Search arXiv⌕ Search

arXiv subjects

Chao Zhang

Publications and source records attributed to Chao Zhang.

At least 631 records · Page 35Linked to original sources
arXiv2023

SHAPFUZZ: Efficient Fuzzing via Shapley-Guided Byte Selection

Mutation-based fuzzing is popular and effective in discovering unseen code and exposing bugs. However, only a few studies have concentrated on quantifying the importance of input bytes, which refers to the degree to which a byte contributes to the discovery of new code. They often focus on obtaining the relationship between input bytes and path constraints, ignoring the fact that not all constraint-related bytes can discover new code. In this paper, we conduct Shapely analysis to understand the effect of byte positions on fuzzing performance, and find that some byte positions contribute more than others and this property often holds across seeds. Based on this observation, we propose a novel fuzzing solution, ShapFuzz, to guide byte selection and mutation. Specifically, ShapFuzz updates Shapley values (importance) of bytes when each input is tested during fuzzing with a low overhead, and utilizes contextual multi-armed bandit to trade off between mutating high Shapley value bytes and low-frequently chosen bytes. We implement a prototype of this solution based on AFL++, i.e., ShapFuzz. We evaluate ShapFuzz against ten state-of-the-art fuzzers, including five byte schedule-reinforced fuzzers and five commonly used fuzzers. Compared with byte schedule-reinforced fuzzers, ShapFuzz discovers more edges and exposes more bugs than the best baseline on three different sets of initial seeds. Compared with commonly used fuzzers, ShapFuzz exposes 20 more bugs than the best comparison fuzzer, and discovers 6 more CVEs than the best baseline on MAGMA. Furthermore, ShapFuzz discovers 11 new bugs on the latest versions of programs, and 3 of them are confirmed by vendors.

cs.CR↗
arXiv2023

Superconductivity in the high-entropy ceramics Ti0.2Zr0.2Nb0.2Mo0.2Ta0.2Cx with possible nontrivial band topology

Topological superconductors have drawn significant interest from the scientific community due to the accompanying Majorana fermions. Here, we report the discovery of electronic structure and superconductivity in high-entropy ceramics Ti0.2Zr0.2Nb0.2Mo0.2Ta0.2Cx (x = 1 and 0.8) combined with experiments and first-principles calculations. The Ti0.2Zr0.2Nb0.2Mo0.2Ta0.2Cx high-entropy ceramics show bulk type-II superconductivity with Tc about 4.00 K (x = 1) and 2.65 K (x = 0.8), respectively. The specific heat jump is equal to 1.45 (x = 1) and 1.52 (x = 0.8), close to the expected value of 1.43 for the BCS superconductor in the weak coupling limit. The high-pressure resistance measurements show that a robust superconductivity against high physical pressure in Ti0.2Zr0.2Nb0.2Mo0.2Ta0.2C, with a slight Tc variation of 0.3 K within 82.5 GPa. Furthermore, the first-principles calculations indicate that the Dirac-like point exists in the electronic band structures of Ti0.2Zr0.2Nb0.2Mo0.2Ta0.2C, which is potentially a topological superconductor. The Dirac-like point is mainly contributed by the d orbitals of transition metals M and the p orbitals of C. The high-entropy ceramics provide an excellent platform for the fabrication of novel quantum devices, and our study may spark significant future physics investigations in this intriguing material.

cond-mat.supr-con↗
arXiv2023

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the action space, amplifying the critical need for efficient action space navigation. However, existing methods either struggle with unidirectional exploration in expansive action spaces, trapped into a locally optimal solution, or suffer from exhaustively traversing all potential actions, causing inefficient navigation. To address these issues, we propose ToolChain*, an efficient tree search-based planning algorithm for LLM-based agents. It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan. By incorporating the A* search algorithm with task-specific cost function design, it efficiently prunes high-cost branches that may involve incorrect actions, identifying the most low-cost valid path as the solution. Extensive experiments on multiple tool-use and reasoning tasks demonstrate that ToolChain* efficiently balances exploration and exploitation within an expansive action space. It outperforms state-of-the-art baselines on planning and reasoning tasks by 3.1% and 3.5% on average while requiring 7.35x and 2.31x less time, respectively.

cs.CL↗
arXiv2023

When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting

Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting, where the goal is to model and forecast multivariate time-series that have underlying hierarchical relations. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. Recent state-of-art probabilistic forecasting methods also impose hierarchical relations on point predictions and samples of distribution which does not account for coherency of forecast distributions. Previous works also silently assume that datasets are always consistent with given hierarchical relations and do not adapt to real-world datasets that show deviation from this assumption. We close both these gap and propose PROFHiT, which is a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy. PROFHiT uses a flexible probabilistic Bayesian approach and introduces a novel Distributional Coherency regularization to learn from hierarchical relations for entire forecast distribution that enables robust and calibrated forecasts as well as adapt to datasets of varying hierarchical consistency. On evaluating PROFHiT over wide range of datasets, we observed 41-88% better performance in accuracy and significantly better calibration. Due to modeling the coherency over full distribution, we observed that PROFHiT can robustly provide reliable forecasts even if up to 10% of input time-series data is missing where other methods' performance severely degrade by over 70%.

cs.LG↗
arXiv2023

When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting

Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting, where the goal is to model and forecast multivariate time-series that have underlying hierarchical relations. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. Recent state-of-art probabilistic forecasting methods also impose hierarchical relations on point predictions and samples of distribution which does not account for coherency of forecast distributions. Previous works also silently assume that datasets are always consistent with given hierarchical relations and do not adapt to real-world datasets that show deviation from this assumption. We close both these gap and propose PROFHiT, which is a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy. PROFHiT uses a flexible probabilistic Bayesian approach and introduces a novel Distributional Coherency regularization to learn from hierarchical relations for entire forecast distribution that enables robust and calibrated forecasts as well as adapt to datasets of varying hierarchical consistency. On evaluating PROFHiT over wide range of datasets, we observed 41-88% better performance in accuracy and significantly better calibration. Due to modeling the coherency over full distribution, we observed that PROFHiT can robustly provide reliable forecasts even if up to 10% of input time-series data is missing where other methods' performance severely degrade by over 70%.

cs.LG↗
arXiv2023

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our investigation focuses on datasets with high cardinality and diverse domains, wherein we demonstrate that attributed prompts outperform simple class-conditional prompts in terms of the resulting model's performance. Additionally, we present a comprehensive empirical study on data generation encompassing vital aspects like bias, diversity, and efficiency, and highlight three key observations: firstly, synthetic datasets generated by simple prompts exhibit significant biases, such as regional bias; secondly, attribute diversity plays a pivotal role in enhancing model performance; lastly, attributed prompts achieve the performance of simple class-conditional prompts while utilizing only 5\% of the querying cost of ChatGPT associated with the latter. The data and code are available on \url{https://github.com/yueyu1030/AttrPrompt}.

cs.CL↗
arXiv2023

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. Despite this promise, MARL policies often lack robustness and are therefore sensitive to small changes in their environment. This presents a serious concern for the real world deployment of MARL algorithms, where the testing environment may slightly differ from the training environment. In this work we show that we can gain robustness by controlling a policy's Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Based on these insights, we propose a new robust MARL framework, ERNIE, that promotes the Lipschitz continuity of the policies with respect to the state observations and actions by adversarial regularization. The ERNIE framework provides robustness against noisy observations, changing transition dynamics, and malicious actions of agents. However, ERNIE's adversarial regularization may introduce some training instability. To reduce this instability, we reformulate adversarial regularization as a Stackelberg game. We demonstrate the effectiveness of the proposed framework with extensive experiments in traffic light control and particle environments. In addition, we extend ERNIE to mean-field MARL with a formulation based on distributionally robust optimization that outperforms its non-robust counterpart and is of independent interest. Our code is available at https://github.com/abukharin3/ERNIE.

cs.LG↗
arXiv2023

Higher-dimensional symmetric informationally complete measurement via programmable photonic integrated optics

Symmetric informationally complete measurements are both important building blocks in many quantum information protocols and the seminal example of a generalised, non-orthogonal, quantum measurement. In higher-dimensional systems, these measurements become both increasingly interesting and increasingly complex to implement. Here, we demonstrate an integrated quantum photonic platform to realize such a measurement on three-level quantum systems. The device operates at the high fidelities necessary for verifying a genuine many-outcome quantum measurement, performing near-optimal quantum state discrimination, and beating the projective limit in quantum random number generation. Moreover, it is programmable and can readily implement other quantum measurements at similarly high quality. Our work paves the way for the implementation of sophisticated higher-dimensional quantum measurements that go beyond the traditional orthogonal projections.

quant-ph↗
arXiv2023

Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models

Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs. To this end, a fine-grained audio-visual joint representation (FAVOR) learning framework for multimodal LLMs is proposed in this paper, which extends a text-based LLM to simultaneously perceive speech and audio events in the audio input stream and images or videos in the visual input stream, at the frame level. To fuse the audio and visual feature streams into joint representations and to align the joint space with the LLM input embedding space, we propose a causal Q-Former structure with a causal attention module to enhance the capture of causal relations of the audio-visual frames across time. An audio-visual evaluation benchmark (AVEB) is also proposed which comprises six representative single-modal tasks with five cross-modal tasks reflecting audio-visual co-reasoning abilities. While achieving competitive single-modal performance on audio, speech and image tasks in AVEB, FAVOR achieved over 20% accuracy improvements on the video question-answering task when fine-grained information or temporal causal reasoning is required. FAVOR, in addition, demonstrated remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other multimodal LLMs. An interactive demo of FAVOR is available at https://github.com/BriansIDP/AudioVisualLLM.git, and the training code and model checkpoints will be released soon.

eess.AS↗
arXiv2023

Query-dominant User Interest Network for Large-Scale Search Ranking

Historical behaviors have shown great effect and potential in various prediction tasks, including recommendation and information retrieval. The overall historical behaviors are various but noisy while search behaviors are always sparse. Most existing approaches in personalized search ranking adopt the sparse search behaviors to learn representation with bottleneck, which do not sufficiently exploit the crucial long-term interest. In fact, there is no doubt that user long-term interest is various but noisy for instant search, and how to exploit it well still remains an open problem. To tackle this problem, in this work, we propose a novel model named Query-dominant user Interest Network (QIN), including two cascade units to filter the raw user behaviors and reweigh the behavior subsequences. Specifically, we propose a relevance search unit (RSU), which aims to search a subsequence relevant to the query first and then search the sub-subsequences relevant to the target item. These items are then fed into an attention unit called Fused Attention Unit (FAU). It should be able to calculate attention scores from the ID field and attribute field separately, and then adaptively fuse the item embedding and content embedding based on the user engagement of past period. Extensive experiments and ablation studies on real-world datasets demonstrate the superiority of our model over state-of-the-art methods. The QIN now has been successfully deployed on Kuaishou search, an online video search platform, and obtained 7.6% improvement on CTR.

cs.IR↗
arXiv2023

RAIN: Your Language Models Can Align Themselves without Finetuning

Large language models (LLMs) often demonstrate inconsistencies with human preferences. Previous research typically gathered human preference data and then aligned the pre-trained models using reinforcement learning or instruction tuning, a.k.a. the finetuning step. In contrast, aligning frozen LLMs without requiring alignment data is more appealing. This work explores the potential of the latter setting. We discover that by integrating self-evaluation and rewind mechanisms, unaligned LLMs can directly produce responses consistent with human preferences via self-boosting. We introduce a novel inference method, Rewindable Auto-regressive INference (RAIN), that allows pre-trained LLMs to evaluate their own generation and use the evaluation results to guide rewind and generation for AI safety. Notably, RAIN operates without the need of extra data for model alignment and abstains from any training, gradient computation, or parameter updates. Experimental results evaluated by GPT-4 and humans demonstrate the effectiveness of RAIN: on the HH dataset, RAIN improves the harmlessness rate of LLaMA 30B from 82% of vanilla inference to 97%, while maintaining the helpfulness rate. On the TruthfulQA dataset, RAIN improves the truthfulness of the already-well-aligned LLaMA-2-chat 13B model by 5%.

cs.CL↗
arXiv2023

Conditional Diffusion Model for Target Speaker Extraction

We propose DiffSpEx, a generative target speaker extraction method based on score-based generative modelling through stochastic differential equations. DiffSpEx deploys a continuous-time stochastic diffusion process in the complex short-time Fourier transform domain, starting from the target speaker source and converging to a Gaussian distribution centred on the mixture of sources. For the reverse-time process, a parametrised score function is conditioned on a target speaker embedding to extract the target speaker from the mixture of sources. We utilise ECAPA-TDNN target speaker embeddings and condition the score function alternately on the SDE time embedding and the target speaker embedding. The potential of DiffSpEx is demonstrated with the WSJ0-2mix dataset, achieving an SI-SDR of 12.9 dB and a NISQA score of 3.56. Moreover, we show that fine-tuning a pre-trained DiffSpEx model to a specific speaker further improves performance, enabling personalisation in target speaker extraction.

eess.AS↗
arXiv2023

Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection

The detection of Alzheimer's disease (AD) from spontaneous speech has attracted increasing attention while the sparsity of training data remains an important issue. This paper handles the issue by knowledge transfer, specifically from both speech-generic and depression-specific knowledge. The paper first studies sequential knowledge transfer from generic foundation models pretrained on large amounts of speech and text data. A block-wise analysis is performed for AD diagnosis based on the representations extracted from different intermediate blocks of different foundation models. Apart from the knowledge from speech-generic representations, this paper also proposes to simultaneously transfer the knowledge from a speech depression detection task based on the high comorbidity rates of depression and AD. A parallel knowledge transfer framework is studied that jointly learns the information shared between these two tasks. Experimental results show that the proposed method improves AD and depression detection, and produces a state-of-the-art F1 score of 0.928 for AD diagnosis on the commonly used ADReSSo dataset.

cs.CL↗
arXiv2023

Joint Projection Learning and Tensor Decomposition Based Incomplete Multi-view Clustering

Incomplete multi-view clustering (IMVC) has received increasing attention since it is often that some views of samples are incomplete in reality. Most existing methods learn similarity subgraphs from original incomplete multi-view data and seek complete graphs by exploring the incomplete subgraphs of each view for spectral clustering. However, the graphs constructed on the original high-dimensional data may be suboptimal due to feature redundancy and noise. Besides, previous methods generally ignored the graph noise caused by the inter-class and intra-class structure variation during the transformation of incomplete graphs and complete graphs. To address these problems, we propose a novel Joint Projection Learning and Tensor Decomposition Based method (JPLTD) for IMVC. Specifically, to alleviate the influence of redundant features and noise in high-dimensional data, JPLTD introduces an orthogonal projection matrix to project the high-dimensional features into a lower-dimensional space for compact feature learning.Meanwhile, based on the lower-dimensional space, the similarity graphs corresponding to instances of different views are learned, and JPLTD stacks these graphs into a third-order low-rank tensor to explore the high-order correlations across different views. We further consider the graph noise of projected data caused by missing samples and use a tensor-decomposition based graph filter for robust clustering.JPLTD decomposes the original tensor into an intrinsic tensor and a sparse tensor. The intrinsic tensor models the true data similarities. An effective optimization algorithm is adopted to solve the JPLTD model. Comprehensive experiments on several benchmark datasets demonstrate that JPLTD outperforms the state-of-the-art methods. The code of JPLTD is available at https://github.com/weilvNJU/JPLTD.

cs.LG↗
arXiv2023

PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering

Subspace clustering methods which embrace a self-expressive model that represents each data point as a linear combination of other data points in the dataset provide powerful unsupervised learning techniques. However, when dealing with large datasets, representation of each data point by referring to all data points via a dictionary suffers from high computational complexity. To alleviate this issue, we introduce a parallelizable multi-subset based self-expressive model (PMS) which represents each data point by combining multiple subsets, with each consisting of only a small proportion of the samples. The adoption of PMS in subspace clustering (PMSSC) leads to computational advantages because the optimization problems decomposed over each subset are small, and can be solved efficiently in parallel. Furthermore, PMSSC is able to combine multiple self-expressive coefficient vectors obtained from subsets, which contributes to an improvement in self-expressiveness. Extensive experiments on synthetic and real-world datasets show the efficiency and effectiveness of our approach in comparison to other methods.

cs.CV↗
arXiv2023

Molecular dynamics simulations of metal-electrolyte interfaces under potential control

The interfaces between metal electrodes and liquid electrolytes are prototypical in electrochemistry. That is why it is crucial to have a molecular and dynamical understating of such interfaces for both electrical properties and chemical reactivities under potential control. In this short review, we will categorize different schemes for modelling electrified metal-electrolyte interfaces used in molecular dynamics simulations. Our focus is on the similarities between seemingly different methods and their conceptual connections in terms of relevant electrochemical quantities. Therefore, it can be used as a guideline for developing new methods and building modularized computational protocols for simulating electrified interfaces.

physics.chem-ph↗
arXiv2023

Multi-Dimension-Embedding-Aware Modality Fusion Transformer for Psychiatric Disorder Clasification

Deep learning approaches, together with neuroimaging techniques, play an important role in psychiatric disorders classification. Previous studies on psychiatric disorders diagnosis mainly focus on using functional connectivity matrices of resting-state functional magnetic resonance imaging (rs-fMRI) as input, which still needs to fully utilize the rich temporal information of the time series of rs-fMRI data. In this work, we proposed a multi-dimension-embedding-aware modality fusion transformer (MFFormer) for schizophrenia and bipolar disorder classification using rs-fMRI and T1 weighted structural MRI (T1w sMRI). Concretely, to fully utilize the temporal information of rs-fMRI and spatial information of sMRI, we constructed a deep learning architecture that takes as input 2D time series of rs-fMRI and 3D volumes T1w. Furthermore, to promote intra-modality attention and information fusion across different modalities, a fusion transformer module (FTM) is designed through extensive self-attention of hybrid feature maps of multi-modality. In addition, a dimension-up and dimension-down strategy is suggested to properly align feature maps of multi-dimensional from different modalities. Experimental results on our private and public OpenfMRI datasets show that our proposed MFFormer performs better than that using a single modality or multi-modality MRI on schizophrenia and bipolar disorder diagnosis.

eess.IV↗
arXiv2023

Light polarons with electron-phonon coupling

In most cases, as the strength of electron-phonon coupling increases, the effective mass of polarons typically increases. However, in this paper, we uncover a fascinating phenomenon: the presence of light polarons even within the strong coupling regime, where electron-phonon coupling includes both Holstein and bond types (electron-phonon coupling occurring on the hopping bonds). To investigate this, we employ a novel Diagrammatic Monte Carlo method based on the path-integral formulation of the particle sector and the Fock-state representation of the phonon sector. Our study centers on analyzing the impact of bond electron-phonon coupling on the Holstein polaron's essential properties, including its effective mass, ground state energy, and the average number of phonons. We examine two distinct scenarios: one where the phonon frequency of both Holstein and bond types is the same, and another where the phonon frequency of the Holstein type is twice as large as that of the bond type. In both of these two cases, when the Holstein coupling falls within the light mass regime, we observe minimal changes in the effective mass as a function of bond coupling, compared to the case of the bare bond polaron. However, the behavior of the effective mass undergoes a significant change in the heavy mass regime. Most intriguingly, we discover a non-monotonic dependence of the effective mass on the bond coupling $g_B$ when the Holstein coupling $g_H$ falls within the heavy mass regime. This finding holds promise, particularly in the context of bipolaron, where achieving a light effective mass and a large binding energy to get the compact size, is crucial.

cond-mat.str-el↗