arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 577 records · Page 32Linked to original sources

arXiv2024

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and Union), providing an in-depth analysis of the model's resilience across three critical phases: tool selection, parameter identification, and content filling. Experiments involving six widely-used models underscore the urgent necessity for enhancing the robustness of LLMs in tool learning. For instance, the performance of GPT-4 even drops significantly from 80.00 to 58.10 when there is no substantial change in manual accuracy. More surprisingly, the noise correction capability inherent in the GPT family paradoxically impedes its adaptability in the face of mild noise. In light of these findings, we propose RoTTuning, a strategy that enriches the diversity of training environments to bolster the robustness of LLMs in tool learning. The code and data are available at https://github.com/Junjie-Ye/RoTBench.

cs.CL↗

arXiv2024

Online Learning via Memory: Retrieval-Augmented Detector Adaptation

This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.

cs.CV↗

arXiv2024

WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models

In recent years, AI-based weather forecasting models have matched or even outperformed numerical weather prediction systems. However, most of these models have been trained and evaluated on reanalysis datasets like ERA5. These datasets, being products of numerical models, often diverge substantially from actual observations in some crucial variables like near-surface temperature, wind, precipitation and clouds - parameters that hold significant public interest. To address this divergence, we introduce WeatherReal, a novel benchmark dataset for weather forecasting, derived from global near-surface in-situ observations. WeatherReal also features a publicly accessible quality control and evaluation framework. This paper details the sources and processing methodologies underlying the dataset, and further illustrates the advantage of in-situ observations in capturing hyper-local and extreme weather through comparative analyses and case studies. Using WeatherReal, we evaluated several data-driven models and compared them with leading numerical models. Our work aims to advance the AI-based weather forecasting research towards a more application-focused and operation-ready approach.

physics.ao-ph↗

arXiv2024

Directional WPT Charging for Routing-Asymmetric WRSNs with a Mobile Charger

Mobile Charge Scheduling for wirelessly charging nodes in Wireless Rechargeable Sensor Networks (WRSNs) is a promising but still evolving research area. Existing research mostly assumes a symmetric environment, where the routing costs in opposite directions between two locations are considered identical. However, various factors such as terrain restrictions and wind or water flows may invalidate the routing-symmetric assumption in practical environments, thereby significantly limiting the performance of these solutions in routing-asymmetric WRSNs (RA-WRSNs). To address the routing-asymmetric challenges in mobile charge scheduling for WRSNs, this paper systematically investigates the underlying Asymmetric Directional Mobile Charger (DMC) Charge Scheduling (ADMCCS) problem, aiming to minimize energy loss while satisfying the charging demands of the network nodes. The DMC model is assumed because its results can be easily applied to the specialized case of an Omnidirectional Mobile Charger (OMC). To solve the ADMCCS problem, we propose a four-step framework. First, a minimum-size efficient charging position set is selected using our designed K-means-based Charging Position Generation (KCPG) algorithm, addressing the challenge of the unlimited charging position selection space. Next, minimum-size functional-equivalent direction sets at these positions are determined using an optimal algorithm, tackling the challenge of infinite charging directions. Subsequently, the optimal energy transmission time lengths for all directions at the positions are obtained by formulating and solving a Nonlinear Program (NLP) problem. Finally, the Lin-Kernighan Heuristic (LKH) algorithm for the Asymmetric Traveling Salesman Problem is adapted to obtain a highly probable optimal loop tour, addressing the routing-asymmetric challenge.

cs.NI↗

arXiv2024

The Power of Lorentz Quantum Computer

We demonstrate the superior capabilities of the recently proposed Lorentz quantum computer (LQC) compared to conventional quantum computers. We introduce an associated computational complexity class termed bounded-error Lorentz quantum polynomial-time (BLQP), demonstrating its equivalence to the complexity class ${\text P}^{\sharp \text{P}}$. We present LQC algorithms that efficiently solve the problem of maximum independent set, PP (probabilistic polynomial-time), and consequently ${\text P}^{\sharp \text{P}}$, all within polynomial time. Additionally, we show that the quantum computing with postselection proposed by Aaronson can be efficiently simulated by LQC, but not vice versa.

quant-ph↗

arXiv2024

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and present challenges in sample efficiency and stability. In this paper, we introduce Inverse-Q*, an innovative framework that transcends traditional RL methods by optimizing token-level reinforcement learning without the need for additional reward or value models. Inverse-Q* leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model's responses, facilitating more granular and flexible policy shaping. Our approach reduces reliance on human annotation and external supervision, making it especially suitable for low-resource settings. We present extensive experimental results demonstrating that Inverse-Q* not only matches but potentially exceeds the effectiveness of PPO in terms of convergence speed and the alignment of model responses with human preferences. Our findings suggest that Inverse-Q* offers a practical and robust alternative to conventional RLHF approaches, paving the way for more efficient and adaptable model training approaches.

cs.CL↗

arXiv2024

Structural Representation Learning and Disentanglement for Evidential Chinese Patent Approval Prediction

Automatic Chinese patent approval prediction is an emerging and valuable task in patent analysis. However, it involves a rigorous and transparent decision-making process that includes patent comparison and examination to assess its innovation and correctness. This resultant necessity of decision evidentiality, coupled with intricate patent comprehension presents significant challenges and obstacles for the patent analysis community. Consequently, few existing studies are addressing this task. This paper presents the pioneering effort on this task using a retrieval-based classification approach. We propose a novel framework called DiSPat, which focuses on structural representation learning and disentanglement to predict the approval of Chinese patents and offer decision-making evidence. DiSPat comprises three main components: base reference retrieval to retrieve the Top-k most similar patents as a reference base; structural patent representation to exploit the inherent claim hierarchy in patents for learning a structural patent representation; disentangled representation learning to learn disentangled patent representations that enable the establishment of an evidential decision-making process. To ensure a thorough evaluation, we have meticulously constructed three datasets of Chinese patents. Extensive experiments on these datasets unequivocally demonstrate our DiSPat surpasses state-of-the-art baselines on patent approval prediction, while also exhibiting enhanced evidentiality.

cs.IR↗

arXiv2024

Enhanced Visual SLAM for Collision-free Driving with Lightweight Autonomous Cars

The paper presents a vision-based obstacle avoidance strategy for lightweight self-driving cars that can be run on a CPU-only device using a single RGB-D camera. The method consists of two steps: visual perception and path planning. The visual perception part uses ORBSLAM3 enhanced with optical flow to estimate the car's poses and extract rich texture information from the scene. In the path planning phase, we employ a method combining a control Lyapunov function and control barrier function in the form of quadratic program (CLF-CBF-QP) together with an obstacle shape reconstruction process (SRP) to plan safe and stable trajectories. To validate the performance and robustness of the proposed method, simulation experiments were conducted with a car in various complex indoor environments using the Gazebo simulation environment. Our method can effectively avoid obstacles in the scenes. The proposed algorithm outperforms benchmark algorithms in achieving more stable and shorter trajectories across multiple simulated scenes.

cs.RO↗

arXiv2024

Parareal algorithms for stochastic Maxwell equations with the damping term driven by additive noise

In this paper, we investigate the strong convergence analysis of parareal algorithms for stochastic Maxwell equations with the damping term driven by additive noise. The proposed parareal algorithms proceed as two-level temporal parallelizable integrators with the stochastic exponential integrator as the coarse propagator and both the exact solution integrator and the stochastic exponential integrator as the fine propagator. It is proved that the convergence order of the proposed algorithms linearly depends on the iteration number. Numerical experiments are performed to illustrate the convergence of the parareal algorithms for different choices of the iteration number and the damping coefficient.

math.NA↗

arXiv2024

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios. While current research primarily emphasizes leveraging tools to augment LLMs, it frequently neglects emerging safety considerations tied to their application. To fill this gap, we present *ToolSword*, a comprehensive framework dedicated to meticulously investigating safety issues linked to LLMs in tool learning. Specifically, ToolSword delineates six safety scenarios for LLMs in tool learning, encompassing **malicious queries** and **jailbreak attacks** in the input stage, **noisy misdirection** and **risky cues** in the execution stage, and **harmful feedback** and **error conflicts** in the output stage. Experiments conducted on 11 open-source and closed-source LLMs reveal enduring safety challenges in tool learning, such as handling harmful queries, employing risky tools, and delivering detrimental feedback, which even GPT-4 is susceptible to. Moreover, we conduct further studies with the aim of fostering research on tool learning safety. The data is released in https://github.com/Junjie-Ye/ToolSword.

cs.CL↗

arXiv2024

Generalization Enhancement Strategies to Enable Cross-year Cropland Mapping with Convolutional Neural Networks Trained Using Historical Samples

The accuracy of mapping agricultural fields across large areas is steadily improving with high-resolution satellite imagery and deep learning (DL) models, even in regions where fields are small and geometrically irregular. However, developing effective DL models often requires large, expensive label datasets, typically available only for specific years or locations. This limits the ability to create annual maps essential for agricultural monitoring, as domain shifts occur between years and regions due to changes in farming practices and environmental conditions. The challenge is to design a model flexible enough to account for these shifts without needing yearly labels. While domain adaptation techniques or semi-supervised training are common solutions, we explored enhancing the model's generalization power. Our results indicate that a holistic approach is essential, combining methods to improve generalization. Specifically, using an area-based loss function, such as Tversky-focal loss (TFL), significantly improved predictions across multiple years. The use of different augmentation techniques helped to encode different types of invariance, particularly photometric augmentations encoded invariance to brightness changes, though they increased false positives. The combination of photometric augmentation, TFL loss, and MC-dropout produced the best results, although dropout alone led to more false negatives in subsequent year predictions. Additionally, the choice of input normalization had a significant impact, with the best results obtained when statistics were calculated either locally or across the entire dataset over all bands (lab and gab). We developed a workflow that enabled a U-Net model to generate effective multi-year crop maps over large areas. Our code, available at: https://github.com/agroimpacts/cnn-generalization-enhancement, will be regularly updated with improvements.

cs.CV↗

arXiv2024

UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents

The recognition of named entities in visually-rich documents (VrD-NER) plays a critical role in various real-world scenarios and applications. However, the research in VrD-NER faces three major challenges: complex document layouts, incorrect reading orders, and unsuitable task formulations. To address these challenges, we propose a query-aware entity extraction head, namely UNER, to collaborate with existing multi-modal document transformers to develop more robust VrD-NER models. The UNER head considers the VrD-NER task as a combination of sequence labeling and reading order prediction, effectively addressing the issues of discontinuous entities in documents. Experimental evaluations on diverse datasets demonstrate the effectiveness of UNER in improving entity extraction performance. Moreover, the UNER head enables a supervised pre-training stage on various VrD-NER datasets to enhance the document transformer backbones and exhibits substantial knowledge transfer from the pre-training stage to the fine-tuning stage. By incorporating universal layout understanding, a pre-trained UNER-based model demonstrates significant advantages in few-shot and cross-linguistic scenarios and exhibits zero-shot entity extraction abilities.

cs.CL↗

arXiv2024

On the Identifiability from Modulo Measurements under DFT Sensing Matrix

Modulo sampling (MS) has been recently introduced to enhance the dynamic range of conventional ADCs by applying a modulo operator before sampling. This paper examines the identifiability of a measurement model where measurements are taken using a discrete Fourier transform (DFT) sensing matrix, followed by a modulo operator (modulo-DFT). Firstly, we derive a necessary and sufficient condition for the unique identification of the modulo-DFT sensing model based on the number of measurements and the indices of zero elements in the original signal. Then, we conduct a deeper analysis of three specific cases: when the number of measurements is a power of $2$, a prime number, and twice a prime number. Additionally, we investigate the identifiability of periodic bandlimited (PBL) signals under MS, which can be considered as the modulo-DFT sensing model with additional symmetric and conjugate constraints on the original signal. We also provide a necessary and sufficient condition based solely on the number of samples in one period for the unique identification of the PBL signal under MS, though with an ambiguity in the direct current (DC) component. Furthermore, we show that when the oversampling factor exceeds $3(1+1/P)$, the PBL signal can be uniquely identified with an ambiguity in the DC component, where $P$ is the number of harmonics, including the fundamental component, in the positive frequency part. Finally, we also present a recovery algorithm that estimates the original signal by solving integer linear equations, and we conduct simulations to validate our conclusions.

cs.IT↗

arXiv2024

Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach

This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with Shapley Values. The approach aims to quantify and compare the contributions of different state dimensions to various action choices. To more accurately analyze these impacts, we introduce new characteristic value functions, the ``Counterfactual Difference Characteristic Value" and the ``Average Counterfactual Difference Characteristic Value." These functions help calculate the Shapley values to evaluate the differences in contributions between optimal and non-optimal actions. Experiments across several RL domains, such as GridWorld, FrozenLake, and Taxi, demonstrate the effectiveness of the CSV method. The results show that this method not only improves transparency in complex RL systems but also quantifies the differences across various decisions.

cs.AI↗

arXiv2024

Lite-Mind: Towards Efficient and Robust Brain Representation Network

The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval. State-of-the-art MindEye remarkably improves fMRI-to-image retrieval performance by leveraging a large model, i.e., a 996M MLP Backbone per subject, to align fMRI embeddings to the final hidden layer of CLIP's Vision Transformer (ViT). However, significant individual variations exist among subjects, even under identical experimental setups, mandating the training of large subject-specific models. The substantial parameters pose significant challenges in deploying fMRI decoding on practical devices. To this end, we propose Lite-Mind, a lightweight, efficient, and robust brain representation learning paradigm based on Discrete Fourier Transform (DFT), which efficiently aligns fMRI voxels to fine-grained information of CLIP. We elaborately design a DFT backbone with Spectrum Compression and Frequency Projector modules to learn informative and robust voxel embeddings. Our experiments demonstrate that Lite-Mind achieves an impressive 94.6% fMRI-to-image retrieval accuracy on the NSD dataset for Subject 1, with 98.7% fewer parameters than MindEye. Lite-Mind is also proven to be able to be migrated to smaller fMRI datasets and establishes a new state-of-the-art for zero-shot classification on the GOD dataset.

cs.CV↗

arXiv2024

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°

Creating a 360° parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360° renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360° free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released at https://nju-3dv.github.io/projects/Head360.

cs.CV↗

arXiv2024

A symmetry-oriented crystal structure prediction method for crystals with rigid bodies

We have developed an efficient crystal structure prediction (CSP) method for desired chemical compositions, specifically suited for compounds featuring recurring molecules or rigid bodies. We applied this method to two metal chalcogenides: $\text{Li}_3\text{PS}_4$ and $\text{Na}_6\text{Ge}_2\text{Se}_6$, treating $\text{PS}_4$ as a tetrahedral rigid body and $\text{Ge}_2\text{Se}_6$ as an ethane-like dimer rigid body. Initial trials not only identified the experimentally observed structures of these compounds but also uncovered several novel phases, including a new stannite-type $\text{Li}_3\text{PS}_4$ structure and a potential metastable structure for $\text{Na}_6\text{Ge}_2\text{Se}_6$ that exhibits significantly lower energy than the observed phase, as evaluated by density functional theory (DFT) calculations. We compared our results with those obtained using USPEX, a popular CSP package leveraging genetic algorithms. Both methods predicted the same lowest energy structures in both compounds. However, our method demonstrated better performance in predicting metastable structures. The method is implemented with Python code which is available at https://github.com/ColdSnaap/sgrcsp.git.

cond-mat.mtrl-sci↗

arXiv2024

Comparative analysis of structural, elastic, electronic, phonon, thermal and optical properties of two $\text{Na}_6\text{Ge}_2\text{Se}_6$ phases from first principles calculations

The demand for new alkali metal chalcogenide materials is continuously increasing due to their potential applications across various technological fields. Recently, a new compound, $\text{Na}_6\text{Ge}_2\text{Se}_6$, was computationally predicted, representing a new phase distinct from the experimentally observed $\text{Na}_6\text{Ge}_2\text{Se}_6$ reported in 1985. Notably, this newly predicted phase displays a lower total energy compared to the previously known experimental phase, as determined by first-principles calculations. In this study, we undertake a thorough comparative analysis of the structural, elastic, electronic, phonon, thermal, and optical properties of these two $\text{Na}_6\text{Ge}_2\text{Se}_6$ phases. Our results show that both phases meet mechanical and dynamical stability criteria. The electronic band structure analysis confirms the semiconducting nature of both materials, with a 2.97 eV indirect band gap for the predicted phase and a 2.93 eV direct band gap for the observed phase. Optically, both phases exhibit strong absorption in the ultraviolet region. Thermal properties analysis reveals that the predicted phase is more thermodynamically stable below 907 K, while the observed phase shows greater thermodynamic stability above this temperature.

cond-mat.mtrl-sci↗