arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 325 records · Page 18Linked to original sources

arXiv2024

Embedding Pose Graph, Enabling 3D Foundation Model Capabilities with a Compact Representation

This paper presents the Embedding Pose Graph (EPG), an innovative method that combines the strengths of foundation models with a simple 3D representation suitable for robotics applications. Addressing the need for efficient spatial understanding in robotics, EPG provides a compact yet powerful approach by attaching foundation model features to the nodes of a pose graph. Unlike traditional methods that rely on bulky data formats like voxel grids or point clouds, EPG is lightweight and scalable. It facilitates a range of robotic tasks, including open-vocabulary querying, disambiguation, image-based querying, language-directed navigation, and re-localization in 3D environments. We showcase the effectiveness of EPG in handling these tasks, demonstrating its capacity to improve how robots interact with and navigate through complex spaces. Through both qualitative and quantitative assessments, we illustrate EPG's strong performance and its ability to outperform existing methods in re-localization. Our work introduces a crucial step forward in enabling robots to efficiently understand and operate within large-scale 3D spaces.

cs.RO↗

arXiv2024

ANCoEF: Asynchronous Neuromorphic Algorithm/Hardware Co-Exploration Framework with a Fully Asynchronous Simulator

Developing asynchronous neuromorphic hardware to meet the demands of diverse real-life edge scenarios remains significant challenges. These challenges include constraints on hardware resources and power budgets while satisfying the requirements for real-time responsiveness, reliable inference accuracy, and so on. Besides, the existing system-level simulators for asynchronous neuromorphic hardware suffer from runtime limitations. To address these challenges, we propose an Asynchronous Neuromorphic algorithm/hardware Co-Exploration Framework (ANCoEF) including multi-objective reinforcement learning (RL)-based hardware architecture optimization method, and a fully asynchronous simulator (TrueAsync) which achieves over 2 times runtime speedups than the state-of-the-art (SOTA) simulator. Our experimental results show that, the RL-based hardware architecture optimization approach of ANCoEF outperforms the SOTA method by reducing 1.81 times hardware energy-delay product (EDP) with 2.73 times less search time on N-MNIST dataset, and the co-exploration framework of ANCoEF improves SNN accuracy by 9.72% and reduces hardware EDP by 28.85 times compared to the SOTA work on DVS128Gesture dataset. Furthermore, ANCoEF framework is evaluated on external neuromorphic dataset CIFAR10-DVS, and static datasets including CIFAR10, CIFAR100, SVHN, and Tiny-ImageNet. For instance, after 26.23 ThreadHour of co-exploration process, the result on CIFAR10-DVS dataset achieves an SNN accuracy of 98.48% while consuming hardware EDP of 0.54 s nJ per sample.

cs.AR↗

arXiv2024

Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker

During software evolution, it is advocated that test code should co-evolve with production code. In real development scenarios, test updating may lag behind production code changing, which may cause compilation failure or bring other troubles. Existing techniques based on pre-trained language models can be directly adopted to repair obsolete tests caused by such unsynchronized code changes, especially syntactic-related ones. However, the lack of task-oriented contextual information affects the repair accuracy on large-scale projects. Starting from an obsolete test, the key challenging task is precisely identifying and constructing Test-Repair-Oriented Contexts (TROCtxs) from the whole repository within a limited token size. In this paper, we propose SYNTER (SYNtactic-breaking-changes-induced TEst Repair), a novel approach based on LLMs to automatically repair obsolete test cases via precise and concise TROCtxs construction. Inspired by developers' programming practices, we design three types of TROCtx: class context, usage context, and environment context. Given an obsolete test case to repair, SYNTER firstly collects the related code information for each type of TROCtx through static analysis techniques automatically. Then, it generates reranking queries to identify the most relevant TROCtxs, which will be taken as the repair-required key contexts and be input to the large language model for the final test repair. To evaluate the effectiveness of SYNTER, we construct a benchmark dataset that contains a set of obsolete tests caused by syntactic breaking changes. The experimental results show that SYNTER outperforms baseline approaches both on textual- and intent-matching metrics. With the augmentation of constructed TROCtxs, hallucinations are reduced by 57.1%.

cs.SE↗

arXiv2024

DIP: Diffusion Learning of Inconsistency Pattern for General DeepFake Detection

With the advancement of deepfake generation techniques, the importance of deepfake detection in protecting multimedia content integrity has become increasingly obvious. Recently, temporal inconsistency clues have been explored to improve the generalizability of deepfake video detection. According to our observation, the temporal artifacts of forged videos in terms of motion information usually exhibits quite distinct inconsistency patterns along horizontal and vertical directions, which could be leveraged to improve the generalizability of detectors. In this paper, a transformer-based framework for Diffusion Learning of Inconsistency Pattern (DIP) is proposed, which exploits directional inconsistencies for deepfake video detection. Specifically, DIP begins with a spatiotemporal encoder to represent spatiotemporal information. A directional inconsistency decoder is adopted accordingly, where direction-aware attention and inconsistency diffusion are incorporated to explore potential inconsistency patterns and jointly learn the inherent relationships. In addition, the SpatioTemporal Invariant Loss (STI Loss) is introduced to contrast spatiotemporally augmented sample pairs and prevent the model from overfitting nonessential forgery artifacts. Extensive experiments on several public datasets demonstrate that our method could effectively identify directional forgery clues and achieve state-of-the-art performance.

cs.CV↗

arXiv2024

MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models

Recently, pathological diagnosis has achieved superior performance by combining deep learning models with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixeled nature of WSIs poses a great challenge for efficient MIL. Existing studies either do not consider global dependencies among instances, or use approximations such as linear attentions to model the pair-to-pair instance interactions, which inevitably brings performance bottlenecks. To tackle this challenge, we propose a framework named MamMIL for WSI analysis by cooperating the selective structured state space model (i.e., Mamba) with MIL, enabling the modeling of global instance dependencies while maintaining linear complexity. Specifically, considering the irregularity of the tissue regions in WSIs, we represent each WSI as an undirected graph. To address the problem that Mamba can only process 1D sequences, we further propose a topology-aware scanning mechanism to serialize the WSI graphs while preserving the topological relationships among the instances. Finally, in order to further perceive the topological structures among the instances and incorporate short-range feature interactions, we propose an instance aggregation block based on graph neural networks. Experiments show that MamMIL can achieve advanced performance than the state-of-the-art frameworks. The code can be accessed at https://github.com/Vison307/MamMIL.

cs.CV↗

arXiv2024

Large Spatial Model: End-to-end Unposed Images to Semantic 3D

Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations between different data representations. For instance, dense reconstruction through Structure-from-Motion (SfM) involves converting images into key points, optimizing camera parameters, and estimating structures. Afterward, accurate sparse reconstructions are required for further dense modeling, which is subsequently fed into task-specific neural networks. This multi-step process results in considerable processing time and increased engineering complexity. In this work, we present the Large Spatial Model (LSM), which processes unposed RGB images directly into semantic radiance fields. LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward operation, and it can generate versatile label maps by interacting with language at novel viewpoints. Leveraging a Transformer-based architecture, LSM integrates global geometry through pixel-aligned point maps. To enhance spatial attribute regression, we incorporate local context aggregation with multi-scale fusion, improving the accuracy of fine local details. To tackle the scarcity of labeled 3D semantic data and enable natural language-driven scene manipulation, we incorporate a pre-trained 2D language-based segmentation model into a 3D-consistent semantic feature field. An efficient decoder then parameterizes a set of semantic anisotropic Gaussians, facilitating supervised end-to-end learning. Extensive experiments across various tasks show that LSM unifies multiple 3D vision tasks directly from unposed images, achieving real-time semantic 3D reconstruction for the first time.

cs.CV↗

arXiv2024

EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning

This paper introduces a framework, called EMOTION, for generating expressive motion sequences in humanoid robots, enhancing their ability to engage in humanlike non-verbal communication. Non-verbal cues such as facial expressions, gestures, and body movements play a crucial role in effective interpersonal interactions. Despite the advancements in robotic behaviors, existing methods often fall short in mimicking the diversity and subtlety of human non-verbal communication. To address this gap, our approach leverages the in-context learning capability of large language models (LLMs) to dynamically generate socially appropriate gesture motion sequences for human-robot interaction. We use this framework to generate 10 different expressive gestures and conduct online user studies comparing the naturalness and understandability of the motions generated by EMOTION and its human-feedback version, EMOTION++, against those by human operators. The results demonstrate that our approach either matches or surpasses human performance in generating understandable and natural robot motions under certain scenarios. We also provide design implications for future research to consider a set of variables when generating expressive robotic gestures.

cs.RO↗

arXiv2024

General Capelli-type identities

The classical Capelli identity is an important determinantal identity of a matrix with noncommutative entries that determines the center of the enveloping algebra of the general linear Lie algebra, and was used by Weyl as a main tool to study irreducible representations in his famous book on classical groups. In 1996 Okounkov found higher Capelli identities involving immanants of the generating matrix of $U(gl(n))$ which correspond to arbitrary orthogonal idempotent of the symmetric group. It turns out that Williamson also discovered a general Capelli identity of immanants for $U(gl(n))$ in 1981. In this paper, we use a new method to derive a family of even more general Capelli identities that include the aforementioned Capelli identities as special cases as well as many other Capelli-type identities as corollaries. In particular, we obtain generalized Turnbull's identities for both symmetric and antisymmetric matrices, as well as the generalized Howe-Umeda-Kostant-Sahi identities for antisymmetric matrices which confirm the conjecture of Caracciolo, Sokal, and Sportiello.

math.QA↗

arXiv2024

Normalized solutions to Kirchhoff type equations with a critical growth nonlinearity

In this paper, we are concerned with normalized solutions of the Kirchhoff type equation \begin{equation*} -M\left(\int_{\R^N}|\nabla u|^2\mathrm{d} x\right)Δu = λu +f(u) \ \ \mathrm{in} \ \ \mathbb{R}^N \end{equation*} with $u \in S_c:=\left\{u \in H^1(\R^N): \int_{\R^N}u^2 \mathrm{d}x=c^2\right\}$. When $N=2$ and $f$ has exponential critical growth at infinity, normalized mountain pass type solutions are obtained via the variational methods. When $N \ge 4$, $M(t)=a+bt$ with $a$, $b>0$ and $f$ has Sobolev critical growth at infinity, we investigate the existence of normalized ground state solutions and normalized mountain pass type solutions. Moreover, the non-existence of normalized solutions is also considered.

math.AP↗

arXiv2024

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges.

cs.CV↗

arXiv2024

Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation

Semi-supervised learning (SSL) techniques address the high labeling costs in 3D medical image segmentation, with the teacher-student model being a common approach. However, using an exponential moving average (EMA) in single-teacher models may cause coupling issues, where the weights of the student and teacher models become similar, limiting the teacher's ability to provide additional knowledge for the student. Dual-teacher models were introduced to address this problem but often neglected the importance of maintaining teacher model diversity, leading to coupling issues among teachers. To address the coupling issue, we incorporate a double-copy-paste (DCP) technique to enhance the diversity among the teachers. Additionally, we introduce the Staged Selective Ensemble (SSE) module, which selects different ensemble methods based on the characteristics of the samples and enables more accurate segmentation of label boundaries, thereby improving the quality of pseudo-labels. Experimental results demonstrate the effectiveness of our proposed method in 3D medical image segmentation tasks. Here is the code link: https://github.com/Fazhan-cs/DCP.

cs.CV↗

arXiv2024

Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering

Long-term Video Question Answering (VideoQA) is a challenging vision-and-language bridging task focusing on semantic understanding of untrimmed long-term videos and diverse free-form questions, simultaneously emphasizing comprehensive cross-modal reasoning to yield precise answers. The canonical approaches often rely on off-the-shelf feature extractors to detour the expensive computation overhead, but often result in domain-independent modality-unrelated representations. Furthermore, the inherent gradient blocking between unimodal comprehension and cross-modal interaction hinders reliable answer generation. In contrast, recent emerging successful video-language pre-training models enable cost-effective end-to-end modeling but fall short in domain-specific ratiocination and exhibit disparities in task formulation. Toward this end, we present an entirely end-to-end solution for long-term VideoQA: Multi-granularity Contrastive cross-modal collaborative Generation (MCG) model. To derive discriminative representations possessing high visual concepts, we introduce Joint Unimodal Modeling (JUM) on a clip-bone architecture and leverage Multi-granularity Contrastive Learning (MCL) to harness the intrinsically or explicitly exhibited semantic correspondences. To alleviate the task formulation discrepancy problem, we propose a Cross-modal Collaborative Generation (CCG) module to reformulate VideoQA as a generative task instead of the conventional classification scheme, empowering the model with the capability for cross-modal high-semantic fusion and generation so as to rationalize and answer. Extensive experiments conducted on six publicly available VideoQA datasets underscore the superiority of our proposed method.

cs.CV↗

arXiv2024

Exploration of Halo Substructures in IoM Space with \textit{Gaia} DR3

Using kinematic data from the Gaia Data Release 3 catalog, along with metallicity estimates robustly derived from Gaia XP spectra, we have explored the Galactic stellar halo in search of both known and potentially new substructures. By applying the HDBSCAN clustering algorithm in IoM space (i.e. $E,L_{z}$ and $L_{\perp}$$ = \sqrt{L_{x}^2+L_{y}^2}$), we identified 5 previously known substructures: Gaia-Sausage-Enceladus (GSE), Helmi Streams, I'itoi + Sequoia and Hot Thick Disc. We additionally found NGC 3201 and NGC 5139 in this work, and NGC 3201 shares similar distributions in phase space and metallicties to Arjuna, which possibly implies that they have the same origin. Three newly discovered substructures are Prograde Substructure 1 (PG1), Prograde Substructure 2 (PG2) and the Low Energy Group. PG1, with a higher $V_ϕ$ than typical GSE member stars, is considered as either a low eccentricity and metal-rich part of GSE or part of the metal-poor disc. PG2, sharing kinematic similarities with Aleph, is thought to be its relatively highly eccentric component or the mixture of Aleph and disc. The Low Energy Group, whose metal-poor component of metallicity distribution function has a mean value [M/H] $\sim$ $-$1.29 (compared to that of Heracles [M/H] $\sim$ $-$1.26), may have associations with Heracles.

astro-ph.GA↗

arXiv2024

Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation

Single image-to-3D generation is pivotal for crafting controllable 3D assets. Given its under-constrained nature, we attempt to leverage 3D geometric priors from a novel view diffusion model and 2D appearance priors from an image generation model to guide the optimization process. We note that there is a disparity between the generation priors of these two diffusion models, leading to their different appearance outputs. Specifically, image generation models tend to deliver more detailed visuals, whereas novel view models produce consistent yet over-smooth results across different views. Directly combining them leads to suboptimal effects due to their appearance conflicts. Hence, we propose a 2D-3D hybrid Fourier Score Distillation objective function, hy-FSD. It optimizes 3D Gaussians using 3D priors in spatial domain to ensure geometric consistency, while exploiting 2D priors in the frequency domain through Fourier transform for better visual quality. hy-FSD can be integrated into existing 3D generation methods and produce significant performance gains. With this technique, we further develop an image-to-3D generation pipeline to create high-quality 3D objects within one minute, named Fourier123. Extensive experiments demonstrate that Fourier123 excels in efficient generation with rapid convergence speed and visually-friendly generation results.

cs.CV↗

arXiv2024

GS-Hider: Hiding Messages into 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) has already become the emerging research focus in the fields of 3D scene reconstruction and novel view synthesis. Given that training a 3DGS requires a significant amount of time and computational cost, it is crucial to protect the copyright, integrity, and privacy of such 3D assets. Steganography, as a crucial technique for encrypted transmission and copyright protection, has been extensively studied. However, it still lacks profound exploration targeted at 3DGS. Unlike its predecessor NeRF, 3DGS possesses two distinct features: 1) explicit 3D representation; and 2) real-time rendering speeds. These characteristics result in the 3DGS point cloud files being public and transparent, with each Gaussian point having a clear physical significance. Therefore, ensuring the security and fidelity of the original 3D scene while embedding information into the 3DGS point cloud files is an extremely challenging task. To solve the above-mentioned issue, we first propose a steganography framework for 3DGS, dubbed GS-Hider, which can embed 3D scenes and images into original GS point clouds in an invisible manner and accurately extract the hidden messages. Specifically, we design a coupled secured feature attribute to replace the original 3DGS's spherical harmonics coefficients and then use a scene decoder and a message decoder to disentangle the original RGB scene and the hidden message. Extensive experiments demonstrated that the proposed GS-Hider can effectively conceal multimodal messages without compromising rendering quality and possesses exceptional security, robustness, capacity, and flexibility. Our project is available at: https://xuanyuzhang21.github.io/project/gshider.

cs.CV↗

arXiv2024

FastTalker: Jointly Generating Speech and Conversational Gestures from Text

Generating 3D human gestures and speech from a text script is critical for creating realistic talking avatars. One solution is to leverage separate pipelines for text-to-speech (TTS) and speech-to-gesture (STG), but this approach suffers from poor alignment of speech and gestures and slow inference times. In this paper, we introduce FastTalker, an efficient and effective framework that simultaneously generates high-quality speech audio and 3D human gestures at high inference speeds. Our key insight is reusing the intermediate features from speech synthesis for gesture generation, as these features contain more precise rhythmic information than features re-extracted from generated speech. Specifically, 1) we propose an end-to-end framework that concurrently generates speech waveforms and full-body gestures, using intermediate speech features such as pitch, onset, energy, and duration directly for gesture decoding; 2) we redesign the causal network architecture to eliminate dependencies on future inputs for real applications; 3) we employ Reinforcement Learning-based Neural Architecture Search (NAS) to enhance both performance and inference speed by optimizing our network architecture. Experimental results on the BEAT2 dataset demonstrate that FastTalker achieves state-of-the-art performance in both speech synthesis and gesture generation, processing speech and gestures in 0.17 seconds per second on an NVIDIA 3090.

cs.MM↗

arXiv2024

Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications

Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4 can achieve only 30% precision (when both decision and justification are correct). This is likely because off-the-shelf LLMs were primarily pre-trained on a general text/code corpus and not fine-tuned on the specific domain of Solidity smart contract auditing. In this paper, we propose iAudit, a general framework that combines fine-tuning and LLM-based agents for intuitive smart contract auditing with justifications. Specifically, iAudit is inspired by the observation that expert human auditors first perceive what could be wrong and then perform a detailed analysis of the code to identify the cause. As such, iAudit employs a two-stage fine-tuning approach: it first tunes a Detector model to make decisions and then tunes a Reasoner model to generate causes of vulnerabilities. However, fine-tuning alone faces challenges in accurately identifying the optimal cause of a vulnerability. Therefore, we introduce two LLM-based agents, the Ranker and Critic, to iteratively select and debate the most suitable cause of vulnerability based on the output of the fine-tuned Reasoner model. To evaluate iAudit, we collected a balanced dataset with 1,734 positive and 1,810 negative samples to fine-tune iAudit. We then compared it with traditional fine-tuned models (CodeBERT, GraphCodeBERT, CodeT5, and UnixCoder) as well as prompt learning-based LLMs (GPT4, GPT-3.5, and CodeLlama-13b/34b). On a dataset of 263 real smart contract vulnerabilities, iAudit achieves an F1 score of 91.21% and an accuracy of 91.11%. The causes generated by iAudit achieved a consistency of about 38% compared to the ground truth causes.

cs.SE↗

arXiv2024

EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion

The task of audio-driven portrait animation involves generating a talking head video using an identity image and an audio track of speech. While many existing approaches focus on lip synchronization and video quality, few tackle the challenge of generating emotion-driven talking head videos. The ability to control and edit emotions is essential for producing expressive and realistic animations. In response to this challenge, we propose EMOdiffhead, a novel method for emotional talking head video generation that not only enables fine-grained control of emotion categories and intensities but also enables one-shot generation. Given the FLAME 3D model's linearity in expression modeling, we utilize the DECA method to extract expression vectors, that are combined with audio to guide a diffusion model in generating videos with precise lip synchronization and rich emotional expressiveness. This approach not only enables the learning of rich facial information from emotion-irrelevant data but also facilitates the generation of emotional videos. It effectively overcomes the limitations of emotional data, such as the lack of diversity in facial and background information, and addresses the absence of emotional details in emotion-irrelevant data. Extensive experiments and user studies demonstrate that our approach achieves state-of-the-art performance compared to other emotion portrait animation methods.

cs.CV↗