Search

While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.g., CLIP combined with LLMs). In this paper, we introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences. Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship models such as SDXL and LLaVA-1.6, while eliminating the need for diffusion or compositional architectures. Emu3 is also capable of generating high-fidelity video via predicting the next token in a video sequence. We simplify complex multimodal model designs by converging on a singular focus: tokens, unlocking great potential for scaling both during training and inference. Our results demonstrate that next-token prediction is a promising path towards building general multimodal intelligence beyond language. We open-source key techniques and models to support further research in this direction., Comment: Project Page: https://emu.baai.ac.cn

Novel View Synthesis (NVS) without Structure-from-Motion (SfM) pre-processed camera poses--referred to as SfM-free methods--is crucial for promoting rapid response capabilities and enhancing robustness against variable operating conditions. Recent SfM-free methods have integrated pose optimization, designing end-to-end frameworks for joint camera pose estimation and NVS. However, most existing works rely on per-pixel image loss functions, such as L2 loss. In SfM-free methods, inaccurate initial poses lead to misalignment issue, which, under the constraints of per-pixel image loss functions, results in excessive gradients, causing unstable optimization and poor convergence for NVS. In this study, we propose a correspondence-guided SfM-free 3D Gaussian splatting for NVS. We use correspondences between the target and the rendered result to achieve better pixel alignment, facilitating the optimization of relative poses between frames. We then apply the learned poses to optimize the entire scene. Each 2D screen-space pixel is associated with its corresponding 3D Gaussians through approximated surface rendering to facilitate gradient back propagation. Experimental results underline the superior performance and time efficiency of the proposed approach compared to the state-of-the-art baselines., Comment: arXiv admin note: text overlap with arXiv:2312.07504 by other authors

UWB ranging systems have been adopted in many critical and security sensitive applications due to its precise positioning and secure ranging capabilities. We present a practical jamming attack, namely UWBAD, against commercial UWB ranging systems, which exploits the vulnerability of the adoption of the normalized cross-correlation process in UWB ranging and can selectively and quickly block ranging sessions without prior knowledge of the configurations of the victim devices, potentially leading to severe consequences such as property loss, unauthorized access, or vehicle theft. UWBAD achieves more effective and less imperceptible jamming due to: (i) it efficiently blocks every ranging session by leveraging the field-level jamming, thereby exerting a tangible impact on commercial UWB ranging systems, and (ii) the compact, reactive, and selective system design based on COTS UWB chips, making it affordable and less imperceptible. We successfully conducted real attacks against commercial UWB ranging systems from the three largest UWB chip vendors on the market, e.g., Apple, NXP, and Qorvo. We reported our findings to Apple, related Original Equipment Manufacturers (OEM), and the Automotive Security Research Group, triggering internal security incident response procedures at Volkswagen, Audi, Bosch, and NXP. As of the writing of this paper, the related OEM has acknowledged this vulnerability in their automotive systems and has offered a $5,000 reward as a bounty., Comment: Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security

Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challenging due to the subtle human-body texture details to be generated and the temporal consistency to be considered. Existing approaches typically adopt a conventional GAN with an L1 or L2 loss to produce the target fake video, which intrinsically necessitates a large number of training samples that are challenging to acquire. Meanwhile, current methods still have difficulties in attaining realistic image details and temporal consistency, which unfortunately can be easily perceived by human observers. Motivated by this, we try to tackle the issues from three aspects: (1) We constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance. (2) We present an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations. We also utilize geometrical cues of the face to optimize facial details and refine each key body part with a dedicated local GAN. (3) We advocate generating the foreground in a sequence-to-sequence manner rather than a single-frame manner, explicitly enforcing temporal inconsistency. Empirical results on five datasets, iPER, ComplexMotion, SoloDance, Fish, and Mouse datasets, demonstrate that our method is capable of generating realistic target videos while precisely copying motion from a source video. Our method significantly outperforms state-of-the-art approaches and gains 7.2% and 12.4% improvements in PSNR and FID respectively.

Blockchains, with intricate architectures, encompass various components, e.g., consensus network, smart contracts, decentralized applications, and auxiliary services. While offering numerous advantages, these components expose various attack surfaces, leading to severe threats to blockchains. In this study, we unveil a novel attack surface, i.e., the state storage, in blockchains. The state storage, based on the Merkle Patricia Trie, plays a crucial role in maintaining blockchain state. Besides, we design Nurgle, the first Denial-of-Service attack targeting the state storage. By proliferating intermediate nodes within the state storage, Nurgle forces blockchains to expend additional resources on state maintenance and verification, impairing their performance. We conduct a comprehensive and systematic evaluation of Nurgle, including the factors affecting it, its impact on blockchains, its financial cost, and practically demonstrating the resulting damage to blockchains. The implications of Nurgle extend beyond the performance degradation of blockchains, potentially reducing trust in them and the value of their cryptocurrencies. Additionally, we further discuss three feasible mitigations against Nurgle. At the time of writing, the vulnerability exploited by Nurgle has been confirmed by six mainstream blockchains, and we received thousands of USD bounty from them.

Large Language Models (LLMs) have emerged as powerful tools across various domains within cyber security. Notably, recent studies are increasingly exploring LLMs applied to the context of blockchain security (BS). However, there remains a gap in a comprehensive understanding regarding the full scope of applications, impacts, and potential constraints of LLMs on blockchain security. To fill this gap, we undertake a literature review focusing on the studies that apply LLMs in blockchain security (LLM4BS). Our study aims to comprehensively analyze and understand existing research, and elucidate how LLMs contribute to enhancing the security of blockchain systems. Through a thorough examination of existing literature, we delve into the integration of LLMs into various aspects of blockchain security. We explore the mechanisms through which LLMs can bolster blockchain security, including their applications in smart contract auditing, transaction anomaly detection, vulnerability repair, program analysis of smart contracts, and serving as participants in the cryptocurrency community. Furthermore, we assess the challenges and limitations associated with leveraging LLMs for enhancing blockchain security, considering factors such as scalability, privacy concerns, and ethical concerns. Our thorough review sheds light on the opportunities and potential risks of tasks on LLM4BS, providing valuable insights for researchers, practitioners, and policymakers alike.

Scaling up contrastive language-image pretraining (CLIP) is critical for empowering both vision and multimodal models. We present EVA-CLIP-18B, the largest and most powerful open-source CLIP model to date, with 18-billion parameters. With only 6-billion training samples seen, EVA-CLIP-18B achieves an exceptional 80.7% zero-shot top-1 accuracy averaged across 27 widely recognized image classification benchmarks, outperforming its forerunner EVA-CLIP (5-billion parameters) and other open-source CLIP models by a large margin. Remarkably, we observe a consistent performance improvement with the model size scaling of EVA-CLIP, despite maintaining a constant training dataset of 2-billion image-text pairs from LAION-2B and COYO-700M. This dataset is openly available and much smaller than the in-house datasets (e.g., DFN-5B, WebLI-10B) employed in other state-of-the-art CLIP models. EVA-CLIP-18B demonstrates the potential of EVA-style weak-to-strong visual model scaling. With our model weights made publicly available, we hope to facilitate future research in vision and multimodal foundation models.

The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning, such as visual prompting and object-grounded generation. The model sets a new record on multiple multimodal understanding tasks in few-shot settings. When instruction-tuned to follow specific instructions, Emu2 further achieves new state-of-the-art on challenging tasks such as question answering benchmarks for large multimodal models and open-ended subject-driven generation. These achievements demonstrate that Emu2 can serve as a base model and general-purpose interface for a wide range of multimodal tasks. Code and models are publicly available to facilitate future research., Comment: Accepted to CVPR 2024. Project page: https://baaivision.github.io/emu2

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we identify the root cause as the overly-simplified language structure and lack of knowledge details in existing synthetic captions. To provide higher-quality and more scalable multimodal pretraining data, we propose CapsFusion, an advanced framework that leverages large language models to consolidate and refine information from both web-based image-text pairs and synthetic captions. Extensive experiments show that CapsFusion captions exhibit remarkable all-round superiority over existing captions in terms of model performance (e.g., 18.8 and 18.3 improvements in CIDEr score on COCO and NoCaps), sample efficiency (requiring 11-16 times less computation than baselines), world knowledge depth, and scalability. These effectiveness, efficiency and scalability advantages position CapsFusion as a promising candidate for future scaling of LMM training., Comment: CVPR 2024. Code & Dataset: https://github.com/baaivision/CapsFusion

Due to the drawbacks of Federated Learning (FL) such as vulnerability of a single central server, centralized federated learning is shifting to decentralized federated learning, a paradigm which takes the advantages of blockchain. A key enabler for adoption of blockchain-based federated learning is how to select suitable participants to train models collaboratively. Selecting participants by storing and querying the metadata of data owners on blockchain could ensure the reliability of selected data owners, which is helpful to obtain high-quality models in FL. However, querying multi-dimensional metadata on blockchain needs to traverse every transaction in each block, making the query time-consuming. An efficient query method for multi-dimensional metadata in the blockchain for selecting participants in FL is absent and challenging. In this paper, we propose a novel data structure to improve the query efficiency within each block named MerkleRB-Tree. In detail, we leverage Minimal Bounding Rectangle(MBR) and bloom-filters for the query process of multi-dimensional continuous-valued attributes and discrete-valued attributes respectively. Furthermore, we migrate the idea of the skip list along with an MBR and a bloom filter at the head of each block to enhance the query efficiency for inter-blocks. The performance analysis and extensive evaluation results on the benchmark dataset demonstrate the superiority of our method in blockchain-based FL.

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g., interleaved image, text and video) through a one-model-for-all autoregressive training process. First, visual signals are encoded into embeddings, and together with text tokens form an interleaved input sequence. Emu is then end-to-end trained with a unified objective of classifying the next text token or regressing the next visual embedding in the multimodal sequence. This versatile multimodality empowers the exploration of diverse pretraining data sources at scale, such as videos with interleaved frames and text, webpages with interleaved images and text, as well as web-scale image-text pairs and video-text pairs. Emu can serve as a generalist multimodal interface for both image-to-text and text-to-image tasks, and supports in-context image and text generation. Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models. Extended capabilities such as multimodal assistants via instruction tuning are also demonstrated with impressive performance., Comment: Accepted to ICLR 2024. Code and Models: https://github.com/baaivision/Emu

Millions of smart contracts have been deployed onto Ethereum for providing various services, whose functions can be invoked. For this purpose, the caller needs to know the function signature of a callee, which includes its function id and parameter types. Such signatures are critical to many applications focusing on smart contracts, e.g., reverse engineering, fuzzing, attack detection, and profiling. Unfortunately, it is challenging to recover the function signatures from contract bytecode, since neither debug information nor type information is present in the bytecode. To address this issue, prior approaches rely on source code, or a collection of known signatures from incomplete databases or incomplete heuristic rules, which, however, are far from adequate and cannot cope with the rapid growth of new contracts. In this paper, we propose a novel solution that leverages how functions are handled by Ethereum virtual machine (EVM) to automatically recover function signatures. In particular, we exploit how smart contracts determine the functions to be invoked to locate and extract function ids, and propose a new approach named type-aware symbolic execution (TASE) that utilizes the semantics of EVM operations on parameters to identify the number and the types of parameters. Moreover, we develop SigRec, a new tool for recovering function signatures from contract bytecode without the need of source code and function signature databases. The extensive experimental results show that SigRec outperforms all existing tools, achieving an unprecedented 98.7 percent accuracy within 0.074 seconds. We further demonstrate that the recovered function signatures are useful in attack detection, fuzzing and reverse engineering of EVM bytecode.

We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formulated as an in-context coloring problem with random color mapping for each data sample. The objective is to accomplish diverse tasks according to the context, rather than relying on specific colors. After training, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text. SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation. Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively., Comment: Code and Demo: https://github.com/baaivision/Painter

Blockchain smart contracts have given rise to a variety of interesting and compelling applications and emerged as a revolutionary force for the Internet. Quite a few practitioners have devoted themselves to developing tools for detecting bugs in smart contracts. One line of efforts revolve around static analysis techniques, which heavily suffer from high false-positive rates. Another line of works concentrate on fuzzing techniques. Unfortunately, current fuzzing approaches for smart contracts tend to conduct fuzzing starting from the initial state of the contract, which expends too much energy revolving around the initial state and thus is usually unable to unearth bugs triggered by other states. Moreover, most existing methods treat each branch equally, failing to take care of the branches that are rare or more likely to possess bugs. This might lead to resources wasted on normal branches. In this paper, we try to tackle these challenges from three aspects: (1) In generating function invocation sequences, we explicitly consider data dependencies between functions to facilitate exploring richer states. We further prolong a function invocation sequence S1 by appending a new sequence S2, so that S2 can start fuzzing from states that are different from the initial state. (2) We incorporate a branch distance-based measure to evolve test cases iteratively towards a target branch. (3) We engage a branch search algorithm to discover rare and vulnerable branches, and design an energy allocation mechanism to take care of exercising these crucial branches. We implement IR-Fuzz and extensively evaluate it over 12K real-world contracts. Empirical results show that: (i) IR-Fuzz achieves 28% higher branch coverage than state-of-the-art fuzzing approaches, and (ii) IR-Fuzz detects more vulnerabilities and increases the average accuracy of vulnerability detection by 7% over current methods., Comment: This paper has been accepted by IEEE Transactions On Information Forensics And Security (TIFS 2022)

Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e.g., ViT), albeit hierarchical vision transformers (e.g., Swin Transformer) have potentially better properties in formulating vision inputs. In this paper, we offer a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) that enjoys both high efficiency and good performance in MIM. The key is to remove the unnecessary "local inter-unit operations", deriving structurally simple hierarchical vision transformers in which mask-units can be serialized like plain vision transformers. For this purpose, we start with Swin Transformer and (i) set the masking unit size to be the token size in the main stage of Swin Transformer, (ii) switch off inter-unit self-attentions before the main stage, and (iii) eliminate all operations after the main stage. Empirical studies demonstrate the advantageous performance of HiViT in terms of fully-supervised, self-supervised, and transfer learning. In particular, in running MAE on ImageNet-1K, HiViT-B reports a +0.6% accuracy gain over ViT-B and a 1.9$\times$ speed-up over Swin-B, and the performance gain generalizes to downstream tasks of detection and segmentation. Code will be made publicly available.

Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models. In this study, we propose to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is ``fully pre-trained" so that detectors' generalization capacity is maximized. The essential differences between imTED with the baseline detector are twofold: (1) migrating the pre-trained transformer decoder to the detector head while removing the randomly initialized FPN from the feature extraction path; and (2) defining a multi-scale feature modulator (MFM) to enhance scale adaptability. Such designs not only reduce randomly initialized parameters significantly but also unify detector training with representation learning intendedly. Experiments on the MS COCO object detection dataset show that imTED consistently outperforms its counterparts by $\sim$2.4 AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6 AP. Code is available at https://github.com/LiewFeng/imTED., Comment: 6 figures, 6 tables