Zhipeng Wang

Nanqing Dong, Zhipeng Wang, Jiahao Sun et al.

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors.

Chengjin Wang, Yanmin Zhou, Zheng Yan et al.

In unknown cluttered environments with densely stacked objects, the free-motion space is extremely barren, posing significant challenges to motion planners. Collision-free planning methods often suffer from catastrophic failures due to unexpected collisions and motion obstructions. To address this issue, this paper proposes an interactive motion planning framework (I-MP), based on a perception-motion loop. This framework empowers robots to autonomously model and reason about contact models, which in turn enables safe expansion of the free-motion space. Specifically, the robot utilizes multimodal tactile perception to acquire stimulus-response signal pairs. This enables real-time identification of objects' mechanical properties and the subsequent construction of contact models. These models are integrated as computational constraints into a reactive planner. Based on fixed-point theorems, the planner computes the spatial state toward the target in real time, thus avoiding the computational burden associated with extrapolating on high-dimensional interaction models. Furthermore, high-dimensional interaction features are linearly superposed in Cartesian space in the form of energy, and the controller achieves trajectory tracking by solving the energy gradient from the current state to the planned state. The experimental results showed that at cruising speeds ranging from 0.01 to 0.07 $m/s$, the robot's initial contact force with objects remained stable at 1.0 +- 0.7 N. In the cabinet scenario test where collision-free trajectories were unavailable, I-MP expanded the free motion space by 37.5 % through active interaction, successfully completing the environmental exploration task.

Xiaofeng Lin, Hejian Sang, Zhipeng Wang et al.

A prevailing view holds that supervised fine-tuning (SFT) memorizes training data and fails to generalize, whereas reinforcement learning (RL) attains broader robustness. We revisit this claim through a systematic evaluation on two decision-making benchmarks, Sokoban and General Points, and arrive at a different conclusion. We show that much of SFT's perceived failure stems from frozen-prompt artifacts: when trained on fixed instruction templates, SFT models cling to training semantics rather than adapting to new ones. Introducing prompt diversity during training breaks this shortcut and yields strong generalization to unseen instruction variants without harming in-distribution performance. Beyond instruction shifts, we ask whether SFT can generalize to strictly harder tasks. Here, chain-of-thought (CoT) supervision provides an algorithmic scaffold that markedly improves transfer to more difficult regimes, such as larger Sokoban grids with additional boxes and arithmetic with out-of-distribution values or five-card compositions that increase combinatorial complexity. Finally, combining prompt diversity with CoT achieves the best of both worlds: robust generalization across both instruction-variant and difficulty-variant settings, matching or surpassing RL baselines on our benchmarks while retaining SFT's simplicity and stability. These findings challenge the narrative that SFT is inherently inferior to RL and support a data-centric perspective: with appropriately curated demonstrations, vanilla SFT can generalize as strongly as RL. Code reproducing the results in the paper can be found at: https://github.com/XiaofengLin7/debunking-sft-generalization.

Ryan Lucas, Kayhan Behdin, Zhipeng Wang et al.

Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater performance loss than in typical language modeling tasks, and in some cases can make the model slower since they cause the model to produce more thinking tokens but with worse performance. We show that this is partly due to the fact that standard LLM pruning methods often focus on input reconstruction, whereas reasoning is a decode-dominated task. We introduce a simple, drop-in fix: during pruning we jointly reconstruct activations from the input and the model's on-policy chain-of-thought traces. This "Reasoning-Aware Compression" (RAC) integrates seamlessly into existing pruning workflows such as SparseGPT, and boosts their performance significantly. Code reproducing the results in the paper can be found at: https://github.com/RyanLucas3/RAC

Zhipeng Wang, Hao Wang, Jiexi Yan et al.

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is proposed to learn generalized representations to smooth the domain gap by mining relations with additional augmented samples. Furthermore, a category-specific memory bank with sketch features is explored to reduce intra-class diversity in the sketch domain. Extensive experiments demonstrate that our approach notably outperforms the state-of-the-art methods in both Sketchy and TU-Berlin datasets. Our source code is publicly available at https://github.com/haowang1992/DSN.

Bing Yuan, Zhang Jiang, Aobo Lyu et al.

Emergence and causality are two fundamental concepts for understanding complex systems. They are interconnected. On one hand, emergence refers to the phenomenon where macroscopic properties cannot be solely attributed to the cause of individual properties. On the other hand, causality can exhibit emergence, meaning that new causal laws may arise as we increase the level of abstraction. Causal emergence theory aims to bridge these two concepts and even employs measures of causality to quantify emergence. This paper provides a comprehensive review of recent advancements in quantitative theories and applications of causal emergence. Two key problems are addressed: quantifying causal emergence and identifying it in data. Addressing the latter requires the use of machine learning techniques, thus establishing a connection between causal emergence and artificial intelligence. We highlighted that the architectures used for identifying causal emergence are shared by causal representation learning, causal model abstraction, and world model-based reinforcement learning. Consequently, progress in any of these areas can benefit the others. Potential applications and future perspectives are also discussed in the final section of the review.

Zhipeng Wang, Rui Sun, Elizabeth Lui et al.

The rapid advancement of AI has underscored critical challenges in its development and implementation, largely due to centralized control by a few major corporations. This concentration of power intensifies biases within AI models, resulting from inadequate governance and oversight mechanisms. Additionally, it limits public involvement and heightens concerns about the integrity of model generation. Such monopolistic control over data and AI outputs threatens both innovation and fair data usage, as users inadvertently contribute data that primarily benefits these corporations. In this work, we propose AIArena, a blockchain-based decentralized AI training platform designed to democratize AI development and alignment through on-chain incentive mechanisms. AIArena fosters an open and collaborative environment where participants can contribute models and computing resources. Its on-chain consensus mechanism ensures fair rewards for participants based on their contributions. We instantiate and implement AIArena on the public Base blockchain Sepolia testnet, and the evaluation results demonstrate the feasibility of AIArena in real-world applications.

Fengyi Li, Kayhan Behdin, Natesh Pillai et al.

Text segmentation based on the semantic meaning of sentences is a fundamental task with broad utility in many downstream applications. In this paper, we propose a graphical model-based unsupervised learning approach, named BP-Seg for efficient text segmentation. Our method not only considers local coherence, capturing the intuition that adjacent sentences are often more related, but also effectively groups sentences that are distant in the text yet semantically similar. This is achieved through belief propagation on the carefully constructed graphical models. Experimental results on both an illustrative example and a dataset with long-form documents demonstrate that our method performs favorably compared to competing approaches.

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song et al.

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally yield better generalization and performance, their substantial computational requirements often render them impractical for many real-world scenarios at scale. In this paper, we present a comprehensive set of insights for training and deploying small language models (SLMs) that deliver high performance for a variety of industry use cases. We focus on two key techniques: (1) knowledge distillation and (2) model compression via structured pruning and quantization. These approaches enable SLMs to retain much of the quality of their larger counterparts while significantly reducing training/serving costs and latency. We detail the impact of these techniques on a variety of use cases in a large professional social network platform and share deployment lessons, including hardware optimization strategies that improve speed and throughput for both predictive and reasoning-based applications in Recommendation Systems.

Rui Sun, Zhipeng Wang, Hengrui Zhang et al.

One of the biggest challenges of building artificial intelligence (AI) model in the healthcare area is the data sharing. Since healthcare data is private, sensitive, and heterogeneous, collecting sufficient data for modelling is exhausting, costly, and sometimes impossible. In this paper, we propose a framework for global healthcare modelling using datasets from multi-continents (Europe, North America, and Asia) without sharing the local datasets, and choose glucose management as a study model to verify its effectiveness. Technically, blockchain-enabled federated learning is implemented with adaptation to meet the privacy and safety requirements of healthcare data, meanwhile, it rewards honest participation and penalizes malicious activities using its on-chain incentive mechanism. Experimental results show that the proposed framework is effective, efficient, and privacy-preserving. Its prediction accuracy consistently outperforms models trained on limited personal data and achieves comparable or even slightly better results than centralized training in certain scenarios, all while preserving data privacy. This work paves the way for international collaborations on healthcare projects, where additional data is crucial for reducing bias and providing benefits to humanity.

Zhipeng Wang, Nanqing Dong, Jiahao Sun et al.

Federated learning (FL) is a machine learning paradigm, which enables multiple and decentralized clients to collaboratively train a model under the orchestration of a central aggregator. FL can be a scalable machine learning solution in big data scenarios. Traditional FL relies on the trust assumption of the central aggregator, which forms cohorts of clients honestly. However, a malicious aggregator, in reality, could abandon and replace the client's training models, or insert fake clients, to manipulate the final training results. In this work, we introduce zkFL, which leverages zero-knowledge proofs to tackle the issue of a malicious aggregator during the training model aggregation process. To guarantee the correct aggregation results, the aggregator provides a proof per round, demonstrating to the clients that the aggregator executes the intended behavior faithfully. To further reduce the verification cost of clients, we use blockchain to handle the proof in a zero-knowledge way, where miners (i.e., the participants validating and maintaining the blockchain data) can verify the proof without knowing the clients' local and aggregated models. The theoretical analysis and empirical results show that zkFL achieves better security and privacy than traditional FL, without modifying the underlying FL network structure or heavily compromising the training speed.

Xingjian Li, Di Hu, Xuhong Li et al.

Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples. To obtain better generalization, using the starting point as the reference (SPAR), either through weights or features, has been successfully applied to transfer learning as a regularizer. However, due to the domain discrepancy between the source and target task, there exists obvious risk of negative transfer in a straightforward manner of knowledge preserving. In this paper, we propose a novel transfer learning algorithm, introducing the idea of Target-awareness REpresentation Disentanglement (TRED), where the relevant knowledge with respect to the target task is disentangled from the original source model and used as a regularizer during fine-tuning the target model. Specifically, we design two alternative methods, maximizing the Maximum Mean Discrepancy (Max-MMD) and minimizing the mutual information (Min-MI), for the representation disentanglement. Experiments on various real world datasets show that our method stably improves the standard fine-tuning by more than 2% in average. TRED also outperforms related state-of-the-art transfer learning regularizers such as L2-SP, AT, DELTA, and BSS.

Weishan Zhang, Tao Zhou, Qinghua Lu et al.

Medical diagnostic image analysis (e.g., CT scan or X-Ray) using machine learning is an efficient and accurate way to detect COVID-19 infections. However, sharing diagnostic images across medical institutions is usually not allowed due to the concern of patients' privacy. This causes the issue of insufficient datasets for training the image classification model. Federated learning is an emerging privacy-preserving machine learning paradigm that produces an unbiased global model based on the received updates of local models trained by clients without exchanging clients' local data. Nevertheless, the default setting of federated learning introduces huge communication cost of transferring model updates and can hardly ensure model performance when data heterogeneity of clients heavily exists. To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections. First, we design an architecture for dynamic fusion-based federated learning systems to analyse medical diagnostic images. Further, we present a dynamic fusion method to dynamically decide the participating clients according to their local model performance and schedule the model fusion-based on participating clients' training time. In addition, we summarise a category of medical diagnostic image datasets for COVID-19 detection, which can be used by the machine learning community for image analysis. The evaluation results show that the proposed approach is feasible and performs better than the default setting of federated learning in terms of model performance, communication efficiency and fault tolerance.

Zhipeng Wang, Mingbo Cai

This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected neural network consists of multiple single neurons. Another one is the simplified mechanical arm system which is controlled by multiple neurons. We suppose that each neuron is like an agent and it can do Gibbs sampling of the posterior probability of stimulus features. The policy is optimized in a way that the cumulative global rewards are maximized. The algorithm for the second system is based on the same idea but we incorporate the physics model into the constraints. The simulation results show that for the first system our algorithm converges well. For the second system it does not converge well in a reasonable simulation time length. In summary, we took the initial endeavor to study the reinforcement learning for multi-agents system. The computational complexity is always an issue and significant amount of works have to be done in order to better understand the problem.