Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases. Recent works have proposed methods to improve LLMs' long context capabilities by extending context windows and more sophisticated memory mechanisms. However, comprehensive benchmarks tailored for evaluating long context understanding are lacking. In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding. LongBench comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese). These tasks cover key long-text application areas including single-doc QA, multi-doc QA, summarization, few-shot learning, synthetic tasks, and code completion. All datasets in LongBench are standardized into a unified format, allowing for effortless automatic evaluation of LLMs. Upon comprehensive evaluation of 8 LLMs on LongBench, we find that: (1) Commercial model (GPT-3.5-Turbo-16k) outperforms other open-sourced models, but still struggles on longer contexts. (2) Scaled position embedding and fine-tuning on longer sequences lead to substantial improvement on long context understanding. (3) Context compression technique such as retrieval brings improvement for model with weak ability on long contexts, but the performance still lags behind models that have strong long context understanding capability. The code and datasets are available at https://github.com/THUDM/LongBench.

Recent advancements in artificial intelligence, such as computer vision and deep learning, have led to the emergence of numerous generative AI platforms, particularly for image generation. However, the application of AI-generated image tools in graphic design has not been extensively explored. This study conducted semi-structured interviews with seven designers of varying experience levels to understand their current usage, challenges, and future functional needs for AI-generated image tools in graphic design. As our findings suggest, AI tools serve as creative partners in design, enhancing human creativity, offering strategic insights, and fostering team collaboration and communication. The findings provide guiding recommendations for the future development of AI-generated image tools, aimed at helping engineers optimize these tools to better meet the needs of graphic designers.

This paper introduces a "proof of concept" for a new approach to assistive robotics, integrating edge computing with Natural Language Processing (NLP) and computer vision to enhance the interaction between humans and robotic systems. Our "proof of concept" demonstrates the feasibility of using large language models (LLMs) and vision systems in tandem for interpreting and executing complex commands conveyed through natural language. This integration aims to improve the intuitiveness and accessibility of assistive robotic systems, making them more adaptable to the nuanced needs of users with disabilities. By leveraging the capabilities of edge computing, our system has the potential to minimize latency and support offline capability, enhancing the autonomy and responsiveness of assistive robots. Experimental results from our implementation on a robotic arm show promising outcomes in terms of accurate intent interpretation and object manipulation based on verbal commands. This research lays the groundwork for future developments in assistive robotics, focusing on creating highly responsive, user-centric systems that can significantly improve the quality of life for individuals with disabilities.

Amyloid-$\beta$ (A$\beta$) plaques in conjunction with hyperphosphorylated tau proteins in the form of neurofibrillary tangles are the two neuropathological hallmarks of Alzheimer's disease (AD). In particular, the accumulation of A$\beta$ plaques, as evinced by the A/T/N (amyloid/tau/neurodegeneration) framework, marks the initial stage. Thus, the identification of individuals with A$\beta$ positivity could enable early diagnosis and potentially lead to more effective interventions. Deep learning methods relying mainly on amyloid PET images have been employed to this end. However, PET imaging has some disadvantages, including the need of radiotracers and expensive acquisitions. Hence, in this work, we propose a novel multimodal approach that integrates information from structural, functional, and diffusion MRI data to discriminate A$\beta$ status in the AD continuum. Our method achieved an accuracy of $0.762\pm0.04$. Furthermore, a \textit{post-hoc} explainability analysis (guided backpropagation) was performed to retrieve the brain regions that most influenced the model predictions. This analysis identified some key regions that were common across modalities, some of which were well-established AD-discriminative biomarkers and related to A$\beta$ deposition, such as the hippocampus, thalamus, precuneus, and cingulate gyrus. Hence, our study demonstrates the potential viability of MRI-based characterization of A$\beta$ status, paving the way for further research in this domain.

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: \href{https://github.com/howard-hou/VisualRWKV}{https://github.com/howard-hou/VisualRWKV}.

The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D segmentation. Segmentation is challenging with point cloud data due to substantial redundancy, fluctuating sample density and lack of apparent organization. The research area has a wide range of robotics applications, including intelligent vehicles, autonomous mapping and navigation. A number of researchers have introduced various methodologies and algorithms. Deep learning has been successfully used to a spectrum of 2D vision domains as a prevailing A.I. methods. However, due to the specific problems of processing point clouds with deep neural networks, deep learning on point clouds is still in its initial stages. This study examines many strategies that have been presented to 3D instance and semantic segmentation and gives a complete assessment of current developments in deep learning-based 3D segmentation. In these approaches benefits, draw backs, and design mechanisms are studied and addressed. This study evaluates the impact of various segmentation algorithms on competitiveness on various publicly accessible datasets, as well as the most often used pipelines, their advantages and limits, insightful findings and intriguing future research directions.

Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase powerful vision language (VL) performances by covering diverse tasks via natural language instructions. However, existing open-source LLVMs that perform comparably to closed-source LLVMs such as GPT-4V are often considered too large (e.g., 26B, 34B, and 110B parameters), having a larger number of layers. These large models demand costly, high-end resources for both training and inference. To address this issue, we present a new efficient LLVM family with 1.8B, 3.8B, and 7B LLM model sizes, Traversal of Layers (TroL), which enables the reuse of layers in a token-wise manner. This layer traversing technique simulates the effect of looking back and retracing the answering stream while increasing the number of forward propagation layers without physically adding more layers. We demonstrate that TroL employs a simple layer traversing approach yet efficiently outperforms the open-source LLVMs with larger model sizes and rivals the performances of the closed-source LLVMs with substantial sizes.

Recent research has explored how Language Models (LMs) can be used for feature representation and prediction in tabular machine learning tasks. This involves employing text serialization and supervised fine-tuning (SFT) techniques. Despite the simplicity of these techniques, significant gaps remain in our understanding of the applicability and reliability of LMs in this context. Our study assesses how emerging LM technologies compare with traditional paradigms in tabular machine learning and evaluates the feasibility of adopting similar approaches with these advanced technologies. At the data level, we investigate various methods of data representation and curation of serialized tabular data, exploring their impact on prediction performance. At the classification level, we examine whether text serialization combined with LMs enhances performance on tabular datasets (e.g. class imbalance, distribution shift, biases, and high dimensionality), and assess whether this method represents a state-of-the-art (SOTA) approach for addressing tabular machine learning challenges. Our findings reveal current pre-trained models should not replace conventional approaches.

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume that the labeled data is gold standard and 'perfect'. However, this can be violated in reality with issues such as mislabeling or ambiguity. We address this overlooked aspect and show the importance of investigating labeled data quality to improve any pseudo-labeling method. Specifically, we introduce a novel data characterization and selection framework called DIPS to extend pseudo-labeling. We select useful labeled and pseudo-labeled samples via analysis of learning dynamics. We demonstrate the applicability and impact of DIPS for various pseudo-labeling methods across an extensive range of real-world tabular and image datasets. Additionally, DIPS improves data efficiency and reduces the performance distinctions between different pseudo-labelers. Overall, we highlight the significant benefits of a data-centric rethinking of pseudo-labeling in real-world settings.

There has been a surge in the development of various Large Language Models (LLMs). However, text generation for languages other than English often faces significant challenges, including poor generation quality and the reduced computational performance due to the disproportionate representation of tokens in model's vocabulary. In this work, we address these issues and introduce Vikhr, a new state-of-the-art open-source instruction-tuned LLM designed specifically for the Russian language. Unlike previous efforts for Russian that utilize computationally inexpensive LoRA adapters on top of English-oriented models, Vikhr features an adapted tokenizer vocabulary and undergoes the continued pre-training and instruction tuning of all weights. This approach not only enhances the model's performance but also significantly improves its computational and contextual efficiency. The remarkable performance of Vikhr across various Russian-language benchmarks can also be attributed to our efforts in expanding instruction datasets and corpora for continued pre-training. Vikhr not only sets the new state of the art among open-source LLMs for Russian, but even outperforms some proprietary closed-source models on certain benchmarks. The model weights, instruction sets, and code are publicly available