arXiv subjects

Qi Lv

Publications and source records attributed to Qi Lv.

30 records · Page 2Linked to original sources

arXiv2025

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based semantic segmentation task. This paradigm relies on predefined labels and lacks the ability to comprehend complex natural language, resulting in limited generalization in open-world scene. To address these limitations, we reformulate the traditional affordance detection paradigm into \textit{Instruction Reasoning Affordance Segmentation} (IRAS) task. This task is designed to output a affordance mask region given a query reasoning text, which avoids fixed categories of input labels. We accordingly propose the \textit{3D-AffordanceLLM} (3D-ADLLM), a framework designed for reasoning affordance detection in 3D open-scene. Specifically, 3D-ADLLM introduces large language models (LLMs) to 3D affordance perception with a custom-designed decoder for generating affordance masks, thus achieving open-world reasoning affordance detection. In addition, given the scarcity of 3D affordance datasets for training large models, we seek to extract knowledge from general segmentation data and transfer it to affordance detection. Thus, we propose a multi-stage training strategy that begins with a novel pre-training task, i.e., \textit{Referring Object Part Segmentation}~(ROPS). This stage is designed to equip the model with general recognition and segmentation capabilities at the object-part level. Then followed by fine-tuning with the IRAS task, 3D-ADLLM obtains the reasoning ability for affordance detection. In summary, 3D-ADLLM leverages the rich world knowledge and human-object interaction reasoning ability of LLMs, achieving approximately an 8\% improvement in mIoU on open-vocabulary affordance detection tasks.

cs.CV↗

arXiv2025

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL

While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions. Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intrastep relationships among return-to-gos (RTGs), states, and actions, (3) overfitting suboptimal trajectories with noisy labels. To address these challenges, we propose Decision Mamba (DM), a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy. DM explicitly models the historical hidden state to extract the temporal information by using the mamba architecture. To capture the relationship among RTG-state-action triplets, a fine-grained SSM module is designed and integrated into the original coarse-grained SSM in mamba, resulting in a novel mamba architecture tailored for offline RL. Finally, to mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization. The policy evolves by using its own past knowledge to refine the suboptimal actions, thus enhancing its robustness on noisy demonstrations. Extensive experiments on various tasks show that DM outperforms other baselines substantially.

cs.LG↗

arXiv2024

Critical link identification of power system vulnerability based on modified graph attention network

With the expansion of the power grid and the increase of the proportion of new energy sources, the uncertainty and random factors of the power grid increase, endangering the safe operation of the system. It is particularly important to find out the critical links of vulnerability in the power grid to ensure the reliability of the power grid operation. Aiming at the problem that the identification speed of the traditional critical link of vulnerability identification methods is slow and difficult to meet the actual operation requirements of the power grid, the improved graph attention network (IGAT) based identification method of the critical link is proposed. First, the evaluation index set is established by combining the complex network theory and the actual operation data of power grid. Secondly, IGAT is used to dig out the mapping relationship between various indicators and critical links of vulnerability during the operation of the power grid, establish the identification model of critical links of vulnerability, and optimize the original graph attention network considering the training accuracy and efficiency. Thirdly, the original data set is obtained through simulation, and the identification model is trained, verified and tested. Finally, the model is applied to the improved IEEE 30-node system and the actual power grid, and the results show that the proposed method is feasible, and the accuracy and speed are better than that of traditional methods. It has certain engineering utilization value.

eess.SY↗

arXiv2024

EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024

In this technical report, we present our solution for the EgoPlan Challenge in ICML 2024. To address the real-world egocentric task planning problem, we introduce a novel planning framework which comprises three stages: long-term memory Extraction, context-awared Planning, and multi-iteration Decision, named EPD. Given the task goal, task progress, and current observation, the extraction model first extracts task-relevant memory information from the progress video, transforming the complex long video into summarized memory information. The planning model then combines the context of the memory information with fine-grained visual information from the current observation to predict the next action. Finally, through multi-iteration decision-making, the decision model comprehensively understands the task situation and current state to make the most realistic planning decision. On the EgoPlan-Test set, EPD achieves a planning accuracy of 53.85% over 1,584 egocentric task planning questions. We have made all codes available at https://github.com/Kkskkkskr/EPD .

cs.RO↗

arXiv2024

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with human-selected prompts for embodied agents. However, these methods exhibit limited generalization capabilities on unseen tasks or scenarios, and overlook the multimodal environment information which is critical for robots to make decisions. In this paper, we introduce a novel Robotic Multimodal Perception-Planning (RoboMP$^2$) framework for robotic manipulation which consists of a Goal-Conditioned Multimodal Preceptor (GCMP) and a Retrieval-Augmented Multimodal Planner (RAMP). Specially, GCMP captures environment states by employing a tailored MLLMs for embodied agents with the abilities of semantic reasoning and localization. RAMP utilizes coarse-to-fine retrieval method to find the $k$ most-relevant policies as in-context demonstrations to enhance the planner. Extensive experiments demonstrate the superiority of RoboMP$^2$ on both VIMA benchmark and real-world tasks, with around 10% improvement over the baselines.

cs.RO↗

arXiv2023

RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check

Chinese Spelling Check (CSC) refers to the detection and correction of spelling errors in Chinese texts. In practical application scenarios, it is important to make CSC models have the ability to correct errors across different domains. In this paper, we propose a retrieval-augmented spelling check framework called RSpell, which searches corresponding domain terms and incorporates them into CSC models. Specifically, we employ pinyin fuzzy matching to search for terms, which are combined with the input and fed into the CSC model. Then, we introduce an adaptive process control mechanism to dynamically adjust the impact of external knowledge on the model. Additionally, we develop an iterative strategy for the RSpell framework to enhance reasoning capabilities. We conducted experiments on CSC datasets in three domains: law, medicine, and official document writing. The results demonstrate that RSpell achieves state-of-the-art performance in both zero-shot and fine-tuning scenarios, demonstrating the effectiveness of the retrieval-augmented CSC framework. Our code is available at https://github.com/47777777/Rspell.

cs.CL↗

arXiv2023

Composition Comparison between ICMEs from Active Regions and Quiet-Sun Regions

The composition, including the ionic charge states and elemental abundances of heavy elements, within interplanetary coronal mass ejections (ICMEs) has tight correlations with their source regions and eruption processes. This can help analyze the eruption mechanisms and plasma origins of CMEs, and deepen our understanding of energetic solar activities. The active regions and quiet-Sun regions have different physical properties, thus from a statistical point of view, ICMEs originating from the two types of regions should exhibit different compositional characteristics. To demonstrate the differences comprehensively, we conduct survey studies on the ionic charge states of five elements (Mg, Fe, Si, C, and O) and the relative abundances of six elements (Mg/O, Fe/O, Si/O, C/O, Ne/O, and He/O) within ICMEs from 1998 February to 2011 August through the data of advanced composition explorer. The results show that ICMEs from active regions have higher ionic charge states and relative abundances than those from quiet-Sun regions. For the active-region ICMEs, we further analyze the relations between their composition and flare class, and find a positive relationship between them, i.e., the higher classes of the associated flares, the larger means of ionic charge states and relative abundances (except the C/O) within ICMEs. As more (less) fractions of ICMEs originate from active regions around solar maximum (minimum), and active-region ICMEs usually are associated with higher-class flares, our studies might answer why ICME composition measured near 1 au exhibits the solar cycle dependence.

astro-ph.SR↗

arXiv2022

General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining

The lack of label data is one of the significant bottlenecks for Chinese Spelling Check (CSC). Existing researches use the method of automatic generation by exploiting unlabeled data to expand the supervised corpus. However, there is a big gap between the real input scenario and automatic generated corpus. Thus, we develop a competitive general speller ECSpell which adopts the Error Consistent masking strategy to create data for pretraining. This error consistency masking strategy is used to specify the error types of automatically generated sentences which is consistent with real scene. The experimental result indicates our model outperforms previous state-of-the-art models on the general benchmark. Moreover, spellers often work within a particular domain in real life. Due to lots of uncommon domain terms, experiments on our built domain specific datasets show that general models perform terribly. Inspired by the common practice of input methods, we propose to add an alterable user dictionary to handle the zero-shot domain adaption problem. Specifically, we attach a User Dictionary guided inference module (UD) to a general token classification based speller. Our experiments demonstrate that ECSpell$^{UD}$, namely ECSpell combined with UD, surpasses all the other baselines largely, even approaching the performance on the general benchmark.

cs.CL↗

arXiv2022

Visual Subtitle Feature Enhanced Video Outline Generation

With the tremendously increasing number of videos, there is a great demand for techniques that help people quickly navigate to the video segments they are interested in. However, current works on video understanding mainly focus on video content summarization, while little effort has been made to explore the structure of a video. Inspired by textual outline generation, we introduce a novel video understanding task, namely video outline generation (VOG). This task is defined to contain two sub-tasks: (1) first segmenting the video according to the content structure and then (2) generating a heading for each segment. To learn and evaluate VOG, we annotate a 10k+ dataset, called DuVOG. Specifically, we use OCR tools to recognize subtitles of videos. Then annotators are asked to divide subtitles into chapters and title each chapter. In videos, highlighted text tends to be the headline since it is more likely to attract attention. Therefore we propose a Visual Subtitle feature Enhanced video outline generation model (VSENet) which takes as input the textual subtitles together with their visual font sizes and positions. We consider the VOG task as a sequence tagging problem that extracts spans where the headings are located and then rewrites them to form the final outlines. Furthermore, based on the similarity between video outlines and textual outlines, we use a large number of articles with chapter headings to pretrain our model. Experiments on DuVOG show that our model largely outperforms other baseline methods, achieving 77.1 of F1-score for the video segmentation level and 85.0 of ROUGE-L_F0.5 for the headline generation level.

cs.CV↗

arXiv2021

Fast and Reliable Probabilistic Face Embeddings in the Wild

Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios by integrating data uncertainty into the feature representation. However, existing PFE methods tend to be over-confident in estimating uncertainty and is too slow to apply to large-scale face matching. This paper proposes a regularized probabilistic face embedding method to improve the robustness and speed of PFE. Specifically, the mutual likelihood score (MLS) metric used in PFE is simplified to speedup the matching of face feature pairs. Then, an output-constraint loss is proposed to penalize the variance of the uncertainty output, which can regularize the output of the neural network. In addition, an identification preserving loss is proposed to improve the discriminative of the MLS metric, and a multi-layer feature fusion module is proposed to improve the neural network's uncertainty estimation ability. Comprehensive experiments show that the proposed method can achieve comparable or better results in 9 benchmarks than the state-of-the-art methods, and can improve the performance of risk-controlled face recognition. The code of our work is publicly available in GitHub (https://github.com/KaenChan/ProbFace).

cs.CV↗

arXiv2021

Solar Cycle Dependence of ICME Composition

Coronal mass ejections (CMEs) are one of the most energetic explosions in the solar atmosphere, and their occurrence rates exhibit obvious solar cycle dependence with more events taking place around solar maximum. Composition of interplanetary CMEs (ICMEs), referring to the charge states and elemental abundances of ions, opens an important avenue to investigate CMEs. In this paper, we conduct a statistical study on the charge states of five elements (Mg, Fe, Si, C, and O) and the relative abundances of six elements (Mg/O, Fe/O, Si/O, C/O, Ne/O, and He/O) within ICMEs from 1998 to 2011, and find that all the ICME compositions possess the solar cycle dependence. All of the ionic charge states and most of the relative elemental abundances are positively correlated with sunspot numbers (SSNs), and only the C/O ratios are inversely correlated with the SSNs. The compositions (except the C/O) increase with the SSNs during the ascending phase (1998--2000 and 2009--2011) and remain elevated during solar maximum and descending phase (2000--2005) compared to solar minimum (2007--2009). The charge states of low-FIP (first ionization potential) elements (Mg, Fe, and Si) and their relative abundances are correlated well, while no clear correlation is observed between the C$^{6+}$/C$^{5+}$ or C$^{6+}$/C$^{4+}$ and C/O. Most interestingly, we find that the Ne/O ratios of ICMEs and slow solar wind have the opposite solar cycle dependence.

astro-ph.SR↗

arXiv2016

Relative distance features for gait recognition with Kinect

Gait and static body measurement are important biometric technologies for passive human recognition. Many previous works argue that recognition performance based completely on the gait feature is limited. The reason for this limited performance remains unclear. This study focuses on human recognition with gait feature obtained by Kinect and shows that gait feature can effectively distinguish from different human beings through a novel representation -- relative distance-based gait features. Experimental results show that the recognition accuracy with relative distance features reaches up to 85%, which is comparable with that of anthropometric features. The combination of relative distance features and anthropometric features can provide an accuracy of more than 95%. Results indicate that the relative distance feature is quite effective and worthy of further study in more general scenarios (e.g., without Kinect).

cs.CV↗