Search

Recent years, multi-hop reasoning has been widely studied for knowledge graph (KG) reasoning due to its efficacy and interpretability. However, previous multi-hop reasoning approaches are subject to two primary shortcomings. First, agents struggle to learn effective and robust policies at the early phase due to sparse rewards. Second, these approaches often falter on specific datasets like sparse knowledge graphs, where agents are required to traverse lengthy reasoning paths. To address these problems, we propose a multi-hop reasoning model with dual agents based on hierarchical reinforcement learning (HRL), which is named FULORA. FULORA tackles the above reasoning challenges by eFficient GUidance-ExpLORAtion between dual agents. The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph. In this framework, the low-level agent optimizes a value function that balances two objectives: (1) maximizing return, and (2) integrating efficient guidance from the high-level agent. Experiments conducted on three real-word knowledge graph datasets demonstrate that FULORA outperforms RL-based baselines, especially in the case of long-distance reasoning.

In this paper we present the results of the AI-Debater 2023 Challenge held by the Chinese Conference on Affect Computing (CCAC 2023), and introduce the related datasets. We organize two tracks to handle the argumentative generation tasks in different scenarios, namely, Counter-Argument Generation (Track 1) and Claim-based Argument Generation (Track 2). Each track is equipped with its distinct dataset and baseline model respectively. In total, 32 competing teams register for the challenge, from which we received 11 successful submissions. In this paper, we will present the results of the challenge and a summary of the systems, highlighting commonalities and innovations among participating systems. Datasets and baseline models of the AI-Debater 2023 Challenge have been already released and can be accessed through the official website of the challenge.

In this article, we will prove existence results for the equations of the type $-\Delta_{N}u=H_{l}(u)+\mu$ and $F_{\frac{N}{2}}[-u]=H_{l}(u)+\mu$ in a bounded domain $\Omega$, with Dirichlet boundary condition, where the source term $H_{l}(r)$ takes the form $e^{r}-\sum_{j=0}^{l-1}\frac{r^{j}}{j!}$ and $\mu$ is a nonnegative Radon measure., Comment: 15pages

Depending on the coupling to the environment, symmetries of open quantum systems manifest in two distinct forms, the strong and the weak. We study the spontaneous symmetry breaking among phases with different symmetries. Concrete Liouvillian models with strong and weak symmetry are constructed, and different scenarios of symmetry-breaking transitions are investigated from complementary approaches. It is demonstrated that strong symmetry always spontaneously breaks into the corresponding weak symmetry. For strong $U(1)$ symmetry, we show that strong-to-weak symmetry breaking leads to gapless Goldstone modes dictating diffusion of the symmetry charge in translational invariant systems. We conjecture that this relation among strong-to-weak symmetry breaking, gapless modes, and symmetry-charge diffusion is general for continuous symmetries. It can be interpreted as an "enhanced Lieb-Schultz-Mattis (LSM) theorem" for open quantum systems, according to which the gapless spectrum does not require non-integer filling. We also investigate the scenario where the strong symmetry breaks completely. In the symmetry-broken phase, we identify an effective Keldysh action with two Goldstone modes, describing fluctuations of the order parameter and diffusive hydrodynamics of the symmetry charge, respectively. For a particular model studied here, we uncover a transition from a symmetric phase with a "Bose surface" to a symmetry-broken phase with long-range order induced by tuning the filling. It is also shown that the long-range order of $U(1)$ symmetry breaking is possible in spatial dimension $d\geq 3$, in both weak and strong symmetry cases. Our work outline the typical scenarios of spontaneous symmetry breaking in open quantum systems, and highlights their physical consequences., Comment: 15 pages, 3 figures

Automated software engineering has been greatly empowered by the recent advances in Large Language Models (LLMs) for programming. While current benchmarks have shown that LLMs can perform various software engineering tasks like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks. Solving challenging and practical programming tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs. To assess how well LLMs can solve challenging and practical programming tasks, we introduce Bench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained programming tasks. To evaluate LLMs rigorously, each programming task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of Bench, Benchi, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area., Comment: 44 pages, 14 figures, 7 tables, built with love by the BigCode community :)

Relational concepts are indeed foundational to the structure of knowledge representation, as they facilitate the association between various entity concepts, allowing us to express and comprehend complex world knowledge. By expressing relational concepts in natural language prompts, people can effortlessly interact with large language models (LLMs) and recall desired factual knowledge. However, the process of knowledge recall lacks interpretability, and representations of relational concepts within LLMs remain unknown to us. In this paper, we identify hidden states that can express entity and relational concepts through causal mediation analysis in fact recall processes. Our finding reveals that at the last token position of the input prompt, there are hidden states that solely express the causal effects of relational concepts. Based on this finding, we assume that these hidden states can be treated as relational representations and we can successfully extract them from LLMs. The experimental results demonstrate high credibility of the relational representations: they can be flexibly transplanted into other fact recall processes, and can also be used as robust entity connectors. Moreover, we also show that the relational representations exhibit significant potential for controllable fact recall through relation rewriting.

With the improvement of muon acceleration technology, it has received great interest to exploit high-energy muon beams for collision or target experiments. We investigate possible charged Lepton Flavor Violation (cLFV) processes mediated by an extra massive neutral gauge boson Zprime in electron muon interactions, either at a proposed electron muon collider or in a fixed target experiment with high-energy muon beam hitting electrons in the target. Based on Monte Carlo calculations and fast detector simulations, we study in detail our signal and possible backgrounds, giving the sensitivity results of cLFV signals at the 90% confidence level. Compared with current and prospective limits set by other experiments, electron muon interactions demonstrate significant advantages in the cLFV coupling strength sensitivity with tau in the final states. In addition, a special cLFV coupling combination, lambda_emu * lambda_mumu, can also be probed in our proposal.

In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens. Despite its efficiency, the concatenation approach compromises data integrity -- it inevitably breaks many documents into incomplete pieces, leading to excessive truncations that hinder the model from learning to compose logically coherent and factually consistent content that is grounded on the complete context. To address the issue, we propose Best-fit Packing, a scalable and efficient method that packs documents into training sequences through length-aware combinatorial optimization. Our method completely eliminates unnecessary truncations while retaining the same training efficiency as concatenation. Empirical results from both text and code pre-training show that our method achieves superior performance (e.g., relatively +4.7% on reading comprehension; +16.8% in context following; and +9.2% on program synthesis), and reduces closed-domain hallucination effectively by up to 58.3%., Comment: ICML 2024

Code generation models are not robust to small perturbations, which often lead to inconsistent and incorrect generations and significantly degrade the performance of these models. Improving the robustness of code generation models is crucial to better user experience when these models are deployed in real-world applications. However, existing efforts have not addressed this issue for code generation models. To fill this gap, we propose CodeFort, a framework to improve the robustness of code generation models, generalizing a large variety of code perturbations to enrich the training data and enabling various robust training strategies, mixing data augmentation, batch augmentation, adversarial logits pairing, and contrastive learning, all carefully designed to support high-throughput training. Extensive evaluations show that we improve the average robust pass rates of baseline CodeGen models from 14.79 to 21.74. Notably, the improvement in robustness against code-syntax perturbations is evidenced by a significant decrease in pass rate drop from 95.04% to 53.35%

In this paper, we develop a systematic approach to characterize the 't Hooft anomaly in open quantum systems. Owing to nontrivial couplings to the environment, symmetries in such systems manifest as either strong or weak type. By representing their symmetry transformation through superoperators, we incorporate them in a unified framework that enables a direct calculation of their anomalies. In the case where the full symmetry group is $K\times G$, with $K$ the strong symmetry and $G$ the weak symmetry, we find that anomalies of bosonic systems are classified by $H^{d+2}(K\times G,U(1))/H^{d+2}(G,U(1))$ in $d$ spatial dimensions. To illustrate the power of anomalies in open quantum systems, we generally prove that anomaly must lead to nontrivial mixed-state quantum phases as long as the weak symmetry is imposed. Analogous to the ``anomaly matching" condition ensuring nontrivial low-energy physics in closed systems, anomaly also guarantees nontrivial steady states and long-time dynamics for open quantum systems governed by Lindbladians. Notably, we identify a novel $(1+1)$-D mixed-state quantum phase that has no counterpart in closed systems, where the steady state shows no nontrivial correlation function in the bulk, but displays spontaneous symmetry breaking order on the boundary, which is enforced by anomalies. We further establish the general relations between mixed-state anomalies and such unconventional boundary correlation. Finally, we explore the generalization of the ``anomaly inflow" mechanism in open quantum systems. We construct $(1+1)$-D and $(2+1)$-D Lindbladians whose steady states have mixed-state symmetry-protected-topological order in the bulk, with corresponding edge theories characterized by nontrivial anomalies., Comment: 20+2 pages, 7 figures. Some typos are fixed and new references are added

Generative models, widely utilized in various applications, can often struggle with prompts corresponding to partial tokens. This struggle stems from tokenization, where partial tokens fall out of distribution during inference, leading to incorrect or nonsensical outputs. This paper examines a technique to alleviate the tokenization artifact on text completion in generative models, maintaining performance even in regular non-subword cases. The method, termed token alignment, involves backtracking to the last complete tokens and ensuring the model's generation aligns with the prompt. This approach showcases marked improvement across many partial token scenarios, including nuanced cases like space-prefix and partial indentation, with only a minor time increase. The technique and analysis detailed in this paper contribute to the continuous advancement of generative models in handling partial inputs, bearing relevance for applications like code completion and text autocompletion.

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of generative models to capture the prior distribution of image content, thus impeding further bitrate reduction in extreme compression scenarios (<0.05 bpp). Motivated by the capabilities of predictive language models for lossless compression, this paper introduces a novel Unified Image Generation-Compression (UIGC) paradigm, merging the processes of generation and compression. A key feature of the UIGC framework is the adoption of vector-quantized (VQ) image models for tokenization, alongside a multi-stage transformer designed to exploit spatial contextual information for modeling the prior distribution. As such, the dual-purpose framework effectively utilizes the learned prior for entropy estimation and assists in the regeneration of lost tokens. Extensive experiments demonstrate the superiority of the proposed UIGC framework over existing codecs in perceptual quality and human perception, particularly in ultra-low bitrate scenarios (<=0.03 bpp), pioneering a new direction in generative compression.

The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership with Software Heritage (SWH), we build The Stack v2 on top of the digital commons of their source code archive. Alongside the SWH repositories spanning 619 programming languages, we carefully select other high-quality data sources, such as GitHub pull requests, Kaggle notebooks, and code documentation. This results in a training set that is 4x larger than the first StarCoder dataset. We train StarCoder2 models with 3B, 7B, and 15B parameters on 3.3 to 4.3 trillion tokens and thoroughly evaluate them on a comprehensive set of Code LLM benchmarks. We find that our small model, StarCoder2-3B, outperforms other Code LLMs of similar size on most benchmarks, and also outperforms StarCoderBase-15B. Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size. In addition, it matches or outperforms CodeLlama-34B, a model more than twice its size. Although DeepSeekCoder- 33B is the best-performing model at code completion for high-resource languages, we find that StarCoder2-15B outperforms it on math and code reasoning benchmarks, as well as several low-resource languages. We make the model weights available under an OpenRAIL license and ensure full transparency regarding the training data by releasing the SoftWare Heritage persistent IDentifiers (SWHIDs) of the source code data.

We propose here a set of new methods to directly detect light mass dark matter through its scattering with abundant atmospheric muons or accelerator beams. Firstly, we plan to use the free cosmic-ray muons interacting with dark matter in a volume surrounded by tracking detectors, to trace possible interaction between dark matter and muons. Secondly, we will interface our device with domestic or international muon beams. Due to much larger muon intensity and focused beam, we anticipate the detector can be made further compact and the resulting sensitivity on dark matter searches will be improved. Furthermore, we will measure precisely directional distributions of cosmic-ray muons, either at mountain or sea level, and the differences may reveal possible information of dark matter distributed near the earth. Specifically, our methods can have advantages over `exotic' dark matters which are either muon-philic or slowed down due to some mechanism, and sensitivity on dark matter and muon scattering cross section can reach as low as microbarn level., Comment: Added a few sentences to highlight that our methods can have advantages over exotic dark matters which are either muon-philic or slowed down due to some mechanism

Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications. In this paper, we investigate a challenging yet practical scenario of BDD, Unsupervised Building Damage Detection (U-BDD), where only unlabelled pre- and post-disaster satellite image pairs are provided. As a pilot study, we have first proposed an advanced U-BDD baseline that leverages pre-trained vision-language foundation models (i.e., Grounding DINO, SAM and CLIP) to address the U-BDD task. However, the apparent domain gap between satellite and generic images causes low confidence in the foundation models used to identify buildings and their damages. In response, we further present a novel self-supervised framework, U-BDD++, which improves upon the U-BDD baseline by addressing domain-specific issues associated with satellite imagery. Furthermore, the new Building Proposal Generation (BPG) module and the CLIP-enabled noisy Building Proposal Selection (CLIP-BPS) module in U-BDD++ ensure high-quality self-training. Extensive experiments on the widely used building damage assessment benchmark demonstrate the effectiveness of the proposed method for unsupervised building damage detection. The presented annotation-free and foundation model-based paradigm ensures an efficient learning phase. This study opens a new direction for real-world BDD and sets a strong baseline for future research., Comment: ICDM 2023

We investigate a generalization of topological order from closed systems to open systems, for which the steady states take the place of ground states. We construct typical lattice models with steady-state topological order, and characterize them by complementary approaches based on topological degeneracy of steady states, topological entropy, and dissipative gauge theory. Whereas the (Liouvillian) level splitting between topologically degenerate steady states is exponentially small with respect to the system size, the Liouvillian gap between the steady states and the rest of the spectrum decays algebraically as the system size grows, and closes in the thermodynamic limit. It is shown that steady-state topological order remains definable in the presence of (Liouvillian) gapless modes. The topological phase transition to the trivial phase, where the topological degeneracy is lifted, is accompanied by gapping out the gapless modes. Our work offers a toolbox for investigating open-system topology of steady states., Comment: 33 pages, 17 figures. Joint submission with arXiv:2306.12482

Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly. To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that necessitates an in-depth cross-file contextual understanding to complete the code accurately. CrossCodeEval is built on a diverse set of real-world, open-sourced, permissively-licensed repositories in four popular programming languages: Python, Java, TypeScript, and C#. To create examples that strictly require cross-file context for accurate completion, we propose a straightforward yet efficient static-analysis-based approach to pinpoint the use of cross-file context within the current file. Extensive experiments on state-of-the-art code language models like CodeGen and StarCoder demonstrate that CrossCodeEval is extremely challenging when the relevant cross-file context is absent, and we see clear improvements when adding these context into the prompt. However, despite such improvements, the pinnacle of performance remains notably unattained even with the highest-performing model, indicating that CrossCodeEval is also capable of assessing model's capability in leveraging extensive context to make better code completion. Finally, we benchmarked various methods in retrieving cross-file context, and show that CrossCodeEval can also be used to measure the capability of code retrievers., Comment: To appear at NeurIPS 2023 (Datasets and Benchmarks Track)

LiDAR-based 3D object detection has recently seen significant advancements through active learning (AL), attaining satisfactory performance by training on a small fraction of strategically selected point clouds. However, in real-world deployments where streaming point clouds may include unknown or novel objects, the ability of current AL methods to capture such objects remains unexplored. This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts. To tackle this challenge, we propose a simple yet effective strategy called Open Label Conciseness (OLC), which mines novel 3D objects with minimal annotation costs. Our empirical results show that OLC successfully adapts the 3D detection model to the open world scenario with just a single round of selection. Any generic AL policy can then be integrated with the proposed OLC to efficiently address the OWAL-3D problem. Based on this, we introduce the Open-CRB framework, which seamlessly integrates OLC with our preliminary AL method, CRB, designed specifically for 3D object detection. We develop a comprehensive codebase for easy reproducing and future research, supporting 15 baseline methods (\textit{i.e.}, active learning, out-of-distribution detection and open world detection), 2 types of modern 3D detectors (\textit{i.e.}, one-stage SECOND and two-stage PV-RCNN) and 3 benchmark 3D datasets (\textit{i.e.}, KITTI, nuScenes and Waymo). Extensive experiments evidence that the proposed Open-CRB demonstrates superiority and flexibility in recognizing both novel and known classes with very limited labeling costs, compared to state-of-the-art baselines. Source code is available at \url{https://github.com/Luoyadan/CRB-active-3Ddet/tree/Open-CRB}.

Analyzing model performance in various unseen environments is a critical research problem in the machine learning community. To study this problem, it is important to construct a testbed with out-of-distribution test sets that have broad coverage of environmental discrepancies. However, existing testbeds typically either have a small number of domains or are synthesized by image corruptions, hindering algorithm design that demonstrates real-world effectiveness. In this paper, we introduce CIFAR-10-Warehouse, consisting of 180 datasets collected by prompting image search engines and diffusion models in various ways. Generally sized between 300 and 8,000 images, the datasets contain natural images, cartoons, certain colors, or objects that do not naturally appear. With CIFAR-10-W, we aim to enhance the evaluation and deepen the understanding of two generalization tasks: domain generalization and model accuracy prediction in various out-of-distribution environments. We conduct extensive benchmarking and comparison experiments and show that CIFAR-10-W offers new and interesting insights inherent to these tasks. We also discuss other fields that would benefit from CIFAR-10-W., Comment: ICLR 2024. https://sites.google.com/view/CIFAR-10-warehouse/

Monocular cameras are extensively employed in indoor robotics, but their performance is limited in visual odometry, depth estimation, and related applications due to the absence of scale information.Depth estimation refers to the process of estimating a dense depth map from the corresponding input image, existing researchers mostly address this issue through deep learning-based approaches, yet their inference speed is slow, leading to poor real-time capabilities. To tackle this challenge, we propose an explicit method for rapid monocular depth recovery specifically designed for corridor environments, leveraging the principles of nonlinear optimization. We adopt the virtual camera assumption to make full use of the prior geometric features of the scene. The depth estimation problem is transformed into an optimization problem by minimizing the geometric residual. Furthermore, a novel depth plane construction technique is introduced to categorize spatial points based on their possible depths, facilitating swift depth estimation in enclosed structural scenarios, such as corridors. We also propose a new corridor dataset, named Corr\_EH\_z, which contains images as captured by the UGV camera of a variety of corridors. An exhaustive set of experiments in different corridors reveal the efficacy of the proposed algorithm., Comment: 10 pages, 8 figures. arXiv admin note: text overlap with arXiv:2111.08600 by other authors

This report examines Artificial Intelligence (AI) in the financial sector, outlining its potential to revolutionise the industry and identify its challenges. It underscores the criticality of a well-rounded understanding of AI, its capabilities, and its implications to effectively leverage its potential while mitigating associated risks. The potential of AI potential extends from augmenting existing operations to paving the way for novel applications in the finance sector. The application of AI in the financial sector is transforming the industry. Its use spans areas from customer service enhancements, fraud detection, and risk management to credit assessments and high-frequency trading. However, along with these benefits, AI also presents several challenges. These include issues related to transparency, interpretability, fairness, accountability, and trustworthiness. The use of AI in the financial sector further raises critical questions about data privacy and security. A further issue identified in this report is the systemic risk that AI can introduce to the financial sector. Being prone to errors, AI can exacerbate existing systemic risks, potentially leading to financial crises. Regulation is crucial to harnessing the benefits of AI while mitigating its potential risks. Despite the global recognition of this need, there remains a lack of clear guidelines or legislation for AI use in finance. This report discusses key principles that could guide the formation of effective AI regulation in the financial sector, including the need for a risk-based approach, the inclusion of ethical considerations, and the importance of maintaining a balance between innovation and consumer protection. The report provides recommendations for academia, the finance industry, and regulators.

Egocentric, multi-modal data as available on future augmented reality (AR) devices provides unique challenges and opportunities for machine perception. These future devices will need to be all-day wearable in a socially acceptable form-factor to support always available, context-aware and personalized AI applications. Our team at Meta Reality Labs Research built the Aria device, an egocentric, multi-modal data recording and streaming device with the goal to foster and accelerate research in this area. In this paper, we describe the Aria device hardware including its sensor configuration and the corresponding software tools that enable recording and processing of such data.

In the era of Large Language Models (LLMs), tremendous strides have been made in the field of multimodal understanding. However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and rich world knowledge inherent to these large pre-trained models, and the beneficial connections among tasks within the context of text-rich scenarios have not been sufficiently explored. In this work, we introduce UniDoc, a novel multimodal model equipped with text detection and recognition capabilities, which are deficient in existing approaches. Moreover, UniDoc capitalizes on the beneficial interactions among tasks to enhance the performance of each individual task. To implement UniDoc, we perform unified multimodal instruct tuning on the contributed large-scale instruction following datasets. Quantitative and qualitative experimental results show that UniDoc sets state-of-the-art scores across multiple challenging benchmarks. To the best of our knowledge, this is the first large multimodal model capable of simultaneous text detection, recognition, spotting, and understanding.

Decoherence is a major obstacle to the preparation of topological order in noisy intermediate-scale quantum devices. Here, we show that decoherence can also give rise to new types of topological order. Specifically, we construct concrete examples by proliferating fermionic anyons in the toric code via local quantum channels. The resulting mixed states retain long-range entanglement, which manifests in the nonzero topological entanglement negativity, though the topological quantum memory is destroyed by decoherence. By comparison to the gapless spin liquid in pure states, we show that the identified states represent a novel intrinsic mixed-state quantum topological order, which has no counterpart in pure states. Through the lens of quantum anomalies of 1-form symmetries, we then provide general constructions of intrinsic mixed-state quantum topological order, and reveal the existence of non-bosonic deconfined anyons as another key feature of these novel phases. The extended meaning and characterization of deconfined excitations and their statistics in mixed states are clarified. Moreover, when these deconfined anyons have nontrivial braiding statistics, we prove that the mixed states %must be bipartite long-range entangled for any bipartition. That is, such mixed states cannot be prepared via finite-depth local quantum channels from any bipartite separable states. We further demonstrate our construction using the decohered Kitaev honeycomb model and the decohered double semion model. In the latter case, a surprising scenario arises where decoherence gives rise to additional types of deconfined anyons., Comment: 12+17 pages, 8+3 figures

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve extreme compression ratios ($<0.05$ bpp) remain constrained. In this work, we propose a simple yet effective coding framework by introducing vector quantization (VQ)--based generative models into the image compression domain. The main insight is that the codebook learned by the VQGAN model yields a strong expressive capacity, facilitating efficient compression of continuous information in the latent space while maintaining reconstruction quality. Specifically, an image can be represented as VQ-indices by finding the nearest codeword, which can be encoded using lossless compression methods into bitstreams. We propose clustering a pre-trained large-scale codebook into smaller codebooks through the K-means algorithm, yielding variable bitrates and different levels of reconstruction quality within the coding framework. Furthermore, we introduce a transformer to predict lost indices and restore images in unstable environments. Extensive qualitative and quantitative experiments on various benchmark datasets demonstrate that the proposed framework outperforms state-of-the-art codecs in terms of perceptual quality-oriented metrics and human perception at extremely low bitrates ($\le 0.04$ bpp). Remarkably, even with the loss of up to $20\%$ of indices, the images can be effectively restored with minimal perceptual loss., Comment: Generative Compression, Extreme Compression, VQGANs, Low Bitrate

The interplay between dissipation and correlation can lead to new emergent phenomena. Here we study non-equilibrium phases of matter with robust topological degeneracy of steady states, which is a generalization of the ground-state topological degeneracy of closed systems. Specifically, we construct two representative Lindbladians using engineered dissipation, and exactly solve the steady states with topological degeneracy. We find that while the degeneracy is fragile under noise in two dimensions, it is stable in three dimensions, where a genuine many-body phase with topological degeneracy is realized. We identify universal features of dissipative topological physics such as the deconfined emergent gauge field and slow relaxation dynamics of topological defects. The transition from a topologically ordered phase to a trivial phase is also investigated via numerical simulation. Our work highlights the essential difference between ground-state topological order in closed systems and steady-state topological order in open systems., Comment: 6+9 pages, 3+2 figures

Large language models trained on code have shown great potential to increase productivity of software developers. Several execution-based benchmarks have been proposed to evaluate functional correctness of model-generated code on simple programming problems. Nevertheless, it is expensive to perform the same evaluation on complex real-world projects considering the execution cost. On the contrary, static analysis tools such as linters, which can detect errors without running the program, haven't been well explored for evaluating code generation models. In this work, we propose a static evaluation framework to quantify static errors in Python code completions, by leveraging Abstract Syntax Trees. Compared with execution-based evaluation, our method is not only more efficient, but also applicable to code in the wild. For experiments, we collect code context from open source repos to generate one million function bodies using public models. Our static analysis reveals that Undefined Name and Unused Variable are the most common errors among others made by language models. Through extensive studies, we also show the impact of sampling temperature, model size, and context on static errors in code completions., Comment: Accepted by ACL 2023 industry track

In recent years, on-device deep learning has gained attention as a means of developing affordable deep learning applications for mobile devices. However, on-device models are constrained by limited energy and computation resources. In the mean time, a poisoning attack known as sponge poisoning has been developed.This attack involves feeding the model with poisoned examples to increase the energy consumption during inference. As previous work is focusing on server hardware accelerators, in this work, we extend the sponge poisoning attack to an on-device scenario to evaluate the vulnerability of mobile device processors. We present an on-device sponge poisoning attack pipeline to simulate the streaming and consistent inference scenario to bridge the knowledge gap in the on-device setting. Our exclusive experimental analysis with processors and on-device networks shows that sponge poisoning attacks can effectively pollute the modern processor with its built-in accelerator. We analyze the impact of different factors in the sponge poisoning algorithm and highlight the need for improved defense mechanisms to prevent such attacks on on-device deep learning applications., Comment: Accepted to AsiaCCS Workshop on Secure and Trustworthy Deep Learning Systems (SecTL 2023)

Fourier decay of fractal measures on surfaces plays an important role in geometric measure theory and partial differential equations. In this paper, we study the quadratic surfaces of high co-dimensions. Unlike the case of co-dimension 1, quadratic surfaces of high co-dimensions possess some special scaling structures and degenerate characteristics. We will adopt the strategy from Du and Zhang, combined with the broad-narrow analysis with different dimensions as divisions, to obtain a few lower bounds of Fourier decay of fractal measures on quadratic surfaces of co-dimension two in $\mathbb{R}^5$., Comment: 41 pages

Interoperability remains a challenge in the construction industry. In this study, we propose a semantic enrichment approach to construct BIM knowledge graphs from pure building object geometries and demonstrate its potential to support BIM interoperability. Our approach involves machine learning and rule-based methods for object classification, relationship determination (e.g., hosting and adjacent) and attribute computation. The enriched results are compiled into a BIM graph. A case study was conducted to illustrate the approach for facilitating interoperability between different versions of the BIM authoring software Autodesk Revit. First, pure object geometries of an architectural apartment model were exported from Revit 2023 and fed into the developed tools in sequence to generate a BIM graph. Then, essential information was extracted from the graph and used to reconstruct an architectural model in the version 2022 of Revit. Upon examination, the reconstructed model was consistent with the original one. The success of this experiment demonstrates the feasibility of generating a BIM graph from object geometries and utilizing it to support interoperability.

ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well., Comment: 10 pages, 7 figures, 10 tables

The conventional approach of designing BIM projects requires packaging of building information as files to exchange designs. This study develops a series of components to implement a previously established Cloud BIM (CBIM) platform that facilitates fileless cloud collaboration across BIM disciplines. A CBIM connector was developed to synchronize design changes from one discipline client to a CBIM server. The server processes the modifications and propagates relevant reference geometries to affected disciplines to assist their designs. The success of the case study demonstrates a fileless approach for multidisciplinary BIM collaboration and validates the practicality and capabilities of the CBIM paradigm.