arXiv subjects

Zhenyu Zhang

Publications and source records attributed to Zhenyu Zhang.

At least 163 records · Page 9Linked to original sources

arXiv2024

FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity

The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and toxic content. Previous researchers have invested much effort in assessing the harmlessness of generative language models. However, existing benchmarks are struggling in the era of large language models (LLMs), due to the stronger language generation and instruction following capabilities, as well as wider applications. In this paper, we propose FFT, a new benchmark with 2116 elaborated-designed instances, for LLM harmlessness evaluation with factuality, fairness, and toxicity. To investigate the potential harms of LLMs, we evaluate 9 representative LLMs covering various parameter scales, training stages, and creators. Experiments show that the harmlessness of LLMs is still under-satisfactory, and extensive analysis derives some insightful findings that could inspire future research for harmless LLM research.

cs.CL↗

arXiv2024

Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking

Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-temporal tracking approach named STTrack. In contrast to previous paradigms that solely relied on updating reference information, we introduced a temporal state generator (TSG) that continuously generates a sequence of tokens containing multimodal temporal information. These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target. Furthermore, at the spatial level, we introduced the mamba fusion and background suppression interactive (BSI) modules. These modules establish a dual-stage mechanism for coordinating information interaction and fusion between modalities. Extensive comparisons on five benchmark datasets illustrate that STTrack achieves state-of-the-art performance across various multimodal tracking scenarios. Code is available at: https://github.com/NJU-PCALab/STTrack.

cs.CV↗

arXiv2024

Variable Stiffness & Dynamic Force Sensor for Tissue Palpation

Palpation of human tissue during Minimally Invasive Surgery is hampered due to restricted access. In this extended abstract, we present a variable stiffness and dynamic force range sensor that has the potential to address this challenge. The sensor utilises light reflection to estimate sensor deformation, and from this, the force applied. Experimental testing at different pressures (0, 0.5 and 1 PSI) shows that stiffness and force range increases with pressure. The force calibration results when compared with measured forces produced an average RMSE of 0.016, 0.0715 and 0.1284 N respectively, for these pressures.

physics.med-ph↗

arXiv2024

OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation

As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with content inaccuracies and inconsistencies due to reliance solely on textual inputs. Although recent motion control techniques provide fine-grained control for video generation, directly applying these methods to ODVs often results in spatial distortion and unsatisfactory performance, especially with complex spherical motions. To tackle these challenges, we propose OmniDrag, the first approach enabling both scene- and object-level motion control for accurate, high-quality omnidirectional image-to-video generation. Building on pretrained video diffusion models, we introduce an omnidirectional control module, which is jointly fine-tuned with temporal attention layers to effectively handle complex spherical motion. In addition, we develop a novel spherical motion estimator that accurately extracts motion-control signals and allows users to perform drag-style ODV generation by simply drawing handle and target points. We also present a new dataset, named Move360, addressing the scarcity of ODV data with large scene and object motions. Experiments demonstrate the significant superiority of OmniDrag in achieving holistic scene-level and fine-grained object-level control for ODV generation. The project page is available at https://lwq20020127.github.io/OmniDrag.

cs.CV↗

arXiv2024

Learning to Decouple the Lights for 3D Face Texture Modeling

Existing research has made impressive strides in reconstructing human facial shapes and textures from images with well-illuminated faces and minimal external occlusions. Nevertheless, it remains challenging to recover accurate facial textures from scenarios with complicated illumination affected by external occlusions, e.g. a face that is partially obscured by items such as a hat. Existing works based on the assumption of single and uniform illumination cannot correctly process these data. In this work, we introduce a novel approach to model 3D facial textures under such unnatural illumination. Instead of assuming single illumination, our framework learns to imitate the unnatural illumination as a composition of multiple separate light conditions combined with learned neural representations, named Light Decoupling. According to experiments on both single images and video sequences, we demonstrate the effectiveness of our approach in modeling facial textures under challenging illumination affected by occlusions. Please check https://tianxinhuang.github.io/projects/Deface for our videos and codes.

cs.CV↗

arXiv2024

DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion

Large language models (LLMs) with billions of parameters demonstrate impressive performance. However, the widely used Multi-Head Attention (MHA) in LLMs incurs substantial computational and memory costs during inference. While some efforts have optimized attention mechanisms by pruning heads or sharing parameters among heads, these methods often lead to performance degradation or necessitate substantial continued pre-training costs to restore performance. Based on the analysis of attention redundancy, we design a Decoupled-Head Attention (DHA) mechanism. DHA adaptively configures group sharing for key heads and value heads across various layers, achieving a better balance between performance and efficiency. Inspired by the observation of clustering similar heads, we propose to progressively transform the MHA checkpoint into the DHA model through linear fusion of similar head parameters step by step, retaining the parametric knowledge of the MHA checkpoint. We construct DHA models by transforming various scales of MHA checkpoints given target head budgets. Our experiments show that DHA remarkably requires a mere 0.25\% of the original model's pre-training budgets to achieve 97.6\% of performance while saving 75\% of KV cache. Compared to Group-Query Attention (GQA), DHA achieves a 5$\times$ training acceleration, a maximum of 13.93\% performance improvement under 0.01\% pre-training budget, and 4\% relative improvement under 0.05\% pre-training budget.

cs.LG↗

arXiv2024

Data Uncertainty-Aware Learning for Multimodal Aspect-based Sentiment Analysis

As a fine-grained task, multimodal aspect-based sentiment analysis (MABSA) mainly focuses on identifying aspect-level sentiment information in the text-image pair. However, we observe that it is difficult to recognize the sentiment of aspects in low-quality samples, such as those with low-resolution images that tend to contain noise. And in the real world, the quality of data usually varies for different samples, such noise is called data uncertainty. But previous works for the MABSA task treat different quality samples with the same importance and ignored the influence of data uncertainty. In this paper, we propose a novel data uncertainty-aware multimodal aspect-based sentiment analysis approach, UA-MABSA, which weighted the loss of different samples by the data quality and difficulty. UA-MABSA adopts a novel quality assessment strategy that takes into account both the image quality and the aspect-based cross-modal relevance, thus enabling the model to pay more attention to high-quality and challenging samples. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance on the Twitter-2015 dataset. Further analysis demonstrates the effectiveness of the quality assessment strategy.

cs.CL↗

arXiv2024

ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance

Diffusion models have shown impressive potential on talking head generation. While plausible appearance and talking effect are achieved, these methods still suffer from temporal, 3D or expression inconsistency due to the error accumulation and inherent limitation of single-image generation ability. In this paper, we propose ConsistentAvatar, a novel framework for fully consistent and high-fidelity talking avatar generation. Instead of directly employing multi-modal conditions to the diffusion process, our method learns to first model the temporal representation for stability between adjacent frames. Specifically, we propose a Temporally-Sensitive Detail (TSD) map containing high-frequency feature and contours that vary significantly along the time axis. Using a temporal consistent diffusion module, we learn to align TSD of the initial result to that of the video frame ground truth. The final avatar is generated by a fully consistent diffusion module, conditioned on the aligned TSD, rough head normal, and emotion prompt embedding. We find that the aligned TSD, which represents the temporal patterns, constrains the diffusion process to generate temporally stable talking head. Further, its reliable guidance complements the inaccuracy of other conditions, suppressing the accumulated error while improving the consistency on various aspects. Extensive experiments demonstrate that ConsistentAvatar outperforms the state-of-the-art methods on the generated appearance, 3D, expression and temporal consistency. Project page: https://njust-yang.github.io/ConsistentAvatar.github.io/

cs.CV↗

arXiv2024

Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering

Construction remains one of the most hazardous sectors. Recent advancements in AI, particularly Large Language Models (LLMs), offer promising opportunities for enhancing workplace safety. However, responsible integration of LLMs requires systematic evaluation, as deploying them without understanding their capabilities and limitations risks generating inaccurate information, fostering misplaced confidence, and compromising worker safety. This study evaluates the performance of two widely used LLMs, GPT-3.5 and GPT-4o, across three standardized exams administered by the Board of Certified Safety Professionals (BCSP). Using 385 questions spanning seven safety knowledge areas, the study analyzes the models' accuracy, consistency, and reliability. Results show that both models consistently exceed the BCSP benchmark, with GPT-4o achieving an accuracy rate of 84.6% and GPT-3.5 reaching 73.8%. Both models demonstrate strengths in safety management systems and hazard identification and control, but exhibit weaknesses in science, mathematics, emergency response, and fire prevention. An error analysis identifies four primary limitations affecting LLM performance: lack of knowledge, reasoning flaws, memory issues, and calculation errors. Our study also highlights the impact of prompt engineering strategies, with variations in accuracy reaching 13.5% for GPT-3.5 and 7.9% for GPT-4o. However, no single prompt configuration proves universally effective. This research advances knowledge in three ways: by identifying areas where LLMs can support safety practices and where human oversight remains essential, by offering practical insights into improving LLM implementation through prompt engineering, and by providing evidence-based direction for future research and development. These contributions support the responsible integration of AI in construction safety management toward achieving zero injuries.

cs.AI↗

arXiv2024

QED Effects on Kerr-Newman Black Hole Shadows

Incorporating first-order QED effects, we explore the shadows of Kerr-Newman black holes with a magnetic charge through the numerical backward ray-tracing method. Our investigation accounts for both the direct influence of the electromagnetic field on light rays and the distortion of the background spacetime metric due to QED corrections. We notice that the area of the shadow increases with the QED effect, mainly due to the fact that the photons move more slowly in the effective medium and become easier to be trapped by the black hole.

gr-qc↗

arXiv2024

EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns

Conventional methods, including Decision Tree (DT)-based methods, have been effective in scientific tasks, such as non-image medical diagnostics, system anomaly detection, and inorganic catalysis efficiency prediction. However, most deep-learning techniques have struggled to surpass or even match this level of success as traditional machine-learning methods. The primary reason is that these applications involve multi-source, heterogeneous data where features lack explicit relationships. This contrasts with image data, where pixels exhibit spatial relationships; textual data, where words have sequential dependencies; and graph data, where nodes are connected through established associations. The absence of explicit Feature Relation Patterns (FRPs) presents a significant challenge for deep learning techniques in scientific applications that are not image, text, and graph-based. In this paper, we introduce EAPCR, a universal feature extractor designed for data without explicit FRPs. Tested across various scientific tasks, EAPCR consistently outperforms traditional methods and bridges the gap where deep learning models fall short. To further demonstrate its robustness, we synthesize a dataset without explicit FRPs. While Kolmogorov-Arnold Network (KAN) and feature extractors like Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), and Transformers struggle, EAPCR excels, demonstrating its robustness and superior performance in scientific tasks without FRPs.

cs.LG↗

arXiv2024

MoR: Mixture of Ranks for Low-Rank Adaptation Tuning

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads to a performance bottleneck.(2) MoE-style LoRA methods substantially increase parameters and inference latency, contradicting the goals of efficient fine-tuning and ease of application. To address these challenges, we introduce Mixture of Ranks (MoR), which learns rank-specific information for different tasks based on input and efficiently integrates multi-rank information. We firstly propose a new framework that equates the integration of multiple LoRAs to expanding the rank of LoRA. Moreover, we hypothesize that low-rank LoRA already captures sufficient intrinsic information, and MoR can derive high-rank information through mathematical transformations of the low-rank components. Thus, MoR can reduces the learning difficulty of LoRA and enhances its multi-task capabilities. MoR achieves impressive results, with MoR delivering a 1.31\% performance improvement while using only 93.93\% of the parameters compared to baseline methods.

cs.LG↗

arXiv2024

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging

Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant data requirements and typically rely on large-scale post-training. In this paper, we propose Upcycling Instruction Tuning (UpIT), a data-efficient approach for tuning a dense pre-trained model into a MoE instruction model. Specifically, we first point out that intermediate checkpoints during instruction tuning of the dense model are naturally suitable for specialized experts, and then propose an expert expansion stage to flexibly achieve models with flexible numbers of experts, where genetic algorithm and parameter merging are introduced to ensure sufficient diversity of new extended experts. To ensure that each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to pre-optimize the router. Extensive experiments with various data scales and upcycling settings demonstrate the outstanding performance and data efficiency of UpIT, as well as stable improvement in expert or data scaling. Further analysis reveals the importance of ensuring expert diversity in upcycling.

cs.CL↗

arXiv2024

Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots

Robot-assisted surgery has profoundly influenced current forms of minimally invasive surgery. However, in transurethral suburethral urological surgical robots, they need to work in a liquid environment. This causes vaporization of the liquid when shearing and heating is performed, resulting in bubble atomization that affects the visual perception of the robot. This can lead to the need for uninterrupted pauses in the surgical procedure, which makes the surgery take longer. To address the atomization characteristics of liquids under urological surgical robotic vision, we propose an unsupervised zero-shot dehaze method (RSF-Dehaze) for urological surgical robotic vision. Specifically, the proposed Region Similarity Filling Module (RSFM) of RSF-Dehaze significantly improves the recovery of blurred region tissues. In addition, we organize and propose a dehaze dataset for robotic vision in urological surgery (USRobot-Dehaze dataset). In particular, this dataset contains the three most common urological surgical robot operation scenarios. To the best of our knowledge, we are the first to organize and propose a publicly available dehaze dataset for urological surgical robot vision. The proposed RSF-Dehaze proves the effectiveness of our method in three urological surgical robot operation scenarios with extensive comparative experiments with 20 most classical and advanced dehazing and image recovery algorithms. The proposed source code and dataset are available at https://github.com/wurenkai/RSF-Dehaze .

eess.IV↗

arXiv2024

Coexistence of ferroelectricity and superconductivity in a two-dimensional monolayer

The coupling of ferroelectricity (FE) and superconductivity (SC) becomes the frontier of condensed matter research recently especially in the realm of two-dimensional (2D) materials. Identifying a general strategy to realize coexistence of FE and SC in a single material is extremely important for this active field, but quite challenging thus far. We show in this work that coexistence of robust FE and metallicity/SC can be realized by hole-doping a ferroelectric insulator which hosts antibonding highest valence bands (HVB). Using typical 2D ferroelecrtic SnS monolayer as a concrete example, we demonstrate that 0.30 hole/cell doping leads to enhancement of total polarization mainly ascribed to the increasing of polar displacement and ionic polarization. In addition, due to the strong Fermi surface nesting and prominent softening of out-of-plane acoustic phonon upon hole-doping, SnS can be turned into a single gap superconductor with an unexpectedly high transition temperature (Tc) of ~7 K, whereas the polar phonon mode gives negligible contribution to electron-phonon couplings. Our work provides general principle and realistic material for realizing metallic FE and superconducting FE, which paves the way for reversible and nonvolatile superconducting devices.

cond-mat.supr-con↗

arXiv2024

Analytic forms for the $e^+e^-$ annihilation cross sections around a resonance including initial state radiation

The exact analytic form of cross sections including initial state radiation with Kuraev-Fadin radiative function are obtained for $e^+e^-$ annihilation around a resonance. Despite accounting for vacuum polarization and center-of-mass energy spread effects, the precision remains below 0.1\%, meeting the accuracy requirements of quantum electrodynamics corrections up to $\mathcal{O}(α^2)$. The analytic forms lead to an enhancement in the precision of experimental measurements of physical parameters, such as branching fractions, and demonstrate significantly improved computational efficiency in the regression procedures.

hep-ph↗

arXiv2024

Single-atom-resolved vibrational spectroscopy of a dislocation

Phonon resistance from dislocation scattering is often divided into short-range core interactions and long-range strain field interactions. Using electron energy-loss spectroscopy on a GaN dislocation, we report observations of vibrational modes localized at specific core atoms (short-range) and strain-driven phonon energy shifts around the dislocation (long-range). Ab initio calculations support these findings and draw out additional details. This study reveals atomically resolved vibrational spectra of dislocations, thus offering insights for engineering improved material functionalities.

cond-mat.mtrl-sci↗

arXiv2024

Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior knowledge from specific 3D scene datasets, limiting their applicability in open-world scenarios. The Segment Anything Model (SAM) has demonstrated remarkable zero-shot segmentation capabilities, prompting us to investigate its potential for comprehending 3D scenes without training. In this paper, we introduce OV-SAM3D, a training-free method that contains a universal framework for understanding open-vocabulary 3D scenes. This framework is designed to perform understanding tasks for any 3D scene without requiring prior knowledge of the scene. Specifically, our method is composed of two key sub-modules: First, we initiate the process by generating superpoints as the initial 3D prompts and refine these prompts using segment masks derived from SAM. Moreover, we then integrate a specially designed overlapping score table with open tags from the Recognize Anything Model (RAM) to produce final 3D instances with open-world labels. Empirical evaluations on the ScanNet200 and nuScenes datasets demonstrate that our approach surpasses existing open-vocabulary methods in unknown open-world environments.

cs.CV↗