Search

Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window extending. In fact, anomalous behaviors harming long context extrapolation exist between Rotary Position Embedding (RoPE) and vanilla self-attention unveiled by our work. To address this issue, we propose a novel attention mechanism, CoCA (Collinear Constrained Attention). Specifically, we enforce a collinear constraint between $Q$ and $K$ to seamlessly integrate RoPE and self-attention. While only adding minimal computational and spatial complexity, this integration significantly enhances long context window extrapolation ability. We provide an optimized implementation, making it a drop-in replacement for any existing transformer-based models. Extensive experiments show that CoCA performs extraordinarily well in extending context windows. A CoCA-based GPT model, trained with a context length of 512, can seamlessly extend the context window up to 32K (60$\times$), without any fine-tuning. Additionally, by dropping CoCA in LLaMA-7B, we achieve extrapolation up to 32K within only 2K training length. Our code is publicly available at: https://github.com/codefuse-ai/Collinear-Constrained-Attention, Comment: 16 pages, 7 figures

Accurate dietary intake estimation is critical for informing policies and programs to support healthy eating, as malnutrition has been directly linked to decreased quality of life. However self-reporting methods such as food diaries suffer from substantial bias. Other conventional dietary assessment techniques and emerging alternative approaches such as mobile applications incur high time costs and may necessitate trained personnel. Recent work has focused on using computer vision and machine learning to automatically estimate dietary intake from food images, but the lack of comprehensive datasets with diverse viewpoints, modalities and food annotations hinders the accuracy and realism of such methods. To address this limitation, we introduce NutritionVerse-Synth, the first large-scale dataset of 84,984 photorealistic synthetic 2D food images with associated dietary information and multimodal annotations (including depth images, instance masks, and semantic masks). Additionally, we collect a real image dataset, NutritionVerse-Real, containing 889 images of 251 dishes to evaluate realism. Leveraging these novel datasets, we develop and benchmark NutritionVerse, an empirical study of various dietary intake estimation approaches, including indirect segmentation-based and direct prediction networks. We further fine-tune models pretrained on synthetic data with real images to provide insights into the fusion of synthetic and real data. Finally, we release both datasets (NutritionVerse-Synth, NutritionVerse-Real) on https://www.kaggle.com/nutritionverse/datasets as part of an open initiative to accelerate machine learning for dietary sensing., Comment: Corrections made to Tables 6, 7, and 8, and corrections made to Experiments Part C. Additional clarification made in Section 4

UAV (unmanned aerial vehicle) is rapidly gaining traction in various human activities and has become an integral component of the satellite-air-ground-sea (SAGS) integrated network. As high-speed moving objects, UAVs not only have extremely strict requirements for communication delay, but also cannot be maliciously controlled as a weapon by the attacker. Therefore, an efficient and secure communication method designed for UAV networks is necessary. We propose a communication mechanism ESCM. For high efficiency, ESCM provides a routing protocol based on the artificial bee colony (ABC) algorithm to accelerate communications between UAVs. Meanwhile, we use blockchain to guarantee the security of UAV networks. However, blockchain has unstable links in high-mobility networks resulting in low consensus efficiency and high communication overhead. Consequently, ESCM introduces digital twin (DT), which transforms the UAV network into a static network by mapping UAVs from the physical world into Cyberspace. This virtual UAV network is called CyberUAV. Then, in CyberUAV, we design a blockchain consensus based on network coding, named Proof of Network Coding (PoNC). Analysis and simulation show that the above modules in ESCM have advantages over existing schemes. Through ablation studies, we demonstrate that these modules are indispensable for efficient and secure communication of UAV networks.

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multi-task learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5x smaller), 259 GFLOPs (as much as >5x lower) and as much as >3.15x faster on a NVIDIA Jetson TX2 embedded processor., Comment: Accepted at CVPR-NAS 2023 Workshop

Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpreting visualization experiments. Our framework conceives two experiments with the same setup: one with behavioral agents (human subjects), and the other one with a hypothetical rational agent. A visualization is evaluated by comparing the expected performance of behavioral agents to that of a rational agent under different assumptions. Using recent visualization decision studies from the literature, we demonstrate how the framework can be used to pre-experimentally evaluate the experiment design by bounding the expected improvement in performance from having access to visualizations, and post-experimentally to deconfound errors of information extraction from errors of optimization, among other analyses.

We study the incentivized information acquisition problem, where a principal hires an agent to gather information on her behalf. Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal announces a scoring rule that specifies the payment, and then the agent then chooses an effort level that maximizes her own profit and reports the information. We study the online setting of such a problem from the principal's perspective, i.e., designing the optimal scoring rule by repeatedly interacting with the strategic agent. We design a provably sample efficient algorithm that tailors the UCB algorithm (Auer et al., 2002) to our model, which achieves a sublinear $T^{2/3}$-regret after $T$ iterations. Our algorithm features a delicate estimation procedure for the optimal profit of the principal, and a conservative correction scheme that ensures the desired agent's actions are incentivized. Furthermore, a key feature of our regret bound is that it is independent of the number of states of the environment., Comment: 35 pages, adding an impossible result (Lemma 3.2) with its proof in Section D.1

Magnetic field line curvature (FLC) scattering is a collisionless scattering mechanism that arises when a particle's gyro-radius is comparable to the magnetic field line's curvature radius, resulting in the breaking of the conservation of the first adiabatic invariant. Studies in recent years have explored the implications of FLC scattering on the precipitation of both ring current ions and radiation belt electrons. In this work, we first compare two previous FLC scattering coefficients using test particle calculations. Then, we systematically calculate diffusion coefficients from FLC scattering in radial and MLT directions for particles of various energy levels, as well as its sensitivity to the $Kp$ index. We find that the timescale of FLC scattering is sufficient to account for the sudden loss of MeV electrons near the geostationary orbit during disturbed times. Additionally, the decay time of ring current protons is on the order of hours to minutes, providing an explanation for the ring current decay throughout the recovery phase of magnetic storms. Lastly, we compare the effects of wave-particle resonant scattering and FLC scattering in the vicinity of the midnight equator. Our findings suggest that the impacts of FLC scattering on MeV electrons or hundreds keV protons with smaller pitch angle is comparable to, or even more significant than, the effects of whistler mode or EMIC wave resonant scattering. Our quantitative results should be useful to evaluate the importance of the effects of FLC scattering while modeling the dynamics of radiation belt and ring current.

This paper develops a framework for the design of scoring rules to optimally incentivize an agent to exert a multi-dimensional effort. This framework is a generalization to strategic agents of the classical knapsack problem (cf. Briest, Krysta, and V\"ocking, 2005, Singer, 2010) and it is foundational to applying algorithmic mechanism design to the classroom. The paper identifies two simple families of scoring rules that guarantee constant approximations to the optimal scoring rule. The truncated separate scoring rule is the sum of single dimensional scoring rules that is truncated to the bounded range of feasible scores. The threshold scoring rule gives the maximum score if reports exceed a threshold and zero otherwise. Approximate optimality of one or the other of these rules is similar to the bundling or selling separately result of Babaioff, Immorlica, Lucier, and Weinberg (2014). Finally, we show that the approximate optimality of the best of those two simple scoring rules is robust when the agent's choice of effort is made sequentially.