, or ViL implementation). Here, xLSTM-UNet we designed extend the success in biomedical image segmentation domain. By integrating the local feature extraction strengths of convolutional layers with the long-range dependency capturing abilities of xLSTM, xLSTM-UNet offers a robust solution for comprehensive image analysis. We validate the efficacy of xLSTM-UNet through experiments. Our findings demonstrate that xLSTM-UNet consistently surpasses the performance of leading CNN-based, Transformer-based, and Mamba-based segmentation networks in multiple datasets in biomedical segmentation including organs in abdomen MRI, instruments in endoscopic images, and cells in microscopic images. With comprehensive experiments performed, this technical report highlights the potential of xLSTM-based architectures in advancing biomedical image analysis in both 2D and 3D. The code, models, and datasets are publicly available at http://tianrun-chen.github.io/xLSTM-UNet/

Haoyuan Shi, Tao Xu, Xiaodi Li et al.

Predicting the response of a cancer cell line to a therapeutic drug is pivotal for personalized medicine. Despite numerous deep learning methods that have been developed for drug response prediction, integrating diverse information about biological entities and predicting the directional response remain major challenges. Here, we propose a novel interpretable predictive model, DRExplainer, which leverages a directed graph convolutional network to enhance the prediction in a directed bipartite network framework. DRExplainer constructs a directed bipartite network integrating multi-omics profiles of cell lines, the chemical structure of drugs and known drug response to achieve directed prediction. Then, DRExplainer identifies the most relevant subgraph to each prediction in this directed bipartite network by learning a mask, facilitating critical medical decision-making. Additionally, we introduce a quantifiable method for model interpretability that leverages a ground truth benchmark dataset curated from biological features. In computational experiments, DRExplainer outperforms state-of-the-art predictive methods and another graph-based explanation method under the same experimental setting. Finally, the case studies further validate the interpretability and the effectiveness of DRExplainer in predictive novel drug response. Our code is available at: https://github.com/vshy-dream/DRExplainer.

Maxime Oquab, Daniel Haziza, Ludovic Schwartz et al.

As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism. However, there are some important challenges to tackle in order to improve the experience in real world conditions. In particular, the current approaches fail to represent profile views without distortions, while running in a low compute regime. We focus on this key problem by introducing a multi-frames embedding dubbed Frontalizer to improve profile views rendering. In addition to this core improvement, we explore the learning of a latent code conditioning generations along with landmarks to better convey facial expressions. Our dense models achieves 22% of improvement in perceptual quality and 73% reduction of landmark error over the first order model baseline on a subset of DFDC videos containing head movements. Declined with mobile architectures, our models outperform the previous state-of-the-art (improving perceptual quality by more than 16% and reducing landmark error by more than 47% on two datasets) while running on real time on iPhone 8 with very low bandwidth requirements.

Chaoyao Shen, Linfeng Jiang, Yixian Shen et al.

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal transferability across platforms. In this paper, we introduce TCL, a novel efficient and transferable compiler framework for fast tensor program optimization across diverse hardware platforms to address these challenges. Specifically, TCL is built on three core enablers: (1) the RDU Sampler, a data-efficient active learning strategy that selects only 10% of tensor programs by jointly optimizing Representativeness, Diversity, and Uncertainty, substantially reducing data collection costs while maintaining near-original model accuracy; (2) a new Mamba-based cost model that efficiently captures long-range schedule dependencies while achieving a favorable trade-off between prediction accuracy and computational cost through reduced parameterization and lightweight sequence modeling; and (3) a continuous knowledge distillation framework that effectively and progressively transfers knowledge across multiple hardware platforms while avoiding the parameter explosion and data dependency issues typically caused by traditional multi-task learning. Extensive experiments validate the effectiveness of each individual enabler and the holistic TCL framework. When optimizing a range of mainstream DL models on both CPU and GPU platforms, TCL achieves, on average, 16.8x and 12.48x faster tuning time, and 1.20x and 1.13x lower inference latency, respectively, compared to Tenset-MLP.

Yuan Wang, Huiling Song, Peng Huo et al.

Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels only have a few training instances due to large label dimensionality in XMTC. To solve this data sparsity issue, most existing XMTC methods take advantage of fixed label clusters obtained in early stage to balance performance on tail labels and head labels. However, such label clusters provide static and coarse-grained semantic scope for every text, which ignores distinct characteristics of different texts and has difficulties modelling accurate semantics scope for texts with tail labels. In this paper, we propose a novel framework TReaderXML for XMTC, which adopts dynamic and fine-grained semantic scope from teacher knowledge for individual text to optimize text conditional prior category semantic ranges. TReaderXML dynamically obtains teacher knowledge for each text by similar texts and hierarchical label information in training sets to release the ability of distinctly fine-grained label-oriented semantic scope. Then, TReaderXML benefits from a novel dual cooperative network that firstly learns features of a text and its corresponding label-oriented semantic scope by parallel Encoding Module and Reading Module, secondly embeds two parts by Interaction Module to regularize the text's representation by dynamic and fine-grained label-oriented semantic scope, and finally find target labels by Prediction Module. Experimental results on three XMTC benchmark datasets show that our method achieves new state-of-the-art results and especially performs well for severely imbalanced and sparse datasets.

Adam Polyak, Amit Zohar, Andrew Brown et al. · meta-ai

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

OpenAI OpenAI, Matthias Plappert, Raul Sampedro et al. · openai

We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery, where two agents, Alice and Bob, play a game. Alice is asked to propose challenging goals and Bob aims to solve them. We show that this method can discover highly diverse and complex goals without any human priors. Bob can be trained with only sparse rewards, because the interaction between Alice and Bob results in a natural curriculum and Bob can learn from Alice's trajectory when relabeled as a goal-conditioned demonstration. Finally, our method scales, resulting in a single policy that can generalize to many unseen tasks such as setting a table, stacking blocks, and solving simple puzzles. Videos of a learned policy is available at https://robotics-self-play.github.io.

Alvin Wan, Xiaoliang Dai, Peizhao Zhang et al.

Differentiable Neural Architecture Search (DNAS) has demonstrated great success in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's search space is small when compared to other search methods', since all candidate network layers must be explicitly instantiated in memory. To address this bottleneck, we propose a memory and computationally efficient DNAS variant: DMaskingNAS. This algorithm expands the search space by up to $10^{14}\times$ over conventional DNAS, supporting searches over spatial and channel dimensions that are otherwise prohibitively expensive: input resolution and number of filters. We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands. Furthermore, we employ effective shape propagation to maximize per-FLOP or per-parameter accuracy. The searched FBNetV2s yield state-of-the-art performance when compared with all previous architectures. With up to 421$\times$ less search cost, DMaskingNAS finds models with 0.9% higher accuracy, 15% fewer FLOPs than MobileNetV3-Small; and with similar accuracy but 20% fewer FLOPs than Efficient-B0. Furthermore, our FBNetV2 outperforms MobileNetV3 by 2.6% in accuracy, with equivalent model size. FBNetV2 models are open-sourced at https://github.com/facebookresearch/mobile-vision.

Kaiyi Zhang, Ang Lv, Yuhan Chen et al.

In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to the development of Batch-ICL, an effective, efficient, and order-agnostic inference algorithm for ICL. Differing from the standard N-shot learning approach, Batch-ICL employs $N$ separate 1-shot forward computations and aggregates the resulting meta-gradients. These aggregated meta-gradients are then applied to the forward computation of a zero-shot query to generate the final prediction. This batch processing approach renders the LLM agnostic to the order of ICL examples. Through extensive experiments and analysis, we demonstrate that Batch-ICL consistently outperforms most permutations of ICL examples. In some cases, it even exceeds the performance of the best order for standard ICL, all while reducing the computational resources required. Furthermore, we develop a novel variant of Batch-ICL featuring multiple "epochs" of meta-optimization. This variant implicitly explores permutations of ICL examples, further enhancing ICL performance.

Hongjie Wang, Chih-Yao Ma, Yen-Cheng Liu et al.

Text-to-video generation enhances content creation but is highly computationally intensive: The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number of pixels. This makes minute-length video generation extremely expensive, limiting most existing models to generating videos of only 10-20 seconds length. We propose a Linear-complexity text-to-video Generation (LinGen) framework whose cost scales linearly in the number of pixels. For the first time, LinGen enables high-resolution minute-length video generation on a single GPU without compromising quality. It replaces the computationally-dominant and quadratic-complexity block, self-attention, with a linear-complexity block called MATE, which consists of an MA-branch and a TE-branch. The MA-branch targets short-to-long-range correlations, combining a bidirectional Mamba2 block with our token rearrangement method, Rotary Major Scan, and our review tokens developed for long video generation. The TE-branch is a novel TEmporal Swin Attention block that focuses on temporal correlations between adjacent tokens and medium-range tokens. The MATE block addresses the adjacency preservation issue of Mamba and improves the consistency of generated videos significantly. Experimental results show that LinGen outperforms DiT (with a 75.6% win rate) in video quality with up to 15$\times$ (11.5$\times$) FLOPs (latency) reduction. Furthermore, both automatic metrics and human evaluation demonstrate our LinGen-4B yields comparable video quality to state-of-the-art models (with a 50.5%, 52.1%, 49.1% win rate with respect to Gen-3, LumaLabs, and Kling, respectively). This paves the way to hour-length movie generation and real-time interactive video generation. We provide 68s video generation results and more examples in our project website: https://lineargen.github.io/.

Shangzan Zhang, Sida Peng, Tao Xu et al.

This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods. Project page: https://zju3dv.github.io/MaPa

Li Xiao, Liqing Liu, Hongjun Wu et al.

Recent advances in 2D large-scale and 3D volume electron microscopy have stimulated the rapid development of nanoscale functional analysis at the tissue and organ levels. Digitizing the cell by mapping the intricate organellar networks into its physiological and pathological textures will revolutionarize the contents of cell atlases. To meet the requirements of characterizing intracellular organelles and their interactions within defined cellular cohorts at tissue level, we have developed DeepOrganelle. It adopts a lightweighted Mask2Former frameworks as a universal segmentor and is capable of segmenting and extracting organelles within different cell types, performing statistical quantitative analysis, as well as visualizing and quantifying the spatial distribution of organelle morphologies and interactions across different cell types at tissue scales. Using DeepOrganelle, we systemically perform cross-scale quantification of membrane contact sites(MCSs) dynamics across the progression of the seminiferous epithelial cycle, covering 12 distinct developmental stages and 24 statuses of germ cells. DeepOrganelle uncovers the spatiotemporal gradient of the germ cell differentiation atlas according to different types of organelles and their interactions. Noticeably, it discovers a waved pattern of mitochondria(Mito)-endoplasmic reticulum(ER) contact with a significant increase specifically at Stage X pachytene preceding the transition to diplotene, which aligns well with a newly reported experiment that mitochondrial metabolic proteins like PDHA2 are essential for this transition by maintaining ATP supply for double-strand break(DSB) repair. DeepOrganelle also observes a dynamic restructuring of the blood-testis barrier and stage-specific reorganization of organelle topography in Sertoli cells from preleptotene to leptotene phases of prophase I.

Philippe Hansen-Estruch, David Yan, Ching-Yao Chung et al.

Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. Although scaling Transformer-based generators has been central to recent advances, the tokenizer component itself is rarely scaled, leaving open questions about how auto-encoder design choices influence both its objective of reconstruction and downstream generative performance. Our work aims to conduct an exploration of scaling in auto-encoders to fill in this blank. To facilitate this exploration, we replace the typical convolutional backbone with an enhanced Vision Transformer architecture for Tokenization (ViTok). We train ViTok on large-scale image and video datasets far exceeding ImageNet-1K, removing data constraints on tokenizer scaling. We first study how scaling the auto-encoder bottleneck affects both reconstruction and generation -- and find that while it is highly correlated with reconstruction, its relationship with generation is more complex. We next explored the effect of separately scaling the auto-encoders' encoder and decoder on reconstruction and generation performance. Crucially, we find that scaling the encoder yields minimal gains for either reconstruction or generation, while scaling the decoder boosts reconstruction but the benefits for generation are mixed. Building on our exploration, we design ViTok as a lightweight auto-encoder that achieves competitive performance with state-of-the-art auto-encoders on ImageNet-1K and COCO reconstruction tasks (256p and 512p) while outperforming existing auto-encoders on 16-frame 128p video reconstruction for UCF-101, all with 2-5x fewer FLOPs. When integrated with Diffusion Transformers, ViTok demonstrates competitive performance on image generation for ImageNet-1K and sets new state-of-the-art benchmarks for class-conditional video generation on UCF-101.

Xu Ma, Peize Sun, Haoyu Ma et al.

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image tokens required for AR models, which constrains both training and inference efficiency, as well as image resolution. To address this, we present Token-Shuffle, a novel yet simple method that reduces the number of image tokens in Transformer. Our key insight is the dimensional redundancy of visual vocabularies in Multimodal Large Language Models (MLLMs), where low-dimensional visual codes from visual encoder are directly mapped to high-dimensional language vocabularies. Leveraging this, we consider two key operations: token-shuffle, which merges spatially local tokens along channel dimension to decrease the input token number, and token-unshuffle, which untangles the inferred tokens after Transformer blocks to restore the spatial arrangement for output. Jointly training with textual prompts, our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis in a unified next-token prediction way while maintaining efficient training and inference. For the first time, we push the boundary of AR text-to-image generation to a resolution of 2048x2048 with gratifying generation performance. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15. Exhaustive large-scale human evaluations also demonstrate our prominent image generation ability in terms of text-alignment, visual flaw, and visual appearance. We hope that Token-Shuffle can serve as a foundational design for efficient high-resolution image generation within MLLMs.

Xinrui Yan, Jiangyan Yi, Jianhua Tao et al.

Open environment oriented open set model attribution of deepfake audio is an emerging research topic, aiming to identify the generation models of deepfake audio. Most previous work requires manually setting a rejection threshold for unknown classes to compare with predicted probabilities. However, models often overfit training instances and generate overly confident predictions. Moreover, thresholds that effectively distinguish unknown categories in the current dataset may not be suitable for identifying known and unknown categories in another data distribution. To address the issues, we propose a novel framework for open set model attribution of deepfake audio with rejection threshold adaptation (ReTA). Specifically, the reconstruction error learning module trains by combining the representation of system fingerprints with labels corresponding to either the target class or a randomly chosen other class label. This process generates matching and non-matching reconstructed samples, establishing the reconstruction error distributions for each class and laying the foundation for the reject threshold calculation module. The reject threshold calculation module utilizes gaussian probability estimation to fit the distributions of matching and non-matching reconstruction errors. It then computes adaptive reject thresholds for all classes through probability minimization criteria. The experimental results demonstrate the effectiveness of ReTA in improving the open set model attributes of deepfake audio.

Zhuoxu Huang, Zhenkun Fan, Tao Xu et al.

Point cloud video representation learning is challenging due to complex structures and unordered spatial arrangement. Traditional methods struggle with frame-to-frame correlations and point-wise correspondence tracking. Recently, partial differential equations (PDE) have provided a new perspective in uniformly solving spatial-temporal data information within certain constraints. While tracking tangible point correspondence remains challenging, we propose to formalize point cloud video representation learning as a PDE-solving problem. Inspired by fluid analysis, where PDEs are used to solve the deformation of spatial shape over time, we employ PDE to solve the variations of spatial points affected by temporal information. By modeling spatial-temporal correlations, we aim to regularize spatial variations with temporal features, thereby enhancing representation learning in point cloud videos. We introduce Motion PointNet composed of a PointNet-like encoder and a PDE-solving module. Initially, we construct a lightweight yet effective encoder to model an initial state of the spatial variations. Subsequently, we develop our PDE-solving module in a parameterized latent space, tailored to address the spatio-temporal correlations inherent in point cloud video. The process of solving PDE is guided and refined by a contrastive learning structure, which is pivotal in reshaping the feature distribution, thereby optimizing the feature representation within point cloud video data. Remarkably, our Motion PointNet achieves an impressive accuracy of 97.52% on the MSRAction-3D dataset, surpassing the current state-of-the-art in all aspects while consuming minimal resources (only 0.72M parameters and 0.82G FLOPs).

Xiaoqing Zhang, Hanfeng Shi, Xiangyu Li et al.

Parkinson's disease (PD) is a prevalent neurodegenerative disorder globally. The eye's retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness.

Tao Xu, Zhixin Hu, Li Luo et al.

Digital AI systems spanning large language models, vision models, and generative architectures that operate primarily in symbolic, linguistic, or pixel domains. They have achieved striking progress, but almost all of this progress lives in virtual spaces. These systems transform embeddings and tokens, yet do not themselves touch the world and rarely admit a physical interpretation. In this work we propose a physical transformer that couples modern transformer style computation with geometric representation and physical dynamics. At the micro level, attention heads, and feed-forward blocks are modeled as interacting spins governed by effective Hamiltonians plus non-Hamiltonian bath terms. At the meso level, their aggregated state evolves on a learned Neural Differential Manifold (NDM) under Hamiltonian flows and Hamilton, Jacobi, Bellman (HJB) optimal control, discretized by symplectic layers that approximately preserve geometric and energetic invariants. At the macro level, the model maintains a generative semantic workspace and a two-dimensional information-phase portrait that tracks uncertainty and information gain over a reasoning trajectory. Within this hierarchy, reasoning tasks are formulated as controlled information flows on the manifold, with solutions corresponding to low cost trajectories that satisfy geometric, energetic, and workspace-consistency constraints. On simple toy problems involving numerical integration and dynamical systems, the physical transformer outperforms naive baselines in stability and long-horizon accuracy, highlighting the benefits of respecting underlying geometric and Hamiltonian structure. More broadly, the framework suggests a path toward physical AI that unify digital reasoning with physically grounded manifolds, opening a route to more interpretable and potentially unified models of reasoning, control, and interaction with the real world.

Tao Xu

Existing multimodal document question answering methods universally adopt a supply-side ingestion strategy: running a Vision-Language Model (VLM) on every page during indexing to generate comprehensive descriptions, then answering questions through text retrieval. However, this "pre-ingestion" approach is costly (a 113-page engineering drawing package requires approximately 80,000 VLM tokens), end-to-end unreliable (VLM outputs may fail to be correctly retrieved due to format mismatches in the retrieval infrastructure), and irrecoverable once it fails. This paper proposes the Deferred Visual Ingestion (DVI) framework, adopting a demand-side ingestion strategy: the indexing phase performs only lightweight metadata extraction, deferring visual understanding to the moment users pose specific questions. DVI's core principle is "Index for locating, not understanding"--achieving page localization through structured metadata indexes and BM25 full-text search, then sending original images along with specific questions to a VLM for targeted analysis. Experiments on two real industrial engineering drawings (113 pages + 7 pages) demonstrate that DVI achieves comparable overall accuracy at zero ingestion VLM cost (46.7% vs. 48.9%), an effectiveness rate of 50% on visually necessary queries (vs. 0% for pre-ingestion), and 100% page localization (98% search space compression). DVI also supports interactive refinement and progressive caching, transforming the "QA accuracy" problem into a "page localization" problem--once the correct drawing page is found, obtaining the answer becomes a matter of interaction rounds.

Ziqi Zhang, Yuexiang Li, Yawen Huang et al.

Recent studies have uncovered a new research line, namely source-free domain adaptation, which adapts a model to target domains without using the source data. Such a setting can address the concerns on data privacy and security issues of medical images. However, current source-free domain adaptation frameworks mainly focus on the pseudo label refinement for target data without the consideration of learning procedure. Indeed, a progressive learning process from source to target domain will benefit the knowledge transfer during model adaptation. To this end, we propose a curriculum-based framework, namely learning from curriculum (LFC), for source-free domain adaptation, which consists of easy-to-hard and source-to-target curricula. Concretely, the former curriculum enables the framework to start learning with `easy' samples and gradually tune the optimization direction of model adaption by increasing the sample difficulty. While, the latter can stablize the adaptation process, which ensures smooth transfer of the model from the source domain to the target. We evaluate the proposed source-free domain adaptation approach on the public cross-domain datasets for fundus segmentation and polyp segmentation. The extensive experimental results show that our framework surpasses the existing approaches and achieves a new state-of-the-art.

Dong Han, Zhehong Ai, Pengxiang Cai et al.

Bayesian optimization (BO) is a powerful tool for scientific discovery in chemistry, yet its efficiency is often hampered by the sparse experimental data and vast search space. Here, we introduce ChemBOMAS: a large language model (LLM)-enhanced multi-agent system that accelerates BO through synergistic data- and knowledge-driven strategies. Firstly, the data-driven strategy involves an 8B-scale LLM regressor fine-tuned on a mere 1% labeled samples for pseudo-data generation, robustly initializing the optimization process. Secondly, the knowledge-driven strategy employs a hybrid Retrieval-Augmented Generation approach to guide LLM in dividing the search space while mitigating LLM hallucinations. An Upper Confidence Bound algorithm then identifies high-potential subspaces within this established partition. Across the LLM-refined subspaces and supported by LLM-generated data, BO achieves the improvement of effectiveness and efficiency. Comprehensive evaluations across multiple scientific benchmarks demonstrate that ChemBOMAS set a new state-of-the-art, accelerating optimization efficiency by up to 5-fold compared to baseline methods.

Chun Liu, Hailong Wang, Bingqian Zhu et al.

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, posing significant security threats to their deployment in remote sensing applications. Research on adversarial attacks not only reveals model vulnerabilities but also provides critical insights for enhancing robustness. Although current mixing-based strategies have been proposed to increase the transferability of adversarial examples, they either perform global blending or directly exchange a region in the images, which may destroy global semantic features and mislead the optimization of adversarial examples. Furthermore, their reliance on cross-entropy loss for perturbation optimization leads to gradient diminishing during iterative updates, compromising adversarial example quality. To address these limitations, we focus on non-targeted attacks and propose a novel framework via local mixing and logits optimization. First, we present a local mixing strategy to generate diverse yet semantically consistent inputs. Different from MixUp, which globally blends two images, and MixCut, which stitches images together, our method merely blends local regions to preserve global semantic information. Second, we adapt the logit loss from targeted attacks to non-targeted scenarios, mitigating the gradient vanishing problem of cross-entropy loss. Third, a perturbation smoothing loss is applied to suppress high-frequency noise and enhance transferability. Extensive experiments on FGSCR-42 and MTARSI datasets demonstrate superior performance over 12 state-of-the-art methods across 6 surrogate models. Notably, with ResNet as the surrogate on MTARSI, our method achieves a 17.28% average improvement in black-box attack success rate.

Chun Liu, Panpan Ding, Zheng Zheng et al.

Current ship detection techniques based on remote sensing imagery primarily rely on the object detection capabilities of deep neural networks (DNNs). However, DNNs are vulnerable to adversarial patch attacks, which can lead to misclassification by the detection model or complete evasion of the targets. Numerous studies have demonstrated that data transformation-based methods can improve the transferability of adversarial examples. However, excessive augmentation of image backgrounds or irrelevant regions may introduce unnecessary interference, resulting in false detections of the object detection model. These errors are not caused by the adversarial patches themselves but rather by the over-augmentation of background and non-target areas. This paper proposes a localized augmentation method that applies augmentation only to the target regions, avoiding any influence on non-target areas. By reducing background interference, this approach enables the loss function to focus more directly on the impact of the adversarial patch on the detection model, thereby improving the attack success rate. Experiments conducted on the HRSC2016 dataset demonstrate that the proposed method effectively increases the success rate of adversarial patch attacks and enhances their transferability.

Feng-ao Wang, Shaobo Chen, Yao Xuan et al.

A fundamental limitation of probabilistic deep learning is its predominant reliance on Gaussian priors. This simplistic assumption prevents models from accurately capturing the complex, non-Gaussian landscapes of natural data, particularly in demanding domains like complex biological data, severely hindering the fidelity of the model for scientific discovery. The physically-grounded Boltzmann distribution offers a more expressive alternative, but it is computationally intractable on classical computers. To date, quantum approaches have been hampered by the insufficient qubit scale and operational stability required for the iterative demands of deep learning. Here, we bridge this gap by introducing the Quantum Boltzmann Machine-Variational Autoencoder (QBM-VAE), a large-scale and long-time stable hybrid quantum-classical architecture. Our framework leverages a quantum processor for efficient sampling from the Boltzmann distribution, enabling its use as a powerful prior within a deep generative model. Applied to million-scale single-cell datasets from multiple sources, the QBM-VAE generates a latent space that better preserves complex biological structures, consistently outperforming conventional Gaussian-based deep learning models like VAE and SCVI in essential tasks such as omics data integration, cell-type classification, and trajectory inference. It also provides a typical example of introducing a physics priori into deep learning to drive the model to acquire scientific discovery capabilities that breaks through data limitations. This work provides the demonstration of a practical quantum advantage in deep learning on a large-scale scientific problem and offers a transferable blueprint for developing hybrid quantum AI models.

Tao Xu, Dung-Yang Lee, Momiao Xiong

Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advancements in Transformer architectures and hyperbolic geometry have provided novel solutions to these challenges. This paper introduces a new framework that integrates hyperbolic Transformers into RL for multi-step reasoning. The proposed approach leverages hyperbolic embeddings to model hierarchical structures effectively. We present theoretical insights, algorithmic details, and experimental results that include Frontier Math and nonlinear optimal control problems. Compared to RL with vanilla transformer, the hyperbolic RL largely improves accuracy by (32%~44%) on FrontierMath benchmark, (43%~45%) on nonlinear optimal control benchmark, while achieving impressive reduction in computational time by (16%~32%) on FrontierMath benchmark, (16%~17%) on nonlinear optimal control benchmark. Our work demonstrates the potential of hyperbolic Transformers in reinforcement learning, particularly for multi-step reasoning tasks that involve hierarchical structures.

Chun Liu, Bingqian Zhu, Tao Xu et al.

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, which pose security challenges to hyperspectral image (HSI) classification based on DNNs. Numerous adversarial attack methods have been designed in the domain of natural images. However, different from natural images, HSIs contains high-dimensional rich spectral information, which presents new challenges for generating adversarial examples. Based on the specific characteristics of HSIs, this paper proposes a novel method to enhance the transferability of the adversarial examples for HSI classification using 3D structure-invariant transformation and weighted intermediate feature divergence. While keeping the HSIs structure invariant, the proposed method divides the image into blocks in both spatial and spectral dimensions. Then, various transformations are applied on each block to increase input diversity and mitigate the overfitting to substitute models. Moreover, a weighted intermediate feature divergence loss is also designed by leveraging the differences between the intermediate features of original and adversarial examples. It constrains the perturbation direction by enlarging the feature maps of the original examples, and assigns different weights to different feature channels to destroy the features that have a greater impact on HSI classification. Extensive experiments demonstrate that the adversarial examples generated by the proposed method achieve more effective adversarial transferability on three public HSI datasets. Furthermore, the method maintains robust attack performance even under defense strategies.

Tao Xu, Bo Wu, Ruilong Fan et al.

Gaze estimation is a crucial task in computer vision, however, existing methods suffer from high computational costs, which limit their practical deployment in resource-limited environments. In this paper, we propose a novel lightweight model, FR-Net, for accurate gaze angle estimation while significantly reducing computational complexity. FR-Net utilizes the Fast Fourier Transform (FFT) to extract gaze-relevant features in frequency domains while reducing the number of parameters. Additionally, we introduce a shortcut component that focuses on the spatial domain to further improve the accuracy of our model. Our experimental results demonstrate that our approach achieves substantially lower gaze error angles (3.86 on MPII and 4.51 on EYEDIAP) compared to state-of-the-art gaze estimation methods, while utilizing 17 times fewer parameters (0.67M) and only 12\% of FLOPs (0.22B). Furthermore, our method outperforms existing lightweight methods in terms of accuracy and efficiency for the gaze estimation task. These results suggest that our proposed approach has significant potential applications in areas such as human-computer interaction and driver assistance systems.

Tao Xu, Wang Dang, Jiabao Wang et al.

One of the most significant challenges of EEG-based emotion recognition is the cross-subject EEG variations, leading to poor performance and generalizability. This paper proposes a novel EEG-based emotion recognition model called the domain adversarial graph attention model (DAGAM). The basic idea is to generate a graph to model multichannel EEG signals using biological topology. Graph theory can topologically describe and analyze relationships and mutual dependency between channels of EEG. Then, unlike other graph convolutional networks, self-attention pooling is applied to benefit salient EEG feature extraction from the graph, which effectively improves the performance. Finally, after graph pooling, the domain adversarial based on the graph is employed to identify and handle EEG variation across subjects, efficiently reaching good generalizability. We conduct extensive evaluations on two benchmark datasets (SEED and SEED IV) and obtain state-of-the-art results in subject-independent emotion recognition. Our model boosts the SEED accuracy to 92.59% (4.69% improvement) with the lowest standard deviation of 3.21% (2.92% decrements) and SEED IV accuracy to 80.74% (6.90% improvement) with the lowest standard deviation of 4.14% (3.88% decrements) respectively.

Arvind Neelakantan, Tao Xu, Raul Puri et al.

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and model architecture. In this work, we show that contrastive pre-training on unsupervised data at scale leads to high quality vector representations of text and code. The same unsupervised text embeddings that achieve new state-of-the-art results in linear-probe classification also display impressive semantic search capabilities and sometimes even perform competitively with fine-tuned models. On linear-probe classification accuracy averaging over 7 tasks, our best unsupervised model achieves a relative improvement of 4% and 1.8% over previous best unsupervised and supervised text embedding models respectively. The same text embeddings when evaluated on large-scale semantic search attains a relative improvement of 23.4%, 14.7%, and 10.6% over previous best unsupervised methods on MSMARCO, Natural Questions and TriviaQA benchmarks, respectively. Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20.8% relative improvement over prior best work on code search.

Ziqi Zhang, Yuexiang Li, Hongxin Wei et al.

Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn paradigms (e.g., Co-teaching and JoCoR) to filter the samples with noisy labels from the training set. However, most of them use a simple cross-entropy loss as the criterion for noisy label identification. The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value than the easy cases. In this paper, we propose a plugin module, namely noise ignoring block (NIB), consisting of a probability transition matrix and an inter-class correlation (IC) loss, to separate the hard samples from the mislabeled ones, and further boost the accuracy of image classification network trained with noisy labels. Concretely, our IC loss is calculated as Kullback-Leibler divergence between the network prediction and the accumulative soft label generated by the probability transition matrix. Such that, with the lower value of IC loss, the hard cases can be easily distinguished from mislabeled cases. Extensive experiments are conducted on natural and medical image datasets (CIFAR-10 and ISIC 2019). The experimental results show that our NIB module consistently improves the performances of the state-of-the-art robust training methods.

Jesse Michael Han, Igor Babuschkin, Harrison Edwards et al.

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first use the zero-shot translation ability of large pre-trained language models to generate translations for a small set of unlabeled sentences. We then amplify these zero-shot translations by using them as few-shot demonstrations for sampling a larger synthetic dataset. This dataset is distilled by discarding the few-shot demonstrations and then fine-tuning. During backtranslation, we repeatedly generate translations for a set of inputs and then fine-tune a single language model on both directions of the translation task at once, ensuring cycle-consistency by swapping the roles of gold monotext and generated translations when fine-tuning. By using our method to leverage GPT-3's zero-shot translation capability, we achieve a new state-of-the-art in unsupervised translation on the WMT14 English-French benchmark, attaining a BLEU score of 42.1.

Yuan Xue, Yuan-Chen Guo, Han Zhang et al.

In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross pollination between major image generation paradigms, and evaluation and comparison of generation methods.

Xian Sun, Peijin Wang, Zhiyuan Yan et al.

With the rapid development of deep learning, many deep learning-based approaches have made great achievements in object detection task. It is generally known that deep learning is a data-driven method. Data directly impact the performance of object detectors to some extent. Although existing datasets have included common objects in remote sensing images, they still have some limitations in terms of scale, categories, and images. Therefore, there is a strong requirement for establishing a large-scale benchmark on object detection in high-resolution remote sensing images. In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15,000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M. All objects in the FAIR1M dataset are annotated with respect to 5 categories and 37 sub-categories by oriented bounding boxes. Compared with existing detection datasets dedicated to object detection, the FAIR1M dataset has 4 particular characteristics: (1) it is much larger than other existing object detection datasets both in terms of the quantity of instances and the quantity of images, (2) it provides more rich fine-grained category information for objects in remote sensing images, (3) it contains geographic information such as latitude, longitude and resolution, (4) it provides better image quality owing to a careful data cleaning procedure. To establish a baseline for fine-grained object recognition, we propose a novel evaluation method and benchmark fine-grained object detection tasks and a visual classification task using several State-Of-The-Art (SOTA) deep learning-based models on our FAIR1M dataset. Experimental results strongly indicate that the FAIR1M dataset is closer to practical application and it is considerably more challenging than existing datasets.

Christopher Bendkowski, Laurent Mennillo, Tao Xu et al.

Optoelectronic tweezer-driven microrobots (OETdMs) are a versatile micromanipulation technology based on the use of light induced dielectrophoresis to move small dielectric structures (microrobots) across a photoconductive substrate. The microrobots in turn can be used to exert forces on secondary objects and carry out a wide range of micromanipulation operations, including collecting, transporting and depositing microscopic cargos. In contrast to alternative (direct) micromanipulation techniques, OETdMs are relatively gentle, making them particularly well suited to interacting with sensitive objects such as biological cells. However, at present such systems are used exclusively under manual control by a human operator. This limits the capacity for simultaneous control of multiple microrobots, reducing both experimental throughput and the possibility of cooperative multi-robot operations. In this article, we describe an approach to automated targeting and path planning to enable open-loop control of multiple microrobots. We demonstrate the performance of the method in practice, using microrobots to simultaneously collect, transport and deposit silica microspheres. Using computational simulations based on real microscopic image data, we investigate the capacity of microrobots to collect target cells from within a dissociated tissue culture. Our results indicate the feasibility of using OETdMs to autonomously carry out micromanipulation tasks within complex, unstructured environments.

Maxime Oquab, Pierre Stock, Oran Gafni et al.

To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmitted over the network. In this context, we discuss and evaluate the benefits and disadvantages of several deep adversarial approaches. In particular, we explore quality and bandwidth trade-offs for approaches based on static landmarks, dynamic landmarks or segmentation maps. We design a mobile-compatible architecture based on the first order animation model of Siarohin et al. In addition, we leverage SPADE blocks to refine results in important areas such as the eyes and lips. We compress the networks down to about 3MB, allowing models to run in real time on iPhone 8 (CPU). This approach enables video calling at a few kbits per second, an order of magnitude lower than currently available alternatives.

Tao Xu, Fanhua Shang, Yuanyuan Liu et al.

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we propose the first differentially private ADMM (DP-ADMM) algorithm with performance guarantee of $(ε,δ)$-differential privacy ($(ε,δ)$-DP). From the viewpoint of theoretical analysis, we use the Gaussian mechanism and the conversion relationship between Rényi Differential Privacy (RDP) and DP to perform a comprehensive privacy analysis for our algorithm. Then we establish a new criterion to prove the convergence of the proposed algorithms including DP-ADMM. We also give the utility analysis of our DP-ADMM. Moreover, we propose an accelerated DP-ADMM (DP-AccADMM) with the Nesterov's acceleration technique. Finally, we conduct numerical experiments on many real-world datasets to show the privacy-utility tradeoff of the two proposed algorithms, and all the comparative analysis shows that DP-AccADMM converges faster and has a better utility than DP-ADMM, when the privacy budget $ε$ is larger than a threshold.

Fan Zhang, David Hall, Tao Xu et al.

In this paper, we present a workflow for the simulation of drone operations exploiting realistic background environments constructed within Unreal Engine 4 (UE4). Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface. Given the geographical location of the selected area and the camera parameters employed, the scanning strategy and its associated flight parameters are first determined for image capture. Source imagery can be extracted from virtual globe software or obtained through aerial photography of the scene (e.g. using drones). The latter case is clearly more time consuming but can provide enhanced detail, particularly where coverage of virtual globe software is limited. The captured images are then used to generate 3D background environment models employing photogrammetry software. The reconstructed 3D models are then imported into the simulation interface as background environment assets together with appropriate foreground object models as a basis for shot planning and rehearsal. The tool supports both free-flight and parameterisable standard shot types along with programmable scenarios associated with foreground assets and event dynamics. It also supports the exporting of flight plans. Camera shots can also be designed to provide suitable coverage of any landmarks which need to appear in-shot. This simulation tool will contribute to enhanced productivity, improved safety (awareness and mitigations for crowds and buildings), improved confidence of operators and directors and ultimately enhanced quality of viewer experience.

Jing Chen, Chenhui Wang, Kejun Wang et al.

The study of affective computing in the wild setting is underpinned by databases. Existing multimodal emotion databases in the real-world conditions are few and small, with a limited number of subjects and expressed in a single language. To meet this requirement, we collected, annotated, and prepared to release a new natural state video database (called HEU Emotion). HEU Emotion contains a total of 19,004 video clips, which is divided into two parts according to the data source. The first part contains videos downloaded from Tumblr, Google, and Giphy, including 10 emotions and two modalities (facial expression and body posture). The second part includes corpus taken manually from movies, TV series, and variety shows, consisting of 10 emotions and three modalities (facial expression, body posture, and emotional speech). HEU Emotion is by far the most extensive multi-modal emotional database with 9,951 subjects. In order to provide a benchmark for emotion recognition, we used many conventional machine learning and deep learning methods to evaluate HEU Emotion. We proposed a Multi-modal Attention module to fuse multi-modal features adaptively. After multi-modal fusion, the recognition accuracies for the two parts increased by 2.19% and 4.01% respectively over those of single-modal facial expression recognition.

Yanglan Ou, Yuan Xue, Ye Yuan et al.

Cervical cancer is the second most prevalent cancer affecting women today. As the early detection of cervical carcinoma relies heavily upon screening and pre-clinical testing, digital cervicography has great potential as a primary or auxiliary screening tool, especially in low-resource regions due to its low cost and easy access. Although an automated cervical dysplasia detection system has been desirable, traditional fully-supervised training of such systems requires large amounts of annotated data which are often labor-intensive to collect. To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations. In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution. In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance. Our experimental results on a cervical dysplasia classification dataset show that the proposed framework outperforms previous methods under a semi-supervised setting, especially when the labeled samples are scarce.

Hao Sun, Xianxu Zeng, Tao Xu et al.

Uterine cancer, also known as endometrial cancer, can seriously affect the female reproductive organs, and histopathological image analysis is the gold standard for diagnosing endometrial cancer. However, due to the limited capability of modeling the complicated relationships between histopathological images and their interpretations, these computer-aided diagnosis (CADx) approaches based on traditional machine learning algorithms often failed to achieve satisfying results. In this study, we developed a CADx approach using a convolutional neural network (CNN) and attention mechanisms, called HIENet. Because HIENet used the attention mechanisms and feature map visualization techniques, it can provide pathologists better interpretability of diagnoses by highlighting the histopathological correlations of local (pixel-level) image features to morphological characteristics of endometrial tissue. In the ten-fold cross-validation process, the CADx approach, HIENet, achieved a 76.91 $\pm$ 1.17% (mean $\pm$ s. d.) classification accuracy for four classes of endometrial tissue, namely normal endometrium, endometrial polyp, endometrial hyperplasia, and endometrial adenocarcinoma. Also, HIENet achieved an area-under-the-curve (AUC) of 0.9579 $\pm$ 0.0103 with an 81.04 $\pm$ 3.87% sensitivity and 94.78 $\pm$ 0.87% specificity in a binary classification task that detected endometrioid adenocarcinoma (Malignant). Besides, in the external validation process, HIENet achieved an 84.50% accuracy in the four-class classification task, and it achieved an AUC of 0.9829 with a 77.97% (95% CI, 65.27%-87.71%) sensitivity and 100% (95% CI, 97.42%-100.00%) specificity. In summary, the proposed CADx approach, HIENet, outperformed three human experts and four end-to-end CNN-based classifiers on this small-scale dataset composed of 3,500 hematoxylin and eosin (H&E) images regarding overall classification performance.

Malay Haldar, Mustafa Abdool, Prashant Ramanathan et al.

The application to search ranking is one of the biggest machine learning success stories at Airbnb. Much of the initial gains were driven by a gradient boosted decision tree model. The gains, however, plateaued over time. This paper discusses the work done in applying neural networks in an attempt to break out of that plateau. We present our perspective not with the intention of pushing the frontier of new modeling techniques. Instead, ours is a story of the elements we found useful in applying neural networks to a real life product. Deep learning was steep learning for us. To other teams embarking on similar journeys, we hope an account of our struggles and triumphs will provide some useful pointers. Bon voyage!