The parallels between protein sequences and natural language in their sequential structures have inspired the application of large language models (LLMs) to protein understanding. Despite the success of LLMs in NLP, their effectiveness in comprehending protein sequences remains an open question, largely due to the absence of datasets linking protein sequences to descriptive text. Researchers have then attempted to adapt LLMs for protein understanding by integrating a protein sequence encoder with a pre-trained LLM. However, this adaptation raises a fundamental question: "Can LLMs, originally designed for NLP, effectively comprehend protein sequences as a form of language?" Current datasets fall short in addressing this question due to the lack of a direct correlation between protein sequences and corresponding text descriptions, limiting the ability to train and evaluate LLMs for protein understanding effectively. To bridge this gap, we introduce ProteinLMDataset, a dataset specifically designed for further self-supervised pretraining and supervised fine-tuning (SFT) of LLMs to enhance their capability for protein sequence comprehension. Specifically, ProteinLMDataset includes 17.46 billion tokens for pretraining and 893,000 instructions for SFT. Additionally, we present ProteinLMBench, the first benchmark dataset consisting of 944 manually verified multiple-choice questions for assessing the protein understanding capabilities of LLMs. ProteinLMBench incorporates protein-related details and sequences in multiple languages, establishing a new standard for evaluating LLMs' abilities in protein comprehension. The large language model InternLM2-7B, pretrained and fine-tuned on the ProteinLMDataset, outperforms GPT-4 on ProteinLMBench, achieving the highest accuracy score.
相關內容
Gait asymmetry, a consequence of various neurological or physical conditions such as aging and stroke, detrimentally impacts bipedal locomotion, causing biomechanical alterations, increasing the risk of falls and reducing quality of life. Addressing this critical issue, this paper introduces a novel diagnostic method for gait symmetry analysis through the use of an assistive robotic Smart Walker equipped with an innovative asymmetry detection scheme. This method analyzes sensor measurements capturing the interaction torque between user and walker. By applying a seasonal-trend decomposition tool, we isolate gait-specific patterns within these data, allowing for the estimation of stride durations and calculation of a symmetry index. Through experiments involving 5 experimenters, we demonstrate the Smart Walker's capability in detecting and quantifying gait asymmetry by achieving an accuracy of 84.9% in identifying asymmetric cases in a controlled testing environment. Further analysis explores the classification of these asymmetries based on their underlying causes, providing valuable insights for gait assessment. The results underscore the potential of the device as a precise, ready-to-use monitoring tool for personalized rehabilitation, facilitating targeted interventions for enhanced patient outcomes.
The field of emotion recognition of conversation (ERC) has been focusing on separating sentence feature encoding and context modeling, lacking exploration in generative paradigms based on unified designs. In this study, we propose a novel approach, InstructERC, to reformulate the ERC task from a discriminative framework to a generative framework based on Large Language Models (LLMs). InstructERC makes three significant contributions: (1) it introduces a simple yet effective retrieval template module, which helps the model explicitly integrate multi-granularity dialogue supervision information. (2) We introduce two additional emotion alignment tasks, namely speaker identification and emotion prediction tasks, to implicitly model the dialogue role relationships and future emotional tendencies in conversations. (3) Pioneeringly, we unify emotion labels across benchmarks through the feeling wheel to fit real application scenarios. InstructERC still perform impressively on this unified dataset. Our LLM-based plugin framework significantly outperforms all previous models and achieves comprehensive SOTA on three commonly used ERC datasets. Extensive analysis of parameter-efficient and data-scaling experiments provides empirical guidance for applying it in practical scenarios.
We propose a novel learning framework for Koopman operator of nonlinear dynamical systems that is informed by the governing equation and guarantees long-time stability and robustness to noise. In contrast to existing frameworks where either ad-hoc observables or blackbox neural networks are used to construct observables in the extended dynamic mode decomposition (EDMD), our observables are informed by governing equations via Polyflow. To improve the noise robustness and guarantee long-term stability, we designed a stable parameterization of the Koopman operator together with a progressive learning strategy for roll-out recurrent loss. To further improve model performance in the phase space, a simple iterative strategy of data augmentation was developed. Numerical experiments of prediction and control of classic nonlinear systems with ablation study showed the effectiveness of the proposed techniques over several state-of-the-art practices.
Plasma instabilities are a major concern in plasma science, for applications ranging from particle accelerators to nuclear fusion reactors. In this work, we consider the possibility of controlling such instabilities by adding an external electric field to the Vlasov--Poisson equations. Our approach to determining the external electric field is based on conducting a linear analysis of the resulting equations. We show that it is possible to select external electric fields that completely suppress the plasma instabilities present in the system when the equilibrium distribution and the perturbation are known. In fact, the proposed strategy returns the plasma to its equilibrium with a rate that is faster than exponential in time. We further perform numerical simulations of the nonlinear two-stream and bump-on-tail instabilities to verify our theory and to compare the different strategies that we propose in this work.
We consider a graph coloring algorithm that processes vertices in order taken uniformly at random and assigns colors to them using First-Fit strategy. We show that this algorithm uses, in expectation, at most $(1 + o(1))\cdot \ln n \,/\, \ln\ln n$ different colors to color any forest with $n$ vertices. We also construct a family of forests that shows that this bound is best possible.
Digital twins (DTs), which are virtual environments that simulate, predict, and optimize the performance of their physical counterparts, hold great promise in revolutionizing next-generation wireless networks. While DTs have been extensively studied for wireless networks, their use in conjunction with autonomous vehicles featuring programmable mobility remains relatively under-explored. In this paper, we study DTs used as a development environment to design, deploy, and test artificial intelligence (AI) techniques that utilize real-world (RW) observations, e.g. radio key performance indicators, for vehicle trajectory and network optimization decisions in autonomous vehicle networks (AVN). We first compare and contrast the use of simulation, digital twin (software in the loop (SITL)), sandbox (hardware-in-the-loop (HITL)), and physical testbed (PT) environments for their suitability in developing and testing AI algorithms for AVNs. We then review various representative use cases of DTs for AVN scenarios. Finally, we provide an example from the NSF AERPAW platform where a DT is used to develop and test AI-aided solutions for autonomous unmanned aerial vehicles for localizing a signal source based solely on link quality measurements. Our results in the physical testbed show that SITL DTs, when supplemented with data from RW measurements and simulations, can serve as an ideal environment for developing and testing innovative AI solutions for AVNs.
Recently, numerous methods have achieved impressive performance in remote sensing object detection, relying on convolution or transformer architectures. Such detectors typically have a feature backbone to extract useful features from raw input images. For the remote sensing domain, a common practice among current detectors is to initialize the backbone with pre-training on ImageNet consisting of natural scenes. Fine-tuning the backbone is then typically required to generate features suitable for remote-sensing images. However, this could hinder the extraction of basic visual features in long-term training, thus restricting performance improvement. To mitigate this issue, we propose a novel method named DBF (Dynamic Backbone Freezing) for feature backbone fine-tuning on remote sensing object detection. Our method aims to handle the dilemma of whether the backbone should extract low-level generic features or possess specific knowledge of the remote sensing domain, by introducing a module called 'Freezing Scheduler' to dynamically manage the update of backbone features during training. Extensive experiments on DOTA and DIOR-R show that our approach enables more accurate model learning while substantially reducing computational costs. Our method can be seamlessly adopted without additional effort due to its straightforward design.
We develop a theory of evolutionary spectra for heteroskedasticity and autocorrelation robust (HAR) inference when the data may not satisfy second-order stationarity. Nonstationarity is a common feature of economic time series which may arise either from parameter variation or model misspecification. In such a context, the theories that support HAR inference are either not applicable or do not provide accurate approximations. HAR tests standardized by existing long-run variance estimators then may display size distortions and little or no power. This issue can be more severe for methods that use long bandwidths (i.e., fixed-b HAR tests). We introduce a class of nonstationary processes that have a time-varying spectral representation which evolves continuously except at a finite number of time points. We present an extension of the classical heteroskedasticity and autocorrelation consistent (HAC) estimators that applies two smoothing procedures. One is over the lagged autocovariances, akin to classical HAC estimators, and the other is over time. The latter element is important to flexibly account for nonstationarity. We name them double kernel HAC (DK-HAC) estimators. We show the consistency of the estimators and obtain an optimal DK-HAC estimator under the mean squared error (MSE) criterion. Overall, HAR tests standardized by the proposed DK-HAC estimators are competitive with fixed-b HAR tests, when the latter work well, with regards to size control even when there is strong dependence. Notably, in those empirically relevant situations in which previous HAR tests are undersized and have little or no power, the DK-HAC estimator leads to tests that have good size and power.
The remarkable achievements of ChatGPT and GPT-4 have sparked a wave of interest and research in the field of large language models for Artificial General Intelligence (AGI). These models provide us with intelligent solutions that are more similar to human thinking, enabling us to use general artificial intelligence to solve problems in various applications. However, in the field of remote sensing, the scientific literature on the implementation of AGI remains relatively scant. Existing AI-related research primarily focuses on visual understanding tasks while neglecting the semantic understanding of the objects and their relationships. This is where vision-language models excel, as they enable reasoning about images and their associated textual descriptions, allowing for a deeper understanding of the underlying semantics. Vision-language models can go beyond recognizing the objects in an image and can infer the relationships between them, as well as generate natural language descriptions of the image. This makes them better suited for tasks that require both visual and textual understanding, such as image captioning, text-based image retrieval, and visual question answering. This paper provides a comprehensive review of the research on vision-language models in remote sensing, summarizing the latest progress, highlighting the current challenges, and identifying potential research opportunities. Specifically, we review the application of vision-language models in several mainstream remote sensing tasks, including image captioning, text-based image generation, text-based image retrieval, visual question answering, scene classification, semantic segmentation, and object detection. For each task, we briefly describe the task background and review some representative works. Finally, we summarize the limitations of existing work and provide some possible directions for future development.
Molecular design and synthesis planning are two critical steps in the process of molecular discovery that we propose to formulate as a single shared task of conditional synthetic pathway generation. We report an amortized approach to generate synthetic pathways as a Markov decision process conditioned on a target molecular embedding. This approach allows us to conduct synthesis planning in a bottom-up manner and design synthesizable molecules by decoding from optimized conditional codes, demonstrating the potential to solve both problems of design and synthesis simultaneously. The approach leverages neural networks to probabilistically model the synthetic trees, one reaction step at a time, according to reactivity rules encoded in a discrete action space of reaction templates. We train these networks on hundreds of thousands of artificial pathways generated from a pool of purchasable compounds and a list of expert-curated templates. We validate our method with (a) the recovery of molecules using conditional generation, (b) the identification of synthesizable structural analogs, and (c) the optimization of molecular structures given oracle functions relevant to drug discovery.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191