Zhou Jiang

Zhou Jiang, Yandong Wen, Zhen Liu

One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators. For each prompt, DrPO samples candidates from the current generator, ranks them with a target reward, and uses high- and low-scoring samples to synthesize a feature-space update direction. The update is a non-parametric dipole preference field plus a reference drift estimated from the frozen base generator, and is optimized through a detached feature-space regression target. The target reward is used only for ranking, so DrPO can train with large, black-box, or non-differentiable rewards while inference remains a single generator call. We evaluate DrPO on SD-Turbo and SDXL-Turbo with multiple target rewards and benchmarks, including HPSv3 and GenEval. DrPO improves alignment over reward-gradient-free one-step preference baselines and reduces HPSv3 training computation by $3.51\times$ under the matched effective-batch setting by removing reward-model backpropagation. Initial offline experiments suggest that sample-based gradient synthesis can also be used beyond online reward ranking.

Weixin Mao, Weiheng Zhong, Zhou Jiang et al.

Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulties in pinpointing errors within long-horizon, multi-stage tasks. To address this, we propose RoboMatrix, a skill-centric hierarchical framework designed for scalable robot task planning and execution in open-world environments. RoboMatrix extracts general meta-skills from diverse complex tasks, enabling the completion of unseen tasks through skill composition. Its architecture consists of a high-level scheduling layer that utilizes large language models (LLMs) for task decomposition, an intermediate skill layer housing meta-skill models, and a low-level hardware layer for robot control. A key innovation of our work is the introduction of the first unified vision-language-action (VLA) model capable of seamlessly integrating both movement and manipulation within one model. This is achieved by combining vision and language prompts to generate discrete actions. Experimental results demonstrate that RoboMatrix achieves a 50% higher success rate than task-centric baselines when applied to unseen objects, scenes, and tasks. To advance open-world robotics research, we will open-source code, hardware designs, model weights, and datasets at https://github.com/WayneMao/RoboMatrix.

Zeyuan Ma, Zhiguang Cao, Zhou Jiang et al.

Recent progress in Meta-Black-Box-Optimization (MetaBBO) has demonstrated that using RL to learn a meta-level policy for dynamic algorithm configuration (DAC) over an optimization task distribution could significantly enhance the performance of the low-level BBO algorithm. However, the online learning paradigms in existing works makes the efficiency of MetaBBO problematic. To address this, we propose an offline learning-based MetaBBO framework in this paper, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO. Specifically, we first transform DAC task into long-sequence decision process. This allows us further introduce an effective Q-function decomposition mechanism to reduce the learning difficulty within the intricate algorithm configuration space. Under this setting, we propose three novel designs to meta-learn DAC policy from offline data: we first propose a novel collection strategy for constructing offline DAC experiences dataset with balanced exploration and exploitation. We then establish a decomposition-based Q-loss that incorporates conservative Q-learning to promote stable offline learning from the offline dataset. To further improve the offline learning efficiency, we equip our work with a Mamba architecture which helps long-sequence learning effectiveness and efficiency by selective state model and hardware-aware parallel scan respectively. Through extensive benchmarking, we observe that Q-Mamba achieves competitive or even superior performance to prior online/offline baselines, while significantly improving the training efficiency of existing online baselines. We provide sourcecodes of Q-Mamba at https://github.com/MetaEvo/Q-Mamba.

Yifei Zhang, Huan-ang Gao, Zhou Jiang et al.

3D particle tracking velocimetry (PTV) is a key technique for analyzing turbulent flow, one of the most challenging computational problems of our century. At the core of 3D PTV is the dual-frame fluid motion estimation algorithm, which tracks particles across two consecutive frames. Recently, deep learning-based methods have achieved impressive accuracy in dual-frame fluid motion estimation; however, they heavily depend on large volumes of labeled data. In this paper, we introduce a new method that is completely self-supervised and notably outperforms its fully-supervised counterparts while requiring only 1% of the training samples (without labels) used by previous methods. Our method features a novel zero-divergence loss that is specific to the domain of turbulent flow. Inspired by the success of splat operation in high-dimensional filtering and random fields, we propose a splat-based implementation for this loss which is both efficient and effective. The self-supervised nature of our method naturally supports test-time optimization, leading to the development of a tailored Dynamic Velocimetry Enhancer (DVE) module. We demonstrate that strong cross-domain robustness is achieved through test-time optimization on unseen leave-one-out synthetic domains and real physical/biological domains. Code, data and models are available at https://github.com/Forrest-110/FluidMotionNet.

Yuncong Liu, Yuan Wan, Zhou Jiang et al.

Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it into executable trading strategies without injecting assumptions about unspecified execution decisions remains an open problem. We observe that the gaps in KOL statements are not random deficiencies but a structured separation: KOLs express directional intent (what to buy or sell and why) while leaving execution decisions (when, how much, how long) systematically unspecified. Building on this observation, we propose an intent-preserving policy completion framework that treats KOL discourse as a partial trading policy and uses offline reinforcement learning to complete the missing execution decisions around the KOL-expressed intent. Experiments on multimodal KOL discourse from YouTube and X (2022-2025) show that KICL achieves the best return and Sharpe ratio on both platforms while maintaining zero unsupported entries and zero directional reversals, and ablations confirm that the full framework yields an 18.9% return improvement over the KOL-aligned baseline.

Zhou Jiang, Zhenxin Zhu, Pengfei Li et al.

Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both SDMap and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap, and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets. Through comprehensive experiments, we show that: (1) our SDMap prior can improve online map generation performance, using both rasterized (by up to $+18.73$ $\rm mIoU$) and vectorized (by up to $+8.50$ $\rm mAP$) output representations. (2) our HDMap prior can improve map perceptual metrics by up to $6.34\%$. (3) P-MapNet can be switched into different inference modes that covers different regions of the accuracy-efficiency trade-off landscape. (4) P-MapNet is a far-seeing solution that brings larger improvements on longer ranges. Codes and models are publicly available at https://jike5.github.io/P-MapNet.

Runyi Yang, Zhenxin Zhu, Zhou Jiang et al.

Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory. We credit this high memory footprint to the lack of consideration for the relationship between primitives. In this paper, we propose a memory-efficient Gaussian field named SUNDAE with spectral pruning and neural compensation. On one hand, we construct a graph on the set of Gaussian primitives to model their relationship and design a spectral down-sampling module to prune out primitives while preserving desired signals. On the other hand, to compensate for the quality loss of pruning Gaussians, we exploit a lightweight neural network head to mix splatted features, which effectively compensates for quality losses while capturing the relationship between primitives in its weights. We demonstrate the performance of SUNDAE with extensive results. For example, SUNDAE can achieve 26.80 PSNR at 145 FPS using 104 MB memory while the vanilla Gaussian splatting algorithm achieves 25.60 PSNR at 160 FPS using 523 MB memory, on the Mip-NeRF360 dataset. Codes are publicly available at https://runyiyang.github.io/projects/SUNDAE/.

Zhou Jiang, Yandong Wen, Zhen Liu

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take inspiration from test-time guidance and cast preference alignment as classifier-free guidance (CFG): a finetuned preference model acts as an external control signal during sampling. Building on this view, we propose a simple method that improves alignment without retraining the base model. To further enhance generalization, we decouple preference learning into two modules trained on positive and negative data, respectively, and form a \emph{contrastive guidance} vector at inference by subtracting their predictions (positive minus negative), scaled by a user-chosen strength and added to the base prediction at each step. This yields a sharper and controllable alignment signal. We evaluate on Stable Diffusion 1.5 and Stable Diffusion XL with Pick-a-Pic v2 and HPDv3, showing consistent quantitative and qualitative gains.