Yuhong Liu

Yuhong Liu, Beichen Zhang, Yuhang Zang et al.

Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized tools, or constrained environments that limit scale. We introduce Spatial-SSRL, a self-supervised RL paradigm that derives verifiable signals directly from ordinary RGB or RGB-D images. Spatial-SSRL automatically formulates five pretext tasks that capture 2D and 3D spatial structure: shuffled patch reordering, flipped patch recognition, cropped patch inpainting, regional depth ordering, and relative 3D position prediction. These tasks provide ground-truth answers that are easy to verify and require no human or LVLM annotation. Training on our tasks substantially improves spatial reasoning while preserving general visual capabilities. On seven spatial understanding benchmarks in both image and video settings, Spatial-SSRL delivers average accuracy gains of 4.63% (3B) and 3.89% (7B) over the Qwen2.5-VL baselines. Our results show that simple, intrinsic supervision enables RLVR at scale and provides a practical route to stronger spatial intelligence in LVLMs.

Yefeng Yuan, Yuhong Liu, Liang Cheng

The rapid advancements in generative AI and large language models (LLMs) have opened up new avenues for producing synthetic data, particularly in the realm of structured tabular formats, such as product reviews. Despite the potential benefits, concerns regarding privacy leakage have surfaced, especially when personal information is utilized in the training datasets. In addition, there is an absence of a comprehensive evaluation framework capable of quantitatively measuring the quality of the generated synthetic data and their utility for downstream tasks. In response to this gap, we introduce SynEval, an open-source evaluation framework designed to assess the fidelity, utility, and privacy preservation of synthetically generated tabular data via a suite of diverse evaluation metrics. We validate the efficacy of our proposed framework - SynEval - by applying it to synthetic product review data generated by three state-of-the-art LLMs: ChatGPT, Claude, and Llama. Our experimental findings illuminate the trade-offs between various evaluation metrics in the context of synthetic data generation. Furthermore, SynEval stands as a critical instrument for researchers and practitioners engaged with synthetic tabular data,, empowering them to judiciously determine the suitability of the generated data for their specific applications, with an emphasis on upholding user privacy.

Beichen Zhang, Yuhong Liu, Xiaoyi Dong et al. · pku

Large language models (LLMs) have demonstrated impressive ability in solving complex mathematical problems with multi-step reasoning and can be further enhanced with well-designed in-context learning (ICL) examples. However, this potential is often constrained by two major challenges in ICL: granularity mismatch and irrelevant information. We observe that while LLMs excel at decomposing mathematical problems, they often struggle with reasoning errors in fine-grained steps. Moreover, ICL examples retrieved at the question level may omit critical steps or even mislead the model with irrelevant details. To address this issue, we propose BoostStep, a method that enhances reasoning accuracy through step-aligned ICL, a novel mechanism that carefully aligns retrieved reference steps with the corresponding reasoning steps. Additionally, BoostStep incorporates an effective "first-try" strategy to deliver exemplars highly relevant to the current state of reasoning. BoostStep is a flexible and powerful method that integrates seamlessly with chain-of-thought (CoT) and tree search algorithms, refining both candidate selection and decision-making. Empirical results show that BoostStep improves GPT-4o's CoT performance by 4.6% across mathematical benchmarks, significantly surpassing traditional few-shot learning's 1.2%. Moreover, it can achieve an additional 7.5\% gain combined with tree search. Surprisingly, it enhances state-of-the-art LLMs to solve challenging math problems using simpler examples. It improves DeepSeek-R1-671B's performance on AIME by 2.2%, leveraging simple examples only from the MATH dataset.

Shufang Zhang, Minxue Ni, Lei Wang et al.

The Diffusion model has a strong ability to generate wild images. However, the model can just generate inaccurate images with the guidance of text, which makes it very challenging to directly apply the text-guided generative model for virtual try-on scenarios. Taking images as guiding conditions of the diffusion model, this paper proposes a brand new personalized virtual try-on model (PE-VITON), which uses the two stages (shape control and texture guidance) to decouple the clothing attributes. Specifically, the proposed model adaptively matches the clothing to human body parts through the Shape Control Module (SCM) to mitigate the misalignment of the clothing and the human body parts. The semantic information of the input clothing is parsed by the Texture Guided Module (TGM), and the corresponding texture is generated by directional guidance. Therefore, this model can effectively solve the problems of weak reduction of clothing folds, poor generation effect under complex human posture, blurred edges of clothing, and unclear texture styles in traditional try-on methods. Meanwhile, the model can automatically enhance the generated clothing folds and textures according to the human posture, and improve the authenticity of virtual try-on. In this paper, qualitative and quantitative experiments are carried out on high-resolution paired and unpaired datasets, the results show that the proposed model outperforms the state-of-the-art model.

Ruihuang Li, Caijin Zhou, Shoujian Zheng et al. · tencent-ai

Intelligent game creation represents a transformative advancement in game development, utilizing generative artificial intelligence to dynamically generate and enhance game content. Despite notable progress in generative models, the comprehensive synthesis of high-quality game assets, including both images and videos, remains a challenging frontier. To create high-fidelity game content that simultaneously aligns with player preferences and significantly boosts designer efficiency, we present Hunyuan-Game, an innovative project designed to revolutionize intelligent game production. Hunyuan-Game encompasses two primary branches: image generation and video generation. The image generation component is built upon a vast dataset comprising billions of game images, leading to the development of a group of customized image generation models tailored for game scenarios: (1) General Text-to-Image Generation. (2) Game Visual Effects Generation, involving text-to-effect and reference image-based game visual effect generation. (3) Transparent Image Generation for characters, scenes, and game visual effects. (4) Game Character Generation based on sketches, black-and-white images, and white models. The video generation component is built upon a comprehensive dataset of millions of game and anime videos, leading to the development of five core algorithmic models, each targeting critical pain points in game development and having robust adaptation to diverse game video scenarios: (1) Image-to-Video Generation. (2) 360 A/T Pose Avatar Video Synthesis. (3) Dynamic Illustration Generation. (4) Generative Video Super-Resolution. (5) Interactive Game Video Generation. These image and video generation models not only exhibit high-level aesthetic expression but also deeply integrate domain-specific knowledge, establishing a systematic understanding of diverse game and anime art styles.

Jun Jiang, Yuanliang Li, Luyang Hou et al.

With the large number of prosumers deploying distributed energy resources (DERs), integrating these prosumers into a transactive energy market (TEM) is a trend for the future smart grid. A community-based double auction market is considered a promising TEM that can encourage prosumers to participate and maximize social welfare. However, the traditional TEM is challenging to model explicitly due to the random bidding behavior of prosumers and uncertainties caused by the energy operation of DERs. Furthermore, although reinforcement learning algorithms provide a model-free solution to optimize prosumers' bidding strategies, their use in TEM is still challenging due to their scalability, stability, and privacy protection limitations. To address the above challenges, in this study, we design a double auction-based TEM with multiple DERs-equipped prosumers to transparently and efficiently manage energy transactions. We also propose a deep reinforcement learning (DRL) model with distributed learning and execution to ensure the scalability and privacy of the market environment. Additionally, the design of two bidding actions (i.e., bidding price and quantity) optimizes the bidding strategies for prosumers. Simulation results show that (1) the designed TEM and DRL model are robust; (2) the proposed DRL model effectively balances the energy payment and comfort satisfaction for prosumers and outperforms the state-of-the-art methods in optimizing the bidding strategies.

Bhagyashri Tushir, Vikram K Ramanna, Yuhong Liu et al.

Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. More importantly, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as "device latency," as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency. Specifically, this work introduces "accumulation score" as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency.

Xin Hao, Changyang She, Phee Lep Yeoh et al.

In this paper, we develop a deep learning-based bandwidth allocation policy that is: 1) scalable with the number of users and 2) transferable to different communication scenarios, such as non-stationary wireless channels, different quality-of-service (QoS) requirements, and dynamically available resources. To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN), with which the number of training parameters does not change with the number of users. To enable the generalization of the GNN, we develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios during meta-training. Next, during meta-testing, a few samples are used to fine-tune the GNN with unseen communication scenarios. Simulation results demonstrate that our HML approach can improve the initial performance by 8.79%, and sample efficiency by 73%, compared with existing benchmarks. After fine-tuning, our near-optimal GNN-based policy can achieve close to the same reward with much lower inference complexity compared to the optimal policy obtained using iterative optimization. Numerical results validate that our HML can reduce the computation time by approximately 200 to 2000 times than the optimal iterative algorithm.

Holden Gordon, Conrad Park, Bhagyashri Tushir et al.

With the rise in Internet of Things (IoT) devices, home network management and security are becoming complex. There is an urgent requirement to make smart home network management efficient. This work proposes an SDN-based architecture to secure smart home networks through K-Nearest Neighbor (KNN) based device classifications and malicious traffic detection. The efficiency is further enhanced by offloading the computation-intensive KNN model to Field Programmable Gate Arrays (FPGA), which offers parallel processing power of GPU platforms at lower costs and higher efficiencies, and can be used to accelerate time-sensitive tasks. The proposed parallelization and implementation of KNN on FPGA are achieved by using the Vivado Design Suite from Xilinx and High-Level Synthesis (HLS). When optimized with 10-fold cross-validation, the proposed solution for KNN consistently exhibits the best performances on FPGA when compared with four alternative KNN instances (i.e., 78% faster than the parallel bubble sort-based implementation and 99\% faster than the other three sorting algorithms). Moreover, with 36,225 training samples, the proposed KNN solution classifies a test query with 95% accuracy in approximately 4 milliseconds on FPGA compared to 57 seconds on a CPU platform.

Bhagyashri Tushir, Hetesh Sehgal, Rohan Nair et al.

Mirai is a type of malware that creates a botnet of internet-connected devices, which can later be used to infect other devices or servers. This paper aims to analyze and explain the Mirai code and create a low-cost simulation environment to aid in the dynamic analysis of Mirai. Further, we perform controlled Denial-of-Service attacks while measuring resource consumption on resource-constrained compromised and victim Internet-of-Things (IoT) devices, such as energy consumption, CPU utilization, memory utilization, Ethernet input/output performance, and Secure Digital card usage. The experimental setup shows that when a compromised device sends a User Datagram Protocol (UDP) flood, it consumes 38.44% more energy than its regular usage. In the case of Secure Digital usage, the victim, when flooded with Transmission Control Protocol (TCP) messages, uses 64.6% more storage for reading and 55.45% more for writing. The significant extra resource consumption caused by Mirai attacks on resource-constrained IoT devices can severely threaten such devices' wide adoption and raises great challenges for the security designs in the resource-constrained IoT environment.

Holden Gordon, Christopher Batula, Bhagyashri Tushir et al.

IoT devices have become popular targets for various network attacks due to their lack of industry-wide security standards. In this work, we focus on smart home IoT device identification and defending them against Distributed Denial of Service (DDoS) attacks. The proposed framework protects smart homes by using VLAN-based network isolation. This architecture has two VLANs: one with non-verified devices and the other with verified devices, both of which are managed by the SDN controller. Lightweight stateless flow-based features, including ICMP, TCP, and UDP protocol percentage, packet count and size, and IP diversity ratio, are proposed for efficient feature collections. Further analysis is performed to minimize training data to run on resource-constrained edge devices in smart home networks. Three popular machine learning algorithms, including K-Nearest-Neighbors, Random Forest, and Support Vector Machines, are used to classify IoT devices and detect different types of DDoS attacks, including TCP-SYN, UDP, and ICMP. The system's effectiveness and efficiency are evaluated by emulating a network consisting of an Open vSwitch, Faucet SDN controller, and several IoT device traces from two different testbeds.

Shan Chen, Weiguo Dai, Yuanxi Dai et al.

This paper presents Thinkey, an efficient, secure, infinitely scalable and decentralized blockchain architecture. It ensures system correctness and liveness by a multi-layer structure. In particular, the system is based on a double-chain architecture and uses a multi-layer consensus protocol to guarantee consistency. Thinkey also uses a novel account model which is based on Actor Model to support the complex logic in the multi-chain structure. Experiment results show that the proposed Thinkey architecture can achieve higher throughput as the number of nodes increases.