arXiv subjects

Wenlong Zhang

Publications and source records attributed to Wenlong Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2025

PACE: A Framework for Learning and Control in Linear Incomplete-Information Differential Games

In this paper, we address the problem of a two-player linear quadratic differential game with incomplete information, a scenario commonly encountered in multi-agent control, human-robot interaction (HRI), and approximation methods for solving general-sum differential games. While solutions to such linear differential games are typically obtained through coupled Riccati equations, the complexity increases when agents have incomplete information, particularly when neither is aware of the other's cost function. To tackle this challenge, we propose a model-based Peer-Aware Cost Estimation (PACE) framework for learning the cost parameters of the other agent. In PACE, each agent treats its peer as a learning agent rather than a stationary optimal agent, models their learning dynamics, and leverages this dynamic to infer the cost function parameters of the other agent. This approach enables agents to infer each other's objective function in real time based solely on their previous state observations and dynamically adapt their control policies. Furthermore, we provide a theoretical guarantee for the convergence of parameter estimation and the stability of system states in PACE. Additionally, in our numerical studies, we demonstrate how modeling the learning dynamics of the other agent benefits PACE, compared to approaches that approximate the other agent as having complete information, particularly in terms of stability and convergence speed.

eess.SY↗

arXiv2025

Understanding Layer Significance in LLM Alignment

Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjusts a model's presentation style rather than its foundational knowledge, indicating that only certain components of the model are significantly impacted. To uncover how alignment affects model behavior at a granular level, we propose identifying which layers within LLMs are most critical to the alignment process. Our approach, named ILA, involves learning a binary mask for the parameter changes in each layer during alignment, as an indicator of layer significance. Experimental results reveal that, despite substantial differences in alignment datasets, the important layers of a model identified by ILA exhibit nearly 90\% overlap, highlighting fundamental patterns in LLM alignment. The results also indicate that freezing non-essential layers improves overall model performance, while selectively tuning the most critical layers significantly enhances fine-tuning efficiency with minimal performance loss. Finally, we discuss how these findings extend from LLM alignment to reasoning.

cs.CL↗

arXiv2025

Task as Context Prompting for Accurate Medical Symptom Coding Using Large Language Models

Accurate medical symptom coding from unstructured clinical text, such as vaccine safety reports, is a critical task with applications in pharmacovigilance and safety monitoring. Symptom coding, as tailored in this study, involves identifying and linking nuanced symptom mentions to standardized vocabularies like MedDRA, differentiating it from broader medical coding tasks. Traditional approaches to this task, which treat symptom extraction and linking as independent workflows, often fail to handle the variability and complexity of clinical narratives, especially for rare cases. Recent advancements in Large Language Models (LLMs) offer new opportunities but face challenges in achieving consistent performance. To address these issues, we propose Task as Context (TACO) Prompting, a novel framework that unifies extraction and linking tasks by embedding task-specific context into LLM prompts. Our study also introduces SYMPCODER, a human-annotated dataset derived from Vaccine Adverse Event Reporting System (VAERS) reports, and a two-stage evaluation framework to comprehensively assess both symptom linking and mention fidelity. Our comprehensive evaluation of multiple LLMs, including Llama2-chat, Jackalope-7b, GPT-3.5 Turbo, GPT-4 Turbo, and GPT-4o, demonstrates TACO's effectiveness in improving flexibility and accuracy for tailored tasks like symptom coding, paving the way for more specific coding tasks and advancing clinical text processing methodologies.

cs.CL↗

arXiv2025

Tactile-based Exploration, Mapping and Navigation with Collision-Resilient Aerial Vehicles

This article introduces XPLORER, a passive deformable UAV with a spring-augmented chassis and proprioceptive state awareness, designed to endure collisions and maintain smooth contact. We develop a fast-converging external force estimation algorithm for XPLORER that leverages onboard sensors and proprioceptive data for contact and collision detection. Using this force information, we propose four motion primitives, including three novel tactile-based primitives: tactile-traversal, tactile-turning, and ricocheting-to aid XPLORER in navigating unknown environments. These primitives are synthesized autonomously in real-time to enable efficient exploration and navigation by leveraging collisions and contacts. Experimental results demonstrate the effectiveness of our approach, highlighting the potential of passive deformable UAVs for contact-rich real-world tasks such as non-destructive inspection, surveillance and mapping, and pursuit/evasion.

cs.RO↗

arXiv2025

Learning Nash Equilibrial Hamiltonian for Two-Player Collision-Avoiding Interactions

We consider the problem of learning Nash equilibrial policies for two-player risk-sensitive collision-avoiding interactions. Solving the Hamilton-Jacobi-Isaacs equations of such general-sum differential games in real time is an open challenge due to the discontinuity of equilibrium values on the state space. A common solution is to learn a neural network that approximates the equilibrium Hamiltonian for given system states and actions. The learning, however, is usually supervised and requires a large amount of sample equilibrium policies from different initial states in order to mitigate the risks of collisions. This paper claims two contributions towards more data-efficient learning of equilibrium policies: First, instead of computing Hamiltonian through a value network, we show that the equilibrium co-states have simple structures when collision avoidance dominates the agents' loss functions and system dynamics is linear, and therefore are more data-efficient to learn. Second, we introduce theory-driven active learning to guide data sampling, where the acquisition function measures the compliance of the predicted co-states to Pontryagin's Maximum Principle. On an uncontrolled intersection case, the proposed method leads to more generalizable approximation of the equilibrium policies, and in turn, lower collision probabilities, than the state-of-the-art under the same data acquisition budget.

cs.RO↗

arXiv2025

Parametric Value Approximation for General-sum Differential Games with State Constraints

General-sum differential games can approximate values solved by Hamilton-Jacobi-Isaacs (HJI) equations for efficient inference when information is incomplete. However, solving such games through conventional methods encounters the curse of dimensionality (CoD). Physics-informed neural networks (PINNs) offer a scalable approach to alleviate the CoD and approximate values, but there exist convergence issues for value approximations through vanilla PINNs when state constraints lead to values with large Lipschitz constants, particularly in safety-critical applications. In addition to addressing CoD, it is necessary to learn a generalizable value across a parametric space of games, rather than training multiple ones for each specific player-type configuration. To overcome these challenges, we propose a Hybrid Neural Operator (HNO), which is an operator that can map parameter functions for games to value functions. HNO leverages informative supervised data and samples PDE-driven data across entire spatial-temporal space for model refinement. We evaluate HNO on 9D and 13D scenarios with nonlinear dynamics and state constraints, comparing it against a Supervised Neural Operator (a variant of DeepONet). Under the same computational budget and training data, HNO outperforms SNO for safety performance. This work provides a step toward scalable and generalizable value function approximation, enabling real-time inference for complex human-robot or multi-agent interactions.

cs.RO↗

arXiv2025

Determine the point source of the heat equation with sparse boundary measurements

In this work the authors consider the recovery of the point source in the heat equation. The used data is the sparse boundary measurements. The uniqueness theorem of the inverse problem is given. After that, the numerical reconstruction is considered. We propose a numerical method to reconstruct the location of a Dirac point source by reformulating the inverse problem as a least-squares optimization problem, which is efficiently solved using a gradient descent algorithm. Numerical experiments confirm the accuracy of the proposed method and demonstrate its robustness to noise.

math.NA↗

arXiv2025

Exploring Representation-Aligned Latent Space for Better Generation

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and video synthesis. Latent diffusion models are typically trained using Variational Autoencoders (VAEs), interacting with VAE latents rather than the real samples. While this generative paradigm speeds up training and inference, the quality of the generated outputs is limited by the latents' quality. Traditional VAE latents are often seen as spatial compression in pixel space and lack explicit semantic representations, which are essential for modeling the real world. In this paper, we introduce ReaLS (Representation-Aligned Latent Space), which integrates semantic priors to improve generation performance. Extensive experiments show that fundamental DiT and SiT trained on ReaLS can achieve a 15% improvement in FID metric. Furthermore, the enhanced semantic latent space enables more perceptual downstream tasks, such as segmentation and depth estimation.

cs.LG↗

arXiv2025

Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling

Data-driven artificial intelligence (AI) models have made significant advancements in weather forecasting, particularly in medium-range and nowcasting. However, most data-driven weather forecasting models are black-box systems that focus on learning data mapping rather than fine-grained physical evolution in the time dimension. Consequently, the limitations in the temporal scale of datasets prevent these models from forecasting at finer time scales. This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset. Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale (e.g., 300 seconds) and use a parallel neural networks with a learnable router for bias correction. Furthermore, we introduce a lead time-aware training framework to promote the generalization of the model at different lead times. The weight analysis of physics-AI modules indicates that physics conducts major evolution while AI performs corrections adaptively. Extensive experiments show that WeatherGFT trained on an hourly dataset, effectively generalizes forecasts across multiple time scales, including 30-minute, which is even smaller than the dataset's temporal resolution.

cs.LG↗

arXiv2024

WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning

The Earth's weather system encompasses intricate weather data modalities and diverse weather understanding tasks, which hold significant value to human life. Existing data-driven models focus on single weather understanding tasks (e.g., weather forecasting). Although these models have achieved promising results, they fail to tackle various complex tasks within a single and unified model. Moreover, the paradigm that relies on limited real observations for a single scenario hinders the model's performance upper bound. In response to these limitations, we draw inspiration from the in-context learning paradigm employed in state-of-the-art visual foundation models and large language models. In this paper, we introduce the first generalist weather foundation model (WeatherGFM), designed to address a wide spectrum of weather understanding tasks in a unified manner. More specifically, we initially unify the representation and definition of the diverse weather understanding tasks. Subsequently, we devised weather prompt formats to manage different weather data modalities, namely single, multiple, and temporal modalities. Finally, we adopt a visual prompting question-answering paradigm for the training of unified weather understanding tasks. Extensive experiments indicate that our WeatherGFM can effectively handle up to ten weather understanding tasks, including weather forecasting, super-resolution, weather image translation, and post-processing. Our method also showcases generalization ability on unseen tasks.

cs.LG↗

arXiv2024

DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations

Weather radar data synthesis can fill in data for areas where ground observations are missing. Existing methods often employ reconstruction-based approaches with MSE loss to reconstruct radar data from satellite observation. However, such methods lead to over-smoothing, which hinders the generation of high-frequency details or high-value observation areas associated with convective weather. To address this issue, we propose a two-stage diffusion-based method called DiffSR. We first pre-train a reconstruction model on global-scale data to obtain radar estimation and then synthesize radar reflectivity by combining radar estimation results with satellite data as conditions for the diffusion model. Extensive experiments show that our method achieves state-of-the-art (SOTA) results, demonstrating the ability to generate high-frequency details and high-value areas.

eess.IV↗

arXiv2024

Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data

Over the past decades, we have witnessed a rapid emergence of soft and reconfigurable robots thanks to their capability to interact safely with humans and adapt to complex environments. However, their softness makes accurate control very challenging. High-fidelity sensing is critical in improving control performance, especially posture and contact estimation. To this end, traditional camera-based sensors and load cells have limited portability and accuracy, and they will inevitably increase the robot's cost and weight. In this study, instead of using specialized sensors, we only collect distributed pressure data inside a pneumatics-driven soft arm and apply the physical reservoir computing principle to simultaneously predict its kinematic posture (i.e., bending angle) and payload status (i.e., payload mass). Our results show that, with careful readout training, one can obtain accurate bending angle and payload mass predictions via simple, weighted linear summations of pressure readings. In addition, our comparative analysis shows that, to guarantee low prediction errors within 10\%, bending angle prediction requires less training data than payload prediction. This result reveals that balanced linear and nonlinear body dynamics are critical for the physical reservoir to accomplish complex proprioceptive and exteroceptive information perception tasks. Finally, the method of exploring the most efficient readout training methods presented in this paper could be extended to other soft robotic systems to maximize their perception capabilities.

cs.RO↗

arXiv2024

A Preliminary Exploration Towards General Image Restoration

Despite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being applied to real-world usages: (1) the lack of generalization ability and (2) the complex and unknown degradations in real-world scenarios. Existing deep models, tailored for specific individual image restoration tasks, often fall short in effectively addressing these challenges. In this paper, we present a new problem called general image restoration (GIR) which aims to address these challenges within a unified model. GIR covers most individual image restoration tasks (\eg, image denoising, deblurring, deraining and super-resolution) and their combinations for general purposes. This paper proceeds to delineate the essential aspects of GIR, including problem definition and the overarching significance of generalization performance. Moreover, the establishment of new datasets and a thorough evaluation framework for GIR models is discussed. We conduct a comprehensive evaluation of existing approaches for tackling the GIR challenge, illuminating their strengths and pragmatic challenges. By analyzing these approaches, we not only underscore the effectiveness of GIR but also highlight the difficulties in its practical implementation. At last, we also try to understand and interpret these models' behaviors to inspire the future direction. Our work can open up new valuable research directions and contribute to the research of general vision.

cs.CV↗

arXiv2024

UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation

The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language models for text generation and diffusion models for visual generation, have sparked widespread research interest in applying these multimodal models in the fashion domain. However, tasks involving embeddings, such as image-to-text or text-to-image retrieval, have been largely overlooked from this perspective due to the diverse nature of the multimodal fashion domain. And current research on multi-task single models lack focus on image generation. In this work, we present UniFashion, a unified framework that simultaneously tackles the challenges of multimodal generation and retrieval tasks within the fashion domain, integrating image generation with retrieval tasks and text generation tasks. UniFashion unifies embedding and generative tasks by integrating a diffusion model and LLM, enabling controllable and high-fidelity generation. Our model significantly outperforms previous single-task state-of-the-art models across diverse fashion tasks, and can be readily adapted to manage complex vision-language tasks. This work demonstrates the potential learning synergy between multimodal generation and retrieval, offering a promising direction for future research in the fashion domain. The source code is available at https://github.com/xiangyu-mm/UniFashion.

cs.CV↗

arXiv2024

PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

Precipitation nowcasting plays a pivotal role in socioeconomic sectors, especially in severe convective weather warnings. Although notable progress has been achieved by approaches mining the spatiotemporal correlations with deep learning, these methods still suffer severe blurriness as the lead time increases, which hampers accurate predictions for extreme precipitation. To alleviate blurriness, researchers explore generative methods conditioned on blurry predictions. However, the pairs of blurry predictions and corresponding ground truth need to be generated in advance, making the training pipeline cumbersome and limiting the generality of generative models within blur modes that appear in training data. By rethinking the blurriness in precipitation nowcasting as a blur kernel acting on predictions, we propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. Specifically, we utilize blurry predictions to guide the generation process of a pre-trained unconditional denoising diffusion probabilistic model (DDPM) to obtain high-fidelity predictions with eliminated blurriness. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional DDPM to any blurriness modes varying from datasets and lead times in precipitation nowcasting. Extensive experiments are conducted on 7 precipitation radar datasets, demonstrating the generality and superiority of our method.

cs.CV↗

arXiv2024

Learning A Low-Level Vision Generalist via Visual Task Prompt

Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean restoration tasks, while their applicability to tasks with different target domains (e.g., image stylization) is limited. Methods like PromptGIP can handle multiple input-target domains but rely on the Masked Autoencoder (MAE) paradigm. Consequently, they are tied to the ViT architecture, resulting in suboptimal image reconstruction quality. In addition, these methods are sensitive to prompt image content and often struggle with low-frequency information processing. In this paper, we propose a Visual task Prompt-based Image Processing (VPIP) framework to overcome these challenges. VPIP employs visual task prompts to manage tasks with different input-target domains and allows flexible selection of backbone network suitable for general tasks. Besides, a new prompt cross-attention is introduced to facilitate interaction between the input and prompt information. Based on the VPIP framework, we train a low-level vision generalist model, namely GenLV, on 30 diverse tasks. Experimental results show that GenLV can successfully address a variety of low-level tasks, significantly outperforming existing methods both quantitatively and qualitatively. Codes are available at https://github.com/chxy95/GenLV.

cs.CV↗

arXiv2024

GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity

Traditional single-task image restoration methods excel in handling specific degradation types but struggle with multiple degradations. To address this limitation, we propose Grouped Restoration with Image Degradation Similarity (GRIDS), a novel approach that harmonizes the competing objectives inherent in multiple-degradation restoration. We first introduce a quantitative method for assessing relationships between image degradations using statistical modeling of deep degradation representations. This analysis facilitates the strategic grouping of similar tasks, enhancing both the efficiency and effectiveness of the restoration process. Based on the degradation similarity, GRIDS divides restoration tasks into one of the optimal groups, where tasks within the same group are highly correlated. For instance, GRIDS effectively groups 11 degradation types into 4 cohesive groups. Trained models within each group show significant improvements, with an average improvement of 0.09dB over single-task upper bound models and 2.24dB over the mix-training baseline model. GRIDS incorporates an adaptive model selection mechanism for inference, automatically selecting the appropriate grouped-training model based on the input degradation. This mechanism is particularly useful for real-world scenarios with unknown degradations as it does not rely on explicit degradation classification modules. Furthermore, our method can predict model generalization ability without the need for network inference, providing valuable insights for practitioners.

cs.CV↗

arXiv2024

Small Aerial Target Detection for Airborne Infrared Detection Systems using LightGBM and Trajectory Constraints

Factors, such as rapid relative motion, clutter background, etc., make robust small aerial target detection for airborne infrared detection systems a challenge. Existing methods are facing difficulties when dealing with such cases. We consider that a continuous and smooth trajectory is critical in boosting small infrared aerial target detection performance. A simple and effective small aerial target detection method for airborne infrared detection system using light gradient boosting model (LightGBM) and trajectory constraints is proposed in this article. First, we simply formulate target candidate detection as a binary classification problem. Target candidates in every individual frame are detected via interesting pixel detection and a trained LightGBM model. Then, the local smoothness and global continuous characteristic of the target trajectory are modeled as short-strict and long-loose constraints. The trajectory constraints are used efficiently for detecting the true small infrared aerial targets from numerous target candidates. Experiments on public datasets demonstrate that the proposed method performs better than other existing methods. Furthermore, a public dataset for small aerial target detection in airborne infrared detection systems is constructed. To the best of our knowledge, this dataset has the largest data scale and richest scene types within this field.

cs.CV↗