共找到 20 条结果
We study the market design of keep-alive caching policies applicable in serverless computing. Prior work has assumed that the cost of a cache miss (cold start) is uniform across all customer applications. However, the cost of a cache miss depends on the customer's application. We investigate the market design where the customers submit a bid for their cost of a cache miss. We design a cache allocation policy based on online learning from a mixture of fixed allocation experts. We show that our custom cache allocation policy is asymptotically efficient and monotonically non-increasing with respect to the submitted bid. We examine two ways of charging customers to achieve good incentives. In the first payment scheme the customers are charged based on Myerson's theory, whereas in the second payment scheme the customers are charged their externality. We show via a mix of simulations and theory that both schemes have desirable revenue and incentive properties.
Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to effectively handle diverse tasks and distinguish between inputs in polyptych configurations. To address the data gap, we curated a 12K identity-consistent dataset with 8K real-world and 4K high-quality synthetic samples, avoiding the overly glossy, oversaturated look typical of s
Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as OpenAI-now enable developers to create and publish tailored model instances, known as custom GPTs, via dedicated repositories or application stores. These custom GPTs empower users to browse and interact with specialized applications designed to meet specific needs. However, as custom GPTs see growing adoption, concerns regarding their security vulnerabilities have intensified. Existing research on these vulnerabilities remains largely theoretical, often lacking empirical, large-scale, and statistically rigorous assessments of associated risks. In this study, we analyze 14,904 custom GPTs to assess their susceptibility to seven exploitable threats, such as roleplay-based attacks, system prompt leakage, phishing content generation, and malicious code synthesis, across various categories and popularity tiers within the OpenAI marketplace. We introduce a multi-metric ranking system to examine the relationship between a custom GPT's popularity and its associ
As online higher education expands, sustaining student engagement remains a critical challenge. This paper approaches immersive learning by investigating how custom GPTs foster immersion (as a state of deep mental involvement) for students and instructors. While large language models (LLMs) offer potential for enhancing feedback, little research has examined instructor-created custom GPTs designed to align with specific pedagogical goals. This paper addresses this gap, employing the Immersive Learning Cube framework, which conceptualizes immersion through three dimensions: system (envelopment by the environment), narrative (meaningful context), and agency (commitment to meaning-making). Through a qualitative analysis of two distinct case studies, an accelerated graduate grant writing course in the US and an undergraduate software engineering course in Portugal, we analyze course-embedded artifacts to map how custom GPTs influence these immersion dimensions. In the grant writing course, the custom GPT functioned as a feedback partner, fostering system immersion through its immediacy, narrative immersion by reinforcing the proposal's evolving story, and agency immersion by empowering
User tracking is critical in the mobile ecosystem, which relies on device identifiers to build clear user profiles. In earlier ages, Android allowed easy access to non-resettable device identifiers like device serial numbers and IMEI by third-party apps for user tracking. As privacy concerns grew, Google has tightened restrictions on these identifiers in native Android. Despite this, stakeholders in custom Android systems seek consistent and stable user tracking capabilities across different system and device models, and they have introduced covert channels (e.g., system properties and settings) in customized systems to access identifiers, which undoubtedly increases the risk of user privacy breaches. This paper examines the introduction of non-resettable identifiers through system customization and their vulnerability due to poor access control. We present IDRadar, a scalable and accurate approach for identifying vulnerable properties and settings on custom Android ROMs. Applying our approach to 1,814 custom ROMs, we have identified 8,192 system properties and 3,620 settings that store non-resettable identifiers, with 3,477 properties and 1,336 settings lacking adequate access con
Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent boundary-case performance and high inference costs. Training custom classifiers achieves both accuracy and efficiency, yet demands substantial labeled data that is costly to obtain. We present BARRED (Boundary Alignment Refinement through REflection and Debate), a framework for generating faithful and diverse synthetic training data using only a task description and a small set of unlabeled examples. Our approach decomposes the domain space into dimensions to ensure comprehensive coverage, and employs multi-agent debate to verify label correctness, yielding a high-fidelity training corpus. Experiments across diverse custom policies demonstrate that small language models finetuned on our synthetic data consistently outperform state-of-the-art proprietary LLMs (including reasoning models) and dedicated guardrail models. Ablation studies confirm that both dimension decomposition and debate-based verification are critical for ensuring the diversity and label fidelity required for effective fine-tuning. The BARR
Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, has not yet been well investigated. To address the challenge of one-shot video motion customization, we propose Customize-A-Video that models the motion from a single reference video and adapts it to new subjects and scenes with both spatial and temporal varieties. It leverages low-rank adaptation (LoRA) on temporal attention layers to tailor the pre-trained T2V diffusion model for specific motion modeling. To disentangle the spatial and temporal information during training, we introduce a novel concept of appearance absorbers that detach the original appearance from the reference video prior to motion learning. The proposed modules are trained in a staged pipeline and inferred in a plug-and-play fashion, enabling easy extensions to various downstream tasks such as custom video generation and editing, video appearance customization and multiple motion combination. Our project page can be found at https://customize-a-video.github.io.
Programmers using native languages such as C, C++, or Rust can implement custom memory allocation strategies to improve execution time. In their paper titled "Reconsidering Custom Memory Allocation" almost 25 years ago, Berger et al. showed that while per-class allocators provide no significant speedups over a state-of-the-art general-purpose allocator, region-based allocators can improve execution time by allocating and freeing objects in bulk. This paper revisits that work on a modern hardware platform with modern general-purpose allocators to evaluate whether their conclusions still hold. It also augments the benchmark suite with two large real-world applications (Clang and Blender), and introduces a methodology to explore the effect of memory fragmentation on locality in general-purpose allocators. Our results support and extend the original conclusions, demonstrating the locality advantages of region-based custom memory allocators.
An Application-Specific Instruction Set Processor(ASIP) is a specialized microprocessor that provides a trade-off between the programmability of a General Purpose Processor (GPP) and the performance and energy-efficiency of dedicated hardware accelerators. ASIPs are often derived from off-the-shelf GPPs extended by custom instructions tailored towards a specific software workload. One of the most important challenges of designing an ASIP is to find said custom instructions that help to increase performance without being too costly in terms of area and power consumption. To date, solving this challenge is relatively labor-intensive and typically performed manually. Addressing the lack of automation, we present Custom Instruction Designer for RISC-V Extensions (CIDRE), a front-to-back tool for ASIP design. CIDRE automatically analyzes hotspots in RISC-V applications and generates custom instruction suggestions with a corresponding nML description. The nML description can be used with other electronic design automation tools to accurately assess the cost and benefits of the found suggestions. In a RISC-V benchmark study, we were able to accelerate embedded benchmarks from Embench and
Custom officials across the world encounter huge volumes of transactions. With increased connectivity and globalization, the customs transactions continue to grow every year. Associated with customs transactions is the customs fraud - the intentional manipulation of goods declarations to avoid the taxes and duties. With limited manpower, the custom offices can only undertake manual inspection of a limited number of declarations. This necessitates the need for automating the customs fraud detection by machine learning (ML) techniques. Due the limited manual inspection for labeling the new-incoming declarations, the ML approach should have robust performance subject to the scarcity of labeled data. However, current approaches for customs fraud detection are not well suited and designed for this real-world setting. In this work, we propose $\textbf{GraphFC}$ ($\textbf{Graph}$ neural networks for $\textbf{C}$ustoms $\textbf{F}$raud), a model-agnostic, domain-specific, semi-supervised graph neural network based customs fraud detection algorithm that has strong semi-supervised and inductive capabilities. With upto 252% relative increase in recall over the present state-of-the-art, extens
The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by utilizing sparsity pattern- or target-aware data structures and layouts to enhance memory access latency and bandwidth utilization. However, existing sparse tensor programming models and compilers offer little or no support for productively customizing the sparse formats. Additionally, because these frameworks represent formats using a limited set of per-dimension attributes, they lack the flexibility to accommodate numerous new variations of custom sparse data structures and layouts. To overcome this deficiency, we propose UniSparse, an intermediate language that provides a unified abstraction for representing and customizing sparse formats. Unlike the existing attribute-based frameworks, UniSparse decouples the logical representation of the sparse tensor (i.e., the data structure) from its low-level memory layout, enabling the customization of both. As a result, a rich set of format customizations can be succinctly expressed in a small set of well-def
Compiler technologies in deep learning and domain-specific hardware acceleration are increasingly adopting extensible compiler frameworks such as Multi-Level Intermediate Representation (MLIR) to facilitate more efficient development. With MLIR, compiler developers can easily define their own custom IRs in the form of MLIR dialects. However, the diversity and rapid evolution of such custom IRs make it impractical to manually write a custom test generator for each dialect. To address this problem, we design a new test generator called SYNTHFUZZ that combines grammar-based fuzzing with custom mutation synthesis. The key essence of SYNTHFUZZ is two fold: (1) It automatically infers parameterized context-dependent custom mutations from existing test cases. (2) It then concretizes the mutation's content depending on the target context and reduces the chance of inserting invalid edits by performing k-ancestor and pre(post)fix matching. SYNTHFUZZ obviates the need to manually define custom mutation operators for each dialect. We compare SYNTHFUZZ to three baselines: Grammarinator, MLIRSmith, and NeuRI. We conduct this comprehensive comparison on four different MLIR projects. Each project
Second-order cone programs (SOCPs) with quadratic objective functions are common in optimal control and other fields. Most SOCP solvers which use interior-point methods are designed for linear objectives and convert quadratic objectives into linear ones via slack variables and extra constraints, despite the computational advantages of handling quadratic objectives directly. In applications like model-predictive control and online trajectory optimization, these SOCPs have known sparsity structures and require rapid solutions. When solving these problems, most solvers use sparse linear algebra routines, which introduce computational overhead and hinder performance. In contrast, custom linear algebra routines can exploit the known sparsity structure of problem data and be significantly faster. This work makes two key contributions: (1) the development of QOCO, an open-source C-based solver for quadratic objective SOCPs, and (2) the introduction of QOCOGEN, an open-source custom solver generator for quadratic objective SOCPs, which generates a solver written in C that leverages custom linear algebra. Both implement a primal-dual interior-point method with Mehrotra's predictor-corrector
With network requirements diverging across emerging applications, latency-critical services demand minimal logic delay, while hyperscale training and collectives require sustained line-rate throughput for synchronized bulk transfers. This divergence creates an urgent need for custom network switches tailored to specialized protocols and application-specific traffic patterns. This paper presents SPAC (Switch and Protocol Adaptive Customization), a novel approach that automates the generation of FPGA-based network switches co-optimized for custom protocols and application-specific traffic patterns. SPAC introduces a unified workflow with a domain-specific language (DSL) for protocol-architecture co-design, a library of modular HLS-based adaptive switch components, and a trace-aware Design Space Exploration (DSE) engine. By providing a multi-fidelity simulation stack, SPAC enables rapid identification of Pareto-optimal designs prior to deployment. We demonstrate the efficacy of the domain-specific adaptation of SPAC across a spectrum of real-world scenarios, spanning from latency-sensitive sensor and HFT networks to hyperscale datacenter fabrics. Experimental results show that by tail
Fuel moisture content (FMC) is a key predictor for wildfire rate of spread (ROS). Machine learning models of FMC are being used more in recent years, augmenting or replacing traditional physics-based approaches. Wildfire rate of spread (ROS) has a highly nonlinear relationship with FMC, where small differences in dry fuels lead to large differences in ROS. In this study, custom loss functions that place more weight on dry fuels were examined with a variety of machine learning models of FMC. The models were evaluated with a spatiotemporal cross-validation procedure to examine whether the custom loss functions led to more accurate forecasts of ROS. Results show that the custom loss functions improved accuracy for ROS forecasts by a small amount. Further research would be needed to establish whether the improvement in ROS forecasts leads to more accurate real-time wildfire simulations.
This paper examines customer momentum, defined as a positive relationship between a firm's returns and past returns of its customers. I confirm previous evidence (Cohen and Frazzini 2008) that customer momentum is both statistically and economically significant. Long-short equally-weighted (value-weighted) decile portfolio generates a monthly return of 122 (106) basis points and a t-statistic above 4 (2.8) with respect to Fama-French factor models. The paper reports that customer momentum neither explains nor is explained by price momentum and earnings momentum. Customer momentum is partially driven by the lead-lag relationship between small and large stocks. I find that in the post-discovery sample, customer momentum has a smaller magnitude and loses statistical significance. The results are consistent with the hypothesis that after its discovery, customer momentum decreased due to exploitation by investors.
In the digital age, the dynamics of customer service are evolving, driven by technological advancements and the integration of Large Language Models (LLMs). This research paper introduces a groundbreaking approach to automating customer service using LangChain, a custom LLM tailored for organizations. The paper explores the obsolescence of traditional customer support techniques, particularly Frequently Asked Questions (FAQs), and proposes a paradigm shift towards responsive, context-aware, and personalized customer interactions. The heart of this innovation lies in the fusion of open-source methodologies, web scraping, fine-tuning, and the seamless integration of LangChain into customer service platforms. This open-source state-of-the-art framework, presented as "Sahaay," demonstrates the ability to scale across industries and organizations, offering real-time support and query resolution. Key elements of this research encompass data collection via web scraping, the role of embeddings, the utilization of Google's Flan T5 XXL, Base and Small language models for knowledge retrieval, and the integration of the chatbot into customer service platforms. The results section provides insi
Inferring knowledge from clinical trials using knowledge graph embedding is an emerging area. However, customizing graph embeddings for different use cases remains a significant challenge. We propose custom2vec, an algorithmic framework to customize graph embeddings by incorporating user preferences in training the embeddings. It captures user preferences by adding custom nodes and links derived from manually vetted results of a separate information retrieval method. We propose a joint learning objective to preserve the original network structure while incorporating the user's custom annotations. We hypothesize that the custom training improves user-expected predictions, for example, in link prediction tasks. We demonstrate the effectiveness of custom2vec for clinical trials related to non-small cell lung cancer (NSCLC) with two customization scenarios: recommending immuno-oncology trials evaluating PD-1 inhibitors and exploring similar trials that compare new therapies with a standard of care. The results show that custom2vec training achieves better performance than the conventional training methods. Our approach is a novel way to customize knowledge graph embeddings and enable m
OpenAI's ChatGPT initiated a wave of technical iterations in the space of Large Language Models (LLMs) by demonstrating the capability and disruptive power of LLMs. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI's success in spotlighting AI can be partially attributed to decreased barriers to entry, enabling any individual with an internet-enabled device to interact with LLMs. What was previously relegated to a few researchers and developers with necessary computing resources is now available to all. A desire to customize LLMs to better accommodate individual needs prompted OpenAI's creation of the GPT Store, a central platform where users can create and share custom GPT models. Customization comes in the form of prompt-tuning, analysis of reference resources, browsing, and external API interactions, alongside a promise of revenue sharing for created custom GPTs. In this work, we peer into the window of the GPT Store and measure its impact. Our analysis constitutes a la
In this study, we investigate the use of Large Language Models (LLMs) for the interactive and automated production of customs circuit layouts described in natural language. Our proposed layout automation process leverages a template-and-grid-based layout generation framework to create process-portable layout generators tailored for various custom circuits, including standard cells and high-speed mixed-signal circuits. However, rather than directly describing the layout generators in traditional programming language, we utilize natural language using LLMs to make the layout generation process more intuitive and efficient. This approach also supports interactive modifications of the layout generator code, enhancing customization capabilities. We demonstrate the effectiveness of our LLM-based layout generation method across several custom circuit examples, such as logic standard cells, a serializer and a strong arm latch, including their completeness in terms of Design Rule Check (DRC), Layout Versus Schematic (LVS) test, and post-layout performance for high-speed circuits. Our experimental results indicate that LLMs can generate a diverse range of circuit layouts with substantial cus