Search

Emerging Large Language Model (LLM) applications require long input prompts to perform complex downstream tasks like document analysis and code generation. For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the inference costs increase linearly with sequence length. However, for many of these applications, much of the context in the prompt is fixed across different user inputs, thereby providing the opportunity to perform offline optimizations to process user inputs quickly, as they are received. In this work, we propose Squeezed Attention as a mechanism to accelerate LLM applications where a large portion of the input prompt is fixed. We first leverage K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value. During inference, we compare query tokens from the user input with the centroids to predict which of the keys from the fixed context are semantically relevant and need to be loaded during inference. We then compute exact attention using only these important keys from the fixed context, thereby reducing bandwidth and computational costs. We also extend our method to use a hierarchical centroid lookup to identify important keys, which can reduce the complexity of attention from linear to logarithmic with respect to the context length. We implement optimized Triton kernels for centroid comparison and sparse FlashAttention with important keys, achieving more than 4x speedups during both the prefill and generation phases for long-context inference. Furthermore, we have extensively evaluated our method on various long-context benchmarks including LongBench, where it achieves a 3x reduction in KV cache budget without accuracy loss and up to an 8x reduction with <0.5 point accuracy gap for various models.

Drone-captured images present significant challenges in object detection due to varying shooting conditions, which can alter object appearance and shape. Factors such as drone altitude, angle, and weather cause these variations, influencing the performance of object detection algorithms. To tackle these challenges, we introduce an innovative vision-language approach using learnable prompts. This shift from conventional manual prompts aims to reduce domain-specific knowledge interference, ultimately improving object detection capabilities. Furthermore, we streamline the training process with a one-step approach, updating the learnable prompt concurrently with model training, enhancing efficiency without compromising performance. Our study contributes to domain-generalized object detection by leveraging learnable prompts and optimizing training processes. This enhances model robustness and adaptability across diverse environments, leading to more effective aerial object detection., Comment: ICIP 2024 Workshop accepted paper

A recent article in $\textit{Science}$ by Guess et al. estimated the effect of Facebook's news feed algorithm on exposure to misinformation and political information among Facebook users. However, its reporting and conclusions did not account for a series of temporary emergency changes to Facebook's news feed algorithm in the wake of the 2020 U.S. presidential election that were designed to diminish the spread of voter-fraud misinformation. Here, we demonstrate that these emergency measures systematically reduced the amount of misinformation in the control group of the study, which was using the news feed algorithm. This issue may have led readers to misinterpret the results of the study and to conclude that the Facebook news feed algorithm used outside of the study period mitigates political misinformation as compared to reverse chronological feed.

Training and prototype development in robot-assisted surgery requires appropriate and safe environments for the execution of surgical procedures. Current dry lab laparoscopy phantoms often lack the ability to mimic complex, interactive surgical tasks. This work presents an interactive surgical phantom for the cholecystectomy. The phantom enables the removal of the gallbladder during cholecystectomy by allowing manipulations and cutting interactions with the synthetic tissue. The force-displacement behavior of the gallbladder is modelled based on retraction demonstrations. The force model is compared to the force model of ex-vivo porcine gallbladders and evaluated on its ability to estimate retraction forces., Comment: As presented at CURAC 2023

A promising architecture for next-generation, low energy spintronic devices uses skyrmions -- nanoscale whirlpools of magnetic moment -- as information carriers. Notably, schemes for racetrack memory have been proposed in which skyrmions and antiskyrmions, their antiparticle, serve as the logical bits 1 and 0. However, major challenges exist to designing skyrmion-antiskyrmion based computing. The presence of both particles in one material is often mutually exclusive such that few systems have been identified in which they coexist, and in these systems their appearance is stochastic rather than deterministic. Here, we create a tunable skyrmion-antiskyrmion system in FeGe films through ion-irradiation and annealing, and detail the structural properties of the films under these various conditions. Specifically, we irradiate epitaxial B20-phase FeGe films with 2.8 MeV Au$^{4+}$ ions, showing evidence that the amorphized regions preferentially host antiskyrmions at densities controlled by the irradiation fluence. In this work, we focus on a subsequent, systematic electron diffraction study with in-situ annealing, demonstrating the ability to recrystallize controllable fractions of the material at temperatures ranging from approximately 150$^{\circ}$ C to 250$^{\circ}$ C, enabling further tunability of skyrmion/antiskyrmion populations. We describe the crystallization kinetics using the Johnson-Mehl-Avrami-Kolmogorov model, finding that growth of crystalline grains is consistent with diffusion-controlled one-to-two dimensional growth with a decreasing nucleation rate. The procedures developed here can be applied towards creation of skyrmion-antiskyrmion systems for energy-efficient, high-density data storage, spin wave emission produced by skyrmion-antiskyrmion pair annihilation, and more generally testbeds for research on skyrmion-antiskyrmion liquids and crystals.

This paper introduces StyleSpeech, a novel Text-to-Speech~(TTS) system that enhances the naturalness and accuracy of synthesized speech. Building upon existing TTS technologies, StyleSpeech incorporates a unique Style Decorator structure that enables deep learning models to simultaneously learn style and phoneme features, improving adaptability and efficiency through the principles of Lower Rank Adaptation~(LoRA). LoRA allows efficient adaptation of style features in pre-trained models. Additionally, we introduce a novel automatic evaluation metric, the LLM-Guided Mean Opinion Score (LLM-MOS), which employs large language models to offer an objective and robust protocol for automatically assessing TTS system performance. Extensive testing on benchmark datasets shows that our approach markedly outperforms existing state-of-the-art baseline methods in producing natural, accurate, and high-quality speech. These advancements not only pushes the boundaries of current TTS system capabilities, but also facilitate the application of TTS system in more dynamic and specialized, such as interactive virtual assistants, adaptive audiobooks, and customized voice for gaming. Speech samples can be found in https://style-speech.vercel.app

Polar nematic liquid crystals have two special features, compared with conventional nematic liquid crystals. First, because of flexoelectricity, the combination of polar order and splay reduces the free energy. Second, because of electrostatics, any splay generates a bound charge density, which increases the free energy. To assess the competition between these two effects, we develop a theory that combines flexoelectricity and electrostatics. The theory predicts a phase diagram that includes ferroelectric, antiferroelectric, and conventional nematic phases.

Predicting emotions elicited by news headlines can be challenging as the task is largely influenced by the varying nature of people's interpretations and backgrounds. Previous works have explored classifying discrete emotions directly from news headlines. We provide a different approach to tackling this problem by utilizing people's explanations of their emotion, written in free-text, on how they feel after reading a news headline. Using the dataset BU-NEmo+ (Gao et al., 2022), we found that for emotion classification, the free-text explanations have a strong correlation with the dominant emotion elicited by the headlines. The free-text explanations also contain more sentimental context than the news headlines alone and can serve as a better input to emotion classification models. Therefore, in this work we explored generating emotion explanations from headlines by training a sequence-to-sequence transformer model and by using pretrained large language model, ChatGPT (GPT-4). We then used the generated emotion explanations for emotion classification. In addition, we also experimented with training the pretrained T5 model for the intermediate task of explanation generation before fine-tuning it for emotion classification. Using McNemar's significance test, methods that incorporate GPT-generated free-text emotion explanations demonstrated significant improvement (P-value < 0.05) in emotion classification from headlines, compared to methods that only use headlines. This underscores the value of using intermediate free-text explanations for emotion prediction tasks with headlines., Comment: published at LREC-COLING 2024

Conventional intelligent systems based on deep neural network (DNN) models encounter challenges in achieving human-like continual learning due to catastrophic forgetting. Here, we propose a metaplasticity model inspired by human working memory, enabling DNNs to perform catastrophic forgetting-free continual learning without any pre- or post-processing. A key aspect of our approach involves implementing distinct types of synapses from stable to flexible, and randomly intermixing them to train synaptic connections with different degrees of flexibility. This strategy allowed the network to successfully learn a continuous stream of information, even under unexpected changes in input length. The model achieved a balanced tradeoff between memory capacity and performance without requiring additional training or structural modifications, dynamically allocating memory resources to retain both old and new information. Furthermore, the model demonstrated robustness against data poisoning attacks by selectively filtering out erroneous memories, leveraging the Hebb repetition effect to reinforce the retention of significant data., Comment: 25 pages, 5 figures, 1 table, 4 supplementary figures

Harmful suicide content on the Internet is a significant risk factor inducing suicidal thoughts and behaviors among vulnerable populations. Despite global efforts, existing resources are insufficient, specifically in high-risk regions like the Republic of Korea. Current research mainly focuses on understanding negative effects of such content or suicide risk in individuals, rather than on automatically detecting the harmfulness of content. To fill this gap, we introduce a harmful suicide content detection task for classifying online suicide content into five harmfulness levels. We develop a multi-modal benchmark and a task description document in collaboration with medical professionals, and leverage large language models (LLMs) to explore efficient methods for moderating such content. Our contributions include proposing a novel detection task, a multi-modal Korean benchmark with expert annotations, and suggesting strategies using LLMs to detect illegal and harmful content. Owing to the potential harm involved, we publicize our implementations and benchmark, incorporating an ethical verification process., Comment: 30 pages, 7 figures

Workloads in data processing clusters are often represented in the form of DAG (Directed Acyclic Graph) jobs. Scheduling DAG jobs is challenging. Simple heuristic scheduling algorithms are often adopted in practice in production data centres. There is much room for scheduling performance optimisation for cost saving. Recently, reinforcement learning approaches (like decima) have been attempted to optimise DAG job scheduling and demonstrate clear performance gain in comparison to traditional algorithms. However, reinforcement learning (RL) approaches face their own problems in real-world deployment. In particular, their black-box decision making processes and generalizability in unseen workloads may add a non-trivial burden to the cluster administrators. Moreover, adapting RL models on unseen workloads often requires significant amount of training data, which leaves edge cases run in a sub-optimal mode. To fill the gap, we propose a new method to distill a simple scheduling policy based on observations of the behaviours of a complex deep learning model. The simple model not only provides interpretability of scheduling decisions, but also adaptive to edge cases easily through tuning. We show that our method achieves high fidelity to the decisions made by deep learning models and outperforms these models when additional heuristics are taken into account., Comment: 20 pages, 18 figures

The brain prepares for learning even before interacting with the environment, by refining and optimizing its structures through spontaneous neural activity that resembles random noise. However, the mechanism of such a process has yet to be thoroughly understood, and it is unclear whether this process can benefit the algorithm of machine learning. Here, we study this issue using a neural network with a feedback alignment algorithm, demonstrating that pretraining neural networks with random noise increases the learning efficiency as well as generalization abilities without weight transport. First, we found that random noise training modifies forward weights to match backward synaptic feedback, which is necessary for teaching errors by feedback alignment. As a result, a network with pre-aligned weights learns notably faster than a network without random noise training, even reaching a convergence speed comparable to that of a backpropagation algorithm. Sequential training with both random noise and data brings weights closer to synaptic feedback than training solely with data, enabling more precise credit assignment and faster learning. We also found that each readout probability approaches the chance level and that the effective dimensionality of weights decreases in a network pretrained with random noise. This pre-regularization allows the network to learn simple solutions of a low rank, reducing the generalization loss during subsequent training. This also enables the network robustly to generalize a novel, out-of-distribution dataset. Lastly, we confirmed that random noise pretraining reduces the amount of meta-loss, enhancing the network ability to adapt to various tasks. Overall, our results suggest that random noise training with feedback alignment offers a straightforward yet effective method of pretraining that facilitates quick and reliable learning without weight transport.

This paper demonstrates the integration of Reinforcement Learning (RL) into quantum transpiling workflows, significantly enhancing the synthesis and routing of quantum circuits. By employing RL, we achieve near-optimal synthesis of Linear Function, Clifford, and Permutation circuits, up to 9, 11 and 65 qubits respectively, while being compatible with native device instruction sets and connectivity constraints, and orders of magnitude faster than optimization methods such as SAT solvers. We also achieve significant reductions in two-qubit gate depth and count for circuit routing up to 133 qubits with respect to other routing heuristics such as SABRE. We find the method to be efficient enough to be useful in practice in typical quantum transpiling pipelines. Our results set the stage for further AI-powered enhancements of quantum computing workflows.

Digital identity is evolving from centralized systems to a decentralized approach known as Self-Sovereign Identity (SSI). SSI empowers individuals to control their digital identities, eliminating reliance on third-party data custodians and reducing the risk of data breaches. However, the concept of trust in SSI remains complex and fragmented. This paper systematically analyzes trust in SSI in light of its components and threats posed by various actors in the system. As a result, we derive three distinct trust models that capture the threats and mitigations identified across SSI literature and implementations. Our work provides a foundational framework for future SSI research and development, including a comprehensive catalogue of SSI components and design requirements for trust, shortcomings in existing SSI systems and areas for further exploration., Comment: Accepted at PETS'24 Issue 3

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator initially estimates the logging policy and then estimates the value function model by minimizing the asymptotic variance of the estimator while considering the estimating effect of the logging policy. When the logging policy model is correctly specified, DRUnknown achieves the smallest asymptotic variance within the class containing existing OPE estimators. When the value function model is also correctly specified, DRUnknown is optimal as its asymptotic variance reaches the semiparametric lower bound. We present experimental results conducted in contextual bandits and reinforcement learning to compare the performance of DRUnknown with that of existing methods.

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text generation from LLMs. However, how the outputs from RAG-based LLMs are affected by slightly different inputs is not well studied. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We systematically evaluate the effect of such prefixes on RAG by introducing a novel optimization technique called Gradient Guided Prompt Perturbation (GGPP). GGPP achieves a high success rate in steering outputs of RAG-based LLMs to targeted wrong answers. It can also cope with instructions in the prompts requesting to ignore irrelevant context. We also exploit LLMs' neuron activation difference between prompts with and without GGPP perturbations to give a method that improves the robustness of RAG-based LLMs through a highly effective detector trained on neuron activation triggered by GGPP generated prompts. Our evaluation on open-sourced LLMs demonstrates the effectiveness of our methods., Comment: 12 pages, 9 figures

The Incremental Potential Contact (IPC) method enables robust complex simulations of deformable objects with contact and friction. The key to IPC's robustness is its strict adherence to geometric constraints, avoiding intersections, which are a common cause of robustness issues in contact mechanics. A key element of the IPC approach to contact is a geometric barrier function, which is defined directly in the discrete setting. While IPC achieves its main goal of providing guarantees for contact constraints, its parameters need to be chosen carefully to avoid significant simulation artifacts and inaccuracies. We present a systematic derivation of an IPC-like continuum potential defined for smooth and piecewise smooth surfaces, starting from identifying a set of natural requirements for contact potentials, including the barrier property, locality, differentiable dependence of shape, and absence of forces in rest configurations, based on the idea of candidate sets. Our potential is formulated in a way independent of surface discretization. This new potential is suitable for piecewise-linear surfaces and its efficiency is similar to standard IPC. We demonstrate its behavior and compare it to IPC on a range of challenging contact examples.

Skyrmions and antiskyrmions are nanoscale swirling textures of magnetic moments formed by chiral interactions between atomic spins in magnetic non-centrosymmetric materials and multilayer films with broken inversion symmetry. These quasiparticles are of interest for use as information carriers in next-generation, low-energy spintronic applications. To develop skyrmion-based memory and logic, we must understand skyrmion-defect interactions with two main goals -- determining how skyrmions navigate intrinsic material defects and determining how to engineer disorder for optimal device operation. Here, we introduce a tunable means of creating a skyrmion-antiskyrmion system by engineering the disorder landscape in FeGe using ion irradiation. Specifically, we irradiate epitaxial B20-phase FeGe films with 2.8 MeV Au$^{4+}$ ions at varying fluences, inducing amorphous regions within the crystalline matrix. Using low-temperature electrical transport and magnetization measurements, we observe a strong topological Hall effect with a double-peak feature that serves as a signature of skyrmions and antiskyrmions. These results are a step towards the development of information storage devices that use skyrmions and anitskyrmions as storage bits and our system may serve as a testbed for theoretically predicted phenomena in skyrmion-antiskyrmion crystals.

Millions of people have died worldwide from COVID-19. In addition to its high death toll, COVID-19 has led to unbearable suffering for individuals and a huge global burden to the healthcare sector. Therefore, researchers have been trying to develop tools to detect symptoms of this human-transmissible disease remotely to control its rapid spread. Coughing is one of the common symptoms that researchers have been trying to detect objectively from smartphone microphone-sensing. While most of the approaches to detect and track cough symptoms rely on machine learning models developed from a large amount of patient data, this is not possible at the early stage of an outbreak. In this work, we present an incremental transfer learning approach that leverages the relationship between healthy peoples' coughs and COVID-19 patients' coughs to detect COVID-19 coughs with reasonable accuracy using a pre-trained healthy cough detection model and a relatively small set of patient coughs, reducing the need for large patient dataset to train the model. This type of model can be a game changer in detecting the onset of a novel respiratory virus., Comment: This paper has been accepted to publish at EAI International Conference on Wireless Mobile Communication and Healthcare (MobiHealth'23)

Energy disaggregation techniques, which use smart meter data to infer appliance energy usage, can provide consumers and energy companies valuable insights into energy management. However, these techniques also present privacy risks, such as the potential for behavioral profiling. Local differential privacy (LDP) methods provide strong privacy guarantees with high efficiency in addressing privacy concerns. However, existing LDP methods focus on protecting aggregated energy consumption data rather than individual appliances. Furthermore, these methods do not consider the fact that smart meter data are a form of streaming data, and its processing methods should account for time windows. In this paper, we propose a novel LDP approach (named LDP-SmartEnergy) that utilizes randomized response techniques with sliding windows to facilitate the sharing of appliance-level energy consumption data over time while not revealing individual users' appliance usage patterns. Our evaluations show that LDP-SmartEnergy runs efficiently compared to baseline methods. The results also demonstrate that our solution strikes a balance between protecting privacy and maintaining the utility of data for effective analysis., Comment: 18 pages, 9 figures

Accreting supermassive black holes (SMBHs) produce highly magnetized relativistic jets that tend to collimate gradually as they propagate outward. However, recent radio interferometric observations of the 3C 84 galaxy reveal a stunning, cylindrical jet already at several hundred SMBH gravitational radii, $r\gtrsim350r_{\rm g}$. We explore how such extreme collimation emerges via a suite of 3D general-relativistic magnetohydrodynamic (GRMHD) simulations. We consider an SMBH surrounded by a magnetized torus immersed in a constant-density ambient medium that starts at the edge of the SMBH sphere of influence, chosen to be much larger than the SMBH gravitational radius, $r_{\text{B}}=10^3r_{\text{g}}$. We find that radiatively inefficient accretion flows (e.g., M87) produce winds that collimate the jets into parabolas near the BH. After the disk winds stop collimating the jets at $r\lesssim{}r_\text{B}$, they turn conical. Once outside $r_\text{B}$, the jets run into the ambient medium and form backflows that collimate the jets into cylinders some distance beyond $r_{\text{B}}$. Interestingly, for radiatively-efficient accretion, as in 3C 84, the radiative cooling saps the energy out of the disk winds: at early times, they cannot efficiently collimate the jets, which skip the initial parabolic collimation stage, start out conical near the SMBH, and turn into cylinders already at $r\simeq300r_{\rm g}$, as observed in 3C 84. Over time, jet power remains approximately constant, whereas the mass accretion rate increases: the winds grow in strength and start to collimate the jets, which become quasi-parabolic near the base; the transition point to a nearly cylindrical jet profile moves outward while remaining inside $r_\text{B}$., Comment: Submitted to ApJL; comments are welcome. 13 pages, 5 figures, uses aastex631. Movies available at https://www.youtube.com/playlist?list=PLvffyB6zGl7TEkAw-VaBfvrqWhVAerhZI

Maximum mean discrepancy (MMD) refers to a general class of nonparametric two-sample tests that are based on maximizing the mean difference over samples from one distribution $P$ versus another $Q$, over all choices of data transformations $f$ living in some function space $\mathcal{F}$. Inspired by recent work that connects what are known as functions of $\textit{Radon bounded variation}$ (RBV) and neural networks (Parhi and Nowak, 2021, 2023), we study the MMD defined by taking $\mathcal{F}$ to be the unit ball in the RBV space of a given smoothness order $k \geq 0$. This test, which we refer to as the $\textit{Radon-Kolmogorov-Smirnov}$ (RKS) test, can be viewed as a generalization of the well-known and classical Kolmogorov-Smirnov (KS) test to multiple dimensions and higher orders of smoothness. It is also intimately connected to neural networks: we prove that the witness in the RKS test -- the function $f$ achieving the maximum mean difference -- is always a ridge spline of degree $k$, i.e., a single neuron in a neural network. This allows us to leverage the power of modern deep learning toolkits to (approximately) optimize the criterion that underlies the RKS test. We prove that the RKS test has asymptotically full power at distinguishing any distinct pair $P \not= Q$ of distributions, derive its asymptotic null distribution, and carry out extensive experiments to elucidate the strengths and weakenesses of the RKS test versus the more traditional kernel MMD test.