Search Results for author:
Found 80 papers, 50 papers with code
DD-TIG at SemEval-2022 Task 5: Investigating the Relationships Between Multimodal and Unimodal Information in Misogynous Memes Detection and Classification
This paper describes our submission for task 5 Multimedia Automatic Misogyny Identification (MAMI) at SemEval-2022.
Free Process Rewards without Process Labels
The only assumption is to parameterize the outcome reward as the log-likelihood ratios of the policy and reference models, which can be optimized regardless of the specific choice of loss objectives.
MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers
This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers.
Automating Exploratory Proteomics Research via Language Models
By automating complex proteomics analysis workflows and hypothesis generation, PROTEUS has the potential to considerably accelerate the pace of scientific discovery in proteomics research, enabling researchers to efficiently explore large-scale datasets and uncover biological insights.
Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal.
CALF: Benchmarking Evaluation of LFQA Using Chinese Examinations
To address this gap, we make the first attempt by proposing a well-constructed, reference-based benchmark named Chinese exAmination for LFQA Evaluation (CALF), aiming to rigorously assess the performance of automatic evaluation metrics for LFQA.
Space evaluation based on pitch control using drone video in Ultimate
A distinctive aspect of Ultimate is that the player holding the disc is unable to move, underscoring the significance of creating space to receive passes.
Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views
Based on the sparse depth maps and a normal estimator, we generate sparse normal maps for training a normal completion prior with precise standard deviations.
EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation
Current evaluation metrics either use traditional metrics like ROUGE and BERTScore, which rely on surface-level similarity and fail to consider informativeness, or simple LLM-based metrics, which are not robust and easily overwhelmed by the long contexts.
Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
Our research underscores that the fundamental distinction between System 1 and System 2 lies in the uncertainty of next token predictions, where interventions by System 2 are crucial to support System 1.
Zero-Shot Generalization during Instruction Tuning: Insights from Similarity and Granularity
For the first time, we show that zero-shot generalization during instruction tuning is a form of similarity-based generalization between training and test data at the instance level.
UltraMedical: Building Specialized Generalists in Biomedicine
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas.
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
To obtain a unified understanding, we interpret SFT and PO with two sub-processes -- Preference Estimation and Transition Optimization -- defined at token level within the Markov Decision Process (MDP) framework.
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then transferring the models to downstream VL tasks via end-to-end parameter-efficient fine-tuning (PEFT).
TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos
Multi-object tracking (MOT) is a critical and challenging task in computer vision, particularly in situations involving objects with similar appearances but diverse movements, as seen in team sports.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
Advancing LLM Reasoning Generalists with Preference Trees
We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning.
Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
Underlying data distributions of natural language, programming code, and mathematical symbols vary vastly, presenting a complex challenge for large language models (LLMs) that strive to achieve high performance across all three domains simultaneously.
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
With the advancement of language models (LMs), their exposure to private data is increasingly inevitable, and their deployment (especially for smaller ones) on personal devices, such as PCs and smartphones, has become a prevailing trend.
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment tax" -a compromise where enhancements in alignment within one objective (e. g., harmlessness) can diminish performance in others (e. g., helpfulness).
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
Different from previous works that simply translate English instructions, we consider both the language-specific and language-agnostic abilities of LLMs.
Sparse Low-rank Adaptation of Pre-trained Language Models
Recognizing the need for more flexible adaptation, we extend the methodology of LoRA to an innovative approach we call sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process.
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair
INTERVENOR prompts Large Language Models (LLMs) to play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher.
Ranked #26 on
Code Generation
on MBPP
CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model
Instruction tuning has recently been recognized as an effective way of aligning Large Language Models (LLMs) to enhance their generalization ability across various tasks.
Predicting Emergent Abilities with Infinite Resolution Evaluation
With PassUntil, we conduct a quantitative investigation into the scaling law of task performance.
UltraFeedback: Boosting Language Models with Scaled AI Feedback
Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models, serving as a solid foundation for future feedback learning research.
Health diagnosis and recuperation of aged Li-ion batteries with data analytics and equivalent circuit modeling
Battery health assessment and recuperation play a crucial role in the utilization of second-life Li-ion batteries.
Empowering Private Tutoring by Chaining Large Language Models
Artificial intelligence has been applied in various aspects of online education to facilitate teaching and learning.
The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset
Object detection is a crucial component of autonomous driving, and many detection applications have been developed to address this task.
Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
In this paper, we propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+2
OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models
The scale of large pre-trained models (PTMs) poses significant challenges in adapting to downstream tasks due to the high optimization overhead and storage costs associated with full-parameter fine-tuning.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
Exploring the Impact of Model Scaling on Parameter-Efficient Tuning
Our investigations reveal that model scaling (1) mitigates the effects of the positions of tunable parameters on performance, and (2) enables tuning methods to achieve performance comparable to full-parameter fine-tuning by optimizing fewer tunable parameters.
GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks?
We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations and achieve better performance.
Exploring Lottery Prompts for Pre-trained Language Models
Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning.
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT.
SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving
On the other hand, unknown objects, which have not been seen in training sample set, are one of the reasons that hinder autonomous vehicles from driving beyond the operational domain.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
We recruit annotators to search for relevant information using our interface and then answer questions.
Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge
Unfortunately, obtaining the annotations needed to train machine learning models to identify and localize surgical tools is a difficult task.
Estimation of control area in badminton doubles with pose information from top and back view drone videos
In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
Enhancing Depth Completion with Multi-View Monitored Distillation
Our approach builds upon the state-of-the-art ensemble distillation method, in which we introduce a stereo-based model as a teacher model to improve the accuracy of the student model for depth completion.
FractalAD: A simple industrial anomaly detection method using fractal anomaly generation and backbone knowledge distillation
Moreover, we designed a backbone knowledge distillation structure to extract prior knowledge contained in normal samples.
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning
In the meantime, we make full use of the structured information in the hierarchical labels to learn an accurate affinity graph for contrastive learning.
Network Expansion for Practical Training Acceleration
Recently, the sizes of deep neural networks and training datasets both increase drastically to pursue better performance in a practical sense.
Decoder Tuning: Efficient Language Understanding as Decoding
With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting.
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude.
Few-shot Classification with Hypersphere Modeling of Prototypes
Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere.
EEG-Fest: Few-shot based Attention Network for Driver's Vigilance Estimation with EEG Signals
A lack of driver's vigilance is the main cause of most vehicle crashes.
Sparse Structure Search for Delta Tuning
Generally, DT methods exquisitely design delta modules (DT modules) which could be applied to arbitrary fine-grained positions inside PTMs.
Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning
To fathom the mystery, we hypothesize that the adaptations of different DETs could all be reparameterized as low-dimensional optimizations in a unified optimization subspace, which could be found by jointly decomposing independent solutions of different DETs.
Improving Task Generalization via Unified Schema Prompt
Task generalization has been a long standing challenge in Natural Language Processing (NLP).
Sparse Structure Search for Parameter-Efficient Tuning
The searched structures preserve more than 99\% fine-tuning performance with 0. 01\% trainable parameters.
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
ProQA: Structural Prompt-based Pre-training for Unified Question Answering
Furthermore, ProQA exhibits strong ability in both continual learning and transfer learning by taking the advantages of the structural prompt.
Source-Free Domain Adaptation via Distribution Estimation
Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Prototypical Verbalizer for Prompt-based Few-shot Tuning
However, manual verbalizers heavily depend on domain-specific prior knowledge and human efforts, while finding appropriate label words automatically still remains challenging. In this work, we propose the prototypical verbalizer (ProtoVerb) which is built directly from training data.
Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
This necessitates a new branch of research focusing on the parameter-efficient adaptation of PLMs, dubbed as delta tuning in this paper.
Upright-Net: Learning Upright Orientation for 3D Point Cloud
A mass of experiments shows that the pose of the input 3D models exerts a tremendous influence on automatic 3D shape analysis.
OpenPrompt: An Open-source Framework for Prompt-learning
Prompt-learning has become a new paradigm in modern natural language processing, which directly adapts pre-trained language models (PLMs) to $cloze$-style prediction, autoregressive modeling, or sequence to sequence generation, resulting in promising performances on various tasks.
Exploring Universal Intrinsic Task Subspace via Prompt Tuning
In the experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 250-dimensional subspace found with 100 tasks, by only tuning 250 free parameters, we can recover 97% and 83% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace.
Few-shot Learning with Big Prototypes
A big prototype could be effectively modeled by two sets of learnable parameters, one is the center of the hypersphere, which is an embedding with the same dimension of training examples.
Prompt-Learning for Fine-Grained Entity Typing
In this work, we investigate the application of prompt-learning on fine-grained entity typing in fully supervised, few-shot and zero-shot scenarios.
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
Discriminative-Generative Representation Learning for One-Class Anomaly Detection
As a kind of generative self-supervised learning methods, generative adversarial nets have been widely studied in the field of anomaly detection.
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding
Recent works aimed to improve the robustness of pre-trained models mainly focus on adversarial training from perturbed examples with similar semantics, neglecting the utilization of different or even opposite semantics.
Pre-Trained Models: Past, Present and Future
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
PTR: Prompt Tuning with Rules for Text Classification
This indicates that PTR is a promising approach to take advantage of both human prior knowledge and PLMs for those complicated classification tasks.
Few-NERD: A Few-Shot Named Entity Recognition Dataset
In this paper, we present Few-NERD, a large-scale human-annotated few-shot NER dataset with a hierarchy of 8 coarse-grained and 66 fine-grained entity types.
Ranked #6 on
Named Entity Recognition (NER)
on Few-NERD (SUP)
Prototypical Representation Learning for Relation Extraction
This approach allows us to learn meaningful, interpretable prototypes for the final classification.
A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9).
Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
We also provide a theoretical explanation of our method.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
TP-LSD: Tri-Points Based Line Segment Detector
To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment.
Ranked #2 on
Line Segment Detection
on York Urban Dataset
Length-Controllable Image Captioning
We verify the merit of the proposed length level embedding on three models: two state-of-the-art (SOTA) autoregressive models with different types of decoder, as well as our proposed non-autoregressive model, to show its generalization ability.
Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation
In order to simultaneously alleviate these two issues, this paper proposes to couple distant annotation and adversarial training for cross-domain CWS.
Hierarchy-Aware Global Model for Hierarchical Text Classification
Hierarchical text classification is an essential yet challenging subtask of multi-label text classification with a taxonomic hierarchy.
General Classification
Hierarchical Multi-label Classification
+3
Event Detection with Trigger-Aware Lattice Neural Network
To ad- dress the two issues simultaneously, we pro- pose the Trigger-aware Lattice Neural Net- work (TLNN).
DELTA: A DEep learning based Language Technology plAtform
In this paper we present DELTA, a deep learning based language technology platform.
Ranked #3 on
Named Entity Recognition
on CoNLL 2003 (English)
Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge
Chinese relation extraction is conducted using neural networks with either character-based or word-based inputs, and most existing methods typically suffer from segmentation errors and ambiguity of polysemy.
