Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial neural networks (ANNs). To facilitate deployment on memory-constrained devices, numerous studies have explored SNN pruning. However, these efforts are hindered by challenges such as scalability challenges in more complex architectures and accuracy degradation. Amidst these challenges, the Lottery Ticket Hypothesis (LTH) emerges as a promising pruning strategy. It posits that within dense neural networks, there exist winning tickets or subnetworks that are sparser but do not compromise performance. To explore a more structure-sparse and energy-saving model, we investigate the unique synergy of SNNs with LTH and design two novel spiking winning tickets to push the boundaries of sparsity within SNNs. Furthermore, we introduce an innovative algorithm capable of simultaneously identifying both weight and patch-level winning tickets, enabling the achievement of sparser structures without compromising on the final model's performance. Through comprehensive experiments on both RGB-based and event-based datasets, we demonstrate that our spiking lottery ticket achieves comparable or superior performance even when the model structure is extremely sparse.
Large language models (LLMs) have revolutionized the landscape of Natural Language Processing systems, but are computationally expensive. To reduce the cost without sacrificing performance, previous studies have explored various approaches to harness the potential of Small Language Models (SLMs) as cost-effective alternatives to their larger counterparts. Driven by findings that SLMs and LLMs exhibit complementary strengths in a structured knowledge extraction task, this work presents a novel SLM/LLM routing framework designed to improve computational efficiency and enhance task performance. First, exemplar pools are created to represent the types of contexts where each LM provides a more reliable answer, leveraging a sentence embedding fine-tuned so that context similarity is close to dialogue state similarity. Then, during inference, the k-nearest exemplars to the testing instance are retrieved, and the instance is routed according to majority vote. In dialogue state tracking tasks, the proposed routing framework enhances performance substantially compared to relying solely on LLMs, while reducing the computational costs by over 50%.
In the evaluation of medical text generation, it is essential to scrutinize each piece of information and ensure the utmost accuracy of the evaluation. Existing evaluation metrics either focus on coarse-level evaluation that assigns one score for the whole generated output or rely on evaluation models trained on general domain, resulting in inaccuracies when adapted to the medical domain. To address these issues, we propose a set of factuality-centric evaluation aspects and design corresponding GPT-4-based metrics for medical text generation. We systematically compare these metrics with existing ones on clinical note generation and medical report summarization tasks, revealing low inter-metric correlation. A comprehensive human evaluation confirms that the proposed GPT-4-based metrics exhibit substantially higher agreement with human judgments than existing evaluation metrics. Our study contributes to the understanding of medical text generation evaluation and offers a more reliable alternative to existing metrics.
Training AI models has always been challenging, especially when there is a need for custom models to provide personalized services. Algorithm engineers often face a lengthy process to iteratively develop models tailored to specific business requirements, making it even more difficult for non-experts. The quest for high-quality and efficient model development, along with the emergence of Large Language Model (LLM) Agents, has become a key focus in the industry. Leveraging the powerful analytical, planning, and decision-making capabilities of LLM, we propose a TrainerAgent system comprising a multi-agent framework including Task, Data, Model and Server agents. These agents analyze user-defined tasks, input data, and requirements (e.g., accuracy, speed), optimizing them comprehensively from both data and model perspectives to obtain satisfactory models, and finally deploy these models as online service. Experimental evaluations on classical discriminative and generative tasks in computer vision and natural language processing domains demonstrate that our system consistently produces models that meet the desired criteria. Furthermore, the system exhibits the ability to critically identify and reject unattainable tasks, such as fantastical scenarios or unethical requests, ensuring robustness and safety. This research presents a significant advancement in achieving desired models with increased efficiency and quality as compared to traditional model development, facilitated by the integration of LLM-powered analysis, decision-making, and execution capabilities, as well as the collaboration among four agents. We anticipate that our work will contribute to the advancement of research on TrainerAgent in both academic and industry communities, potentially establishing it as a new paradigm for model development in the field of AI.
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-language models and can activate relevant tools based on users' inputs to fulfill real-world tasks. LLaVA-Plus is trained on multimodal instruction-following data to acquire the ability to use tools, covering visual understanding, generation, external knowledge retrieval, and compositions. Empirical results show that LLaVA-Plus outperforms LLaVA in existing capabilities and exhibits new ones. It is distinct in that the image query is directly grounded and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios.
Although remarkable progress has been achieved in preventing large language model (LLM) hallucinations using instruction tuning and retrieval augmentation, it remains challenging to measure the reliability of LLMs using human-crafted evaluation data which is not available for many tasks and domains and could suffer from data leakage. Inspired by adversarial machine learning, this paper aims to develop a method of automatically generating evaluation data by appropriately modifying existing data on which LLMs behave faithfully. Specifically, this paper presents AutoDebug, an LLM-based framework to use prompting chaining to generate transferable adversarial attacks in the form of question-answering examples. We seek to understand the extent to which these examples trigger the hallucination behaviors of LLMs. We implement AutoDebug using ChatGPT and evaluate the resulting two variants of a popular open-domain question-answering dataset, Natural Questions (NQ), on a collection of open-source and proprietary LLMs under various prompting settings. Our generated evaluation data is human-readable and, as we show, humans can answer these modified questions well. Nevertheless, we observe pronounced accuracy drops across multiple LLMs including GPT-4. Our experimental results show that LLMs are likely to hallucinate in two categories of question-answering scenarios where (1) there are conflicts between knowledge given in the prompt and their parametric knowledge, or (2) the knowledge expressed in the prompt is complex. Finally, we find that the adversarial examples generated by our method are transferable across all considered LLMs. The examples generated by a small model can be used to debug a much larger model, making our approach cost-effective.
The widespread utilization of smartphones has provided extensive availability to Inertial Measurement Units, providing a wide range of sensory data that can be advantageous for the detection of transportation modes. The objective of this study is to propose a novel end-to-end approach to effectively explore a reduced amount of sensory data collected from a smartphone to achieve accurate mode detection in common daily traveling activities. Our approach, called Feature Pyramid biLSTM (FPbiLSTM), is characterized by its ability to reduce the number of sensors required and processing demands, resulting in a more efficient modeling process without sacrificing the quality of the outcomes than the other current models. FPbiLSTM extends an existing CNN biLSTM model with the Feature Pyramid Network, leveraging the advantages of both shallow layer richness and deeper layer feature resilience for capturing temporal moving patterns in various transportation modes. It exhibits an excellent performance by employing the data collected from only three out of seven sensors, i.e. accelerometers, gyroscopes, and magnetometers, in the 2018 Sussex-Huawei Locomotion (SHL) challenge dataset, attaining a noteworthy accuracy of 95.1% and an F1-score of 94.7% in detecting eight different transportation modes.
ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the auxiliary model. Notably, this model, which is jointly trained with the main model, only serves to assist the training of the main model and is discarded post-training. This results in a substantial amount of training cost being expended in vain. To mitigate this issue, we propose Fast-ELECTRA, which leverages an existing language model as the auxiliary model. To construct a learning curriculum for the main model, we smooth its output distribution via temperature scaling following a descending schedule. Our approach rivals the performance of state-of-the-art ELECTRA-style pre-training methods, while significantly eliminating the computation and memory cost brought by the joint training of the auxiliary model. Our method also reduces the sensitivity to hyper-parameters and enhances the pre-training stability.
Although Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive skills in various domains, their ability for mathematical reasoning within visual contexts has not been formally examined. Equipping LLMs and LMMs with this capability is vital for general-purpose AI assistants and showcases promising potential in education, data analysis, and scientific discovery. To bridge this gap, we present MathVista, a benchmark designed to amalgamate challenges from diverse mathematical and visual tasks. We first taxonomize the key task types, reasoning skills, and visual contexts from the literature to guide our selection from 28 existing math-focused and visual question answering datasets. Then, we construct three new datasets, IQTest, FunctionQA, and PaperQA, to accommodate for missing types of visual contexts. The problems featured often require deep visual understanding beyond OCR or image captioning, and compositional reasoning with rich domain-specific tools, thus posing a notable challenge to existing models. We conduct a comprehensive evaluation of 11 prominent open-source and proprietary foundation models (LLMs, LLMs augmented with tools, and LMMs), and early experiments with GPT-4V. The best-performing model, Multimodal Bard, achieves only 58% of human performance (34.8% vs 60.3%), indicating ample room for further improvement. Given this significant gap, MathVista fuels future research in the development of general-purpose AI agents capable of tackling mathematically intensive and visually rich real-world tasks. Preliminary tests show that MathVista also presents challenges to GPT-4V, underscoring the benchmark's importance. The project is available at https://mathvista.github.io/.
Spiking Neural Network (SNN) as a brain-inspired strategy receives lots of attention because of the high-sparsity and low-power properties derived from its inherent spiking information state. To further improve the efficiency of SNN, some works declare that the Lottery Tickets (LTs) Hypothesis, which indicates that the Artificial Neural Network (ANN) contains a subnetwork without sacrificing the performance of the original network, also exists in SNN. However, the spiking information handled by SNN has a natural similarity and affinity with binarization in sparsification. Therefore, to further explore SNN efficiency, this paper focuses on (1) the presence or absence of LTs in the binary SNN, and (2) whether the spiking mechanism is a superior strategy in terms of handling binary information compared to simple model binarization. To certify these consumptions, a sparse training method is proposed to find Binary Weights Spiking Lottery Tickets (BinW-SLT) under different network structures. Through comprehensive evaluations, we show that BinW-SLT could attain up to +5.86% and +3.17% improvement on CIFAR-10 and CIFAR-100 compared with binary LTs, as well as achieve 1.86x and 8.92x energy saving compared with full-precision SNN and ANN.