arXiv subjects

Ye Han

Publications and source records attributed to Ye Han.

16 recordsLinked to original sources

arXiv2026

Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Quality

Evaluating Multi-Agent Reinforcement Learning (MARL) policies in autonomous driving fundamentally relies on extrinsic statistical indicators (e.g., reward curves and success rates), which often mask intrinsic policy degradation and algorithmic blind spots. To break this black-box evaluation, this letter proposes a novel information-theoretic diagnostic framework. By leveraging a fully converged Monte Carlo Tree Search (MCTS) as an asymptotic oracle, we establish a theoretical ground-truth baseline distribution. We formulate a bounded policy optimality score ($\mathcal{M}_{opt}$) using the forward KL divergence to rigorously penalize fatal collaborative omissions. Crucially, we semantically decouple this metric into lateral and longitudinal dimensions, creating a granular "semantic microscope". Extensive spatial and temporal diagnostics on state-of-the-art MARL architectures and exploration mechanisms demonstrate that our framework conclusively exposes hidden directional biases, identifies temporal average-policy traps, and transforms heuristic hyperparameter tuning into a visually trackable trajectory optimization. This framework establishes a rigorous, model-agnostic standard for benchmarking intrinsic multi-agent policy quality.

cs.LG↗

arXiv2026

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

Mixture-of-Experts (MoE) architecture offers enhanced efficiency for Large Language Models (LLMs) with modularized computation, yet its inherent sparsity poses significant hardware deployment challenges, including memory locality issues, communication overhead, and inefficient computing resource utilization. Inspired by the modular organization of the human brain, we propose Mozart, a novel algorithm-hardware co-design framework tailored for efficient training of MoE-based LLMs on 3.5D wafer-scale chiplet architectures. On the algorithm side, Mozart exploits the inherent modularity of chiplets and introduces: (1) an expert allocation strategy that enables efficient on-package all-to-all communication, and (2) a fine-grained scheduling mechanism that improves communication-computation overlap through streaming tokens and experts. On the architecture side, Mozart adaptively co-locates heterogeneous modules on specialized chiplets with a 2.5D NoP-Tree topology and hierarchical memory structure. Evaluation across three popular MoE models demonstrates significant efficiency gains, enabling more effective parallelization and resource utilization for large-scale modularized MoE-LLMs.

cs.AR↗

arXiv2025

Hybrid Differential Reward: Combining Temporal Difference and Action Gradients for Efficient Multi-Agent Reinforcement Learning in Cooperative Driving

In multi-vehicle cooperative driving tasks involving high-frequency continuous control, traditional state-based reward functions suffer from the issue of vanishing reward differences. This phenomenon results in a low signal-to-noise ratio (SNR) for policy gradients, significantly hindering algorithm convergence and performance improvement. To address this challenge, this paper proposes a novel Hybrid Differential Reward (HDR) mechanism. We first theoretically elucidate how the temporal quasi-steady nature of traffic states and the physical proximity of actions lead to the failure of traditional reward signals. Building on this analysis, the HDR framework innovatively integrates two complementary components: (1) a Temporal Difference Reward (TRD) based on a global potential function, which utilizes the evolutionary trend of potential energy to ensure optimal policy invariance and consistency with long-term objectives; and (2) an Action Gradient Reward (ARG), which directly measures the marginal utility of actions to provide a local guidance signal with a high SNR. Furthermore, we formulate the cooperative driving problem as a Multi-Agent Partially Observable Markov Game (POMDPG) with a time-varying agent set and provide a complete instantiation scheme for HDR within this framework. Extensive experiments conducted using both online planning (MCTS) and Multi-Agent Reinforcement Learning (QMIX, MAPPO, MADDPG) algorithms demonstrate that the HDR mechanism significantly improves convergence speed and policy stability. The results confirm that HDR guides agents to learn high-quality cooperative policies that effectively balance traffic efficiency and safety.

cs.AI↗

arXiv2025

RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction

3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have not yet been adopted in resource-constrained edge devices due to insufficient speed. Addressing this, we identify notable redundancies across the SLAM pipeline for acceleration. While conceptually straightforward, practical approaches are required to minimize the overhead associated with identifying and eliminating these redundancies. In response, we propose RTGS, an algorithm-hardware co-design framework that comprehensively reduces the redundancies for real-time 3DGS-SLAM on edge. To minimize the overhead, RTGS fully leverages the characteristics of the 3DGS-SLAM pipeline. On the algorithm side, we introduce (1) an adaptive Gaussian pruning step to remove the redundant Gaussians by reusing gradients computed during backpropagation; and (2) a dynamic downsampling technique that directly reuses the keyframe identification and alpha computing steps to eliminate redundant pixels. On the hardware side, we propose (1) a subtile-level streaming strategy and a pixel-level pairwise scheduling strategy that mitigates workload imbalance via a Workload Scheduling Unit (WSU) guided by previous iteration information; (2) a Rendering and Backpropagation (R&B) Buffer that accelerates the rendering backpropagation by reusing intermediate data computed during rendering; and (3) a Gradient Merging Unit (GMU) to reduce intensive memory accesses caused by atomic operations while enabling pipelined aggregation. Integrated into an edge GPU, RTGS achieves real-time performance (>= 30 FPS) on four datasets and three algorithms, with up to 82.5x energy efficiency over the baseline and negligible quality loss. Code is available at https://github.com/UMN-ZhaoLab/RTGS.

cs.AR↗

arXiv2025

Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs

Decentralized multi-agent cooperative decision-making in continuous environments is fundamentally bottlenecked by the curse of dimensionality, where undirected exploration typically converges to conservative local optima. We propose Topology-Enhanced Multi-Agent Reinforcement Learning (TPE-MARL) to reformulate multi-agent exploration as a structured topological traversal. We introduce the Game Topology Tensor, utilizing locality-sensitive hashing to project the continuous physical manifold into a discrete quotient space. This abstraction operates as an adversarial Information Bottleneck, decoupling strategic coordination intents from environmental noise. Within this space, a dual intrinsic reward mechanism drives exploration: a novelty reward maximizes the marginal entropy of visited topologies, while a collaboration reward, optimized via a variational Evidence Lower Bound (ELBO), minimizes conditional entropy to exploit cooperative joint configurations. Evaluations demonstrate that TPE-MARL achieves near-optimal decision distributions, closely approximating the theoretical bounds established by a Monte Carlo Tree Search (MCTS) oracle. Furthermore, physical testbed experiments validate the framework's zero-shot out-of-distribution (OOD) generalization. Supported by a spatial relaxation mechanism, the learned representations reliably execute dynamic negotiations, such as cooperative zipper-merging, exhibiting inherent robustness against real-world covariate shifts and actuation latencies.

cs.AI↗

arXiv2025

Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction

The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token .

cs.LG↗

arXiv2025

A Differentiated Reward Method for Reinforcement Learning based Multi-Vehicle Cooperative Decision-Making Algorithms

Reinforcement learning (RL) shows great potential for optimizing multi-vehicle cooperative driving strategies through the state-action-reward feedback loop, but it still faces challenges such as low sample efficiency. This paper proposes a differentiated reward method based on steady-state transition systems, which incorporates state transition gradient information into the reward design by analyzing traffic flow characteristics, aiming to optimize action selection and policy learning in multi-vehicle cooperative decision-making. The performance of the proposed method is validated in RL algorithms such as MAPPO, MADQN, and QMIX under varying autonomous vehicle penetration. The results show that the differentiated reward method significantly accelerates training convergence and outperforms centering reward and others in terms of traffic efficiency, safety, and action rationality. Additionally, the method demonstrates strong scalability and environmental adaptability, providing a novel approach for multi-agent cooperative decision-making in complex traffic scenarios.

cs.AI↗

arXiv2024

GITSR: Graph Interaction Transformer-based Scene Representation for Multi Vehicle Collaborative Decision-making

In this study, we propose GITSR, an effective framework for Graph Interaction Transformer-based Scene Representation for multi-vehicle collaborative decision-making in intelligent transportation system. In the context of mixed traffic where Connected Automated Vehicles (CAVs) and Human Driving Vehicles (HDVs) coexist, in order to enhance the understanding of the environment by CAVs to improve decision-making capabilities, this framework focuses on efficient scene representation and the modeling of spatial interaction behaviors of traffic states. We first extract features of the driving environment based on the background of intelligent networking. Subsequently, the local scene representation, which is based on the agent-centric and dynamic occupation grid, is calculated by the Transformer module. Besides, feasible region of the map is captured through the multi-head attention mechanism to reduce the collision of vehicles. Notably, spatial interaction behaviors, based on motion information, are modeled as graph structures and extracted via Graph Neural Network (GNN). Ultimately, the collaborative decision-making among multiple vehicles is formulated as a Markov Decision Process (MDP), with driving actions output by Reinforcement Learning (RL) algorithms. Our algorithmic validation is executed within the extremely challenging scenario of highway off-ramp task, thereby substantiating the superiority of agent-centric approach to scene representation. Simulation results demonstrate that the GITSR method can not only effectively capture scene representation but also extract spatial interaction data, outperforming the baseline method across various comparative metrics.

cs.LG↗

arXiv2024

SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles

In mixed autonomy traffic environment, every decision made by an autonomous-driving car may have a great impact on the transportation system. Because of the complex interaction between vehicles, it is challenging to make decisions that can ensure both high traffic efficiency and safety now and futher. Connected automated vehicles (CAVs) have great potential to improve the quality of decision-making in this continuous, highly dynamic and interactive environment because of their stronger sensing and communicating ability. For multi-vehicle collaborative decision-making algorithms based on deep reinforcement learning (DRL), we need to represent the interactions between vehicles to obtain interactive features. The representation in this aspect directly affects the learning efficiency and the quality of the learned policy. To this end, we propose a CAV decision-making architecture based on transformer and reinforcement learning algorithms. A learnable policy token is used as the learning medium of the multi-vehicle joint policy, the states of all vehicles in the area of interest can be adaptively noticed in order to extract interactive features among agents. We also design an intuitive physical positional encodings, the redundant location information of which optimizes the performance of the network. Simulations show that our model can make good use of all the state information of vehicles in traffic scenario, so as to obtain high-quality driving decisions that meet efficiency and safety objectives. The comparison shows that our method significantly improves existing DRL-based multi-vehicle cooperative decision-making algorithms.

cs.AI↗

arXiv2024

A Value Based Parallel Update MCTS Method for Multi-Agent Cooperative Decision Making of Connected and Automated Vehicles

To solve the problem of lateral and logitudinal joint decision-making of multi-vehicle cooperative driving for connected and automated vehicles (CAVs), this paper proposes a Monte Carlo tree search (MCTS) method with parallel update for multi-agent Markov game with limited horizon and time discounted setting. By analyzing the parallel actions in the multi-vehicle joint action space in the partial-steady-state traffic flow, the parallel update method can quickly exclude potential dangerous actions, thereby increasing the search depth without sacrificing the search breadth. The proposed method is tested in a large number of randomly generated traffic flow. The experiment results show that the algorithm has good robustness and better performance than the SOTA reinforcement learning algorithms and heuristic methods. The vehicle driving strategy using the proposed algorithm shows rationality beyond human drivers, and has advantages in traffic efficiency and safety in the coordinating zone.

cs.MA↗

arXiv2024

Geodesic-based Predictive Shape Modeling of the Right Ventricle in Patients with Hypoplastic Left Heart Syndrome

Hypoplastic left heart syndrome (HLHS) is characterized by severe underdevelopment of left ventricle requiring staged surgical reconstruction (stages) to allow the right ventricle (RV) alone to support the circulation. In this setting changes in RV size and shape over time reflect adaptations to single-ventricle physiology, dysfunction of the associated tricuspid valve (TV), and are associated with circulatory failure. As such, an accurate prediction of the RV shape of a patient would inform understanding of both RV and TV failure, as well as clinical prognosis and associated decision making. We present a geodesic-based predictive shape modeling framework applied a cohort of RVs obtained from 15 HLHS patients at three individual time points. Reasonable predictions on stage 1 RV shapes can generated using pre-stage 1 RV shapes and two predictors from prior clinical and demographic measures. Our results demonstrate the future potential for a data-driven method to predict how the morphology of the RV of an individual patient will change in size and shape over time. Future studies will seek to expand the training sample size and integrate more comprehensive demographic and morphological data into the proposed predictive model.

physics.med-ph↗

arXiv2021

An Applied Deep Learning Approach for Estimating Soybean Relative Maturity from UAV Imagery to Aid Plant Breeding Decisions

For a global breeding organization, identifying the next generation of superior crops is vital for its success. Recognizing new genetic varieties requires years of in-field testing to gather data about the crop's yield, pest resistance, heat resistance, etc. At the conclusion of the growing season, organizations need to determine which varieties will be advanced to the next growing season (or sold to farmers) and which ones will be discarded from the candidate pool. Specifically for soybeans, identifying their relative maturity is a vital piece of information used for advancement decisions. However, this trait needs to be physically observed, and there are resource limitations (time, money, etc.) that bottleneck the data collection process. To combat this, breeding organizations are moving toward advanced image capturing devices. In this paper, we develop a robust and automatic approach for estimating the relative maturity of soybeans using a time series of UAV images. An end-to-end hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) is proposed to extract features and capture the sequential behavior of time series data. The proposed deep learning model was tested on six different environments across the United States. Results suggest the effectiveness of our proposed CNN-LSTM model compared to the local regression method. Furthermore, we demonstrate how this newfound information can be used to aid in plant breeding advancement decisions.

cs.CV↗

arXiv2020

Real-time Prediction of Soft Tissue Deformations Using Data-driven Nonlinear Presurgical Simulations

Imaging modalities provide clinicians with real-time visualization of anatomical regions of interest (ROI) for the purpose of minimally invasive surgery. During the procedure, low-resolution image data are acquired and registered with high-resolution preoperative 3D reconstruction to guide the execution of surgical preplan. Unfortunately, due to the potential large strain and nonlinearities in the deformation of soft biological tissues, significant mismatch may be observed between ROI shapes during pre- and intra-operative imaging stages, making the surgical preplan prone to failure. In an effort to bridge the gap between the two imaging stages, this paper presents a data-driven approach based on artificial neural network for predicting the ROI deformation in real-time with sparsely registered fiducial markers. For a head-and-neck tumor model with an average maximum displacement of 30 mm, the maximum surface offsets between benchmarks and predictions using the proposed approach for 98% of the test cases are under 1.0 mm, which is the typical resolution of high-quality interventional ultrasound. Each of the prediction processes takes less than 0.5 s. With the resulting prediction accuracy and computational efficiency, the proposed approach demonstrates its potential to be clinically relevant.

physics.med-ph↗

arXiv2020

High-Throughput Image-Based Plant Stand Count Estimation Using Convolutional Neural Networks

The future landscape of modern farming and plant breeding is rapidly changing due to the complex needs of our society. The explosion of collectable data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of information is necessary to ensure that optimal decisions are made at key points of the breeding cycle. However, due to the shear size of a breeding program and current resource limitations, the ability to collect precise data on individual plants is not possible. In particular, efficient phenotyping of crops to record its color, shape, chemical properties, disease susceptibility, etc. is severely limited due to labor requirements and, oftentimes, expert domain knowledge. In this paper, we propose a deep learning based approach, named DeepStand, for image-based corn stand counting at early phenological stages. The proposed method adopts a truncated VGG-16 network as a backbone feature extractor and merges multiple feature maps with different scales to make the network robust against scale variation. Our extensive computational experiments suggest that our proposed method can successfully count corn stands and out-perform other state-of-the-art methods. It is the goal of our work to be used by the larger agricultural community as a way to enable high-throughput phenotyping without the use of extensive time and labor requirements.

cs.CV↗

arXiv2020

DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation

The success of modern farming and plant breeding relies on accurate and efficient collection of data. For a commercial organization that manages large amounts of crops, collecting accurate and consistent data is a bottleneck. Due to limited time and labor, accurately phenotyping crops to record color, head count, height, weight, etc. is severely limited. However, this information, combined with other genetic and environmental factors, is vital for developing new superior crop species that help feed the world's growing population. Recent advances in machine learning, in particular deep learning, have shown promise in mitigating this bottleneck. In this paper, we propose a novel deep learning method for counting on-ear corn kernels in-field to aid in the gathering of real-time data and, ultimately, to improve decision making to maximize yield. We name this approach DeepCorn, and show that this framework is robust under various conditions. DeepCorn estimates the density of corn kernels in an image of corn ears and predicts the number of kernels based on the estimated density map. DeepCorn uses a truncated VGG-16 as a backbone for feature extraction and merges feature maps from multiple scales of the network to make it robust against image scale variations. We also adopt a semi-supervised learning approach to further improve the performance of our proposed method. Our proposed method achieves the MAE and RMSE of 41.36 and 60.27 in the corn kernel counting task, respectively. Our experimental results demonstrate the superiority and effectiveness of our proposed method compared to other state-of-the-art methods.

cs.CV↗

arXiv2020

Convolutional Neural Networks for Image-based Corn Kernel Detection and Counting

Precise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time consuming and prone to human error. From an algorithmic perspective, the detection of the kernels from a single corn ear image is challenging due to the large number of kernels at different angles and very small distance among the kernels. In this paper, we propose a kernel detection and counting method based on a sliding window approach. The proposed method detect and counts all corn kernels in a single corn ear image taken in uncontrolled lighting conditions. The sliding window approach uses a convolutional neural network (CNN) for kernel detection. Then, a non-maximum suppression (NMS) is applied to remove overlapping detections. Finally, windows that are classified as kernel are passed to another CNN regression model for finding the (x,y) coordinates of the center of kernel image patches. Our experiments indicate that the proposed method can successfully detect the corn kernels with a low detection error and is also able to detect kernels on a batch of corn ears positioned at different angles.

cs.CV↗