arXiv subjects

Jing Shi

Publications and source records attributed to Jing Shi.

At least 55 records · Page 3Linked to original sources

arXiv2025

MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained separately with distinct objectives (generation and representation learning). This separation overlooks the opportunity for developing a more versatile language model and for these objectives to complement each other. In this work, we propose MAGNET, a method for adapting decoder-only LLMs to generate robust representations and infill missing text spans. MAGNET employs three self-supervised training objectives and introduces an attention mechanism that combines bidirectional and causal attention, enabling unified training across all objectives. Our results demonstrate that LLMs adapted with MAGNET (1) surpass strong text encoders on token-level and sentence-level representation learning tasks, (2) generate contextually appropriate text infills by leveraging past and future contexts, (3) perform open-ended text generation without excessive repetition of words or phrases, and (4) preserve the knowledge and reasoning capability gained by the LLM during pretraining.

cs.CL↗

arXiv2024

SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner

We present SUGAR, a zero-shot method for subject-driven video customization. Given an input image, SUGAR is capable of generating videos for the subject contained in the image and aligning the generation with arbitrary visual attributes such as style and motion specified by user-input text. Unlike previous methods, which require test-time fine-tuning or fail to generate text-aligned videos, SUGAR achieves superior results without the need for extra cost at test-time. To enable zero-shot capability, we introduce a scalable pipeline to construct synthetic dataset which is specifically designed for subject-driven customization, leading to 2.5 millions of image-video-text triplets. Additionally, we propose several methods to enhance our model, including special attention designs, improved training strategies, and a refined sampling algorithm. Extensive experiments are conducted. Compared to previous methods, SUGAR achieves state-of-the-art results in identity preservation, video dynamics, and video-text alignment for subject-driven video customization, demonstrating the effectiveness of our proposed method.

cs.CV↗

arXiv2024

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering, and cross-modal retrieval. Despite their superior capabilities, VLMs struggle with fine-grained image regional composition information perception. Specifically, they have difficulty accurately aligning the segmentation masks with the corresponding semantics and precisely describing the compositional aspects of the referred regions. However, compositionality - the ability to understand and generate novel combinations of known visual and textual components - is critical for facilitating coherent reasoning and understanding across modalities by VLMs. To address this issue, we propose FINECAPTION, a novel VLM that can recognize arbitrary masks as referential inputs and process high-resolution images for compositional image captioning at different granularity levels. To support this endeavor, we introduce COMPOSITIONCAP, a new dataset for multi-grained region compositional image captioning, which introduces the task of compositional attribute-aware regional image captioning. Empirical results demonstrate the effectiveness of our proposed model compared to other state-of-the-art VLMs. Additionally, we analyze the capabilities of current VLMs in recognizing various visual prompts for compositional region image captioning, highlighting areas for improvement in VLM design and training.

cs.CV↗

arXiv2024

Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models

Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, has not yet been well investigated. To address the challenge of one-shot video motion customization, we propose Customize-A-Video that models the motion from a single reference video and adapts it to new subjects and scenes with both spatial and temporal varieties. It leverages low-rank adaptation (LoRA) on temporal attention layers to tailor the pre-trained T2V diffusion model for specific motion modeling. To disentangle the spatial and temporal information during training, we introduce a novel concept of appearance absorbers that detach the original appearance from the reference video prior to motion learning. The proposed modules are trained in a staged pipeline and inferred in a plug-and-play fashion, enabling easy extensions to various downstream tasks such as custom video generation and editing, video appearance customization and multiple motion combination. Our project page can be found at https://customize-a-video.github.io.

cs.CV↗

arXiv2024

Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images

The B-mode ultrasound based computer-aided diagnosis (CAD) has demonstrated its effectiveness for diagnosis of Developmental Dysplasia of the Hip (DDH) in infants. However, due to effect of speckle noise in ultrasound im-ages, it is still a challenge task to accurately detect hip landmarks. In this work, we propose a novel hip landmark detection model by integrating the Topological GCN (TGCN) with an Improved Conformer (TGCN-ICF) into a unified frame-work to improve detection performance. The TGCN-ICF includes two subnet-works: an Improved Conformer (ICF) subnetwork to generate heatmaps and a TGCN subnetwork to additionally refine landmark detection. This TGCN can effectively improve detection accuracy with the guidance of class labels. Moreo-ver, a Mutual Modulation Fusion (MMF) module is developed for deeply ex-changing and fusing the features extracted from the U-Net and Transformer branches in ICF. The experimental results on the real DDH dataset demonstrate that the proposed TGCN-ICF outperforms all the compared algorithms.

eess.IV↗

arXiv2024

Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters

Scaling Deep Neural Networks (DNNs) requires significant computational resources in terms of GPU quantity and compute capacity. In practice, there usually exists a large number of heterogeneous GPU devices due to the rapid release cycle of GPU products. It is highly needed to efficiently and economically harness the power of heterogeneous GPUs, so that it can meet the requirements of DNN research and development. The paper introduces Poplar, a distributed training system that extends Zero Redundancy Optimizer (ZeRO) with heterogeneous-aware capabilities. We explore a broader spectrum of GPU heterogeneity, including compute capability, memory capacity, quantity and a combination of them. In order to achieve high computational efficiency across all heterogeneous conditions, Poplar conducts fine-grained measurements of GPUs in each ZeRO stage. We propose a novel batch allocation method and a search algorithm to optimize the utilization of heterogeneous GPUs clusters. Furthermore, Poplar implements fully automated parallelism, eliminating the need for deploying heterogeneous hardware and finding suitable batch size. Extensive experiments on three heterogeneous clusters, comprising six different types of GPUs, demonstrate that Poplar achieves a training throughput improvement of 1.02-3.92x over current state-of-the-art heterogeneous training systems.

cs.DC↗

arXiv2024

FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform complex reasoning for VLMs, current models often struggle to effectively and precisely capture the compositional information on both the image and text sides. To address this, we propose FineMatch, a new aspect-based fine-grained text and image matching benchmark, focusing on text and image mismatch detection and correction. This benchmark introduces a novel task for boosting and evaluating the VLMs' compositionality for aspect-based fine-grained text and image matching. In this task, models are required to identify mismatched aspect phrases within a caption, determine the aspect's class, and propose corrections for an image-text pair that may contain between 0 and 3 mismatches. To evaluate the models' performance on this new task, we propose a new evaluation metric named ITM-IoU for which our experiments show a high correlation to human evaluation. In addition, we also provide a comprehensive experimental analysis of existing mainstream VLMs, including fully supervised learning and in-context learning settings. We have found that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches. Moreover, models (e.g., GPT-4V, Gemini Pro Vision) with strong abilities to perform multimodal in-context learning are not as skilled at fine-grained compositional image and text matching analysis. With FineMatch, we are able to build a system for text-to-image generation hallucination detection and correction.

cs.CV↗

arXiv2024

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation

Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone pre-trained on image-only data, with only lightweight, newly inserted adapters being trainable. This shared backbone facilitates both audio and video generation. Specifically, the video branch incorporates a trainable temporal attention layer into a frozen pre-trained DiT block for temporal consistency. Additionally, a small number of trainable parameters adapt the image-based DiT block for audio generation. An extra shared DiT block, equipped with lightweight parameters, facilitates feature interaction between audio and visual modalities, ensuring alignment. Extensive experiments on the AIST++ and Landscape datasets demonstrate that AV-DiT achieves state-of-the-art performance in joint audio-visual generation with significantly fewer tunable parameters. Furthermore, our results highlight that a single shared image generative backbone with modality-specific adaptations is sufficient for constructing a joint audio-video generator. Our source code and pre-trained models will be released.

cs.CV↗

arXiv2024

Martian seismic anisotropy underneath Elysium Planitia revealed by direct S wave splitting

Seismic anisotropy, arising from the crystallographic or lattice-preferred orientation of anisotropic minerals or the shape-preferred orientation of melts or cracks, can establish a critical link between Mars's past evolution and its current state. So far, although seismic anisotropy in Mars has been proposed due to different velocities of vertically and horizontally polarized shear waves in the Martian crust, obtained from crustal converted waves, multiples, and surface waves recorded by the InSight seismometer, the evidence is plausible. Notably, the shear wave splitting, which stands out as a straight indicator of seismic anisotropy, has not been reported using marsquake records. In this study, we employ Low-frequency marsquakes detected by the InSight seismometer to reveal shear wave splitting in Mars. We find that the direct S waves of three marsquake recordings (S0173a, S0235b, and S1133c) with high signal-to-noise ratios exhibit the splitting pheonmenon. We rule out the possibility of apparent anisotropy through synthetic tests, affirming the presence of seismic anisotropy in Mars. The delay time (about 1.33 s on average) measured from the direct S wave splitting is too large to be solely attributed to the seismic anisotropy in the upper crust (0 - 10 km) beneath the InSight. Thus, seismic anisotropy in the deeper region of Mars is indispensable. Combined with other geophysical evidence near the InSight landing site, the strong seismic anisotropy observed in this study implies the porous crust with aligned cracks being greater than 10 km beneath the InSight and/or the presence of an active mantle plume underneath the Elysium Planitia of Mars.

physics.geo-ph↗

arXiv2024

Mapping the intrinsic photocurrent streamlines through micromagnetic heterostructure devices

Like air flowing over a wing, optimizing the flow of electronic charge is essential to the operation of nanoscale devices. Unfortunately, the delicate interplay of charge, spin, and heat in complex devices has precluded detailed imaging of charge flow. Here, we report on the visualization of intrinsic charge current streamlines through yttrium iron garnet micromagnetic heterostructures. Scanning photovoltage microscopy of precisely designed devices leads to striking spatial patterns, with prominent photovoltage features emerging in corners and narrow constrictions. These patterns, which evolve continuously with rotation of an external magnetic field, enable rich spatial mapping of fluid-like flow. Taking inspiration from aerodynamic Clark Y airfoils, we engineer micromagnetic wing shaped devices, called electrofoils, which allow us to precisely contort, compress and decompress flowlines of electronic charge.120 (39) e2221815120

cond-mat.mtrl-sci↗

arXiv2024

VIXEN: Visual Text Comparison Network for Image Difference Captioning

We present VIXEN - a technique that succinctly summarizes in text the visual differences between a pair of images in order to highlight any content manipulation present. Our proposed network linearly maps image features in a pairwise manner, constructing a soft prompt for a pretrained large language model. We address the challenge of low volume of training data and lack of manipulation variety in existing image difference captioning (IDC) datasets by training on synthetically manipulated images from the recent InstructPix2Pix dataset generated via prompt-to-prompt editing framework. We augment this dataset with change summaries produced via GPT-3. We show that VIXEN produces state-of-the-art, comprehensible difference captions for diverse image contents and edit types, offering a potential mitigation against misinformation disseminated via manipulated image content. Code and data are available at http://github.com/alexblck/vixen

cs.CV↗

arXiv2024

Text-to-Audio Generation Synchronized with Videos

In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the correlation between audio and text embeddings, fall short when it comes to maintaining a seamless synchronization between the produced audio and its video. This often results in discernible audio-visual mismatches. To bridge this gap, we introduce a groundbreaking benchmark for Text-to-Audio generation that aligns with Videos, named T2AV-Bench. This benchmark distinguishes itself with three novel metrics dedicated to evaluating visual alignment and temporal consistency. To complement this, we also present a simple yet effective video-aligned TTA generation model, namely T2AV. Moving beyond traditional methods, T2AV refines the latent diffusion approach by integrating visual-aligned text embeddings as its conditional foundation. It employs a temporal multi-head attention transformer to extract and understand temporal nuances from video data, a feat amplified by our Audio-Visual ControlNet that adeptly merges temporal visual representations with text embeddings. Further enhancing this integration, we weave in a contrastive learning objective, designed to ensure that the visual-aligned text embeddings resonate closely with the audio features. Extensive evaluations on the AudioCaps and T2AV-Bench demonstrate that our T2AV sets a new standard for video-aligned TTA generation in ensuring visual alignment and temporal consistency.

cs.SD↗

arXiv2024

A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction

This paper focuses on term-status pair extraction from medical dialogues (MD-TSPE), which is essential in diagnosis dialogue systems and the automatic scribe of electronic medical records (EMRs). In the past few years, works on MD-TSPE have attracted increasing research attention, especially after the remarkable progress made by generative methods. However, these generative methods output a whole sequence consisting of term-status pairs in one stage and ignore integrating prior knowledge, which demands a deeper understanding to model the relationship between terms and infer the status of each term. This paper presents a knowledge-enhanced two-stage generative framework (KTGF) to address the above challenges. Using task-specific prompts, we employ a single model to complete the MD-TSPE through two phases in a unified generative form: we generate all terms the first and then generate the status of each generated term. In this way, the relationship between terms can be learned more effectively from the sequence containing only terms in the first phase, and our designed knowledge-enhanced prompt in the second phase can leverage the category and status candidates of the generated term for status generation. Furthermore, our proposed special status "not mentioned" makes more terms available and enriches the training data in the second phase, which is critical in the low-resource setting. The experiments on the Chunyu and CMDD datasets show that the proposed method achieves superior results compared to the state-of-the-art models in the full training and low-resource settings.

cs.CL↗

arXiv2023

VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition

Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and linguistic cues can also benefit in many scenarios. In this paper, we first propose ViLaS (Vision and Language into Automatic Speech Recognition), a novel multimodal ASR model based on the continuous integrate-and-fire (CIF) mechanism, which can integrate visual and textual context simultaneously or separately, to facilitate speech recognition. Next, we introduce an effective training strategy that improves performance in modal-incomplete test scenarios. Then, to explore the effects of integrating vision and language, we create VSDial, a multimodal ASR dataset with multimodal context cues in both Chinese and English versions. Finally, empirical results are reported on the public Flickr8K and self-constructed VSDial datasets. We explore various cross-modal fusion schemes, analyze fine-grained crossmodal alignment on VSDial, and provide insights into the effects of integrating multimodal information on speech recognition.

eess.AS↗

arXiv2023

Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation

Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged as a promising research direction. However, previous works may be limited by the inflexible structures of PLMs and the insufficient utilization of PLMs. To alleviate these problems, we propose the hierarchical knowledge distillation (HKD) on the continuous integrate-and-fire (CIF) based ASR models. To transfer knowledge from PLMs to the ASR models, HKD employs cross-modal knowledge distillation with contrastive loss at the acoustic level and knowledge distillation with regression loss at the linguistic level. Compared with the original CIF-based model, our method achieves 15% and 9% relative error rate reduction on the AISHELL-1 and LibriSpeech datasets, respectively.

cs.CL↗

arXiv2023

X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages

Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifically, X-LLM aligns multiple frozen single-modal encoders and a frozen LLM using X2L interfaces, where ``X'' denotes multi-modalities such as image, speech, and videos, and ``L'' denotes languages. X-LLM's training consists of three stages: (1) Converting Multimodal Information: The first stage trains each X2L interface to align with its respective single-modal encoder separately to convert multimodal information into languages. (2) Aligning X2L representations with the LLM: single-modal encoders are aligned with the LLM through X2L interfaces independently. (3) Integrating multiple modalities: all single-modal encoders are aligned with the LLM through X2L interfaces to integrate multimodal capabilities into the LLM. Our experiments show that X-LLM demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 84.5\% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. And we also conduct quantitative tests on using LLM for ASR and multimodal ASR, hoping to promote the era of LLM-based speech recognition.

cs.CL↗

arXiv2023

DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as the condition. However, they ignored the synchronization between audio and visual content in the video, and tended to generate audio mismatching from video frames. In this work, we propose a novel and personalized text-to-sound generation approach with visual alignment based on latent diffusion models, namely DiffAVA, that can simply fine-tune lightweight visual-text alignment modules with frozen modality-specific encoders to update visual-aligned text embeddings as the condition. Specifically, our DiffAVA leverages a multi-head attention transformer to aggregate temporal information from video features, and a dual multi-modal residual network to fuse temporal visual representations with text embeddings. Then, a contrastive learning objective is applied to match visual-aligned text embeddings with audio features. Experimental results on the AudioCaps dataset demonstrate that the proposed DiffAVA can achieve competitive performance on visual-aligned text-to-audio generation.

cs.CV↗

arXiv2023

Mixture of personality improved Spiking actor network for efficient multi-agent cooperation

Adaptive human-agent and agent-agent cooperation are becoming more and more critical in the research area of multi-agent reinforcement learning (MARL), where remarked progress has been made with the help of deep neural networks. However, many established algorithms can only perform well during the learning paradigm but exhibit poor generalization during cooperation with other unseen partners. The personality theory in cognitive psychology describes that humans can well handle the above cooperation challenge by predicting others' personalities first and then their complex actions. Inspired by this two-step psychology theory, we propose a biologically plausible mixture of personality (MoP) improved spiking actor network (SAN), whereby a determinantal point process is used to simulate the complex formation and integration of different types of personality in MoP, and dynamic and spiking neurons are incorporated into the SAN for the efficient reinforcement learning. The benchmark Overcooked task, containing a strong requirement for cooperative cooking, is selected to test the proposed MoP-SAN. The experimental results show that the MoP-SAN can achieve both high performances during not only the learning paradigm but also the generalization test (i.e., cooperation with other unseen agents) paradigm where most counterpart deep actor networks failed. Necessary ablation experiments and visualization analyses were conducted to explain why MoP and SAN are effective in multi-agent reinforcement learning scenarios while DNN performs poorly in the generalization test.

cs.AI↗