arXiv subjects

Xinghao Wang

Publications and source records attributed to Xinghao Wang.

32 records · Page 2Linked to original sources

arXiv2025

Nonlinear transport of Wigner solid phase surrounding the two-flux composite fermion liquid

We have investigated the low temperature (T) transport properties of fractional quantum Hall (FQH) states in a high-mobility two-dimensional hole gas. According to the composite fermion (CF) model, FQH states stemming from a half-filled Landau level, specifically at filling factors $ν=p/(2p+1) (p=\pm 1,\pm 2,\pm 3,...)$, can be associated with two-flux-attached CFs at the corresponding Lambda filling factor p. The zero-resistance minima and Hall plateaus of these states exhibit unusual temperature dependencies, characterized by rapid increases in width below a threshold temperature around 100 mK. Differential conductivity measurements from Corbino samples reveal that the regimes surrounding the CF liquid display clear nonlinear transport characteristics. This nonlinearity implies that each CF liquid is surrounded by CF solid phase composed of dilute CF excitations. Quantitatively, the applied electric field E influences the motion of CF solid in a way analogous to T, which is dubbed the "E-T duality". Our analysis indicates that this E-T duality is consistent with the Berezinskii-Kosterlitz-Thouless theory in two-dimensional phase transitions.

cond-mat.mes-hall↗

arXiv2025

Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement

Malicious image manipulation poses societal risks, increasing the importance of effective image manipulation detection methods. Recent approaches in image manipulation detection have largely been driven by fully supervised approaches, which require labor-intensive pixel-level annotations. Thus, it is essential to explore weakly supervised image manipulation localization methods that only require image-level binary labels for training. However, existing weakly supervised image manipulation methods overlook the importance of edge information for accurate localization, leading to suboptimal localization performance. To address this, we propose a Context-Aware Boundary Localization (CABL) module to aggregate boundary features and learn context-inconsistency for localizing manipulated areas. Furthermore, by leveraging Class Activation Mapping (CAM) and Segment Anything Model (SAM), we introduce the CAM-Guided SAM Refinement (CGSR) module to generate more accurate manipulation localization maps. By integrating two modules, we present a novel weakly supervised framework based on a dual-branch Transformer-CNN architecture. Our method achieves outstanding localization performance across multiple datasets.

cs.CV↗

arXiv2025

BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enhanced LLM capabilities, the primary bottleneck has shifted from \textit{capability} to \textit{availability}, emphasizing the need for efficient memory management. Traditional compression methods, such as quantization, often require predefined compression ratios and separate compression processes for each setting, complicating deployment in variable memory environments. In this paper, we introduce \textbf{BitStack}, a novel, training-free weight compression approach that enables megabyte-level trade-offs between memory usage and model performance. By leveraging weight decomposition, BitStack can dynamically adjust the model size with minimal transmission between running memory and storage devices. Our approach iteratively decomposes weight matrices while considering the significance of each parameter, resulting in an approximately 1-bit per parameter residual block in each decomposition iteration. These blocks are sorted and stacked in storage as basic transmission units, with different quantities loaded based on current memory availability. Extensive experiments across a wide range of tasks demonstrate that, despite offering fine-grained size control, BitStack consistently matches or surpasses strong quantization baselines, particularly at extreme compression ratios. To the best of our knowledge, this is the first decomposition-based method that effectively bridges the gap to practical compression techniques like quantization. Code is available at https://github.com/xinghaow99/BitStack.

cs.CL↗

arXiv2024

Concise and Precise Context Compression for Tool-Using Language Models

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool, occupying the input window as well as slowing down the decoding process. Given the progress in general-purpose compression, soft context compression is a suitable approach to alleviate the problem. However, when compressing tool documentation, existing methods suffer from the weaknesses of key information loss (specifically, tool/parameter name errors) and difficulty in adjusting the length of compressed sequences based on documentation lengths. To address these problems, we propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models. 1) Selective compression strategy mitigates key information loss by deliberately retaining key information as raw text tokens. 2) Block compression strategy involves dividing tool documentation into short chunks and then employing a fixed-length compression model to achieve variable-length compression. This strategy facilitates the flexible adjustment of the compression ratio. Results on API-Bank and APIBench show that our approach reaches a performance comparable to the upper-bound baseline under up to 16x compression ratio.

cs.CL↗

arXiv2024

Interaction between Surface Acoustic Wave and Quantum Hall Effects

Surface Acoustic Wave (SAW) is a powerful technique for investigating quantum phases appearing in two-dimensional electron systems. The electrons respond to the piezoelectric field of SAWthrough screening, attenuating its amplitude and shifting its velocity, which is described by the relaxation model. In this work, we systematically study this interaction using orders of magnitude lower SAW amplitude than that in previous studies. At high magnetic fields when electrons form highly correlated states such as the quantum Hall effect, we observe an anomalously large attenuation of SAW while the acoustic speed remains considerably high, inconsistent with the conventional relaxation model. This anomaly exists only when the SAW power is sufficiently low.

cond-mat.mes-hall↗

arXiv2024

Aharonov-Borm oscillation and Microwave-induced edge-magnetoplasmon modes enhanced by quantum point contact

AB oscillation in weak magnetic field (B<1.5kG) is observed in QPC due to interference between electrons propagating along different QPC channels. We also investigate photo-induced magnetoresistance oscillation in open-regime split-gate QPC under MW irradiation. It is attributed to EMPs interfering in the QPC region. The influence of MW power, frequency and split gate voltage is discussed thoroughly. We unify the result of photoconductance at B=0 with EMP theories.

cond-mat.mes-hall↗

arXiv2024

Superballistic flow of viscous electron fluid induced by microwave irradiation in quantum point contact

We measure the resistance oscillation of quantum point contact (QPC) under microwave (MW) radiation. What is different from the common resistance oscillation induced by edge magnetoplasmon (EMP) is that at lower magnetic field (ω>ω_c), photoconductance is positive (negative) with weak (strong) MW radiation. This transport phenomenon is proved to be related to superballistic flow of electrons through QPC. The distinction between the regions ω>ω_c and ω<ω_c is attributed to different absorption rate of MW radiation. Violent absorption occurs when cyclotron orbits or current domains are destroyed in QPC region.

cond-mat.mes-hall↗

arXiv2024

DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning

Contrastive-learning-based methods have dominated sentence representation learning. These methods regularize the representation space by pulling similar sentence representations closer and pushing away the dissimilar ones and have been proven effective in various NLP tasks, e.g., semantic textual similarity (STS) tasks. However, it is challenging for these methods to learn fine-grained semantics as they only learn from the inter-sentence perspective, i.e., their supervision signal comes from the relationship between data samples. In this work, we propose a novel denoising objective that inherits from another perspective, i.e., the intra-sentence perspective. By introducing both discrete and continuous noise, we generate noisy sentences and then train our model to restore them to their original form. Our empirical evaluations demonstrate that this approach delivers competitive results on both semantic textual similarity (STS) and a wide range of transfer tasks, standing up well in comparison to contrastive-learning-based methods. Notably, the proposed intra-sentence denoising objective complements existing inter-sentence contrastive methodologies and can be integrated with them to further enhance performance. Our code is available at https://github.com/xinghaow99/DenoSent.

cs.CL↗

arXiv2024

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop \textbf{InferAligner}, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.

cs.CL↗

arXiv2024

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus incorrectly changing the essential semantics of the original image. To balance image diversity and semantic consistency in augmented images, we propose SGID, a Semantic-guided Generative Image augmentation method with Diffusion models for image classification. Specifically, SGID employs diffusion models to generate augmented images with good image diversity. More importantly, SGID takes image labels and captions as guidance to maintain semantic consistency between the augmented and original images. Experimental results show that SGID outperforms the best augmentation baseline by 1.72% on ResNet-50 (from scratch), 0.33% on ViT (ImageNet-21k), and 0.14% on CLIP-ViT (LAION-2B). Moreover, SGID can be combined with other image augmentation baselines and further improves the overall performance. We demonstrate the semantic consistency and image diversity of SGID through quantitative human and automated evaluations, as well as qualitative case studies.

cs.CV↗

arXiv2023

MetaPrompting: Learning to Learn Better Prompts

Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task and has to restart from scratch for each new task. To remedy this, we propose a generalized soft prompting method called MetaPrompting, which adopts the well-recognized model-agnostic meta-learning algorithm to automatically find better prompt initialization that facilitates fast adaptation to new prompting tasks.Extensive experiments show MetaPrompting tackles soft prompt initialization problem and brings significant improvement on four different datasets (over 6 points improvement in accuracy for 1-shot setting), achieving new state-of-the-art performance.

cs.CL↗

arXiv2022

Hydrodynamic charge transport in GaAs/AlGaAs ultrahigh-mobility two-dimensional electron gas

Viscous fluid in an ultrahigh-mobility two-dimensional electron gas (2DEG) in GaAs/AlGaAs quantum wells is systematically studied through measurements of negative magnetoresistance (NMR) and photoresistance under microwave radiation, and the data are analyzed according to recent theoretical work by e.g., Alekseev, Physical Review Letters 117,166601 (2016). Size-dependent and temperature dependent NMR are found to conform to the theoretical predictions. In particular, transport of 2DEG with relatively weak Coulomb interaction (interparticle interaction parameter r_s<1) manifests a crossover between viscous liquid and viscous gas. The size dependence of microwave induced resistance oscillations and that of the '2nd harmonic' peak indicate that 2DEG in a moderate magnetic field should be regarded as viscous fluid as well. Our results suggest that the hydrodynamic effects must be considered in order to understand semiclassical electronic transport in a clean 2DEG.

cond-mat.mes-hall↗

arXiv2022

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing Web-scale KGs. Over the course of its development, the label supervision has been considered necessary for accurate alignments. Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment. Commonly, the label information (positive entity pairs) is used to supervise the process of pulling the aligned entities in each positive pair closer. However, our theoretical analysis suggests that the learning of entity alignment can actually benefit more from pushing unlabeled negative pairs far away from each other than pulling labeled positive pairs close. By leveraging this discovery, we develop the self-supervised learning objective for entity alignment. We present SelfKG with efficient strategies to optimize this objective for aligning entities without label supervision. Extensive experiments on benchmark datasets demonstrate that SelfKG without supervision can match or achieve comparable results with state-of-the-art supervised baselines. The performance of SelfKG suggests that self-supervised learning offers great potential for entity alignment in KGs. The code and data are available at https://github.com/THUDM/SelfKG.

cs.LG↗

arXiv2021

A Self-supervised Method for Entity Alignment

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for accurate alignments. Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment. Existing supervised methods for this task focus on pulling each pair of positive (labeled) entities close to each other. However, our analysis suggests that the learning of entity alignment can actually benefit more from pushing sampled (unlabeled) negatives far away than pulling positive aligned pairs close. We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs. Extensive experiments on benchmark datasets demonstrate that SelfKG without supervision can match or achieve comparable results with state-of-the-art supervised baselines. The performance of SelfKG demonstrates self-supervised learning offers great potential for entity alignment in KGs.

cs.CL↗