arXiv subjects

Yu Gu

Publications and source records attributed to Yu Gu.

At least 145 records · Page 8Linked to original sources

arXiv2024

SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model

This paper presents an advanced end-to-end singing voice synthesis (SVS) system based on the source-filter mechanism that directly translates lyrical and melodic cues into expressive and high-fidelity human-like singing. Similarly to VISinger 2, the proposed system also utilizes training paradigms evolved from VITS and incorporates elements like the fundamental pitch (F0) predictor and waveform generation decoder. To address the issue that the coupling of mel-spectrogram features with F0 information may introduce errors during F0 prediction, we consider two strategies. Firstly, we leverage mel-cepstrum (mcep) features to decouple the intertwined mel-spectrogram and F0 characteristics. Secondly, inspired by the neural source-filter models, we introduce source excitation signals as the representation of F0 in the SVS system, aiming to capture pitch nuances more accurately. Meanwhile, differentiable mcep and F0 losses are employed as the waveform decoder supervision to fortify the prediction accuracy of speech envelope and pitch in the generated speech. Experiments on the Opencpop dataset demonstrate efficacy of the proposed model in synthesis quality and intonation accuracy.

eess.AS↗

arXiv2024

MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging

In this work, we present MedImageInsight, an open-source medical imaging embedding model. MedImageInsight is trained on medical images with associated text and labels across a diverse collection of domains, including X-Ray, CT, MRI, dermoscopy, OCT, fundus photography, ultrasound, histopathology, and mammography. Rigorous evaluations demonstrate MedImageInsight's ability to achieve state-of-the-art (SOTA) or human expert level performance across classification, image-image search, and fine-tuning tasks. Specifically, on public datasets, MedImageInsight achieves SOTA in CT 3D medical image retrieval, as well as SOTA in disease classification and search for chest X-ray, dermatology, and OCT imaging. Furthermore, MedImageInsight achieves human expert performance in bone age estimation (on both public and partner data), as well as AUC above 0.9 in most other domains. When paired with a text decoder, MedImageInsight achieves near SOTA level single image report findings generation with less than 10\% the parameters of other models. Compared to fine-tuning GPT-4o with only MIMIC-CXR data for the same task, MedImageInsight outperforms in clinical metrics, but underperforms on lexical metrics where GPT-4o sets a new SOTA. Importantly for regulatory purposes, MedImageInsight can generate ROC curves, adjust sensitivity and specificity based on clinical need, and provide evidence-based decision support through image-image search (which can also enable retrieval augmented generation). In an independent clinical evaluation of image-image search in chest X-ray, MedImageInsight outperformed every other publicly available foundation model evaluated by large margins (over 6 points AUC), and significantly outperformed other models in terms of AI fairness (across age and gender). We hope releasing MedImageInsight will help enhance collective progress in medical imaging AI research and development.

eess.IV↗

arXiv2024

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments. Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments -- knowledge bases (KBs) and databases -- we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with the middleware, GPT-4 achieves 2.8X the performance of the best baseline in tasks requiring access to database content and 2.2X in KB tasks. Our findings illuminate the path for advancing language agents in real-world applications.

cs.CL↗

arXiv2024

Autonomous Hiking Trail Navigation via Semantic Segmentation and Geometric Analysis

Natural environments pose significant challenges for autonomous robot navigation, particularly due to their unstructured and ever-changing nature. Hiking trails, with their dynamic conditions influenced by weather, vegetation, and human traffic, represent one such challenge. This work introduces a novel approach to autonomous hiking trail navigation that balances trail adherence with the flexibility to adapt to off-trail routes when necessary. The solution is a Traversability Analysis module that integrates semantic data from camera images with geometric information from LiDAR to create a comprehensive understanding of the surrounding terrain. A planner uses this traversability map to navigate safely, adhering to trails while allowing off-trail movement when necessary to avoid on-trail hazards or for safe off-trail shortcuts. The method is evaluated through simulation to determine the balance between semantic and geometric information in traversability estimation. These simulations tested various weights to assess their impact on navigation performance across different trail scenarios. Weights were then validated through field tests at the West Virginia University Core Arboretum, demonstrating the method's effectiveness in a real-world environment.

cs.RO↗

arXiv2024

Video-to-Audio Generation with Fine-grained Temporal Semantics

With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e.g., Sora). However, it remains a challenge to produce temporally aligned audio to synchronize the generated video, considering the complicated semantic information included in the latter. In this work, inspired by the recent success of text-to-audio (TTA) generation, we first investigate the video-to-audio (VTA) generation framework based on latent diffusion model (LDM). Similar to latest pioneering exploration in VTA, our preliminary results also show great potentials of LDM in VTA task, but it still suffers from sub-optimal temporal alignment. To this end, we propose to enhance the temporal alignment of VTA with frame-level semantic information. With the recently popular grounding segment anything model (Grounding SAM), we can extract the fine-grained semantics in video frames to enable VTA to produce better-aligned audio signal. Extensive experiments demonstrate the effectiveness of our system on both objective and subjective evaluation metrics, which shows both better audio quality and fine-grained temporal alignment.

eess.AS↗

arXiv2024

Loopy Movements: Emergence of Rotation in a Multicellular Robot

Unlike most human-engineered systems, many biological systems rely on emergent behaviors from low-level interactions, enabling greater diversity and superior adaptation to complex, dynamic environments. This study explores emergent decentralized rotation in the Loopy multicellular robot, composed of homogeneous, physically linked, 1-degree-of-freedom cells. Inspired by biological systems like sunflowers, Loopy uses simple local interactions-diffusion, reaction, and active transport of simulated chemicals, called morphogens-without centralized control or knowledge of its global morphology. Through these interactions, the robot self-organizes to achieve coordinated rotational motion and forms lobes-local protrusions created by clusters of motor cells. This study investigates how these interactions drive Loopy's rotation, the impact of its morphology, and its resilience to actuator failures. Our findings reveal two distinct behaviors: 1) inner valleys between lobes rotate faster than the outer peaks, contrasting with rigid body dynamics, and 2) cells rotate in the opposite direction of the overall morphology. The experiments show that while Loopy's morphology does not affect its angular velocity relative to its cells, larger lobes increase cellular rotation and decrease morphology rotation relative to the environment. Even with up to one-third of its actuators disabled and significant morphological changes, Loopy maintains its rotational abilities, highlighting the potential of decentralized, bio-inspired strategies for resilient and adaptable robotic systems.

cs.RO↗

arXiv2024

Feeling Optimistic? Ambiguity Attitudes for Online Decision Making

Due to the complexity of many decision making problems, tree search algorithms often have inadequate information to produce accurate transition models. This results in ambiguities (uncertainties for which there are multiple plausible models). Faced with ambiguities, robust methods have been used to produce safe solutions--often by maximizing the lower bound over the set of plausible transition models. However, they often overlook how much the representation of uncertainty can impact how a decision is made. This work introduces the Ambiguity Attitude Graph Search (AAGS), advocating for more comprehensive representations of ambiguities in decision making. Additionally, AAGS allows users to adjust their ambiguity attitude (or preference), promoting exploration and improving users' ability to control how an agent should respond when faced with a set of plausible alternatives. Simulation in a dynamic sailing environment shows how environments with high entropy transition models can lead robust methods to fail. Results further demonstrate how adjusting ambiguity attitudes better fulfills objectives while mitigating this failure mode of robust approaches. Because this approach is a generalization of the robust framework, these results further demonstrate how algorithms focused on ambiguity have applicability beyond safety-critical systems.

cs.RO↗

arXiv2024

Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs

Camera traps are important tools in animal ecology for biodiversity monitoring and conservation. However, their practical application is limited by issues such as poor generalization to new and unseen locations. Images are typically associated with diverse forms of context, which may exist in different modalities. In this work, we exploit the structured context linked to camera trap images to boost out-of-distribution generalization for species classification tasks in camera traps. For instance, a picture of a wild animal could be linked to details about the time and place it was captured, as well as structured biological knowledge about the animal species. While often overlooked by existing studies, incorporating such context offers several potential benefits for better image understanding, such as addressing data scarcity and enhancing generalization. However, effectively incorporating such heterogeneous context into the visual domain is a challenging problem. To address this, we propose a novel framework that transforms species classification as link prediction in a multimodal knowledge graph (KG). This framework enables the seamless integration of diverse multimodal contexts for visual recognition. We apply this framework for out-of-distribution species classification on the iWildCam2020-WILDS and Snapshot Mountain Zebra datasets and achieve competitive performance with state-of-the-art approaches. Furthermore, our framework enhances sample efficiency for recognizing under-represented species.

cs.CV↗

arXiv2024

LCM-SVC: Latent Diffusion Model Based Singing Voice Conversion with Inference Acceleration via Latent Consistency Distillation

Any-to-any singing voice conversion (SVC) aims to transfer a target singer's timbre to other songs using a short voice sample. However many diffusion model based any-to-any SVC methods, which have achieved impressive results, usually suffered from low efficiency caused by a mass of inference steps. In this paper, we propose LCM-SVC, a latent consistency distillation (LCD) based latent diffusion model (LDM) to accelerate inference speed. We achieved one-step or few-step inference while maintaining the high performance by distilling a pre-trained LDM based SVC model, which had the advantages of timbre decoupling and sound quality. Experimental results show that our proposed method can significantly reduce the inference time and largely preserve the sound quality and timbre similarity comparing with other state-of-the-art SVC models. Audio samples are available at https://sounddemos.github.io/lcm-svc.

eess.AS↗

arXiv2024

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual foundation agents across diverse scenarios, including Embodied, Graphical User Interface, and Visual Design, with tasks formulated to probe the depth of LMMs' understanding and interaction capabilities. Through rigorous testing across nine proprietary LMM APIs and eight open models, we demonstrate the considerable yet still developing agent capabilities of these models. Additionally, VAB constructs a trajectory training set constructed through hybrid methods including Program-based Solvers, LMM Agent Bootstrapping, and Human Demonstrations, promoting substantial performance improvements in LMMs through behavior cloning. Our work not only aims to benchmark existing models but also provides a solid foundation for future development into visual foundation agents. Code, train \& test data, and part of fine-tuned open LMMs are available at \url{https://github.com/THUDM/VisualAgentBench}.

cs.AI↗

arXiv2024

Cellular Plasticity Model for Bottom-Up Robotic Design

Traditional top-down robotic design often lacks the adaptability needed to handle real-world complexities, prompting the need for more flexible approaches. Therefore, this study introduces a novel cellular plasticity model tailored for bottom-up robotic design. The proposed model utilizes an activator-inhibitor reaction, a common foundation of Turing patterns, which are fundamental in morphogenesis -- the emergence of form from simple interactions. Turing patterns describe how diffusion and interactions between two chemical substances-an activator and an inhibitor-can lead to complex patterns and structures, such as the formation of limbs and feathers. Our study extends this concept by modeling cellular plasticity as an activator-inhibitor reaction augmented with environmental stimuli, encapsulating the core phenomena observed across various cell types: stem cells, neurons, and muscle cells. In addition to demonstrating self-regulation and self-containment, this approach ensures that a robot's form and function are direct emergent responses to its environment without a comprehensive environmental model. In the proposed model, a factory acts as the activator, producing a product that serves as the inhibitor, which is then influenced by environmental stimuli through consumption. These components are regulated by cellular plasticity phenomena as feedback loops. We calculate the equilibrium points of the model and the stability criterion. Simulations examine how varying parameters affect the system's transient behavior and the impact of competing functions on its functional capacity. Results show the model converges to a single stable equilibrium tuned to the environmental stimulation. Such dynamic behavior underscores the model's utility for generating predictable responses within robotics and biological systems, showcasing its potential for navigating the complexities of adaptive systems.

cs.RO↗

arXiv2024

Jointly stationary solutions of periodic Burgers flow

For the one dimensional Burgers equation with a random and periodic forcing, it is well-known that there exists a family of invariant measures, each corresponding to a different average velocity. In this paper, we consider the coupled invariant measures and study how they change as the velocity parameter varies. We show that the derivative of the invariant measure with respect to the velocity parameter exists, and it can be interpreted as the steady state of a diffusion advected by the Burgers flow

math.PR↗

arXiv2024

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For \textbf{ability modeling}, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering $19$ tasks. (2) For \textbf{data}, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For \textbf{evaluation criteria}, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models and a unique self-contrast metric for automatically evaluating knowledge-creating ability. We evaluate $28$ open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset and open-participation leaderboard are publicly released at https://kola.xlore.cn and will be continuously updated to provide references for developing LLMs and knowledge-related systems.

cs.CL↗

arXiv2024

Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation

The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world clinics. Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications. More importantly, less-acknowledged pragmatic issues, including accessibility, model cost, and tedious manual evaluation make it hard for clinicians to use state-of-the-art large models directly on private patient data. Here, we explore training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space, as exemplified by LLaVA-Med. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LlaVA-Rad (7B) model attains state-of-the-art results on standard radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.

cs.CL↗

arXiv2024

Effective diffusivities in periodic KPZ

For the KPZ equation on a torus with a $1+1$ spacetime white noise, it was shown in \cite{GK21,ADYGTK22} that the height function satisfies a central limit theorem, and the variance can be written as the expectation of an exponential functional of Brownian bridges. In this paper, we consider another physically relevant quantity, the winding number of the directed polymer on a cylinder, or equivalently, the displacement of the directed polymer endpoint in a spatially periodic random environment. It was shown in \cite{YGTK22} that the polymer endpoint satisfies a central limit theorem on diffusive scales. The main result of this paper is an explicit expression of the effective diffusivity, in terms of the expectation of another exponential functional of Brownian bridges. Our argument is based on a combination of tools from Malliavin calculus, homogenization, and diffusion in distribution-valued random environments.

math.PR↗

arXiv2024

MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin

This paper proposes Multi-modAl Retrieval model via Visual modulE pLugin (MARVEL), which learns an embedding space for queries and multi-modal documents to conduct retrieval. MARVEL encodes queries and multi-modal documents with a unified encoder model, which helps to alleviate the modality gap between images and texts. Specifically, we enable the image understanding ability of the well-trained dense retriever, T5-ANCE, by incorporating the visual module's encoded image features as its inputs. To facilitate the multi-modal retrieval tasks, we build the ClueWeb22-MM dataset based on the ClueWeb22 dataset, which regards anchor texts as queries, and extracts the related text and image documents from anchor-linked web pages. Our experiments show that MARVEL significantly outperforms the state-of-the-art methods on the multi-modal retrieval dataset WebQA and ClueWeb22-MM. MARVEL provides an opportunity to broaden the advantages of text retrieval to the multi-modal scenario. Besides, we also illustrate that the language model has the ability to extract image semantics and partly map the image features to the input word embedding space. All codes are available at https://github.com/OpenMatch/MARVEL.

cs.IR↗

arXiv2024

LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance

Any-to-any singing voice conversion (SVC) is an interesting audio editing technique, aiming to convert the singing voice of one singer into that of another, given only a few seconds of singing data. However, during the conversion process, the issue of timbre leakage is inevitable: the converted singing voice still sounds like the original singer's voice. To tackle this, we propose a latent diffusion model for SVC (LDM-SVC) in this work, which attempts to perform SVC in the latent space using an LDM. We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project based on the VITS framework, which is then used for the LDM training. Besides, we propose a singer guidance training method based on classifier-free guidance to further suppress the timbre of the original singer. Experimental results show the superiority of the proposed method over previous works in both subjective and objective evaluations of timbre similarity.

eess.AS↗

arXiv2024

BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once

Biomedical image analysis is fundamental for biomedical discovery in cell biology, pathology, radiology, and many other biomedical domains. Holistic image analysis comprises interdependent subtasks such as segmentation, detection, and recognition of relevant objects. Here, we propose BiomedParse, a biomedical foundation model for imaging parsing that can jointly conduct segmentation, detection, and recognition for 82 object types across 9 imaging modalities. Through joint learning, we can improve accuracy for individual tasks and enable novel applications such as segmenting all relevant objects in an image through a text prompt, rather than requiring users to laboriously specify the bounding box for each object. We leveraged readily available natural-language labels or descriptions accompanying those datasets and use GPT-4 to harmonize the noisy, unstructured text information with established biomedical object ontologies. We created a large dataset comprising over six million triples of image, segmentation mask, and textual description. On image segmentation, we showed that BiomedParse is broadly applicable, outperforming state-of-the-art methods on 102,855 test image-mask-label triples across 9 imaging modalities (everything). On object detection, which aims to locate a specific object of interest, BiomedParse again attained state-of-the-art performance, especially on objects with irregular shapes (everywhere). On object recognition, which aims to identify all objects in a given image along with their semantic types, we showed that BiomedParse can simultaneously segment and label all biomedical objects in an image (all at once). In summary, BiomedParse is an all-in-one tool for biomedical image analysis by jointly solving segmentation, detection, and recognition for all major biomedical image modalities, paving the path for efficient and accurate image-based biomedical discovery.

cs.CV↗