arXiv subjects

Chenhao Zhang

Publications and source records attributed to Chenhao Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

On imaginary quadratic fields with non-cyclic class groups

For a fixed abelian group $H$, let $N_H(X)$ be the number of square-free positive integers $d\leq X$ such that H is a subgroup of $CL(\mathbb{Q}(\sqrt{-d}))$. We obtain asymptotic lower bounds for $N_H(X)$ as $X\to\infty$ in two cases: $H=\mathbb{Z}/g_1\mathbb{Z}\times (\mathbb{Z}/2\mathbb{Z})^l$ for $l\geq 2$ and $2\nmid g_1\geq 3$, $H=(\mathbb{Z}/g\mathbb{Z})^2$ for $2\nmid g\geq 5$. More precisely, for any $ε>0$, we showed $N_H(X)\gg X^{\frac{1}{2}+\frac{3}{2g_1+2}-ε}$ when $H=\mathbb{Z}/g_1\mathbb{Z}\times (\mathbb{Z}/2\mathbb{Z})^l$ for $l\geq 2$ and $2\nmid g_1\geq 3$. For the second case, under a well known conjecture for square-free density of integral multivariate polynomials, for any $ε>0$, we showed $N_H(X)\gg X^{\frac{1}{g-1}-ε}$ when $H=(\mathbb{Z}/g\mathbb{Z})^2$ for $ g\geq 5$. The first case is an adaptation of Soundararajan's results for $H=\mathbb{Z}/g\mathbb{Z}$, and the second conditionally improves the bound $X^{\frac{1}{g}-ε}$ due to Byeon and the bound $X^{\frac{1}{g}}/(\log X)^{2}$ due to Kulkarni and Levin.

math.NT↗

arXiv2025

Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach

Graph representation learning methods are highly effective in handling complex non-Euclidean data by capturing intricate relationships and features within graph structures. However, traditional methods face challenges when dealing with heterogeneous graphs that contain various types of nodes and edges due to the diverse sources and complex nature of the data. Existing Heterogeneous Graph Neural Networks (HGNNs) have shown promising results but require prior knowledge of node and edge types and unified node feature formats, which limits their applicability. Recent advancements in graph representation learning using Large Language Models (LLMs) offer new solutions by integrating LLMs' data processing capabilities, enabling the alignment of various graph representations. Nevertheless, these methods often overlook heterogeneous graph data and require extensive preprocessing. To address these limitations, we propose a novel method that leverages the strengths of both LLM and GNN, allowing for the processing of graph data with any format and type of nodes and edges without the need for type information or special preprocessing. Our method employs LLM to automatically summarize and classify different data formats and types, aligns node features, and uses a specialized GNN for targeted learning, thus obtaining effective graph representations for downstream tasks. Theoretical analysis and experimental validation have demonstrated the effectiveness of our method.

cs.LG↗

arXiv2025

Off-diagonal coupling of supersymmetric SYK model

In this work, we consider the off-diagonal coupling between two supersymmetric SYK models, which preserves both supersymmetry and solvability. We found that the interaction terms of the $N=2$ supersymmetric SYK have a holographic interpretation as a possible supersymmetric traversable wormhole. First we introduce the coupling in the trivial Homologic $N=1$ SYK model as a simplified example. Similar couplings can be implied in $N=2$ chiral SYK model with BPS states. We propose a special form of $N=4$ SYK by introducing supermultiplets, and which also naturally include the coupling terms. The holographic picture of $N=4$ SYK does not have an eternal solution in the low energy limit. And the effective actions are studied in both thermal limit and low energy limit. We also investigate the SYK-like thermal field double states of the supersymmetric SYK and the transmission amplitude between single-side $N=2$ models in Lorentz time. Additionally, the multi-side $N=2,4$ OTOCs are also studied.

hep-th↗

arXiv2025

Regulation of Algorithmic Collusion, Refined: Testing Pessimistic Calibrated Regret

We study the regulation of algorithmic (non-)collusion amongst sellers in dynamic imperfect price competition by auditing their data as introduced by Hartline et al. [2024]. We develop an auditing method that tests whether a seller's pessimistic calibrated regret is low. The pessimistic calibrated regret is the highest calibrated regret of outcomes compatible with the observed data. This method relaxes the previous requirement that a pricing algorithm must use fully-supported price distributions to be auditable. This method is at least as permissive as any auditing method that has a high probability of failing algorithmic outcomes with non-vanishing calibrated regret. Additionally, we strengthen the justification for using vanishing calibrated regret, versus vanishing best-in-hindsight regret, as the non-collusion definition, by showing that even without any side information, the pricing algorithms that only satisfy weaker vanishing best-in-hindsight regret allow an opponent to manipulate them into posting supra-competitive prices. This manipulation cannot be excluded with a non-collusion definition of vanishing best-in-hindsight regret. We motivate and interpret the approach of auditing algorithms from their data as suggesting a per se rule. However, we demonstrate that it is possible for algorithms to pass the audit by pretending to have higher costs than they actually do. For such scenarios, the rule of reason can be applied to bound the range of costs to those that are reasonable for the domain.

cs.GT↗

arXiv2025

II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models

The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challenging and comprehensive benchmarks have been proposed to more accurately assess the capabilities of MLLMs. However, there is a dearth of exploration of the higher-order perceptual capabilities of MLLMs. To fill this gap, we propose the Image Implication understanding Benchmark, II-Bench, which aims to evaluate the model's higher-order perception of images. Through extensive experiments on II-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on II-Bench. The pinnacle accuracy of MLLMs attains 74.8%, whereas human accuracy averages 90%, peaking at an impressive 98%. Subsequently, MLLMs perform worse on abstract and complex images, suggesting limitations in their ability to understand high-level semantics and capture image details. Finally, it is observed that most models exhibit enhanced accuracy when image sentiment polarity hints are incorporated into the prompts. This observation underscores a notable deficiency in their inherent understanding of image sentiment. We believe that II-Bench will inspire the community to develop the next generation of MLLMs, advancing the journey towards expert artificial general intelligence (AGI). II-Bench is publicly available at https://huggingface.co/datasets/m-a-p/II-Bench.

cs.CL↗

arXiv2024

Toward Efficient Data-Free Unlearning

Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods.

cs.LG↗

arXiv2024

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations

In this paper, we introduce a novel psychological benchmark, CPsyExam, constructed from questions sourced from Chinese language examinations. CPsyExam is designed to prioritize psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios. From the pool of 22k questions, we utilize 4k to create the benchmark that offers balanced coverage of subjects and incorporates a diverse range of case analysis techniques.Furthermore, we evaluate a range of existing large language models~(LLMs), spanning from open-sourced to API-based models. Our experiments and analysis demonstrate that CPsyExam serves as an effective benchmark for enhancing the understanding of psychology within LLMs and enables the comparison of LLMs across various granularities.

cs.CL↗

arXiv2024

Voxel-Mesh Hybrid Representation for Real-Time View Synthesis

The neural radiance fields (NeRF) have emerged as a prominent methodology for synthesizing realistic images of novel views. While neural radiance representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality or speed, each has limitations in the other aspect. In response, we propose a hybrid representation named Vosh, seamlessly combining both voxel and mesh components in hybrid rendering for view synthesis. Vosh is meticulously crafted by optimizing the voxel grid based on neural rendering, strategically meshing a portion of the volumetric density field to surface. Therefore, it excels in fast rendering scenes with simple geometry and textures through its mesh component, while simultaneously enabling high-quality rendering in intricate regions by leveraging voxel component. The flexibility of Vosh is showcased through the ability to adjust hybrid ratios, providing users the ability to control the balance between rendering quality and speed based on flexible usage. Experimental results demonstrate that our method achieves commendable trade-off between rendering quality and speed, and notably has real-time performance on mobile devices. The interactive web demo and code are available at https://zyyzyy06.github.io/Vosh.

cs.CV↗

arXiv2024

$T\bar{T}$ deformation on non-Hermitian two coupled SYK model

We investigate $T\bar{T}$ deformation on non-Hermitian coupled Sachdev-Ye-Kitaev (SYK) model and the holographic picture. The relationship between ground state and thermofield double state is preserved under the $T\bar{T}$ deformation. We prove that $T\bar{T}$ deformed theory provides a reparameterization in large $N$ limit. These deformation effects is calculated numerically with green functions and free energy. The thermodynamic phase structures show the equivalence of the wormhole-black hole picture between non-Hermitian model and Hermitian model still holds under $T\bar{T}$ deformation. We also study the correlation function in Lorentz time and revival dynamic.

hep-th↗

arXiv2024

Can MLLMs Understand the Deep Implication Behind Chinese Images?

As the capabilities of Multimodal Large Language Models (MLLMs) continue to improve, the need for higher-order capability evaluation of MLLMs is increasing. However, there is a lack of work evaluating MLLM for higher-order perception and understanding of Chinese visual content. To fill the gap, we introduce the **C**hinese **I**mage **I**mplication understanding **Bench**mark, **CII-Bench**, which aims to assess the higher-order perception and understanding capabilities of MLLMs for Chinese images. CII-Bench stands out in several ways compared to existing benchmarks. Firstly, to ensure the authenticity of the Chinese context, images in CII-Bench are sourced from the Chinese Internet and manually reviewed, with corresponding answers also manually crafted. Additionally, CII-Bench incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, which can deeply reflect the model's understanding of Chinese traditional culture. Through extensive experiments on CII-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on CII-Bench. The highest accuracy of MLLMs attains 64.4%, where as human accuracy averages 78.2%, peaking at an impressive 81.0%. Subsequently, MLLMs perform worse on Chinese traditional culture images, suggesting limitations in their ability to understand high-level semantics and lack a deep knowledge base of Chinese traditional culture. Finally, it is observed that most models exhibit enhanced accuracy when image emotion hints are incorporated into the prompts. We believe that CII-Bench will enable MLLMs to gain a better understanding of Chinese semantics and Chinese-specific images, advancing the journey towards expert artificial general intelligence (AGI). Our project is publicly available at https://cii-bench.github.io/.

cs.CL↗

arXiv2024

Slow Equilibrium Relaxation in a Chiral Magnet Mediated by Topological Defects

We performed a pump-probe experiment on the chiral magnet Cu$_2$OSeO$_3$ to study the relaxation dynamics of its non-collinear magnetic orders, employing a millisecond magnetic field pulse as the pump and resonant elastic x-ray scattering as the probe. Our findings reveal that the system requires $\sim$0.2 s to stabilize after the perturbation applied to both the conical and skyrmion lattice phase; significantly slower than the typical nanosecond timescale observed in micromagnetics. This prolonged relaxation is attributed to the formation and slow dissipation of local topological defects, such as emergent monopoles. By unveiling the experimental lifetime of these emergent singularities in a non-collinear magnetic system, our study highlights a universal relaxation mechanism in solitonic textures within the slow dynamics regime, offering new insights into topological physics and advanced information storage solutions.

cond-mat.mes-hall↗

arXiv2024

Regulation of Algorithmic Collusion

Consider sellers in a competitive market that use algorithms to adapt their prices from data that they collect. In such a context it is plausible that algorithms could arrive at prices that are higher than the competitive prices and this may benefit sellers at the expense of consumers (i.e., the buyers in the market). This paper gives a definition of plausible algorithmic non-collusion for pricing algorithms. The definition allows a regulator to empirically audit algorithms by applying a statistical test to the data that they collect. Algorithms that are good, i.e., approximately optimize prices to market conditions, can be augmented to contain the data sufficient to pass the audit. Algorithms that have colluded on, e.g., supra-competitive prices cannot pass the audit. The definition allows sellers to possess useful side information that may be correlated with supply and demand and could affect the prices used by good algorithms. The paper provides an analysis of the statistical complexity of such an audit, i.e., how much data is sufficient for the test of non-collusion to be accurate.

cs.GT↗

arXiv2024

Standard compliant video coding using low complexity, switchable neural wrappers

The proliferation of high resolution videos posts great storage and bandwidth pressure on cloud video services, driving the development of next-generation video codecs. Despite great progress made in neural video coding, existing approaches are still far from economical deployment considering the complexity and rate-distortion performance tradeoff. To clear the roadblocks for neural video coding, in this paper we propose a new framework featuring standard compatibility, high performance, and low decoding complexity. We employ a set of jointly optimized neural pre- and post-processors, wrapping a standard video codec, to encode videos at different resolutions. The rate-distorion optimal downsampling ratio is signaled to the decoder at the per-sequence level for each target rate. We design a low complexity neural post-processor architecture that can handle different upsampling ratios. The change of resolution exploits the spatial redundancy in high-resolution videos, while the neural wrapper further achieves rate-distortion performance improvement through end-to-end optimization with a codec proxy. Our light-weight post-processor architecture has a complexity of 516 MACs / pixel, and achieves 9.3% BD-Rate reduction over VVC on the UVG dataset, and 6.4% on AOM CTC Class A1. Our approach has the potential to further advance the performance of the latest video coding standards using neural processing with minimal added complexity.

cs.CV↗

arXiv2024

GENIU: A Restricted Data Access Unlearning for Imbalanced Data

With the increasing emphasis on data privacy, the significance of machine unlearning has grown substantially. Class unlearning, which involves enabling a trained model to forget data belonging to a specific class learned before, is important as classification tasks account for the majority of today's machine learning as a service (MLaaS). Retraining the model on the original data, excluding the data to be forgotten (a.k.a forgetting data), is a common approach to class unlearning. However, the availability of original data during the unlearning phase is not always guaranteed, leading to the exploration of class unlearning with restricted data access. While current unlearning methods with restricted data access usually generate proxy sample via the trained neural network classifier, they typically focus on training and forgetting balanced data. However, the imbalanced original data can cause trouble for these proxies and unlearning, particularly when the forgetting data consists predominantly of the majority class. To address this issue, we propose the GENerative Imbalanced Unlearning (GENIU) framework. GENIU utilizes a Variational Autoencoder (VAE) to concurrently train a proxy generator alongside the original model. These generated proxies accurately represent each class and are leveraged in the unlearning phase, eliminating the reliance on the original training data. To further mitigate the performance degradation resulting from forgetting the majority class, we introduce an in-batch tuning strategy that works with the generated proxies. GENIU is the first practical framework for class unlearning in imbalanced data settings and restricted data access, ensuring the preservation of essential information for future unlearning. Experimental results confirm the superiority of GENIU over existing methods, establishing its effectiveness in empirical scenarios.

cs.LG↗

arXiv2024

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling

Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun

cs.CL↗

arXiv2024

ReDas: A Lightweight Architecture for Supporting Fine-Grained Reshaping and Multiple Dataflows on Systolic Array

The systolic accelerator is one of the premier architectural choices for DNN acceleration. However, the conventional systolic architecture suffers from low PE utilization due to the mismatch between the fixed array and diverse DNN workloads. Recent studies have proposed flexible systolic array architectures to adapt to DNN models. However, these designs support only coarse-grained reshaping or significantly increase hardware overhead. In this study, we propose ReDas, a flexible and lightweight systolic array that supports dynamic fine-grained reshaping and multiple dataflows. First, ReDas integrates lightweight and reconfigurable roundabout data paths, which achieve fine-grained reshaping using only short connections between adjacent PEs. Second, we redesign the PE microarchitecture and integrate a set of multi-mode data buffers around the array. The PE structure enables additional data bypassing and flexible data switching. Simultaneously, the multi-mode buffers facilitate fine-grained reallocation of on-chip memory resources, adapting to various dataflow requirements. ReDas can dynamically reconfigure to up to 129 different logical shapes and 3 dataflows for a 128x128 array. Finally, we propose an efficient mapper to generate appropriate configurations for each layer of DNN workloads. Compared to the conventional systolic array, ReDas can achieve about 4.6x speedup and 8.3x energy-delay product (EDP) reduction.

cs.AR↗

arXiv2024

Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models

Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have emerged. However, these methods typically rely on complete supervision throughout the unlearning process. Unfortunately, obtaining such supervision, whether for the forgetting or remaining data, can be impractical due to the substantial cost associated with annotating real-world datasets. This challenge prompts us to propose a supervision-free unlearning approach that operates without the need for labels during the unlearning process. Specifically, we introduce a variational approach to approximate the distribution of representations for the remaining data. Leveraging this approximation, we adapt the original model to eliminate information from the forgotten data at the representation level. To further address the issue of lacking supervision information, which hinders alignment with ground truth, we introduce a contrastive loss to facilitate the matching of representations between the remaining data and those of the original model, thus preserving predictive performance. Experimental results across various unlearning tasks demonstrate the effectiveness of our proposed method, Label-Agnostic Forgetting (LAF) without using any labels, which achieves comparable performance to state-of-the-art methods that rely on full supervision information. Furthermore, our approach excels in semi-supervised scenarios, leveraging limited supervision information to outperform fully supervised baselines. This work not only showcases the viability of supervision-free unlearning in deep models but also opens up a new possibility for future research in unlearning at the representation level.

cs.LG↗

arXiv2024

CaMU: Disentangling Causal Effects in Deep Model Unlearning

Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing forgetting data without considering the negative impact this can have on the information of the remaining data, resulting in significant performance degradation after data removal. Although some methods try to repair the performance of remaining data after removal, the forgotten information can also return after repair. Such an issue is due to the intricate intertwining of the forgetting and remaining data. Without adequately differentiating the influence of these two kinds of data on the model, existing algorithms take the risk of either inadequate removal of the forgetting data or unnecessary loss of valuable information from the remaining data. To address this shortcoming, the present study undertakes a causal analysis of the unlearning and introduces a novel framework termed Causal Machine Unlearning (CaMU). This framework adds intervention on the information of remaining data to disentangle the causal effects between forgetting data and remaining data. Then CaMU eliminates the causal impact associated with forgetting data while concurrently preserving the causal relevance of the remaining data. Comprehensive empirical results on various datasets and models suggest that CaMU enhances performance on the remaining data and effectively minimizes the influences of forgetting data. Notably, this work is the first to interpret deep model unlearning tasks from a new perspective of causality and provide a solution based on causal analysis, which opens up new possibilities for future research in deep model unlearning.

cs.LG↗