While Large Language Models (LLMs) have demonstrated enhanced capabilities in function-calling, these advancements primarily rely on accessing the functions' responses. This methodology is practical for simpler APIs but faces scalability issues with irreversible APIs that significantly impact the system, such as a database deletion API. Similarly, processes requiring extensive time for each API call and those necessitating forward planning, like automated action pipelines, present complex challenges. Furthermore, scenarios often arise where a generalized approach is needed because algorithms lack direct access to the specific implementations of these functions or secrets to use them. Traditional tool planning methods are inadequate in these cases, compelling the need to operate within black-box environments. Unlike their performance in tool manipulation, LLMs excel in black-box tasks, such as program synthesis. Therefore, we harness the program synthesis capabilities of LLMs to strategize tool usage in black-box settings, ensuring solutions are verified prior to implementation. We introduce TOPGUN, an ingeniously crafted approach leveraging program synthesis for black box tool planning. Accompanied by SwissNYF, a comprehensive suite that integrates black-box algorithms for planning and verification tasks, addressing the aforementioned challenges and enhancing the versatility and effectiveness of LLMs in complex API interactions. The public code for SwissNYF is available at https://github.com/iclr-dummy-user/SwissNYF.
This paper addresses the difficulty of characterizing the time-varying nature of fading channels. The current time-invariant models often fall short of capturing and tracking these dynamic characteristics. To overcome this limitation, we explore using of stochastic differential equations (SDEs) and Markovian projection to model signal envelope variations, considering scenarios involving Rayleigh, Rice, and Hoyt distributions. Furthermore, it is of practical interest to study the performance of channels modeled by SDEs. In this work, we investigate the fade duration metric, representing the time during which the signal remains below a specified threshold within a fixed time interval. We estimate the complementary cumulative distribution function (CCDF) of the fade duration using Monte Carlo simulations, and analyze the influence of system parameters on its behavior. Finally, we leverage importance sampling, a known variance-reduction technique, to estimate the tail of the CCDF efficiently.
Medical imaging is nowadays a pillar in diagnostics and therapeutic follow-up. Current research tries to integrate established - but ionizing - tomographic techniques with technologies offering reduced radiation exposure. Diffuse Optical Tomography (DOT) uses non-ionizing light in the Near-Infrared (NIR) window to reconstruct optical coefficients in living beings, providing functional indications about the composition of the investigated organ/tissue. Due to predominant light scattering at NIR wavelengths, DOT reconstruction is, however, a severely ill-conditioned inverse problem. Conventional reconstruction approaches show severe weaknesses when dealing also with mildly complex cases and/or are computationally very intensive. In this work we explore deep learning techniques for DOT inversion. Namely, we propose a fully data-driven approach based on a modularity concept: first data and originating signal are separately processed via autoencoders, then the corresponding low-dimensional latent spaces are connected via a bridging network which acts at the same time as a learned regularizer.
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization. Despite achieving better flatness, existing WA methods might fall into worse final performances or require extra test-time computations. This work unveils the full potential of EMA with a single line of modification, i.e., switching the EMA parameters to the original model after each epoch, dubbed as Switch EMA (SEMA). From both theoretical and empirical aspects, we demonstrate that SEMA can help DNNs to reach generalization optima that better trade-off between flatness and sharpness. To verify the effectiveness of SEMA, we conduct comparison experiments with discriminative, generative, and regression tasks on vision and language datasets, including image classification, self-supervised learning, object detection and segmentation, image generation, video prediction, attribute regression, and language modeling. Comprehensive results with popular optimizers and networks show that SEMA is a free lunch for DNN training by improving performances and boosting convergence speeds.
Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several static analysis-based contributors to pipelines that involve neural networks. This change allows the proposal of longer code suggestions while maintaining the relatively short time spent on generation itself. At JetBrains, we put a lot of effort into perfecting the code completion workflow so it can be both helpful and non-distracting for a programmer. We managed to ship the Full Line Code Completion feature to PyCharm Pro IDE and proved its usefulness in A/B testing on hundreds of real Python users. The paper describes our approach to context composing for the Transformer model that is a core of the feature's implementation. In addition to that, we share our next steps to improve the feature and emphasize the importance of several research aspects in the area.
Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using spiking signals on general-purpose computing platforms remains inefficient. In this paper, we propose a novel framework leveraging stochastic computing (SC) to effectively execute the dot-product attention for SNN-based Transformers. We demonstrate that our approach can achieve high classification accuracy ($83.53\%$) on CIFAR-10 within 10 time steps, which is comparable to the performance of a baseline artificial neural network implementation ($83.66\%$). We estimate that the proposed SC approach can lead to over $6.3\times$ reduction in computing energy and $1.7\times$ reduction in memory access costs for a digital CMOS-based ASIC design. We experimentally validate our stochastic attention block design through an FPGA implementation, which is shown to achieve $48\times$ lower latency as compared to a GPU implementation, while consuming $15\times$ less power.
Integrated Sensing and Communications (ISAC) has been identified as a pillar usage scenario for the impending 6G era. Bi-static sensing, a major type of sensing in \ac{isac}, is promising to expedite ISAC in the near future, as it requires minimal changes to the existing network infrastructure. However, a critical challenge for bi-static sensing is clock asynchronism due to the use of different clocks at far separated transmitter and receiver. This causes the received signal to be affected by time-varying random phase offsets, severely degrading, or even failing, direct sensing. Considerable research attention has been directed toward addressing the clock asynchronism issue in bi-static sensing. In this white paper, we endeavor to fill the gap by providing an overview of the issue and existing techniques developed in an ISAC background. Based on the review and comparison, we also draw insights into the future research directions and open problems, aiming to nurture the maturation of bi-static sensing in ISAC.
The advent of deep-learning-based registration networks has addressed the time-consuming challenge in traditional iterative methods.However, the potential of current registration networks for comprehensively capturing spatial relationships has not been fully explored, leading to inadequate performance in large-deformation image registration.The pure convolutional neural networks (CNNs) neglect feature enhancement, while current Transformer-based networks are susceptible to information redundancy.To alleviate these issues, we propose a pyramid attention network (PAN) for deformable medical image registration.Specifically, the proposed PAN incorporates a dual-stream pyramid encoder with channel-wise attention to boost the feature representation.Moreover, a multi-head local attention Transformer is introduced as decoder to analyze motion patterns and generate deformation fields.Extensive experiments on two public brain magnetic resonance imaging (MRI) datasets and one abdominal MRI dataset demonstrate that our method achieves favorable registration performance, while outperforming several CNN-based and Transformer-based registration networks.Our code is publicly available at https://github.com/JuliusWang-7/PAN.
With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile devices and TVs. Existing PTQ schemes, however, consume considerable time and resources, which could be a bottleneck in real situations where frequent model updates and multiple hyper-parameter tunings are required. As a cost-effective alternative, one-shot PTQ schemes have been proposed. Still, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a very important feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while considering cross-layer dependency to preserve the attention score. Through extensive experiments on various language models and complexity analysis, we demonstrate that aespa is accurate and efficient in quantizing Transformer models.
Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis, distinguished by its focus on extensive input sequences, in contrast to the constrained lengths typical of traditional approaches. While longer sequences inherently convey richer information, potentially enhancing predictive precision, prevailing techniques often respond by escalating model complexity. These intricate models can inflate into millions of parameters, incorporating parameter-intensive elements like positional encodings, feed-forward networks and self-attention mechanisms. This complexity, however, leads to prohibitive model scale, particularly given the time series data's semantic simplicity. Motivated by the pursuit of parsimony, our research employs conditional correlation and auto-correlation as investigative tools, revealing significant redundancies within the input data. Leveraging these insights, we introduce the HDformer, a lightweight Transformer variant enhanced with hierarchical decomposition. This novel architecture not only inverts the prevailing trend toward model expansion but also accomplishes precise forecasting with drastically fewer computations and parameters. Remarkably, HDformer outperforms existing state-of-the-art LTSF models, while requiring over 99\% fewer parameters. Through this work, we advocate a paradigm shift in LTSF, emphasizing the importance to tailor the model to the inherent dynamics of time series data-a timely reminder that in the realm of LTSF, bigger is not invariably better.