Yufeng Hu

Haifeng Wang, Hua Wu, Tian Wu et al.

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Wei Liu, Jiyuan Zhang, Binxiong Zheng et al.

End-to-end autonomous driving has advanced significantly, offering benefits such as system simplicity and stronger driving performance in both open-loop and closed-loop settings than conventional pipelines. However, existing frameworks still suffer from low success rates in closed-loop evaluations, highlighting their limitations in real-world deployment. In this paper, we introduce X-Driver, a unified multi-modal large language models(MLLMs) framework designed for closed-loop autonomous driving, leveraging Chain-of-Thought(CoT) and autoregressive modeling to enhance perception and decision-making. We validate X-Driver across multiple autonomous driving tasks using public benchmarks in CARLA simulation environment, including Bench2Drive[6]. Our experimental results demonstrate superior closed-loop performance, surpassing the current state-of-the-art(SOTA) while improving the interpretability of driving decisions. These findings underscore the importance of structured reasoning in end-to-end driving and establish X-Driver as a strong baseline for future research in closed-loop autonomous driving.

Muhui Jiang, Tianyi Xu, Yajin Zhou et al.

Emulator is widely used to build dynamic analysis frameworks due to its fine-grained tracing capability, full system monitoring functionality, and scalability of running on different operating systemsand architectures. However, whether the emulator is consistent with real devices is unknown. To understand this problem, we aim to automatically locate inconsistent instructions, which behave differently between emulators and real devices. We target ARM architecture, which provides machine readable specification. Based on the specification, we propose a test case generator by designing and implementing the first symbolic execution engine for ARM architecture specification language (ASL). We generate 2,774,649 representative instruction streams and conduct differential testing with these instruction streams between four ARM real devices in different architecture versions (i.e., ARMv5, ARMv6, ARMv7-a, and ARMv8-a) and the state-of-the-art emulators (i.e., QEMU). We locate 155,642 inconsistent instruction streams, which cover 30% of all instruction encodings and 47.8% of the instructions. We find undefined implementation in ARM manual and implementation bugs of QEMU are the major causes of inconsistencies. Furthermore, we discover four QEMU bugs, which are confirmed and patched by thedevelopers, covering 13 instruction encodings including the most commonly used ones (e.g.,STR,BLX). With the inconsistent instructions, we build three security applications and demonstrate thecapability of these instructions on detecting emulators, anti-emulation, and anti-fuzzing.

Lei Wu, Yufeng Hu, Yajin Zhou et al.

One reason for the popularity of Bitcoin is due to its anonymity. Although several heuristics have been used to break the anonymity, new approaches are proposed to enhance its anonymity at the same time. One of them is the mixing service. Unfortunately, mixing services have been abused to facilitate criminal activities, e.g., money laundering. As such, there is an urgent need to systematically understand Bitcoin mixing services. In this paper, we take the first step to understand state-of-the-art Bitcoin mixing services. Specifically, we propose a generic abstraction model for mixing services and observe that there are two mixing mechanisms in the wild, i.e. {swapping} and {obfuscating}. Based on this model, we conduct a transaction-based analysis and successfully reveal the mixing mechanisms of four representative services. Besides, we propose a method to identify mixing transactions that leverage the obfuscating mechanism. The proposed approach is able to identify over $92$\% of the mixing transactions. Based on identified transactions, we then estimate the profit of mixing services and provide a case study of tracing the money flow of stolen Bitcoins.

Bo Chen, Xiaotao Gu, Yufeng Hu et al.

Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET). Despite its efficiency in reducing manual labeling efforts, it also brings the challenge of dealing with false entity type labels, as distant supervision assigns labels in a context agnostic manner. Existing works alleviated this issue with partial-label loss, but usually suffer from confirmation bias, which means the classifier fit a pseudo data distribution given by itself. In this work, we propose to regularize distantly supervised models with Compact Latent Space Clustering (CLSC) to bypass this problem and effectively utilize noisy data yet. Our proposed method first dynamically constructs a similarity graph of different entity mentions; infer the labels of noisy instances via label propagation. Based on the inferred labels, mention embeddings are updated accordingly to encourage entity mentions with close semantics to form a compact cluster in the embedding space,thus leading to better classification performance. Extensive experiments on standard benchmarks show that our CLSC model consistently outperforms state-of-the-art distantly supervised entity typing systems by a significant margin.