Search

Bandwidth limitation is the major bottleneck that hinders scaling throughput of proof-of-work blockchains. To guarantee security, the mining rate of the blockchain is determined by the miners with the lowest bandwidth, resulting in an inefficient bandwidth utilization among fast miners. We propose Manifoldchain, an innovative blockchain sharding protocol that alleviates the impact of slow miners to maximize blockchain throughput. Manifoldchain utilizes a bandwidth-clustered shard formation mechanism that groups miners with similar bandwidths into the same shard. Consequently, this approach enables us to set an optimal mining rate for each shard based on its bandwidth, effectively reducing the waiting time caused by slow miners. Nevertheless, the adversary could corrupt miners with similar bandwidths, thereby concentrating hashing power and potentially creating an adversarial majority within a single shard. To counter this adversarial strategy, we introduce sharing mining, allowing the honest mining power of the entire network to participate in the secure ledger formation of each shard, thereby achieving the same level of security as an unsharded blockchain. Additionally, we introduce an asynchronous atomic commitment mechanism to ensure transaction atomicity across shards with various mining rates. Our theoretical analysis demonstrates that Manifoldchain scales linearly in throughput with the increase in shard numbers and inversely with network delay in each shard. We implement a full system prototype of Manifoldchain, comprehensively evaluated on both simulated and real-world testbeds. These experiments validate its vertical scalability with network bandwidth and horizontal scalability with network size, achieving a substantial improvement of 186% in throughput over baseline sharding protocols, for scenarios where bandwidths of miners range from 5Mbps to 60Mbps.

The all-pairs shortest distances (APSD) with differential privacy (DP) problem takes as input an undirected, weighted graph $G = (V,E, \mathbf{w})$ and outputs a private estimate of the shortest distances in $G$ between all pairs of vertices. In this paper, we present a simple $\widetilde{O}(n^{1/3}/\varepsilon)$-accurate algorithm to solve APSD with $\varepsilon$-DP, which reduces to $\widetilde{O}(n^{1/4}/\varepsilon)$ in the $(\varepsilon, \delta)$-DP setting, where $n = |V|$. Our algorithm greatly improves upon the error of prior algorithms, namely $\widetilde{O}(n^{2/3}/\varepsilon)$ and $\widetilde{O}(\sqrt{n}/\varepsilon)$ in the two respective settings, and is the first to be optimal up to a polylogarithmic factor, based on a lower bound of $\widetilde{\Omega}(n^{1/4})$. In the case where a multiplicative approximation is allowed, we give two different constructions of algorithms with reduced additive error. Our first construction allows a multiplicative approximation of $O(k\log{\log{n}})$ and has additive error $\widetilde{O}(k\cdot n^{1/k}/\varepsilon)$ in the $\varepsilon$-DP case and $\widetilde{O}(\sqrt{k}\cdot n^{1/(2k)}/\varepsilon)$ in the $(\varepsilon, \delta)$-DP case. Our second construction allows multiplicative approximation $2k-1$ and has the same asymptotic additive error as the first construction. Both constructions significantly improve upon the currently best-known additive error of, $\widetilde{O}(k\cdot n^{1/2 + 1/(4k+2)}/\varepsilon)$ and $\widetilde{O}(k\cdot n^{1/3 + 2/(9k+3)}/\varepsilon)$, respectively. Our algorithms are straightforward and work by decomposing a graph into a set of spanning trees, and applying a key observation that we can privately release APSD in trees with $O(\text{polylog}(n))$ error., Comment: Error in Section 3: (1) Improper assumption that the topology of the shortest path trees are public. (2) Improper usage of Lemma 2.4. Error in Section 4: Improper assumption that the topology of the shortest path trees are public

Test-time adaptation (TTA) aims to enhance the performance of source-domain pretrained models when tested on unknown shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data. Recently, diffusion-driven TTA methods have demonstrated strong performance by using an unconditional diffusion model, which is also trained on the source domain to transform target data into synthetic data as a source domain projection. This allows the source model to make predictions without weight adaptation. In this paper, we argue that the domains of the source model and the synthetic data in diffusion-driven TTA methods are not aligned. To adapt the source model to the synthetic domain of the unconditional diffusion model, we introduce a Synthetic-Domain Alignment (SDA) framework to fine-tune the source model with synthetic data. Specifically, we first employ a conditional diffusion model to generate labeled samples, creating a synthetic dataset. Subsequently, we use the aforementioned unconditional diffusion model to add noise to and denoise each sample before fine-tuning. This process mitigates the potential domain gap between the conditional and unconditional models. Extensive experiments across various models and benchmarks demonstrate that SDA achieves superior domain alignment and consistently outperforms existing diffusion-driven TTA methods. Our code is available at https://github.com/SHI-Labs/Diffusion-Driven-Test-Time-Adaptation-via-Synthetic-Domain-Alignment., Comment: GitHub: https://github.com/SHI-Labs/Diffusion-Driven-Test-Time-Adaptation-via-Synthetic-Domain-Alignment

Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision tasks. In this paper, we reveal that the powerful Mamba model shares surprising similarities with linear attention Transformer, which typically underperform conventional Transformer in practice. By exploring the similarities and disparities between the effective Mamba and subpar linear attention Transformer, we provide comprehensive analyses to demystify the key factors behind Mamba's success. Specifically, we reformulate the selective state space model and linear attention within a unified formulation, rephrasing Mamba as a variant of linear attention Transformer with six major distinctions: input gate, forget gate, shortcut, no attention normalization, single-head, and modified block design. For each design, we meticulously analyze its pros and cons, and empirically evaluate its impact on model performance in vision tasks. Interestingly, the results highlight the forget gate and block design as the core contributors to Mamba's success, while the other four designs are less crucial. Based on these findings, we propose a Mamba-Like Linear Attention (MLLA) model by incorporating the merits of these two key designs into linear attention. The resulting model outperforms various vision Mamba models in both image classification and high-resolution dense prediction tasks, while enjoying parallelizable computation and fast inference speed. Code is available at https://github.com/LeapLabTHU/MLLA.

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens. To enhance the capabilities of ConvLLaVA, we propose two critical optimizations. Since the low-resolution pretrained ConvNeXt underperforms when directly applied on high resolution, we update it to bridge the gap. Moreover, since ConvNeXt's original compression ratio is inadequate for much higher resolution inputs, we train a successive stage to further compress the visual tokens, thereby reducing redundancy. These optimizations enable ConvLLaVA to support inputs of 1536x1536 resolution generating only 576 visual tokens, capable of handling images of arbitrary aspect ratios. Experimental results demonstrate that our method achieves competitive performance with state-of-the-art models on mainstream benchmarks. The ConvLLaVA model series are publicly available at https://github.com/alibaba/conv-llava., Comment: 17 pages

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/., Comment: The report paper of NTIRE2024 Efficient Super-resolution, accepted by CVPRW2024

We calculate the form factor $M(q^2)$ for the Dalitz decay $J/\psi\to \gamma^*(q^2)\eta_{(N_f=1)}$ with $\eta_{(N_f)}$ being the SU($N_f$) flavor singlet pseudoscalar meson. The difference among the partial widths $\Gamma(J/\psi\to \gamma \eta_{(N_f)})$ at different $N_f$ can be attributed in part to the $\mathbf{U}_A(1)$ anomaly that induces a $N_f$ scaling. $M(q^2)$'s in $N_f=1,2$ are both well described by the single pole model $M(q^2)=M(0)/(1-q^2/\Lambda^2)$. Combined with the known experimental results of the Dalitz decays $J/\psi\to Pe^+e^-$, the pseudoscalar mass $m_P$ dependence of the pole parameter $\Lambda$ is approximated by $\Lambda(m_P^2)=\Lambda_1(1-m_P^2/\Lambda_2^2)$ with $\Lambda_1=2.64(4)~\mathrm{GeV}$ and $\Lambda_2=2.97(33)~\mathrm{GeV}$. These results provide inputs for future theoretical and experimental studies on the Dalitz decays $J/\psi\to Pe^+e^-$., Comment: 9 pages, 5 figures

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA-1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD includes three key components: (1) An image modularization strategy that divides native-resolution images into smaller variable-sized slices for efficient and extensible encoding, (2) a compression module that further condenses image tokens from visual encoders, and (3) a spatial schema to organize slice tokens for LLMs. Comprehensive experiments show that LLaVA-UHD outperforms established LMMs trained with 2-3 orders of magnitude more data on 9 benchmarks. Notably, our model built on LLaVA-1.5 336x336 supports 6 times larger (i.e., 672x1088) resolution images using only 94% inference computation, and achieves 6.4 accuracy improvement on TextVQA. Moreover, the model can be efficiently trained in academic settings, within 23 hours on 8 A100 GPUs (vs. 26 hours of LLaVA-1.5). We make the data and code publicly available at https://github.com/thunlp/LLaVA-UHD., Comment: Preprint

In this paper, we propose an end-to-end prior-based three-phases supervised fine-tuned model, which is proved more competitive than traditional fine-tuning method. More specifically, our model realizes the structural disassembly and incremental guided output of educational knowledge. To this end, we robustify data classification of three types via a sampler and overlap estimation neural network, and inject the preprocessing datasets into pre-trained model in three batches for LORA fine-tuning. Then, we design a prior module couples system prompt, vector databases, and abstract syntax tree task segmentation. Finally, the compression method and regularization constraint are applied to the prior-based fine-tuned model, followed by text filter at the output end to obtain incremental guided results. Our model represents the first research effort to truly embody the tutor role with the features of abundant educational knowledge, step-by-step incremental guided outputs and non-disclosure of answers. Extensive experiments report that our model also achieves state-of-the-art in code abilities compared to open-source models, reaching an impressive 75.10% on the HumanEval (@pass 1) benchmark. Additionally, our model maintains strong conversational capabilities, with the 13B quantized version achieving scores of 56.34, 50.60, and 45.27 respectively on the MMLU, C-Eval, and AGIEval (5 shot) dialogue evaluation benchmarks., Comment: 9 pages, 2 figures

The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines, including computer science and social science. Recent advancements in Artificial Intelligence (AI) have significantly reshaped this field, offering fresh insights into understanding and enhancing cooperation. This survey examines three key areas at the intersection of AI and cooperation in social dilemmas. First, focusing on multi-agent cooperation, we review the intrinsic and external motivations that support cooperation among rational agents, and the methods employed to develop effective strategies against diverse opponents. Second, looking into human-agent cooperation, we discuss the current AI algorithms for cooperating with humans and the human biases towards AI agents. Third, we review the emergent field of leveraging AI agents to enhance cooperation among humans. We conclude by discussing future research avenues, such as using large language models, establishing unified theoretical frameworks, revisiting existing theories of human cooperation, and exploring multiple real-world applications.

We study the $S$-wave $D\bar{D}^*(I=0)$ scattering at four different pion masses $m_\pi$ ranging from 250 MeV to 417 MeV from $N_f=2$ lattice QCD. A bound state near the $D\bar{D}^*$ threshold likely exists even after considering the possible left-hand cut effect due to the one pion exchange interaction. At $m_\pi\approx 417$ MeV where the effective range expansion is valid, the compositeness of the bound state is $X\approx 1$ and indicates a predominant $D\bar{D}^*$ component. This state may correspond to $X(3872)$. On the other hand, our results of the finite volume energies also hint at the existence of a $1^{++}$ resonance below 4.0 GeV with a width around 60 MeV., Comment: 17 pages, 11 figures

This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area. With the proliferation of LLMs comes a host of challenges, including hallucinations, outdated knowledge, prohibitive commercial application costs, and memory issues. VecDBs emerge as a compelling solution to these issues by offering an efficient means to store, retrieve, and manage the high-dimensional vector representations intrinsic to LLM operations. Through this nuanced review, we delineate the foundational principles of LLMs and VecDBs and critically analyze their integration's impact on enhancing LLM functionalities. This discourse extends into a discussion on the speculative future developments in this domain, aiming to catalyze further research into optimizing the confluence of LLMs and VecDBs for advanced data handling and knowledge extraction capabilities.

Traffic flow prediction plays a crucial role in alleviating traffic congestion and enhancing transport efficiency. While combining graph convolution networks with recurrent neural networks for spatial-temporal modeling is a common strategy in this realm, the restricted structure of recurrent neural networks limits their ability to capture global information. For spatial modeling, many prior studies learn a graph structure that is assumed to be fixed and uniform at all time steps, which may not be true. This paper introduces a novel traffic prediction framework, Global-Aware Enhanced Spatial-Temporal Graph Recurrent Network (GA-STGRN), comprising two core components: a spatial-temporal graph recurrent neural network and a global awareness layer. Within this framework, three innovative prediction models are formulated. A sequence-aware graph neural network is proposed and integrated into the Gated Recurrent Unit (GRU) to learn non-fixed graphs at different time steps and capture local temporal relationships. To enhance the model's global perception, three distinct global spatial-temporal transformer-like architectures (GST^2) are devised for the global awareness layer. We conduct extensive experiments on four real traffic datasets and the results demonstrate the superiority of our framework and the three concrete models.

This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhance performance across all models tested. For example, integrating Louvain with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains are noted when Louvain is paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent uplift in performance reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to fine-tune the underlying models. However, crafting an efficient reward model demands extensive datasets, optimal architecture, and manual hyperparameter tuning, making the process both time and cost-intensive. The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model. However, the extensive GPU memory requirement of the diffusion model's denoising process hinders the direct application of the DPO method. To address this issue, we introduce the Direct Preference for Denoising Diffusion Policy Optimization (D3PO) method to directly fine-tune diffusion models. The theoretical analysis demonstrates that although D3PO omits training a reward model, it effectively functions as the optimal reward model trained using human feedback data to guide the learning process. This approach requires no training of a reward model, proving to be more direct, cost-effective, and minimizing computational overhead. In experiments, our method uses the relative scale of objectives as a proxy for human preference, delivering comparable results to methods using ground-truth rewards. Moreover, D3PO demonstrates the ability to reduce image distortion rates and generate safer images, overcoming challenges lacking robust reward models. Our code is publicly available at https://github.com/yk7333/D3PO., Comment: CVPR 2024 accepted; huggingface daily paper

A vector database is used to store high-dimensional data that cannot be characterized by traditional DBMS. Although there are not many articles describing existing or introducing new vector database architectures, the approximate nearest neighbor search problem behind vector databases has been studied for a long time, and considerable related algorithmic articles can be found in the literature. This article attempts to comprehensively review relevant algorithms to provide a general understanding of this booming research area. The basis of our framework categorises these studies by the approach of solving ANNS problem, respectively hash-based, tree-based, graph-based and quantization-based approaches. Then we present an overview of existing challenges for vector databases. Lastly, we sketch how vector databases can be combined with large language models and provide new possibilities.

Traffic flow prediction is one of the most fundamental tasks of intelligent transportation systems. The complex and dynamic spatial-temporal dependencies make the traffic flow prediction quite challenging. Although existing spatial-temporal graph neural networks hold prominent, they often encounter challenges such as (1) ignoring the fixed graph that limits the predictive performance of the model, (2) insufficiently capturing complex spatial-temporal dependencies simultaneously, and (3) lacking attention to spatial-temporal information at different time lengths. In this paper, we propose a Multi-Scale Spatial-Temporal Recurrent Network for traffic flow prediction, namely MSSTRN, which consists of two different recurrent neural networks: the single-step gate recurrent unit and the multi-step gate recurrent unit to fully capture the complex spatial-temporal information in the traffic data under different time windows. Moreover, we propose a spatial-temporal synchronous attention mechanism that integrates adaptive position graph convolutions into the self-attention mechanism to achieve synchronous capture of spatial-temporal dependencies. We conducted extensive experiments on four real traffic datasets and demonstrated that our model achieves the best prediction accuracy with non-trivial margins compared to all the twenty baseline methods.

We present an exploratory $N_f=2$ lattice QCD study of $\psi_2(3823)\to \gamma \chi_{c1}$ at a pion mass $m_{\pi}\approx 350$~MeV. The related two-point and three-piont functions are calculated using the distillation method. The electromagnetic multipole form factor $\hat{V}(0)=2.083(11)$ for $J/\psi\to\gamma \eta_c$ is consistent with previous lattice results, the form factors $\hat{E}_1(0)$, $\hat{M}_2(0)$ and $\hat{E}_3(0)$ for $\Gamma(\chi_{c2}\to\gamma J/\psi)$ have the same hierarchy as that derived from experiments and the predicted decay width $\Gamma(\chi_{c2}\to\gamma J/\psi)=368(5)~\text{keV}$ is in excellent agreement with the PDG value $374(10)~\text{keV}$ and previous lattice QCD results in the quenched approximation. The same strategy is applied to the study of the process $\psi_2(3823)\to \gamma \chi_{c1}$ and the partial decay width is predicted to be $337(27)~\text{keV}$. According to the BESIII constraints on the $\psi_2(3823)$ decay channels and some phenomenological results, we estimate the total width $\Gamma(\psi_2(3823))=520(100)~\text{keV}$.

Traffic prediction has been an active research topic in the domain of spatial-temporal data mining. Accurate real-time traffic prediction is essential to improve the safety, stability, and versatility of smart city systems, i.e., traffic control and optimal routing. The complex and highly dynamic spatial-temporal dependencies make effective predictions still face many challenges. Recent studies have shown that spatial-temporal graph neural networks exhibit great potential applied to traffic prediction, which combines sequential models with graph convolutional networks to jointly model temporal and spatial correlations. However, a survey study of graph learning, spatial-temporal graph models for traffic, as well as a fair comparison of baseline models are pending and unavoidable issues. In this paper, we first provide a systematic review of graph learning strategies and commonly used graph convolution algorithms. Then we conduct a comprehensive analysis of the strengths and weaknesses of recently proposed spatial-temporal graph network models. Furthermore, we build a study called STG4Traffic using the deep learning framework PyTorch to establish a standardized and scalable benchmark on two types of traffic datasets. We can evaluate their performance by personalizing the model settings with uniform metrics. Finally, we point out some problems in the current study and discuss future directions. Source codes are available at https://github.com/trainingl/STG4Traffic.

By extracting the transition amplitudes, we give the first lattice QCD prediction of the two-body decay partial widths of the $1^{-+}$ charmoniumlike hybrid $\eta_{c1}$. Given the calculated mass value $m_{\eta_{c1}}=4.329(36)$ GeV, the $\eta_{c1}$ decay is dominated by the open charm modes $D_1\bar{D}$, $D^*\bar{D}$ and $D^*\bar{D}^*$ with partial widths of $258(133)$ MeV, $88(18)$ MeV and $150(118)$ MeV, respectively. The coupling of $\eta_{c1}$ to $\chi_{c1}$ plus a flavor singlet pseudoscalar is not small, but $\chi_{c1}\eta$ decay is suppressed by the small $\eta-\eta'$ mixing angle. The partial width of $\eta_{c1}\to \eta_c\eta'$ is estimated to be around 1 MeV. We suggest experiments to search for $\eta_{c1}$ in the $P$-wave $D^*\bar{D}$ and $D^*\bar{D}^*$ systems. Especially, the polarization of $D^*\bar{D}^*$ can be used to distinguish the $1^{-+}$ product (total spin $S=1$) from $1^{--}$ products ($S=0$)., Comment: 17 pages, 7 figures. Revised to article format