Search

Although language model (LM) agents are demonstrating growing potential in many domains, their success in cybersecurity has been limited due to simplistic design and the lack of fundamental features for this domain. We present EnIGMA, an LM agent for autonomously solving Capture The Flag (CTF) challenges. EnIGMA introduces new Agent-Computer Interfaces (ACIs) to improve the success rate on CTF challenges. We establish the novel Interactive Agent Tool concept, which enables LM agents to run interactive command-line utilities essential for these challenges. Empirical analysis of EnIGMA on over 350 CTF challenges from three different benchmarks indicates that providing a robust set of new tools with demonstration of their usage helps the LM solve complex problems and achieves state-of-the-art results on the NYU CTF and Intercode-CTF benchmarks. Finally, we discuss insights on ACI design and agent behavior on cybersecurity tasks that highlight the need to adapt real-world tools for LM agents.

Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively, far exceeding the previous state-of-the-art achieved with non-interactive LMs. Finally, we provide insight on how the design of the ACI can impact agents' behavior and performance., Comment: Code, data, and demo available at https://swe-agent.com

The use of computer technology to automate the enforcement of law is a promising alternative to simplify bureaucratic procedures. However, careless automation might result in an inflexible and dehumanise law enforcement system driven by algorithms that do not account for the particularities of individuals or minorities. In this paper, we argue that hybrid smart contracts deployed to monitor rather than to blindly enforce regulations can be used to add flexibility. Enforcement is a suitable alternative only when prevention is strictly necessary; however, we argue that in many situations a corrective approach based on monitoring is more flexible and suitable. To add more flexibility, the hybrid smart contract can be programmed to stop to request the intervention of a human or of a group of them when human judgement is needed., Comment: Eleven pages in total. Four pdf figures. Paper accepted for publication in Data and Policy Journal

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation tasks. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. The best-performing model, Claude 2, is able to solve a mere $1.96$% of the issues. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous., Comment: Data, code, and leaderboard are available at https://www.swebench.com ICLR 2024, https://openreview.net/forum?id=VTF8yNQM66

Semantic textual similarity (STS), a cornerstone task in NLP, measures the degree of similarity between a pair of sentences, and has broad application in fields such as information retrieval and natural language understanding. However, sentence similarity can be inherently ambiguous, depending on the specific aspect of interest. We resolve this ambiguity by proposing a novel task called Conditional STS (C-STS) which measures sentences' similarity conditioned on an feature described in natural language (hereon, condition). As an example, the similarity between the sentences "The NBA player shoots a three-pointer." and "A man throws a tennis ball into the air to serve." is higher for the condition "The motion of the ball" (both upward) and lower for "The size of the ball" (one large and one small). C-STS's advantages are two-fold: (1) it reduces the subjectivity and ambiguity of STS and (2) enables fine-grained language model evaluation through diverse natural language conditions. We put several state-of-the-art models to the test, and even those performing well on STS (e.g. SimCSE, Flan-T5, and GPT-4) find C-STS challenging; all with Spearman correlation scores below 50. To encourage a more comprehensive evaluation of semantic similarity and natural language understanding, we make nearly 19K C-STS examples and code available for others to train and test their models., Comment: Published in EMNLP 2023

The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited affordable access and poses a pressing need for efficiency approaches geared towards high throughput and performance. Multi-input multi-output (MIMO) algorithms such as data multiplexing, offer a promising solution with a many-fold increase in throughput by performing inference for multiple inputs at the cost of a single input. Yet these approaches are not currently performant enough to be deployed in modern systems. We change that by developing MUX-PLMs, a class of high throughput pre-trained language models (PLMs) trained with data multiplexing, that can be fine-tuned for any downstream task to yield high-throughput high-performance. Our novel multiplexing and demultiplexing modules proficiently entangle and disentangle inputs, and enable high-performance high throughput \muxplms{} that are competitive with vanilla PLMs while achieving 2x/5x inference speedup with only a $1-4\%$ drop on a broad suite of tasks.

We introduce CARETS, a systematic test suite to measure consistency and robustness of modern VQA models through a series of six fine-grained capability tests. In contrast to existing VQA test sets, CARETS features balanced question generation to create pairs of instances to test models, with each pair focusing on a specific capability such as rephrasing, logical symmetry or image obfuscation. We evaluate six modern VQA systems on CARETS and identify several actionable weaknesses in model comprehension, especially with concepts such as negation, disjunction, or hypernym invariance. Interestingly, even the most sophisticated models are sensitive to aspects such as swapping the order of terms in a conjunction or varying the number of answer choices mentioned in the question. We release CARETS to be used as an extensible tool for evaluating multi-modal model robustness., Comment: ACL 2022

We perform extended numerical studies to maximize the overall photon coupling efficiency of fiber-coupled quantum dot single-photon sources emitting in the near-infrared and telecom regime. Using the finite element method, we optimize the photon extraction and fiber-coupling efficiency of quantum dot single-photon sources based on micromesas, microlenses, circular Bragg grating cavities and micropillars. The numerical simulations which consider the entire system consisting of the quantum dot source itself, the coupling lens, and the single-mode fiber yield overall photon coupling efficiencies of up to 83%. Our work provides objectified comparability of different fiber-coupled single-photon sources and proposes optimized geometries for the realization of practical and highly efficient quantum dot single-photon sources.

In this paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation. DataMUX demonstrates that neural networks are capable of generating accurate predictions over mixtures of inputs, resulting in increased throughput with minimal extra memory requirements. Our approach uses two key components -- 1) a multiplexing layer that performs a fixed linear transformation to each input before combining them to create a mixed representation of the same size as a single input, which is then processed by the base network, and 2) a demultiplexing layer that converts the base network's output back into independent representations before producing predictions for each input. We show the viability of DataMUX for different architectures (Transformers, and to a lesser extent MLPs and CNNs) across six different tasks spanning sentence classification, named entity recognition and image classification. For instance, DataMUX for Transformers can multiplex up to $20$x/$40$x inputs, achieving $11$x/$18$x increase in throughput with minimal absolute performance drops of $<2\%$ and $<4\%$ respectively on MNLI, a natural language inference task. We also provide a theoretical construction for multiplexing in self-attention networks and analyze the effect of various design elements in DataMUX., Comment: NeurIPS 2022

The hype about Bitcoin has overrated the potential of smart contracts deployed on-blockchains (on-chains) and underrated the potential of smart contracts deployed on-Trusted Third Parties (on-TTPs). As a result, current research and development in this field is focused mainly on smart contract applications that use on-chain smart contracts. We argue that there is a large class of smart contract applications where on-TTP smart contracts are a better alternative. The problem with on-chain smart contracts is that the fully decentralised model and indelible append-only data model followed by blockchains introduces several engineering problems that are hard to solve. In these situations, the inclusion of a TTP (assuming that the application can tolerate its inconveniences) instead of a blockchain to host the smart contract simplifies the problems and offers pragmatic solutions. The intention and contribution of this paper is to shed some light on this issue. We use a hypothetical use case of a car insurance application to illustrate technical problems that are easier to solve with on-TTP smart contracts than with on-chain smart contracts., Comment: The document consists of 14 pages and includes four figures, one table and 76 references. It the work of five authors. Carlos Molina-Jimenez is the corresponding and responsible author

We suggest the re-introduction of bartering to create a cryptocurrencyless, currencyless, and moneyless economy segment. We contend that a barter economy would benefit enterprises, individuals, governments and societies. For instance, the availability of an online peer-to-peer barter marketplace would convert ordinary individuals into potential traders of both tangible and digital items and services. For example, they will be able to barter files and data that they collect. Equally motivating, they will be able to barter and re-introduce to the economy items that they no longer need such as, books, garden tools, and bikes which are normally kept and wasted in garages and sheds. We argue that most of the pieces of technology needed for building a barter system are now available, including blockchains, smart contracts, cryptography, secure multiparty computations and fair exchange protocols. However, additional research is needed to refine and integrate the pieces together. We discuss potential research directions., Comment: The document consists of 22 pages in total, including references and two figures. The author list has five authors

We report the existence of persistently rotating azimuthons in media with self-focusing Kerr and absorption nonlinearities. The nonlinear loss is balanced by power influx from the peripheral reservoir stored in slowly decaying tails of the azimuthons. These modes are excited by a superposition of two Bessel beams with opposite vorticities, $\pm s$, and slightly different conicities. The excited azimuthon exhibits opposite vorticity in its center to that of the input Bessel-beam superposition due to spontaneous inversion of the topological charge in the course of the azimuthon formation. Unlike azimuthons in loss-free media, number $N$ of rotating intensity maxima and $s$ are not mutually independent, being related by $N=2s$. The robustness of the rotating azimuthons is enhanced in comparison to similar static dissipative patterns. They can be excited in almost any transparent material, in the range of intensities for which the nonlinear absorption, induced by multiphoton absorption, is relevant. Close to the ionization threshold, the rotating azimuthons reproduce recently observed helical filaments of light in air and CS$_{2}$., Comment: To be published in Phys. Rev. A. 10 pages, 11 figures

Given a bounded open subset $\Omega$ of $\mathbb R^n$, we establish the weak closure of the affine ball $B^{\mathcal A}_p(\Omega) = \{f \in W^{1,p}_0(\Omega):\ \mathcal E_p f \leq 1\}$ with respect to the affine functional $\mathcal E_pf$ introduced by Lutwak, Yang and Zhang in [43] as well as its compactness in $L^p(\Omega)$ for any $p \geq 1$. These points use strongly the celebrated Blaschke-Santal\'{o} inequality. As counterpart, we develop the basic theory of $p$-Rayleigh quotients in bounded domains, in the affine case, for $p\geq 1$. More specifically, we establish $p$-affine versions of the Poincar\'e inequality and some of their consequences. We introduce the affine invariant $p$-Laplace operator $\Delta_p^{\mathcal A} f$ defining the Euler-Lagrange equation of the minimization problem of the $p$-affine Rayleigh quotient. We also study its first eigenvalue $\lambda^{\mathcal A}_{1,p}(\Omega)$ which satisfies the corresponding affine Faber-Krahn inequality, this is that $\lambda^{\mathcal A}_{1,p}(\Omega)$ is minimized (among sets of equal volume) only when $\Omega$ is an ellipsoid. This point depends fundamentally on PDEs regularity analysis aimed at the operator $\Delta_p^{\mathcal A} f$. We also present some comparisons between affine and classical eigenvalues, including a result of rigidity through the characterization of equality cases for $p \geq 1$. All affine inequalities obtained are stronger and directly imply the classical ones., Comment: 30 pages, comments are welcome

If $K\subset\mathbb{R}^n$ is a convex body and $\Gamma_pK$ is the $p$-centroid body of $K$, the $L_p$ Busemann-Petty centroid inequality states that $\vol(\Gamma_pK) \geq \vol(K)$, with equality if and only if $K$ is an ellipsoid centered at the origin. In this work, we prove inequalities for a type of functional $r$-mixed volume for $1 \leq r < n$, and establish as a consequence, a functional version of the $L_p$ Busemann-Petty centroid inequality. \keywords{Convex body, Moment body, Busemann-Petty centroid} }, Comment: 14 pages. Comments are welcome

Recently, decentralised (on-blockchain) platforms have emerged to complement centralised (off-blockchain) platforms for the implementation of automated, digital (smart) contracts. However, neither alternative can individually satisfy the requirements of a large class of applications. On-blockchain platforms suffer from scalability, performance, transaction costs and other limitations. Off-blockchain platforms are afflicted by drawbacks due to their dependence on single trusted third parties. We argue that in several application areas, hybrid platforms composed from the integration of on- and off-blockchain platforms are more able to support smart contracts that deliver the desired quality of service (QoS). Hybrid architectures are largely unexplored. To help cover the gap, in this paper we discuss the implementation of smart contracts on hybrid architectures. As a proof of concept, we show how a smart contract can be split and executed partially on an off-blockchain contract compliance checker and partially on the Rinkeby Ethereum network. To test the solution, we expose it to sequences of contractual operations generated mechanically by a contract validator tool., Comment: 12 pages, 7 figures

In this paper we discuss how conventional business contracts can be converted into smart contracts---their electronic equivalents that can be used to systematically monitor and enforce contractual rights, obligations and prohibitions at run time. We explain that emerging blockchain technology is certainly a promising platform for implementing smart contracts but argue that there is a large class of applications, where blockchain is inadequate due to performance, scalability, and consistency requirements, and also due to language expressiveness and cost issues that are hard to solve. We explain that in some situations a centralised approach that does not rely on blockchain is a better alternative due to its simplicity, scalability, and performance. We suggest that in applications where decentralisation and transparency are essential, developers can advantageously combine the two approaches into hybrid solutions where some operations are enforced by enforcers deployed on--blockchains and the rest by enforcers deployed on trusted third parties.

We establish sharp affine weighted $L^p$ Sobolev type inequalities by using the $L_p$ Busemann-Petty centroid inequality proved by Lutwak, Yang and Zhang. Our approach consists in combining in a convenient way the latter one with a suitable family of sharp weighted $L^p$ Sobolev type inequalities obtained by Nguyen and allows to characterize all extremizers in some cases. The new inequalities don't rely on any euclidean geometric structure.

We report on the stationary and robust propagation of light beams with rather arbitrary and controllable intensity and dissipation transverse patterns in self-focusing Kerr media with nonlinear absorption. When nonlinear absorption is due to multi-photon ionization at high beam powers in transparent media such as glasses or air, these beams can generate multiple plasma channels with tailored geometries. Their nature and spatial characteristics are discussed in detail, as well as the laws determining their spontaneous formation from coherent superpositions of Bessel beams of different amplitudes and topological charges.

We describe nonlinear Bessel vortex beams as localized and stationary solutions with embedded vorticity to the nonlinear Schr\"odinger equation with a dissipative term that accounts for the multi-photon absorption processes taking place at high enough powers in common optical media. In these beams, power and orbital angular momentum are permanently transferred to matter in the inner, nonlinear rings, at the same time that they are refueled by spiral inward currents of energy and angular momentum coming from the outer linear rings, acting as an intrinsic reservoir. Unlike vortex solitons and dissipative vortex solitons, the existence of these vortex beams does not critically depend on the precise form of the dispersive nonlinearities, as Kerr self-focusing or self-defocusing, and do not require a balancing gain. They have been shown to play a prominent role in "tubular" filamentation experiments with powerful, vortex-carrying Bessel beams, where they act as attractors in the beam propagation dynamics. Nonlinear Bessel vortex beams provide indeed a new solution to the problem of the stable propagation of ring-shaped vortex light beams in homogeneous self-focusing Kerr media. A stability analysis demonstrates that there exist nonlinear Bessel vortex beams with single or multiple vorticity that are stable against azimuthal breakup and collapse, and that the mechanism that renders these vortexes stable is dissipation. The stability properties of nonlinear Bessel vortex beams explain the experimental observations in the tubular filamentation experiments., Comment: Chapter of book

In this paper, we present a NDN based smart home lighting solution where lights are automatically controlled in near real time based on occupancy and daylight. We implemented a reliable solution using NDN architecture exploiting the primitive NDN features in push based data dissemination, multicast forwarding through name prefixes and Interest filtering in application layer. Performance was evaluated benchmarking with respect to a cloud based approach in terms of message delivery latency. Scalability of the solution was also analyzed presenting an analysis on FIB scalability based on Interest filtering. Finally, from this study, we recommend and highlight a few requirements that could improve NDN for sustainable IoT applications.

We establish a sharp affine $L^p$ Sobolev trace inequality by using the $L_p$ Busemann-Petty centroid inequality. For $p = 2$, our affine version is stronger than the famous sharp $L^2$ Sobolev trace inequality proved independently by Escobar and Beckner. Our approach allows also to characterize all cases of equality in this case. For this new inequality, no Euclidean geometric structure is needed., Comment: 17 pages including an appendix. The main results from the previous version remain unchanged. The structure and notations were modified, several typos were corrected and proofs for some technical lemmas were added

We extend the notion of John's ellipsoid to the setting of integrable log-concave functions. This will allow us to define the integral ratio of a log-concave function, which will extend the notion of volume ratio, and we will find the log-concave function maximizing the integral ratio. A reverse functional affine isoperimetric inequality will be given, written in terms of this integral ratio. This can be viewed as a stability version of the functional affine isoperimetric inequality.

In light filamentation induced by axicon-generated, powerful Bessel beams, the spatial propagation dynamics in the nonlinear medium determines the geometry of the filament channel and hence its potential applications. We show that the observed steady and unsteady Bessel beam propagation regimes can be understood in a unified way from the existence of an attractor and its stability properties. The attractor is identified as the nonlinear unbalanced Bessel beam (NL-UBB) whose inward H\"ankel beam amplitude equals the amplitude of the linear Bessel beam that the axicon would generate in linear propagation. A simple analytical formula that determines de NL-UBB attractor is given. Steady or unsteady propagation depends on whether the attracting NL-UBB has a small, exponentially growing, unstable mode. In case of unsteady propagation, periodic, quasi-periodic or chaotic dynamics after the axicon reproduces similar dynamics after the development of the small unstable mode into the large perturbation regime., Comment: 9 pages, 7 figures

We investigate on the nonlinear dynamics of Airy beams in a regime where nonlinear losses due to multi-photon absorption are significant. We identify the nonlinear Airy beam (NAB) that preserves the amplitude of the inward H\"ankel component as an attractor of the dynamics. This attractor governs also the dynamics of finite-power (apodized) Airy beams, irrespective of the location of the entrance plane in the medium with respect to the Airy waist plane. A soft (linear) input long before the waist, however, strongly speeds up NAB formation and its persistence as a quasi-stationary beam in comparison to an abrupt input at the Airy waist plane, and promotes the formation of a new type of highly dissipative, fully nonlinear Airy beam not described so far.

We prove a characterization of the dual mixed volume in terms of functional properties of the polynomial associated to it. To do this, we use tools from the theory of multilinear operators on spaces of continuos functions. Along the way we reprove, with these same techniques, a recently found characterization of the dual mixed volume.

We show that a high-order Bessel beam propagating in a medium with nonlinear absorption is not completely absorbed, but survives in the form of a new propagation invariant vortex beam in which the beam energy and orbital angular momentum are permanently transferred to matter and at the same time refueled by spiral inward currents of energy and angular momentum. Unlike vortex solitons and dissipative vortex solitons, these vortex beams are not supported by specific dispersive nonlinearities (self-focusing or self-defocusing) and do not require gain. Propagation invariance in presence of multiple absorption of photons carrying (possibly high) orbital angular momentum makes these beams attractive for optical pumping of angular momentum over long distances.

We obtain a new extension of Rogers-Shephard inequality providing an upper bound for the volume of the sum of two convex bodies $K$ and $L$. We also give lower bounds for the volume of the $k$-th limiting convolution body of two convex bodies $K$ and $L$. Special attention is paid to the $(n-1)$-th limiting convolution body, for which a sharp inequality, which is equality only when $K=-L$ is a simplex, is given. Since the $n$-th limiting convolution body of $K$ and $-K$ is the polar projection body of $K$, these inequalities can be viewed as an extension of Zhang's inequality., Comment: 16 pages

The Riemann-zeta function regularization procedure has been studied intensively as a good method in the computation of the determinant for pseudo-diferential operator. In this paper we propose a different approach for the computation of the determinant base on the Wheeler-De Witt equation., Comment: 6 pages, 27 equations, no figures

In bilateral accounting of resource consumption both the consumer and provider independently measure the amount of resources consumed by the consumer. The problem here is that potential disparities between the provider's and consumer's accountings, might lead to conflicts between the two parties that need to be resolved. We argue that with the proper mechanisms available, most of these conflicts can be solved online, as opposite to in court resolution; the design of such mechanisms is still a research topic; to help cover the gap, in this paper we propose a peer--to--peer protocol for online dispute resolution over storage consumption. The protocol is peer--to--peer and takes into consideration the possible causes (e.g, transmission delays, unsynchronized metric collectors, etc.) of the disparity between the provider's and consumer's accountings to make, if possible, the two results converge., Comment: 12 pages, 7 figures