Search

Recent approaches for visually-rich document understanding (VrDU) uses manually annotated semantic groups, where a semantic group encompasses all semantically relevant but not obviously grouped words. As OCR tools are unable to automatically identify such grouping, we argue that current VrDU approaches are unrealistic. We thus introduce a new variant of the VrDU task, real-world visually-rich document understanding (ReVrDU), that does not allow for using manually annotated semantic groups. We also propose a new method, ReLayout, compliant with the ReVrDU scenario, which learns to capture semantic grouping through arranging words and bringing the representations of words that belong to the potential same semantic group closer together. Our experimental results demonstrate the performance of existing methods is deteriorated with the ReVrDU task, while ReLayout shows superiour performance.

This paper presents a unified surface reconstruction and rendering framework for LiDAR-visual systems, integrating Neural Radiance Fields (NeRF) and Neural Distance Fields (NDF) to recover both appearance and structural information from posed images and point clouds. We address the structural visible gap between NeRF and NDF by utilizing a visible-aware occupancy map to classify space into the free, occupied, visible unknown, and background regions. This classification facilitates the recovery of a complete appearance and structure of the scene. We unify the training of the NDF and NeRF using a spatial-varying scale SDF-to-density transformation for levels of detail for both structure and appearance. The proposed method leverages the learned NDF for structure-aware NeRF training by an adaptive sphere tracing sampling strategy for accurate structure rendering. In return, NeRF further refines structural in recovering missing or fuzzy structures in the NDF. Extensive experiments demonstrate the superior quality and versatility of the proposed method across various scenarios. To benefit the community, the codes will be released at \url{https://github.com/hku-mars/M2Mapping}.

Large Language Models (LLMs) have demonstrated significant capabilities, particularly in the domain of question answering (QA). However, their effectiveness in QA is often undermined by the vagueness of user questions. To address this issue, we introduce single-round instance-level prompt optimization, referred to as question rewriter. By enhancing the intelligibility of human questions for black-box LLMs, our question rewriter improves the quality of generated answers. The rewriter is optimized using direct preference optimization based on feedback collected from automatic criteria for evaluating generated answers; therefore, its training does not require costly human annotations. The experiments across multiple black-box LLMs and long-form question answering (LFQA) datasets demonstrate the efficacy of our method. This paper provides a practical framework for training question rewriters and sets a precedent for future explorations in prompt optimization within LFQA tasks. Code is available at \url{https://github.com/3244we/Question-Rewriter}., Comment: 7 pages, 4 figures, 5 tables

Large language models (LLMs) have recently showcased remarkable capabilities, spanning a wide range of tasks and applications, including those in the medical domain. Models like GPT-4 excel in medical question answering but may face challenges in the lack of interpretability when handling complex tasks in real clinical settings. We thus introduce the diagnostic reasoning dataset for clinical notes (DiReCT), aiming at evaluating the reasoning ability and interpretability of LLMs compared to human doctors. It contains 511 clinical notes, each meticulously annotated by physicians, detailing the diagnostic reasoning process from observations in a clinical note to the final diagnosis. Additionally, a diagnostic knowledge graph is provided to offer essential knowledge for reasoning, which may not be covered in the training data of existing LLMs. Evaluations of leading LLMs on DiReCT bring out a significant gap between their reasoning ability and that of human doctors, highlighting the critical need for models that can reason effectively in real-world clinical scenarios., Comment: 9 pages,6 figures

At present, the study of the charm-quark Yukawa coupling at the Large Hadron Collider mainly restricts the coupling constant $y_c$ through the Higgs decay channels. Such signal suffers from overwhelming QCD background, and derives most sensitivity from the $Vh$ associated production channel. In addition, sensitivity to a possible CP complex term of $y_c$ is lost. We study the $ch$ associated production channel at the HL-LHC and FCC to probe the charm Yukawa coupling. By making use of the interference contribution among channels, and machine learning techniques to separate the different contributions, sensitivity on possible deviation from a standard model charm Yukawa coupling is derived. Under the $\kappa$ framework, a 1$\sigma$ projected bounds of $\kappa_c < 5.62$ (HL-LHC) and $-1.52 < \kappa_c < 1.62$ (FCC) are achieved. When further allowing for CP-structure for the charm Yukawa, and comparing with other complementary hadron collider signals, we reach projected bounds on the CP-odd and CP-even components of the charm Yukawa of $-2.46 < \tilde{\kappa_c} < 2.46$, $ 0.23 < \kappa_c < 1.74$ at the HL-LHC and $-1.05 < \tilde{\kappa_c} < 1.05$, $ 0.57 < \kappa_c < 1.28$ at the FCC., Comment: 19 pages, 6 figures, 4 tables

Measuring urban safety perception is an important and complex task that traditionally relies heavily on human resources. This process often involves extensive field surveys, manual data collection, and subjective assessments, which can be time-consuming, costly, and sometimes inconsistent. Street View Images (SVIs), along with deep learning methods, provide a way to realize large-scale urban safety detection. However, achieving this goal often requires extensive human annotation to train safety ranking models, and the architectural differences between cities hinder the transferability of these models. Thus, a fully automated method for conducting safety evaluations is essential. Recent advances in multimodal large language models (MLLMs) have demonstrated powerful reasoning and analytical capabilities. Cutting-edge models, e.g., GPT-4 have shown surprising performance in many tasks. We employed these models for urban safety ranking on a human-annotated anchor set and validated that the results from MLLMs align closely with human perceptions. Additionally, we proposed a method based on the pre-trained Contrastive Language-Image Pre-training (CLIP) feature and K-Nearest Neighbors (K-NN) retrieval to quickly assess the safety index of the entire city. Experimental results show that our method outperforms existing training needed deep learning approaches, achieving efficient and accurate urban safety evaluations. The proposed automation for urban safety perception assessment is a valuable tool for city planners, policymakers, and researchers aiming to improve urban environments., Comment: 13 pages, 9 figures

This paper investigates the issue of how to exploit target location distribution for multiple input multiple output (MIMO) radar waveform design. We consider a MIMO radar aiming to estimate the unknown and random angular location parameters of a point target, whose distribution information can be exploited by the radar. First, we establish the models of the MIMO radar system and the target location distribution. Based on the considered models, we propose the first category of target location distribution exploitation methods by analyzing the radar direction-of-angle (DoA) estimation performance and deriving a general form of posterior Cramer-Rao bound (PCRB) as the lower bound of the mean square error of DoA estimation. Following this, to explore more insights, we proposed the second category of target location distribution exploitation methods by introducing a novel radar metric, probability scaled beampattern (PSBP), from the perspective of radar beampattern. To compare the two methods, we formulate the PCRB and PSBP oriented radar waveform design problems and propose corresponding low-complexity and convergence-guaranteed algorithms to tackle them. Finally, numerical simulations are conducted in different scenarios to provide a comprehensive evaluation and comparison of the radar performance.

This paper proposes a cooperative integrated sensing and communication network (Co-ISACNet) adopting hybrid beamforming (HBF) architecture, which improves both radar sensing and communication performance. The main contributions of this work are four-fold. First, we introduce a novel cooperative sensing method for the considered Co-ISACNet, followed by a comprehensive analysis of this method. This analysis mathematically verifies the benefits of Co-ISACNet and provides insightful design guidelines. Second, to show the benefits of Co-ISACNet, we propose to jointly design the HBF to maximize the network communication capacity while satisfying the constraint of beampattern similarity for radar sensing, which results in a highly dimensional and non-convex problem. Third, to facilitate the joint design, we propose a novel distributed optimization framework based on proximal gradient and alternating direction method of multipliers, namely PANDA. Fourth, we further adopt the proposed PANDA framework to solve the joint HBF design problem for the Co-ISACNet. By using the proposed PANDA framework, all access points (APs) optimize the HBF in parallel, where each AP only requires local channel state information and limited message exchange among the APs. Such framework reduces significantly the computational complexity and thus has pronounced benefits in practical scenarios. Simulation results verify the effectiveness of the proposed algorithm compared with the conventional centralized algorithm and show the remarkable performance improvement of radar sensing and communication by deploying Co-ISACNet.

The imperative to comprehend the behaviors of deep learning models is of utmost importance. In this realm, Explainable Artificial Intelligence (XAI) has emerged as a promising avenue, garnering increasing interest in recent years. Despite this, most existing methods primarily depend on gradients or input perturbation, which often fails to embed explanations directly within the model's decision-making process. Addressing this gap, we introduce ESCOUTER, a visually explainable classifier based on the modified slot attention mechanism. ESCOUTER distinguishes itself by not only delivering high classification accuracy but also offering more transparent insights into the reasoning behind its decisions. It differs from prior approaches in two significant aspects: (a) ESCOUTER incorporates explanations into the final confidence scores for each category, providing a more intuitive interpretation, and (b) it offers positive or negative explanations for all categories, elucidating "why an image belongs to a certain category" or "why it does not." A novel loss function specifically for ESCOUTER is designed to fine-tune the model's behavior, enabling it to toggle between positive and negative explanations. Moreover, an area loss is also designed to adjust the size of the explanatory regions for a more precise explanation. Our method, rigorously tested across various datasets and XAI metrics, outperformed previous state-of-the-art methods, solidifying its effectiveness as an explanatory tool., Comment: 16 pages, 12 figures

CTBench is introduced as a benchmark to assess language models (LMs) in aiding clinical study design. Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demographic and relevant features collected at the trial's start from all participants. These baseline features, typically presented in CT publications (often as Table 1), are crucial for characterizing study cohorts and validating results. Baseline features, including confounders and covariates, are also necessary for accurate treatment effect estimation in studies involving observational data. CTBench consists of two datasets: "CT-Repo," containing baseline features from 1,690 clinical trials sourced from clinicaltrials.gov, and "CT-Pub," a subset of 100 trials with more comprehensive baseline features gathered from relevant publications. Two LM-based evaluation methods are developed to compare the actual baseline feature lists against LM-generated responses. "ListMatch-LM" and "ListMatch-BERT" use GPT-4o and BERT scores (at various thresholds), respectively, for evaluation. To establish baseline results, advanced prompt engineering techniques using LLaMa3-70B-Instruct and GPT-4o in zero-shot and three-shot learning settings are applied to generate potential baseline features. The performance of GPT-4o as an evaluator is validated through human-in-the-loop evaluations on the CT-Pub dataset, where clinical experts confirm matches between actual and LM-generated features. The results highlight a promising direction with significant potential for improvement, positioning CTBench as a useful tool for advancing research on AI in CT design and potentially enhancing the efficacy and robustness of CTs.

We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes GLM-4, GLM-4-Air, and GLM-4-9B. They represent our most capable models that are trained with all the insights and lessons gained from the preceding three generations of ChatGLM. To date, the GLM-4 models are pre-trained on ten trillions of tokens mostly in Chinese and English, along with a small set of corpus from 24 languages, and aligned primarily for Chinese and English usage. The high-quality alignment is achieved via a multi-stage post-training process, which involves supervised fine-tuning and learning from human feedback. Evaluations show that GLM-4 1) closely rivals or outperforms GPT-4 in terms of general metrics such as MMLU, GSM8K, MATH, BBH, GPQA, and HumanEval, 2) gets close to GPT-4-Turbo in instruction following as measured by IFEval, 3) matches GPT-4 Turbo (128K) and Claude 3 for long context tasks, and 4) outperforms GPT-4 in Chinese alignments as measured by AlignBench. The GLM-4 All Tools model is further aligned to understand user intent and autonomously decide when and which tool(s) touse -- including web browser, Python interpreter, text-to-image model, and user-defined functions -- to effectively complete complex tasks. In practical applications, it matches and even surpasses GPT-4 All Tools in tasks like accessing online information via web browsing and solving math problems using Python interpreter. Over the course, we have open-sourced a series of models, including ChatGLM-6B (three generations), GLM-4-9B (128K, 1M), GLM-4V-9B, WebGLM, and CodeGeeX, attracting over 10 million downloads on Hugging face in the year 2023 alone. The open models can be accessed through https://github.com/THUDM and https://huggingface.co/THUDM.

Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. However, traditional methods often struggle to capture the complex dynamics of meteorological systems, particularly in the presence of high-resolution data. In this paper, we propose the Spatial-Frequency Attention Network (SFANet), a novel deep learning framework designed to address these challenges and enhance the accuracy of spatiotemporal weather prediction. Drawing inspiration from the limitations of existing methodologies, we present an innovative approach that seamlessly integrates advanced token mixing and attention mechanisms. By leveraging both pooling and spatial mixing strategies, SFANet optimizes the processing of high-dimensional spatiotemporal sequences, preserving inter-component relational information and modeling extensive long-range relationships. To further enhance feature integration, we introduce a novel spatial-frequency attention module, enabling the model to capture intricate cross-modal correlations. Our extensive experimental evaluation on two distinct datasets, the Storm EVent ImageRy (SEVIR) and the Institute for Climate and Application Research (ICAR) - El Ni\~{n}o Southern Oscillation (ENSO) dataset, demonstrates the remarkable performance of SFANet. Notably, SFANet achieves substantial advancements over state-of-the-art methods, showcasing its proficiency in forecasting precipitation patterns and predicting El Ni\~{n}o events.

This paper investigates a hardware-efficient massive multiple-input multiple-output integrated sensing and communication (MIMO-ISAC) system with 1-bit analog-to-digital converters (ADCs)/digital-to-analog converters (DACs). The proposed system, referred to as 1BitISAC, employs 1-bit DACs at the ISAC transmitter and 1-bit ADCs at the sensing receiver, achieving significant reductions in power consumption and hardware costs. For such kind of systems, two 1BitISAC joint transceiver designs, i.e., i) quality of service constrained 1BitISAC design and ii) quality of detection constrained design, are considered and the corresponding problems are formulated. In order to address these problems, we thoroughly analyze the radar detection performance after 1-bit ADCs quantization and the communication bit error rate. This analysis yields new design insights and leads to unique radar and communication metrics, which enables us to simplify the original problems and employ majorization-minimization and integer linear programming methods to solve the problems. Numerical results are provided to validate the performance analysis of the proposed 1BitISAC and to compare with other ISAC configurations. The superiority of the proposed 1BitISAC system in terms of balancing ISAC performance and energy efficiency is also demonstrated.

This paper investigates the issues of the hybrid beamforming design for the orthogonal frequency division multiplexing dual-function radar-communication (DFRC) system in multiple task scenarios involving the radar scanning and detection task and the target tracking task. To meet different task requirements of the DFRC system, we introduce two novel radar beampattern metrics, the average integrated sidelobe to minimum mainlobe ratio (AISMMR) and average peak sidelobe to integrated mainlobe ratio (APSIMR), to characterize the space-frequency spectra in different scenarios. Then, two HBF design problems are formulated for two task scenarios by minimizing the AISMMR and APSIMR respectively subject to the constraints of communication quality-of-service (QoS), power budget, and hardware. Due to the non-linearity and close coupling between the analog and digital beamformers in both the objective functions and QoS constraint, the resultant formulated problems are challenging to solve. Towards that end, a unified optimization algorithm based on a consensus alternating direction method of multipliers (CADMM) is proposed to solve these two problems. Moreover, under the unified CADMM framework, the closed-form solutions of primal variables in the original two problems are obtained with low complexity. Numerical simulations are provided to demonstrate the feasibility and effectiveness of the proposed algorithm.

In this letter, we investigate enhancing the physical layer security (PLS) for the dual-function radar-communication (DFRC) system with hybrid beamforming (HBF) architecture, where the base station (BS) achieves downlink communication and radar target detection simultaneously. We consider an eavesdropper intercepting the information transmitted from the BS to the downlink communication users with imperfectly known channel state information. Additionally, the location of the radar target is also imperfectly known by the BS. To enhance PLS in the considered DFRC system, we propose a novel HBF architecture, which introduces a new integrated sensing and security (I2S) symbol. The secure HBF design problem for DFRC is formulated by maximizing the minimum legitimate user communication rate subject to radar signal-to-interference-plus-noise ratio, eavesdropping rate, hardware and power constraints. To solve this non-convex problem, we propose an alternating optimization based method to jointly optimize transmit and receive beamformers. Numerical simulation results validate the effectiveness of the proposed algorithm and show the superiority of the proposed I2S-aided HBF architecture for achieving DFRC and enhancing PLS.

In recent years, self-burrowing probes have been studied since they can be suitable for soil monitoring in locations with limited access such as outer space bodies and underneath existing structures. We study the performance of a self-burrowing probe under different gravity conditions, from low gravity (i.e., 1/6g, 1/3g and 1g) to high gravity (i.e., 5g, 10g and 15g), specifically in terms of penetration distance and energy consumption. Results show that the probe reaches efficient penetration in all gravity conditions and that it achieves larger penetration distances in high gravity conditions. However, the penetration efficiency, shown as unit energy per meter, is higher in low gravity. Additionally, we prove that a simple dimensional analysis provides reasonable scaling factors for first order effects in forces, velocities and energy. The findings in this study give confidence to the potential use of self-burrowing probes in campaigns of soil testing and sensor deployment in outer space or centrifuges in which the gravity conditions can differ from Earth.

The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to achieve efficient serving. In this work, we introduce a parallel auto-regressive generation method. By instruct-tuning on general domain data that contains hierarchical structures, we enable LLMs to independently plan their generation process and perform auto-parallel auto-regressive (APAR) generation, significantly reducing the number of generation steps. APAR alone can achieve up to 2x speed-up, and when combined with speculative decoding, the speed-up can reach up to 4x. In addition, APAR reduces the key-value cache consumption and attention computation during generation. This leads to a throughput increase of 20-70% and a latency reduce of 20-35% in high-throughput scenarios, compared to state-of-the-art serving frameworks., Comment: 14 pages

Voice command interfaces (VCIs) have gained increasing importance, enabling hands-free and eyes-free interaction with digital devices. However, the inherent complexity in constructing effective voice interfaces has limited the VCIs' functionalities to only a small fraction of GUI applications and tasks. This paper presents AutoTask, a VCI capable of automating any task in any mobile application without configuration or modification from developers or end users. The primary challenge for AutoTask is the lack of knowledge, as it needs to accomplish unknown tasks (e.g., user commands) within an unknown environment (e.g., GUI). To address this challenge, AutoTask employs two strategies: (1) trial and error: AutoTask explores the GUI, attempts potential operation sequences, and recovers from errors through backtracking; (2) learning from the environment: AutoTask accumulates experiences during exploration and summarizes correct knowledge from these experiences. We implemented AutoTask on Android devices and conducted an evaluation study, which proved the feasibility of AutoTask.

Visual prompting, an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a robust source model: Whether a visual prompt derived from a robust model can inherit the robustness while suffering from the generalization performance decline, albeit for a downstream dataset that is different from the source dataset? In this work, we get an affirmative answer of the above question and give an explanation on the visual representation level. Moreover, we introduce a novel technique named Prompt Boundary Loose (PBL) to effectively mitigates the suboptimal results of visual prompt on standard accuracy without losing (or even significantly improving) its adversarial robustness when using a robust model as source model. Extensive experiments across various datasets show that our findings are universal and demonstrate the significant benefits of our proposed method.

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models for different tasks by providing instructive prompts but without updating model parameters. This idea is now being explored in computer vision, where an input-output image pair (called an in-context pair) is supplied to the model with a query image as a prompt to exemplify the desired output. The efficacy of visual ICL often depends on the quality of the prompts. We thus introduce a method coined Instruct Me More (InMeMo), which augments in-context pairs with a learnable perturbation (prompt), to explore its potential. Our experiments on mainstream tasks reveal that InMeMo surpasses the current state-of-the-art performance. Specifically, compared to the baseline without learnable prompt, InMeMo boosts mIoU scores by 7.35 and 15.13 for foreground segmentation and single object detection tasks, respectively. Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training. Code is available at https://github.com/Jackieam/InMeMo., Comment: Accepted at WACV 2024

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. For the input sequence of video frames, CatMAE keeps the initial frame unchanged while applying substantial masking (95%) to subsequent frames. The encoder in CatMAE is responsible for encoding visible patches for each frame individually; subsequently, for each masked frame, the decoder leverages visible patches from both previous and current frames to reconstruct the original image. Our proposed method enables the model to estimate the motion information between visible patches, match the correspondences between preceding and succeeding frames, and ultimately learn the evolution of scenes. Furthermore, we propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets. This further encourages the model to utilize continuous motion details and correspondences to complete the reconstruction, thereby enhancing the model's capabilities. Compared to the most advanced pre-training methods, CatMAE achieves a leading level in video segmentation tasks and action recognition tasks., Comment: https://github.com/minhoooo1/CatMAE

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a resource-efficient solution to fine-tune the pre-trained language models (PLMs) while keeping their weight frozen. Existing soft prompt methods mainly focus on designing the input-independent prompts that steer the model to fit the domain of the new dataset. Those methods often ignore the fine-grained information about the task and context of the text. In this paper, we propose a multi-level prompt tuning (MPrompt) method for machine reading comprehension. It utilizes prompts at task-specific, domain-specific, and context-specific levels to enhance the comprehension of input semantics at different granularities. We also propose an independence constraint to steer each domain-specific prompt to focus on information within its domain to avoid redundancy. Moreover, we present a prompt generator that incorporates context-related knowledge in the prompt generation to enhance contextual relevancy. We conducted extensive experiments on 12 benchmarks of various QA formats and achieved an average improvement of 1.94\% over the state-of-the-art methods., Comment: 13 pages, 5 figures, accepted by EMNLP2023-Findings

Since ChatGPT released its API for public use, the number of applications built on top of commercial large language models (LLMs) increase exponentially. One popular usage of such models is leveraging its in-context learning ability and generating responses given user queries leveraging knowledge obtained by retrieval augmentation. One problem of deploying commercial retrieval-augmented LLMs is the cost due to the additionally retrieved context that largely increases the input token size of the LLMs. To mitigate this, we propose a token compression scheme that includes two methods: summarization compression and semantic compression. The first method applies a T5-based model that is fine-tuned by datasets generated using self-instruct containing samples with varying lengths and reduce token size by doing summarization. The second method further compresses the token size by removing words with lower impact on the semantic. In order to adequately evaluate the effectiveness of the proposed methods, we propose and utilize a dataset called Food-Recommendation DB (FRDB) focusing on food recommendation for women around pregnancy period or infants. Our summarization compression can reduce 65% of the retrieval token size with further 0.3% improvement on the accuracy; semantic compression provides a more flexible way to trade-off the token size with performance, for which we can reduce the token size by 20% with only 1.6% of accuracy drop., Comment: EMNLP 2023 Findings

Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world. These agent tasks employ LLMs as the central controller responsible for planning, memorization, and tool utilization, necessitating both fine-grained prompting methods and robust LLMs to achieve satisfactory performance. Though many prompting methods have been proposed to complete particular agent tasks, there is lack of research focusing on improving the agent capabilities of LLMs themselves without compromising their general abilities. In this work, we present AgentTuning, a simple and general method to enhance the agent abilities of LLMs while maintaining their general LLM capabilities. We construct AgentInstruct, a lightweight instruction-tuning dataset containing high-quality interaction trajectories. We employ a hybrid instruction-tuning strategy by combining AgentInstruct with open-source instructions from general domains. AgentTuning is used to instruction-tune the Llama 2 series, resulting in AgentLM. Our evaluations show that AgentTuning enables LLMs' agent capabilities without compromising general abilities. The AgentLM-70B is comparable to GPT-3.5-turbo on unseen agent tasks, demonstrating generalized agent capabilities. We open source the AgentInstruct and AgentLM-7B, 13B, and 70B models at https://github.com/THUDM/AgentTuning, serving open and powerful alternatives to commercial LLMs for agent tasks., Comment: 31 pages

Facade parsing stands as a pivotal computer vision task with far-reaching applications in areas like architecture, urban planning, and energy efficiency. Despite the recent success of deep learning-based methods in yielding impressive results on certain open-source datasets, their viability for real-world applications remains uncertain. Real-world scenarios are considerably more intricate, demanding greater computational efficiency. Existing datasets often fall short in representing these settings, and previous methods frequently rely on extra models to enhance accuracy, which requires much computation cost. In this paper, we introduce Comprehensive Facade Parsing (CFP), a dataset meticulously designed to encompass the intricacies of real-world facade parsing tasks. Comprising a total of 602 high-resolution street-view images, this dataset captures a diverse array of challenging scenarios, including sloping angles and densely clustered buildings, with painstakingly curated annotations for each image. We introduce a new pipeline known as Revision-based Transformer Facade Parsing (RTFP). This marks the pioneering utilization of Vision Transformers (ViT) in facade parsing, and our experimental results definitively substantiate its merit. We also design Line Acquisition, Filtering, and Revision (LAFR), an efficient yet accurate revision algorithm that can improve the segment result solely from simple line detection using prior knowledge of the facade. In ECP 2011, RueMonge 2014, and our CFP, we evaluate the superiority of our method., Comment: 13 pages, 7 figures, 9 tables

Sorting is fundamental and ubiquitous in modern computing systems. Hardware sorting systems are built based on comparison operations with Von Neumann architecture, but their performance are limited by the bandwidth between memory and comparison units and the performance of complementary metal-oxide-semiconductor (CMOS) based circuitry. Sort-in-memory (SIM) based on emerging memristors is desired but not yet available due to comparison operations that are challenging to be implemented within memristive memory. Here we report fast and reconfigurable SIM system enabled by digit read (DR) on 1-transistor-1-resistor (1T1R) memristor arrays. We develop DR tree node skipping (TNS) that support variable data quantity and data types, and extend TNS with multi-bank, bit-slice and multi-level strategies to enable cross-array TNS (CA-TNS) for practical adoptions. Experimented on benchmark sorting datasets, our memristor-enabled SIM system presents up to 3.32x~7.70x speedup, 6.23x~183.5x energy efficiency improvement and 2.23x~7.43x area reduction compared with state-of-the-art sorting systems. We apply such SIM system for shortest path search with Dijkstra's algorithm and neural network inference with in-situ pruning, demonstrating the capability in solving practical sorting tasks and the compatibility in integrating with other compute-in-memory (CIM) schemes. The comparison-free TNS/CA-TNS SIM enabled by memristors pushes sorting into a new paradigm of sort-in-memory for next-generation sorting systems., Comment: Submitted to Nature Electronics

With the increasing size of pre-trained language models (PLMs), fine-tuning all the parameters in the model is not efficient, especially when there are a large number of downstream tasks, which incur significant training and storage costs. Many parameter-efficient fine-tuning (PEFT) approaches have been proposed, among which, Low-Rank Adaptation (LoRA) is a representative approach that injects trainable rank decomposition matrices into every target module. Yet LoRA ignores the importance of parameters in different modules. To address this problem, many works have been proposed to prune the parameters of LoRA. However, under limited training conditions, the upper bound of the rank of the pruned parameter matrix is still affected by the preset values. We, therefore, propose IncreLoRA, an incremental parameter allocation method that adaptively adds trainable parameters during training based on the importance scores of each module. This approach is different from the pruning method as it is not limited by the initial number of training parameters, and each parameter matrix has a higher rank upper bound for the same training overhead. We conduct extensive experiments on GLUE to demonstrate the effectiveness of IncreLoRA. The results show that our method owns higher parameter efficiency, especially when under the low-resource settings where our method significantly outperforms the baselines. Our code is publicly available.