Search Results for author:
Found 106 papers, 39 papers with code
TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification
Based on continuous prompt embeddings, we propose TransPrompt, a transferable prompting framework for few-shot learning across similar tasks.
Meta Distant Transfer Learning for Pre-trained Language Models
For tasks related to distant domains with different class label sets, PLMs may memorize non-transferable knowledge for the target domain and suffer from negative transfer.
MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks.
Toward Safety-First Human-Like Decision Making for Autonomous Vehicles in Time-Varying Traffic Flow
Despite the recent advancements in artificial intelligence technologies have shown great potential in improving transport efficiency and safety, autonomous vehicles(AVs) still face great challenge of driving in time-varying traffic flow, especially in dense and interactive situations.
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse layouts.
Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
Appearance editing according to user needs is a pivotal task in video editing.
EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models
In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs).
Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations
Based on the proposed OmniThought dataset, we further train and release a series of high-performing LRMs, specifically equipped with stronger reasoning abilities and optimal CoT output length and difficulty level.
Deep Learning in Renewable Energy Forecasting: A Cross-Dataset Evaluation of Temporal and Spatial Models
Unpredictability of renewable energy sources coupled with the complexity of those methods used for various purposes in this area calls for the development of robust methods such as DL models within the renewable energy domain.
CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios
With the increasing demand for heterogeneous Unmanned Aerial Vehicle (UAV) swarms to perform complex tasks in urban environments, system design now faces major challenges, including efficient semantic understanding, flexible task planning, and the ability to dynamically adjust coordination strategies in response to evolving environmental conditions and continuously changing task requirements.
DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
These distilled models exhibit enhanced instruction-following capabilities compared to the original models based on a series of distillation techniques that incorporate knowledge from much larger LLMs.
Understanding Attention Mechanism in Video Diffusion Models
Notably, high-entropy attention maps are often key elements linked to superior video quality, whereas low-entropy attention maps are associated with the video's intra-frame structure.
Training Small Reasoning LLMs with Cognitive Preference Alignment
We further propose the cognitive preference optimization (CogPO) algorithm to enhance the reasoning abilities of smaller models by aligning thoughts of these models with their cognitive capacities.
AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding
Unmanned Aerial Vehicles (UAVs) are increasingly important in dynamic environments such as logistics transportation and disaster response.
Spatiotemporal Impact of Trade Policy Variables on Asian Manufacturing Hubs: Bayesian Global Vector Autoregression Model
A novel spatiotemporal framework using diverse econometric approaches is proposed in this research to analyze relationships among eight economy-wide variables in varying market conditions.
Beyond Existance: Fulfill 3D Reconstructed Scenes with Pseudo Details
The emergence of 3D Gaussian Splatting (3D-GS) has significantly advanced 3D reconstruction by providing high fidelity and fast training speeds across various scenarios.
Renewable Energy Prediction: A Comparative Study of Deep Learning Models for Complex Dataset Analysis
The results demonstrate that the combination of early stopping, dropout, and L1 regularization provides the best performance to reduce overfitting in the CNN and TD-MLP models with larger training set, while the combination of early stopping, dropout, and L2 regularization is the most effective to reduce the overfitting in CNN-LSTM and AE models with smaller training set.
UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
Low-altitude mobility, exemplified by unmanned aerial vehicles (UAVs), has introduced transformative advancements across various domains, like transportation, logistics, and agriculture.
Fingerprinting Denoising Diffusion Probabilistic Models
Diffusion models, especially denoising diffusion probabilistic models (DDPMs), are prevalent tools in generative AI, making their intellectual property (IP) protection increasingly important.
Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis
By encapsulating the T2V temporal-only prior into the T2I generation process, EVS successfully leverages the strengths of both types of models, resulting in videos of improved imaging and motion quality.
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
By lightly integrating visual patch tokens and 2D positional tokens into LLMs' input and encoding the document content using the LLMs themselves, we fully take advantage of the document comprehension capability of LLMs and enhance their perception of OCR information.
Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
The burgeoning field of foundation models necessitates advanced data processing mechanisms capable of harnessing vast and valuable data with various types used by these models.
Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud
Specializing LLMs in various domain-specific tasks has emerged as a critical step towards achieving high performance.
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services.
Radical-mediated Electrical Enzyme Assay For At-home Clinical Test
To meet the growing demand for accurate, rapid, and cost-effective at-home clinical testing, we developed a radical-mediated enzyme assay (REEA) integrated with a paper fluidic system and electrically read by a handheld field-effect transistor (FET) device.
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
To address these deficiencies, we propose a novel metric called SemVarEffect and a benchmark named SemVarBench, designed to evaluate the causality between semantic variations in inputs and outputs in T2I synthesis.
VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications.
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Text-rich document understanding (TDU) refers to analyzing and comprehending documents containing substantial textual content.
Rotation center identification based on geometric relationships for rotary motion deblurring
Existing methods directly estimate the rotation center from the RMB image.
Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
Inferring future activity information based on observed activity data is a crucial step to improve the accuracy of early activity prediction.
On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
Retrieval augmented generation (RAG) exhibits outstanding performance in promoting the knowledge capabilities of large language models (LLMs) with retrieved documents related to user queries.
Will Southeast Asia be the next global manufacturing hub? A multiway cointegration, causality, and dynamic connectedness analyses on factors influencing offshore decisions
The results of the cointegration, causality, and dynamic connectedness analyses show that a subset of Southeast Asian countries have spillover effects on each other.
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
(2) Considering that auxiliary parameters are required to store the knowledge for sequential editing, we construct a new dataset named \textbf{DAFSet}, fulfilling recent, popular, long-tail and robust properties to enhance the generality of sequential editing.
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
The motion module can be adapted to various DiT baseline methods to generate video with different styles.
Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning
In addition, by incorporating curriculum planning, our approach systematically escalates the difficulty levels of tasks, progressively enhancing the student LLM's capabilities.
Exploring Graph-based Knowledge: Multi-Level Feature Distillation via Channels Relational Graph
In visual tasks, large teacher models capture essential features and deep information, enhancing performance.
R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models
The reordering learning process is divided into two steps according to the quality of the generated responses: document order adjustment and document representation enhancement.
Guided AbsoluteGrad: Magnitude of Gradients Matters to Explanation's Localization and Saliency
This paper proposes a new gradient-based XAI method called Guided AbsoluteGrad for saliency map explanations.
AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework
The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering.
TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding.
DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
We present DiffChat, a novel method to align Large Language Models (LLMs) to "chat" with prompt-as-input Text-to-Image Synthesis (TIS) models (e. g., Stable Diffusion) for interactive image creation.
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative Text-to-image generation.
Do Large Language Models Understand Logic or Just Mimick Context?
Over the past few years, the abilities of large language models (LLMs) have received extensive attention, which have performed exceptionally well in complicated scenarios such as logical reasoning and symbolic inference.
Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models
Toon shading is a type of non-photorealistic rendering task of animation.
A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics
We use Winoground-T2I with a dual objective: to evaluate the performance of T2I models and the metrics used for their evaluation.
Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper
This paper delves into the pressing need in Parameter-Efficient Fine-Tuning (PEFT) for Large Language Models (LLMs).
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier
In the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches.
From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models
Reasoning is a distinctive human capacity, enabling us to address complex problems by breaking them down into a series of manageable cognitive steps.
Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension
In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference.
BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis
Then, to ensure that our generated prompts can generate more beautiful images, we further propose a Reinforcement Learning with Visual AI Feedback technique to fine-tune our model to maximize the reward values of the generated prompts, where the reward values are calculated based on the PickScore and the Aesthetic Scores.
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios.
Hierarchical Side-Tuning for Vision Transformers
In this paper, we introduce Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks.
Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System
The MST graph provides a virtual representation of the status and scheduling relationships among service instances of a real-world microservice system.
EasyPhoto: Your Smart AI Photo Generator
By training a digital doppelganger of a specific user ID using 5 to 20 relevant images, the finetuned model (according to the trained LoRA model) allows for the generation of AI photos using arbitrary templates.
Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance.
DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion
Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks.
Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters
Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks.
PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud
Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.
TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification
We propose TransPrompt v2, a novel transferable prompting framework for few-shot learning across similar or distant text classification tasks.
DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis
In recent years, diffusion models have emerged as the most powerful approach in image synthesis.
On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life.
Scale-Aware Modulation Meet Transformer
Specifically, SMT with 11. 5M / 2. 4GFLOPs and 32M / 7. 7GFLOPs can achieve 82. 2% and 84. 3% top-1 accuracy on ImageNet-1K, respectively.
On the Robustness of Split Learning against Adversarial Attacks
Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i. e., sever and clients only hold partial sub-networks and exchange intermediate computations).
SLAMB: Accelerated Large Batch Training with Sparse Communication
Distributed training of large deep neural networks requires frequent exchange of massive data between machines, thus communication efficiency is a major concern.
ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
Large-scale pre-trained text-image models with dual-encoder architectures (such as CLIP) are typically adopted for various vision-language applications, including text-image retrieval.
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
In addition, taking the gate as a probing, we validate the efficiency and effectiveness of the variable prefix.
Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models
In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers.
Detection Transformer with Stable Matching
We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR.
Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling
Neural sequence labeling (NSL) aims at assigning labels for input language tokens, which covers a broad range of applications, such as named entity recognition (NER) and slot filling, etc.
Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning
Motivated by the observation that the domain shift between training tasks and target tasks usually can reflect in their style variation, we propose Task Augmented Meta-Learning (TAML) to conduct style transfer-based task augmentation to improve the domain generalization ability.
Fingerprinting Deep Image Restoration Models
This paper proposes a fingerprinting framework for DNN models of image restoration.
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data.
Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training
Recently, knowledge-enhanced pre-trained language models (KEPLMs) improve context-aware representations via learning from structured relations in knowledge graphs, and/or linguistic knowledge from syntactic or dependency analysis.
YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6
We develop an all-in-one computer vision toolbox named EasyCV to facilitate the use of various SOTA computer vision methods.
P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering
Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs).
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP).
Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning
Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data.
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression
Unified in contrastive learning, CAP enables the pruned model to learn from the pre-trained model for task-agnostic knowledge, and fine-tuned model for task-specific knowledge.
DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding
Knowledge-Enhanced Pre-trained Language Models (KEPLMs) are pre-trained models with relation triples injecting from knowledge graphs to improve language understanding abilities.
Millimeter-Wave NR-U and WiGig Coexistence: Joint User Grouping, Beam Coordination and Power Control
Our aim for the proposed coexistence network is to maximize the spectral efficiency while ensuring the strict NR-U delay requirement and the WiGig transmission performance in real time environments.
Multi-layered Semantic Representation Network for Multi-label Image Classification
To this end, this paper designs a Multi-layered Semantic Representation Network (MSRN) which discovers both local and global semantics of labels through modeling label correlations and utilizes the label semantics to guide the semantic representations learning at multiple layers through an attention mechanism.
Ranked #7 on
Multi-Label Classification
on PASCAL VOC 2007
Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads
Therefore, we present CoCoNeT, with a DSL to express a program with both computation and communication.
A heuristic resolution of the Abraham-Minkowski controversy
This paper reviews the history and origin of the Abraham-Minkowski controversy and points out that it is a continuation of the controversy over the speed of light in medium.
Optics
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.
Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations
More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.
EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices
The intensive computation of Automatic Speech Recognition (ASR) models obstructs them from being deployed on mobile devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition
We present EasyASR, a distributed machine learning platform for training and serving large-scale Automatic Speech Recognition (ASR) models, as well as collecting and processing audio data at scale.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction
Existing learning based methods for text labeling task usually require a large amount of labeled examples to train a specific model for each type of document.
Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources
In this paper, we introduce a multi-target MRC task for the medical domain, whose goal is to predict answers to medical questions and the corresponding support sentences from medical information sources simultaneously, in order to ensure the high reliability of medical knowledge serving.
Weakly Supervised Construction of ASR Systems with Massive Video Data
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A Novel Global Spatial Attention Mechanism in Convolutional Neural Network for Medical Image Classification
In this paper, we thus propose a novel global spatial attention mechanism in CNNs mainly for medical image classification.
Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining
In this paper, we propose an effective learning procedure named Meta Fine-Tuning (MFT), served as a meta-learner to solve a group of similar NLP tasks for neural language models.
SwapText: Image Based Texts Transfer in Scenes
First, a novel text swapping network is proposed to replace text labels only in the foreground image.
KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification
We further combine a meta-learning process over the auxiliary task distribution and supervised learning to train the neural lexical relation classifier.
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.
Artificial Intelligence for Prosthetics - challenge solutions
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector.
Review Helpfulness Prediction with Embedding-Gated CNN
Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.
Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
Building multi-turn information-seeking conversation systems is an important and challenging research topic.
Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
Our models and research findings provide new insights on how to utilize external knowledge with deep neural models for response selection and have implications for the design of the next generation of information-seeking conversation systems.
AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience
We present AliMe Assist, an intelligent assistant designed for creating an innovative online shopping experience in E-commerce.
Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain.
AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine
We propose AliMe Chat, an open-domain chatbot engine that integrates the joint results of Information Retrieval (IR) and Sequence to Sequence (Seq2Seq) based generation models.
