Searcharxiv⌕ Search

arXiv subjects

Jing Huang

Publications and source records attributed to Jing Huang.

At least 127 records · Page 7Linked to original sources
arXiv2025

A Multimodal In Vitro Diagnostic Method for Parkinson's Disease Combining Facial Expressions and Behavioral Gait Data

Parkinson's disease (PD), characterized by its incurable nature, rapid progression, and severe disability, poses significant challenges to the lives of patients and their families. Given the aging population, the need for early detection of PD is increasing. In vitro diagnosis has garnered attention due to its non-invasive nature and low cost. However, existing methods present several challenges: 1) limited training data for facial expression diagnosis; 2) specialized equipment and acquisition environments required for gait diagnosis, resulting in poor generalizability; 3) the risk of misdiagnosis or missed diagnosis when relying on a single modality. To address these issues, we propose a novel multimodal in vitro diagnostic method for PD, leveraging facial expressions and behavioral gait. Our method employs a lightweight deep learning model for feature extraction and fusion, aimed at improving diagnostic accuracy and facilitating deployment on mobile devices. Furthermore, we have established the largest multimodal PD dataset in collaboration with a hospital and conducted extensive experiments to validate the effectiveness of our proposed method.

cs.CV↗
arXiv2025

MIB: A Mechanistic Interpretability Benchmark

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recover relevant causal pathways or causal variables in neural language models. The circuit localization track compares methods that locate the model components - and connections between them - most important for performing a task (e.g., attribution patching or information flow routes). The causal variable localization track compares methods that featurize a hidden vector, e.g., sparse autoencoders (SAEs) or distributed alignment search (DAS), and align those features to a task-relevant causal variable. Using MIB, we find that attribution and mask optimization methods perform best on circuit localization. For causal variable localization, we find that the supervised DAS method performs best, while SAE features are not better than neurons, i.e., non-featurized hidden vectors. These findings illustrate that MIB enables meaningful comparisons, and increases our confidence that there has been real progress in the field.

cs.LG↗
arXiv2025

Heating Mechanisms and Radio Response from the Solar Chromosphere to Corona

Heating mechanism in the solar atmosphere (from chromosphere to corona) is one of the top-challenges in modern astronomy. The classic mechanisms can be divided into two categories: wave heating (W) and magnetic reconnection heating (X). Both of them still face some problems currently difficult to overcome. Recently, we proposed a new mechanism, called magnetic-gradient pumping heating (MGP, or P) which seems to overcome those difficulties, but still lacks sufficient observational evidence. Which one really explained the physics of hot corona exactly? How can observations be used to identify and verify the heating mechanism? Since different heating mechanism will generate non-thermal particles from different accelerations and experience different propagations, they will have different response on the broadband spectral radio observations. Among them, the non-thermal electrons from W mechanisms are closely related to shock-wave acceleration, and their radio response should be group of spike bursts with random distribution of drifting rates; the non-thermal electrons from X mechanisms are accelerated by reconnecting electric field with bidirectional flow, and their radio response should be type III pairs or spike pairs; P mechanism will produce energetic particle upflows, and their radio response should be unidirectional fiber bursts with moderate negative drifting rates. Therefore, the heating mechanism can be identified and verified from the the broadband dynamic spectral radio observations. Additionally, using high-resolution radioheliographs and spectral-imaging observations, the heating mechanisms in different regions can be identified and verified separately, thereby demonstrating the physical essence of hot corona.

astro-ph.SR↗
arXiv2025

ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation

The U-shaped encoder-decoder architecture with skip connections has become a prevailing paradigm in medical image segmentation due to its simplicity and effectiveness. While many recent works aim to improve this framework by designing more powerful encoders and decoders, employing advanced convolutional neural networks (CNNs) for local feature extraction, Transformers or state space models (SSMs) such as Mamba for global context modeling, or hybrid combinations of both, these methods often struggle to fully utilize pretrained vision backbones (e.g., ResNet, ViT, VMamba) due to structural mismatches. To bridge this gap, we introduce ACM-UNet, a general-purpose segmentation framework that retains a simple UNet-like design while effectively incorporating pretrained CNNs and Mamba models through a lightweight adapter mechanism. This adapter resolves architectural incompatibilities and enables the model to harness the complementary strengths of CNNs and SSMs-namely, fine-grained local detail extraction and long-range dependency modeling. Additionally, we propose a hierarchical multi-scale wavelet transform module in the decoder to enhance feature fusion and reconstruction fidelity. Extensive experiments on the Synapse and ACDC benchmarks demonstrate that ACM-UNet achieves state-of-the-art performance while remaining computationally efficient. Notably, it reaches 85.12% Dice Score and 13.89mm HD95 on the Synapse dataset with 17.93G FLOPs, showcasing its effectiveness and scalability. Code is available at: https://github.com/zyklcode/ACM-UNet.

cs.CV↗
arXiv2025

RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image

This paper focuses on spatially consistent hundreds of human pose and shape reconstruction from a single large-scene image with various human scales under arbitrary camera FoVs (Fields of View). Due to the small and highly varying 2D human scales, depth ambiguity, and perspective distortion, no existing methods can achieve globally consistent reconstruction with correct reprojection. To address these challenges, we first propose a new concept, Human-scene Virtual Interaction Point (HVIP), to convert the complex 3D human localization into 2D-pixel localization. We then extend it to RCR (Robust Crowd Reconstruction), which achieves globally consistent reconstruction and stable generalization on different camera FoVs without test-time optimization. To perceive humans in varying pixel sizes, we propose an Iterative Ground-aware Cropping to automatically crop the image and then merge the results. To eliminate the influence of the camera and cropping process during the reconstruction, we introduce a canonical Upright 3D Space and the corresponding Upright 2D Space. To link the canonical space and the camera space, we propose the Upright Normalization, which transforms the local crop input into the Upright 2D Space, and transforms the output from the Upright 3D Space into the unified camera space. Besides, we contribute two benchmark datasets, LargeCrowd and SynCrowd, for evaluating crowd reconstruction in large scenes. Experimental results demonstrate the effectiveness of the proposed method. The source code and data will be publicly available for research purposes.

cs.CV↗
arXiv2025

Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control

Manipulating elasto-plastic objects remains a significant challenge due to severe self-occlusion, difficulties of representation, and complicated dynamics. This work proposes a novel framework for elasto-plastic object manipulation with a quasi-static assumption for motions, leveraging 3D occupancy to represent such objects, a learned dynamics model trained with 3D occupancy, and a learning-based predictive control algorithm to address these challenges effectively. We build a novel data collection platform to collect full spatial information and propose a pipeline for generating a 3D occupancy dataset. To infer the 3D occupancy during manipulation, an occupancy prediction network is trained with multiple RGB images supervised by the generated dataset. We design a deep neural network empowered by a 3D convolution neural network (CNN) and a graph neural network (GNN) to predict the complex deformation with the inferred 3D occupancy results. A learning-based predictive control algorithm is introduced to plan the robot actions, incorporating a novel shape-based action initialization module specifically designed to improve the planner efficiency. The proposed framework in this paper can successfully shape the elasto-plastic objects into a given goal shape and has been verified in various experiments both in simulation and the real world.

cs.RO↗
arXiv2025

Photometric analysis of asteroids in the Phocaea region

The Phocaea asteroid family, one of the large ancient families located in the inner main belt, may be the sources of near-Earth asteroids (NEAs) due to the nearby 3:1 mean motion resonance with Jupiter, the v6 secular resonance, and the Yarkovsky and YORP effects. Thus, understanding the influence of the Yarkovsky and YORP effects on the Phocaea family is one of the keys to figuring out the source of NEAs. However, the physical properties of most of the Phocaea family members are unknown at present. We perform a photometric analysis for 44 asteroids in the Phocaea region using photometric data obtained by ground-based and space-based telescopes (i.e., TESS and Gaia). Based on the derived physical properties, we find significant footprints of the Yarkovsky and YORP effects on the Phocaea family members. Selecting five asteroids nearby the inside boundary of the V-shape in the absolute-magnitude semimajor-axis (H, a) space, we estimate their densities considering their migration in semimajor-axis arises from the Yarkovsky effect. The bulk density of (852) Wladilena ({3.54 g/cm3) suggests a link to the H chondrite meteorites. Incorporating the grain density of the H chondrites, we estimate the macroporosities of the asteroids (290) Bruna, (1164) Kobolda, and (587) Hypsipyle, respectively 41%, 47%, and 65%, implying rubble pile structures. Considering the H chondrites link to asteroid (25) Phocaea, we suggest the parent body of the Phocaea family has been composed of H chondrite like material and the Phocaea family may be one of the sources of H chondrite meteorites.

astro-ph.EP↗
arXiv2025

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known, but opaque low-level details of black box AI models. Our contributions are (1) generalizing the theory of causal abstraction from mechanism replacement (i.e., hard and soft interventions) to arbitrary mechanism transformation (i.e., functionals from old mechanisms to new mechanisms), (2) providing a flexible, yet precise formalization for the core concepts of polysemantic neurons, the linear representation hypothesis, modular features, and graded faithfulness, and (3) unifying a variety of mechanistic interpretability methods in the common language of causal abstraction, namely, activation and path patching, causal mediation analysis, causal scrubbing, causal tracing, circuit analysis, concept erasure, sparse autoencoders, differential binary masking, distributed alignment search, and steering.

cs.AI↗
arXiv2025

ScaleTrack: Scaling and back-tracking Automated GUI Agents

Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate executable actions (\emph{e.g.}, click) and operation boxes step by step. Training a GUI agent mainly involves grounding and planning stages, in which the GUI grounding focuses on finding the execution coordinates according to the task, while the planning stage aims to predict the next action based on historical actions. However, previous work suffers from the limitations of insufficient training data for GUI grounding, as well as the ignorance of backtracking historical behaviors for GUI planning. To handle the above challenges, we propose ScaleTrack, a training framework by scaling grounding and backtracking planning for automated GUI agents. We carefully collected GUI samples of different synthesis criterions from a wide range of sources, and unified them into the same template for training GUI grounding models. Moreover, we design a novel training strategy that predicts the next action from the current GUI image, while also backtracking the historical actions that led to the GUI image. In this way, ScaleTrack explains the correspondence between GUI images and actions, which effectively describes the evolution rules of the GUI environment. Extensive experimental results demonstrate the effectiveness of ScaleTrack. Data and code will be available at url.

cs.AI↗
arXiv2025

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts(e.g., the birth year of a person) and enable predictable manipulation. Distributed alignment search (DAS) leverages supervision from counterfactual data to learn concept features within hidden states, but DAS assumes we can afford to conduct a brute force search over potential feature locations. To address this, we present HyperDAS, a transformer-based hypernetwork architecture that (1) automatically locates the token-positions of the residual stream that a concept is realized in and (2) constructs features of those residual stream vectors for the concept. In experiments with Llama3-8B, HyperDAS achieves state-of-the-art performance on the RAVEL benchmark for disentangling concepts in hidden states. In addition, we review the design decisions we made to mitigate the concern that HyperDAS (like all powerful interpretabilty methods) might inject new information into the target model rather than faithfully interpreting it.

cs.CL↗
arXiv2025

UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design

Usability testing is a fundamental yet challenging (e.g., inflexible to iterate the study design flaws and hard to recruit study participants) research method for user experience (UX) researchers to evaluate a web design. Recent advances in Large Language Model-simulated Agent (LLM-Agent) research inspired us to design UXAgent to support UX researchers in evaluating and reiterating their usability testing study design before they conduct the real human subject study. Our system features an LLM-Agent module and a universal browser connector module so that UX researchers can automatically generate thousands of simulated users to test the target website. The results are shown in qualitative (e.g., interviewing how an agent thinks ), quantitative (e.g., # of actions), and video recording formats for UX researchers to analyze. Through a heuristic user evaluation with five UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent-assisted UX study.

cs.HC↗
arXiv2025

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear artificial tomography, supervised steering vectors, linear probes, and representation finetuning. At present, there is no benchmark for making direct comparisons between these proposals. Therefore, we introduce AxBench, a large-scale benchmark for steering and concept detection, and report experiments on Gemma-2-2B and 9B. For steering, we find that prompting outperforms all existing methods, followed by finetuning. For concept detection, representation-based methods such as difference-in-means, perform the best. On both evaluations, SAEs are not competitive. We introduce a novel weakly-supervised representational method (Rank-1 Representation Finetuning; ReFT-r1), which is competitive on both tasks while providing the interpretability advantages that prompting lacks. Along with AxBench, we train and publicly release SAE-scale feature dictionaries for ReFT-r1 and DiffMean.

cs.CL↗
arXiv2025

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models

Chain-of-Thought (CoT) reasoning, which breaks down complex tasks into intermediate reasoning steps, has significantly enhanced the performance of large language models (LLMs) on challenging tasks. However, the detailed reasoning process in CoT often incurs long generation times and high computational costs, partly due to the inclusion of unnecessary steps. To address this, we propose a method to identify critical reasoning steps using perplexity as a measure of their importance: a step is deemed critical if its removal causes a significant increase in perplexity. Our method enables models to focus solely on generating these critical steps. This can be achieved through two approaches: refining demonstration examples in few-shot CoT or fine-tuning the model using selected examples that include only critical steps. Comprehensive experiments validate the effectiveness of our method, which achieves a better balance between the reasoning accuracy and efficiency of CoT.

cs.CL↗
arXiv2025

Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity

Using machine learning (ML) to construct interatomic interactions and thus potential energy surface (PES) has become a common strategy for materials design and simulations. However, those current models of machine learning interatomic potential (MLIP) provide no relevant physical constrains, and thus may owe intrinsic out-of-domain difficulty which underlies the challenges of model generalizability and physical scalability. Here, by incorporating physics-informed Universal-Scaling law and nonlinearity-embedded interaction function, we develop a Super-linear MLIP with both Ultra-Small parameterization and greatly expanded expressive capability, named SUS2-MLIP. Due to the global scaling rooting in universal equation of state (UEOS), SUS2-MLIP not only has significantly-reduced parameters by decoupling the element space from coordinate space, but also naturally outcomes the out-of-domain difficulty and endows the potentials with inherent generalizability and scalability even with relatively small training dataset. The nonlinearity-enbeding transformation for interaction function expands the expressive capability and make the potentials super-linear. The SUS2-MLIP outperforms the state-of-the-art MLIP models with its exceptional computational efficiency especially for multiple-element materials and physical scalability in property prediction. This work not only presents a highly-efficient universal MLIP model but also sheds light on incorporating physical constraints into artificial-intelligence-aided materials simulation.

cond-mat.mtrl-sci↗
arXiv2025

MASTER: A Multi-Agent System with LLM Specialized MCTS

Large Language Models (LLM) are increasingly being explored for problem-solving tasks. However, their strategic planning capability is often viewed with skepticism. Recent studies have incorporated the Monte Carlo Tree Search (MCTS) algorithm to augment the planning capacity of LLM. Despite its potential, MCTS relies on extensive sampling simulations to approximate the true reward distribution, which leads to two primary issues. Firstly, MCTS is effective for tasks like the Game of Go, where simulation results can yield objective rewards (e.g., 1 for a win and 0 for a loss). However, for tasks such as question answering, the result of a simulation is the answer to the question, which cannot yield an objective reward without the ground truth. Secondly, obtaining statistically significant reward estimations typically requires a sample size exceeding 30 simulations, resulting in excessive token usage and time consumption. To address these challenges, we present the Multi-Agent System with Tactical Execution and Reasoning using LLM Specialized MCTS (MASTER), a novel framework that coordinates agent recruitment and communication through LLM specialized MCTS. This system autonomously adjusts the number of agents based on task complexity and ensures focused communication among them. Comprehensive experiments across various tasks demonstrate the effectiveness of our proposed framework. It achieves 76% accuracy on HotpotQA and 80% on WebShop, setting new state-of-the-art performance on these datasets.

cs.AI↗
arXiv2025

Unlocking the Power of Time-Since-Infection Models: Data Augmentation for Improved Instantaneous Reproduction Number Estimation

The Time Since Infection (TSI) models, which use disease surveillance data to model infectious diseases, have become increasingly popular due to their flexibility and capacity to address complex disease control questions. However, a notable limitation of TSI models is their primary reliance on incidence data. Even when hospitalization data are available, existing TSI models have not been crafted to improve the estimation of disease transmission or to estimate hospitalization-related parameters - metrics crucial for understanding a pandemic and planning hospital resources. Moreover, their dependence on reported infection data makes them vulnerable to variations in data quality. In this study, we advance TSI models by integrating hospitalization data, marking a significant step forward in modeling with TSI models. We introduce hospitalization propensity parameters to jointly model incidence and hospitalization data. We use a composite likelihood function to accommodate complex data structure and an Monte Carlo expectation-maximization algorithm to estimate model parameters. We analyze COVID-19 data to estimate disease transmission, assess risk factor impacts, and calculate hospitalization propensity. Our model improves the accuracy of estimating the instantaneous reproduction number in TSI models, particularly when hospitalization data is of higher quality than incidence data. It enables the estimation of key infectious disease parameters without relying on contact tracing data and provides a foundation for integrating TSI models with other infectious disease models.

stat.ME↗
arXiv2025

The occurrence of powerful flares stronger than X10 class in Solar Cycles

Solar flares stronger than X10 (S-flares, >X10) are the highest class flares which significantly impact on the Sun's evolution and space weather. Based on observations of Geostationary Orbiting Environmental Satellites (GOES) at soft X-ray (SXR) wavelength and the daily sunspot numbers (DSNs) since 1975, we obtained some interesting and heuristic conclusions: (1) Both S-flares and the more powerful extremely strong flares (ES-flares, >X14.3) mostly occur in the late phases of solar cycles and low-latitude regions on the solar disk; (2) Similar to X-class flares, the occurrence of S-flares in each solar cycle is somewhat random, but the occurrence of ES-flares seems to be dominated by the mean DSN (Vm) and its root-mean-square deviation during the valley phase (Vd) before the cycle: the ES-flare number is strongly correlated with Vd, and the occurrence time of the first ES-flare is anti-correlated with Vd and Vm. These facts indicate that the higher the Vm and Vd, the stronger the solar cycle, the more the ES-flares and the earlier they occurred. We proposed that the Sun may have a low-latitude active zone (LAZ), and most ES-flares are generated from the interaction between LAZ and the newly emerging active regions. The correlations and the linear regression functions may provide an useful method to predict the occurrence of ES-flares in an upcoming solar cycle, which derives that solar cycle 25 will have about 2 ES-flares after the spring of 2027.

astro-ph.SR↗