Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner

Pre-trained foundation models have recently significantly progressed in structured table understanding and reasoning. However, despite advancements in areas such as table semantic understanding and table question answering, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. In this work, we address this research gap by employing VLLMs in a training-free reasoning paradigm. First, we design a benchmark with various hierarchical dimensions relevant to table recognition. Subsequently, we conduct in-depth evaluations using pre-trained VLLMs, finding that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from these findings, we propose the Neighbor-Guided Toolchain Reasoner (NGTR) framework, which is characterized by integrating multiple lightweight models for low-level visual processing operations aimed at mitigating issues with low-quality input images. Specifically, we utilize a neighbor retrieval mechanism to guide the generation of multiple tool invocation plans, transferring tool selection experiences from similar neighbors to the given input, thereby facilitating suitable tool selection. Additionally, we introduce a reflection module to supervise the tool invocation process. Extensive experiments on public table recognition datasets demonstrate that our approach significantly enhances the recognition capabilities of the vanilla VLLMs. We believe that the designed benchmark and the proposed NGTR framework could provide an alternative solution in table recognition.

TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models

Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification (MTSC). Effective adaptation of LLMs for MTSC necessitates informative data representations. Existing LLM-based methods directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs. Despite their effectiveness, we reveal that these methods conceal three inherent bottlenecks: (1) they struggle to encode temporal and channel-specific information in a lossless manner, both of which are critical components of multivariate time series; (2) it is much difficult to align the learned representation space with the semantic space of the LLMs; (3) they require task-specific retraining, which is both computationally expensive and labor-intensive. To bridge these gaps, we propose TableTime, which reformulates MTSC as a table understanding task. Specifically, TableTime introduces the following strategies: (1) convert multivariate time series into a tabular form, thus minimizing information loss to the greatest extent; (2) represent tabular time series in text format to achieve natural alignment with the semantic space of LLMs; (3) design a reasoning framework that integrates contextual text information, neighborhood assistance, multi-path inference and problem decomposition to enhance the reasoning ability of LLMs and realize zero-shot classification. Extensive experiments performed on 10 publicly representative datasets from UEA archive verify the superiorities of the TableTime.

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess the performance of LLMs across a spectrum of chemical tasks varying in type and complexity. However, existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks. Specifically, ChemEval identified 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks which are informed by open-source data and the data meticulously crafted by chemical experts, ensuring that the tasks have practical value and can effectively evaluate the capabilities of LLMs. In the experiment, we evaluate 12 mainstream LLMs on ChemEval under zero-shot and few-shot learning contexts, which included carefully selected demonstration examples and carefully designed prompts. The results show that while general LLMs like GPT-4 and Claude-3.5 excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge. Conversely, specialized LLMs exhibit enhanced chemical competencies, albeit with reduced literary comprehension. This suggests that LLMs have significant potential for enhancement when tackling sophisticated tasks in the field of chemistry. We believe our work will facilitate the exploration of their potential to drive progress in chemistry. Our benchmark and analysis will be available at {\color{blue} \url{https://github.com/USTC-StarTeam/ChemEval}}.

Temporal Prototype-Aware Learning for Active Voltage Control on Power Distribution Networks

Active Voltage Control (AVC) on the Power Distribution Networks (PDNs) aims to stabilize the voltage levels to ensure efficient and reliable operation of power systems. With the increasing integration of distributed energy resources, recent efforts have explored employing multi-agent reinforcement learning (MARL) techniques to realize effective AVC. Existing methods mainly focus on the acquisition of short-term AVC strategies, i.e., only learning AVC within the short-term training trajectories of a singular diurnal cycle. However, due to the dynamic nature of load demands and renewable energy, the operation states of real-world PDNs may exhibit significant distribution shifts across varying timescales (e.g., daily and seasonal changes). This can render those short-term strategies suboptimal or even obsolete when performing continuous AVC over extended periods. In this paper, we propose a novel temporal prototype-aware learning method, abbreviated as TPA, to learn time-adaptive AVC under short-term training trajectories. At the heart of TPA are two complementary components, namely multi-scale dynamic encoder and temporal prototype-aware policy, that can be readily incorporated into various MARL methods. The former component integrates a stacked transformer network to learn underlying temporal dependencies at different timescales of the PDNs, while the latter implements a learnable prototype matching mechanism to construct a dedicated AVC policy that can dynamically adapt to the evolving operation states. Experimental results on the AVC benchmark with different PDN sizes demonstrate that the proposed TPA surpasses the state-of-the-art counterparts not only in terms of control performance but also by offering model transferability. Our code is available at https://github.com/Canyizl/TPA-for-AVC.

Integration of cognitive tasks into artificial general intelligence test for large models

During the evolution of large models, performance evaluation is necessarily performed on the intermediate models to assess their capabilities, and on the well-trained model to ensure safety before practical application. However, current model evaluations mainly rely on specific tasks and datasets, lacking a united framework for assessing the multidimensional intelligence of large models. In this perspective, we advocate for a comprehensive framework of artificial general intelligence (AGI) test, aimed at fulfilling the testing needs of large language models and multi-modal large models with enhanced capabilities. The AGI test framework bridges cognitive science and natural language processing to encompass the full spectrum of intelligence facets, including crystallized intelligence, a reflection of amassed knowledge and experience; fluid intelligence, characterized by problem-solving and adaptive reasoning; social intelligence, signifying comprehension and adaptation within multifaceted social scenarios; and embodied intelligence, denoting the ability to interact with its physical environment. To assess the multidimensional intelligence of large models, the AGI test consists of a battery of well-designed cognitive tests adopted from human intelligence tests, and then naturally encapsulates into an immersive virtual community. We propose that the complexity of AGI testing tasks should increase commensurate with the advancements in large models. We underscore the necessity for the interpretation of test results to avoid false negatives and false positives. We believe that cognitive science-inspired AGI tests will effectively guide the targeted improvement of large models in specific dimensions of intelligence and accelerate the integration of large models into human society.