Search Results for author:
Found 77 papers, 26 papers with code
Delay-penalized CTC implemented based on Finite State Transducer
Our work is open-sourced and publicly available https://github. com/k2-fsa/k2.
Blank-regularized CTC for Frame Skipping in Neural Transducer
Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems.
PromptASR for contextualized ASR with controllable style
An additional style prompt can be given to the text encoder and guide the ASR system to output different styles of transcriptions.
Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS
Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ natural language processing techniques.
Zipformer: A faster and better encoder for automatic speech recognition
The Conformer has become the most popular encoder model for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information
In this paper, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions.
SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images.
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context
In this paper, we introduce Libriheavy, a large-scale ASR corpus consisting of 50, 000 hours of read English speech derived from LibriVox.
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
We empirically find that the high-frequency (HF) and low-frequency (LF) information from a parametric model has the potential to enhance geometry details and improve robustness to noise, respectively.
PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction.
Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections
To mimic the perception process of humans, in this paper, we propose Cross-Ray NeRF (CR-NeRF) that leverages interactive information across multiple rays to synthesize occlusion-free novel views with the same appearances as the images.
Adversarial Preference Optimization
Human preference alignment is essential to improve the interaction quality of large language models (LLMs).
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs
DiracDeltaNet achieves competitive accuracy on ImageNet (88. 7\% top-5), but with 42$\times$ fewer parameters and 48$\times$ fewer OPs than VGG16.
Masked Retraining Teacher-Student Framework for Domain Adaptive Object Detection
This helps the student model capture target domain characteristics and become a more data-efficient learner to gain knowledge from the limited number of pseudo boxes.
FaceMap: Towards Unsupervised Face Clustering via Map Equation
Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management.
Attentive Mask CLIP
To address this issue, we propose an attentive token removal approach for CLIP training, which retains tokens with a high semantic correlation to the text description.
Lifelong Learning based Disease Diagnosis on Clinical Notes
Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.
LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance.
BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency.
Context-aware Natural Language Generation with Recurrent Neural Networks
This paper studied generating natural languages at particular contexts or situations.
G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images
Novel view synthesis aims to generate new view images of a given view image collection.
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Selected from 10 hours raw videos, about 80, 000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e. g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking.
Ranked #5 on
Object Detection
on UAVDT
Deep Policy Hashing Network with Listwise Supervision
The following three steps are repeated until convergence: 1) the database network encodes all training samples into binary codes to obtain a whole rank list, 2) the query network is trained based on policy learning to maximize a reward that indicates the performance of the whole ranking list of binary codes, e. g., mean average precision (MAP), and 3) the database network is updated as the query network.
Feature Pyramid Hashing
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval.
TAPESTRY: A Blockchain based Service for Trusted Interaction Online
We present a novel blockchain based service for proving the provenance of online digital identity, exposed as an assistive tool to help non-expert users make better decisions about whom to trust online.
A New Unified Deep Learning Approach with Decomposition-Reconstruction-Ensemble Framework for Time Series Forecasting
A new variational mode decomposition (VMD) based deep learning approach is proposed in this paper for time series forecasting problem.
COVID-19 Public Opinion and Emotion Monitoring System Based on Time Series Thermal New Word Mining
With the spread and development of new epidemics, it is of great reference value to identify the changing trends of epidemics in public emotions.
Reverse Perspective Network for Perspective-Aware Object Counting
We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs.
Experiments of Federated Learning for COVID-19 Chest X-ray Images
However, for the protection and respect of the privacy of patients, the hospital's specific medical-related data did not allow leakage and sharing without permission.
Weakly-Supervised Crowd Counting Learns from Sorting rather than Locations
We propose a soft-label sorting network along with the counting network, which sorts the given images by their crowd numbers.
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
Model independent determination of the spin of the $Ω^{-}$ and its polarization alignment in $ψ(3686)\rightarrowΩ^{-}\barΩ^{+}$
We present an analysis of the process $\psi(3686) \to \Omega^- \bar{\Omega}^+$ ($\Omega^-\to K^-\Lambda$, $\bar{\Omega}^+\to K^+\bar{\Lambda}$, $\Lambda\to p\pi^-$, $\bar{\Lambda}\to \bar{p}\pi^+$) based on a data set of $448\times 10^6$ $\psi(3686)$ decays collected with the BESIII detector at the BEPCII electron-positron collider.
High Energy Physics - Experiment
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Evidence for $Z_{c}^{\pm}$ decays into the $ρ^{\pm} η_{c}$ final state
We study $e^{+}e^{-}$ collisions with a $\pi^{+}\pi^{-}\pi^{0}\eta_{c}$ final state using data samples collected with the BESIII detector at center-of-mass energies $\sqrt{s}=4. 226$, $4. 258$, $4. 358$, $4. 416$, and $4. 600$ GeV.
High Energy Physics - Experiment
Quasimodular forms and modular differential equations which are not apparent at cusps: I
In this paper, we explore a two-way connection between quasimodular forms of depth $1$ and a class of second-order modular differential equations with regular singularities on the upper half-plane and the cusps.
Number Theory Classical Analysis and ODEs Primary 11F11, secondary 11F25, 11F37, 34M03, 34M35
Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching
Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge.
Exploiting Sample Correlation for Crowd Counting With Multi-Expert Network
Specifically, we propose a task-driven similarity metric based on sample's mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network.
A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval
To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.
Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
Vital importance has necessity to be attached to cooperation in multi-agent environments, as a result of which some reinforcement learning algorithms combined with graph neural networks have been proposed to understand the mutual interplay between agents.
Adaptive Data Debiasing through Bounded Exploration
Our proposed algorithm includes parameters that can be used to balance between the ultimate goal of removing data biases -- which will in turn lead to more accurate and fair decisions, and the exploration risks incurred to achieve this goal.
Directional Self-supervised Learning for Heavy Image Augmentations
Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV).
DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking
Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results.
Investigating Information Inconsistency in Multilingual Open-Domain Question Answering
Retrieval based open-domain QA systems use retrieved documents and answer-span selection over retrieved documents to find best-answer candidates.
HITSZ-HLT at SemEval-2022 Task 10: A Span-Relation Extraction Framework for Structured Sentiment Analysis
This paper describes our system that participated in the SemEval-2022 Task 10: Structured Sentiment Analysis, which aims to extract opinion tuples from texts. A full opinion tuple generally contains an opinion holder, an opinion target, the sentiment expression, and the corresponding polarity. The complex structure of the opinion tuple makes the task challenging. To address this task, we formalize it as a span-relation extraction problem and propose a two-stage extraction framework accordingly. In the first stage, we employ the span module to enumerate spans and then recognize the type of every span. In the second stage, we employ the relation module to determine the relation between spans. Our system achieves competitive results and ranks among the top-10 systems in almost subtasks.
Online Video Super-Resolution with Convolutional Kernel Bypass Graft
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
Towards Inference Efficient Deep Ensemble Learning
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e. g., can be up to 2048X in large-scale ensemble tasks.
Particle-based Online Bayesian Sampling
Online optimization has gained increasing interest due to its capability of tracking real-world streaming data.
SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning
Federated bilevel optimization (FBO) has shown great potential recently in machine learning and edge computing due to the emerging nested optimization structure in meta-learning, fine-tuning, hyperparameter tuning, etc.
A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels
In this paper, we propose a novel gradient-based approach to enable the detection of noisy labels for the online learning of model parameters, named Online Gradient-based Robust Selection (OGRS).
Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health.
Enabling Real-time Neural Recovery for Cloud Gaming on Mobile Devices
Our approach is extensively evaluated using iPhone 12 and laptop implementations, and we demonstrate the utility of game states in the game video recovery and the effectiveness of our overall design.
Real-Time Neural Video Recovery and Enhancement on Mobile Devices
Although deep learning-based video enhancement techniques are gaining attention, most of them cannot support real-time enhancement on mobile devices.
Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer
In spite of the excellent strides made by end-to-end (E2E) models in speech recognition in recent years, named entity recognition is still challenging but critical for semantic understanding.
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i. e., sources of variation) and aims to discover them in the latent space.
GeoLocator: a location-integrated large multimodal model for inferring geo-privacy
Geographic privacy or geo-privacy refers to the keeping private of one's geographic location, especially the restriction of geographical data maintained by personal electronic devices.
Online Video Quality Enhancement with Spatial-Temporal Look-up Tables
To the best of our knowledge, we are the first to exploit the LUT structure to extract temporal information in video tasks.
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
To overcome the aforementioned challenges, we propose an Unified Medical Image Pre-training framework, namely UniMedI, which utilizes diagnostic reports as common semantic space to create unified representations for diverse modalities of medical images (especially for 2D and 3D images).
Achieving ${O}(ε^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization
In this paper, we revisit the bilevel optimization problem, in which the upper-level objective function is generally nonconvex and the lower-level objective function is strongly convex.
DreamDistribution: Prompt Distribution Learning for Text-to-Image Diffusion Models
We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution.
Unmasking and Quantifying Racial Bias of Large Language Models in Medical Report Generation
Large language models like GPT-3. 5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications.
VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt.
Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning
Developing effective Map Entity Representation Learning (MERL) methods is crucial to extracting embedding information from electronic maps and converting map entities into representation vectors for downstream applications.
A survey of recent methods for addressing AI fairness and bias in biomedicine
Such biases can occur before, during, or after the development of AI models, making it critical to understand and address potential biases to enable the accurate and reliable application of AI models in clinical settings.
An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
We found that delicate designs are not necessary, while an embarrassingly simple composition of off-the-shelf speech encoder, LLM, and the only trainable linear projector is competent for the ASR task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning
Clinical calculators play a vital role in healthcare by offering accurate evidence-based predictions for various purposes such as prognosis.
HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e. g. point position and element shape, into the HIQuery.
Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables.
Understanding Training-free Diffusion Guidance: Mechanisms and Limitations
Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science.
PURPLE: Making a Large Language Model a Better SQL Writer
LLMs can learn to organize operator compositions from the input demonstrations for the given task.
PID Control-Based Self-Healing to Improve the Robustness of Large Language Models
This approach reduces the computational cost to that of using just the P controller, instead of the full PID control.
Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation
To tackle above two problems, we first take query concatenated with the query-based summary and the document summary without query as the input of topic relevance model, which can help model learn the relevance degree between query and the core topic of document.
The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice synthesis (SVS).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Generalization Error Bounds for Learning under Censored Feedback
We then use this CDF error bound to provide a bound on the generalization error guarantees of a classifier trained on such non-IID data.
