Search Results for author:
Found 102 papers, 56 papers with code
Label Smoothing for Text Mining
This paper presents a novel keyword-based LS method to automatically generate soft labels from hard labels via exploiting the relevance between labels and text instances.
DESED: Dialogue-based Explanation for Sentence-level Event Detection
Many recent sentence-level event detection efforts focus on enriching sentence semantics, e. g., via multi-task or prompt-based learning.
Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
Recently, stacked networks show powerful performance in Image Restoration, such as challenging motion deblurring problems.
Improving Embedding-based Large-scale Retrieval via Label Enhancement
Current embedding-based large-scale retrieval models are trained with 0-1 hard label that indicates whether a query is relevant to a document, ignoring rich information of the relevance degree.
HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains.
RewardAnything: Generalizable Principle-Following Reward Models
To measure this capability, we develop RABench, a comprehensive benchmark for RMs focusing on generalization across diverse principles.
Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models
Spatial reasoning is a core component of human cognition, enabling individuals to perceive, comprehend, and interact with the physical world.
Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models, yet it is hard to scale for the low sample efficiency during the rollout phase.
VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains.
MPL: Multiple Programming Languages with Large Language Models for Information Extraction
In this research, we propose \textbf{M}ultiple \textbf{P}rogramming \textbf{L}anguages with large language models for information extraction (abbreviated as \textbf{MPL}), a novel framework that explores the potential of incorporating different PLs in the SFT phase.
Mitigating Spurious Correlations with Causal Logit Perturbation
{This study attempts to implement causal models via logit perturbations and introduces a novel Causal Logit Perturbation (CLP) framework to train classifiers with generated causal logit perturbations for individual samples, thereby mitigating the spurious associations between non-causal attributes (i. e., image backgrounds) and classes.}
Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective
In this paper, we first propose CoV-Eval, a multi-task benchmark covering various tasks such as code completion, vulnerability repair, vulnerability detection and classification, for comprehensive evaluation of LLM code security.
A Comprehensive Survey on Long Context Language Modeling
With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way.
RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
We demonstrate that by separating the process into two tasks and addressing them with the repair and inpainting models, we produce results with detailed textures in both visible and missing regions that outperform state-of-the-art approaches on a diverse set of scenes with extremely sparse inputs.
SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and then performs uniform data sampling across each domain.
All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
A new benchmark dataset, termed MIDD, is constructed for mode image denoising, comprising 120K pairs of noisy/noise-free images captured from real fiber communication systems across various transmission lengths.
Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning.
Deep Spectral Clustering via Joint Spectral Embedding and Kmeans
It first maps data into the spectral embedding space and then uses Kmeans to find clusters.
Robust Multiple Description Neural Video Codec with Masked Transformer for Dynamic and Noisy Networks
We propose a novel MDC video codec, NeuralMDC, demonstrating how bidirectional transformers trained for masked token prediction can vastly simplify the design of MDC video codec.
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
This forces the model to carefully understand the demonstration images and establish a relationship between the images and the symbols to answer questions correctly.
SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
To overcome these issues, we developed SG-Bench, a novel benchmark to assess the generalization of LLM safety across various tasks and prompt types.
Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results
The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing.
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning.
Ranked #205 on
Visual Question Answering
on MM-Vet
SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation
However, training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box annotations.
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction
Specifically, OCR/ASR-based data samples are fed into a well-calibrated CSC model trained on random replacement-based corpora and then filtered based on prediction confidence.
Enhancing In-Context Learning via Implicit Demonstration Augmentation
The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters.
Decoupling Forgery Semantics for Generalizable Deepfake Detection
The unique forgery semantics and irrelevant content semantics may promote over-fitting and hamper generalization for DeepFake detectors.
Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling
Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest expertise and unreliable retention of long-tail knowledge.
AutoSurvey: Large Language Models Can Automatically Write Surveys
This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence.
Concept Matching with Agent for Out-of-Distribution Detection
The remarkable achievements of Large Language Models (LLMs) have captivated the attention of both academia and industry, transcending their initial role in dialogue generation.
A3:Ambiguous Aberrations Captured via Astray-Learning for Facial Forgery Semantic Sublimation
The primary objective of the proposed method is to blend hybrid forgery semantics derived from high-frequency components into authentic imagery, named aberrations.
Deep Hierarchical Graph Alignment Kernels
Typical R-convolution graph kernels invoke the kernel functions that decompose graphs into non-isomorphic substructures and compare them.
Generative manufacturing systems using diffusion models and ChatGPT
In this study, we introduce Generative Manufacturing Systems (GMS) as a novel approach to effectively manage and coordinate autonomous manufacturing assets, thereby enhancing their responsiveness and flexibility to address a wide array of production objectives and human preferences.
Boosting Model Resilience via Implicit Adversarial Data Augmentation
This insight leads us to develop a meta-learning-based framework for optimizing classifiers with this novel loss, introducing the effects of augmentation while bypassing the explicit augmentation process.
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
The rapid development of large language model (LLM) evaluation methodologies and datasets has led to a profound challenge: integrating state-of-the-art evaluation techniques cost-effectively while ensuring reliability, reproducibility, and efficiency.
CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian Splatting (3DGS).
CodeShell Technical Report
Through this process, We have curated 100 billion high-quality pre-training data from GitHub.
NightHaze: Nighttime Image Dehazing via Self-Prior Learning
By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors.
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt.
Generative Retrieval with Large Language Models
When completing knowledge-intensive tasks, humans sometimes need not just an answer but also a corresponding reference passage for auxiliary reading.
Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions.
KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models
Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness.
Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models.
NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction
However, the intricacies of the real world, particularly with the presence of light effects and low-light regions affected by noise, create significant domain gaps, hampering synthetic-trained models in removing rain streaks properly and leading to over-saturation and color shifts.
Ranked #2 on
Rain Removal
on Nightrain
HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection
Compared with leading sparsely-supervised methods HINTED significantly improves the detection performance on hard instances notably outperforming fully-supervised methods in detecting challenging categories like cyclists.
Supervised Knowledge Makes Large Language Models Better In-context Learners
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
PICNN: A Pathway towards Interpretable Convolutional Neural Networks
Experimental results have demonstrated that our method PICNN (the combination of standard CNNs with our proposed pathway) exhibits greater interpretability than standard CNNs while achieving higher or comparable discrimination power.
Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks
Textual label names (descriptions) are typically semantically rich in many natural language understanding (NLU) tasks.
COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems
Combinatorial Optimization (CO) problems over graphs appear routinely in many applications such as in optimizing traffic, viral marketing in social networks, and matching for job allocation.
TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training
Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities.
Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
We first analyzed the representation distribution of textual and visual tokens in MLLM, revealing two important findings: 1) there is a significant gap between textual and visual representations, indicating unsatisfactory cross-modal representation alignment; 2) representations of texts that contain and do not contain hallucinations are entangled, making it challenging to distinguish them.
Ranked #205 on
Visual Question Answering
on MM-Vet
MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models
For developers and amateurs, it is very difficult to grasp all of these task to satisfy their requirements in music processing, especially considering the huge differences in the representations of music data and the model applicability across platforms among various tasks.
Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution
In this paper, we enhance the visibility from a single nighttime haze image by suppressing glow and enhancing low-light regions.
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
Specifically, We incorporate a Text-Semantics-Aware Patch Selector (TSPS) into the ViT backbone to perform a coarse-grained visual token extraction and then attach a flexible Transformer-based Patch Abstraction Decoder (PAD) upon the backbone for top-level visual abstraction.
A Survey on Evaluation of Large Language Models
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications.
EmoGen: Eliminating Subjective Bias in Emotional Music Generation
In this paper, we propose EmoGen, an emotional music generation system that leverages a set of emotion-related music attributes as the bridge between emotion and music, and divides the generation into two stages: emotion-to-attribute mapping with supervised clustering, and attribute-to-music generation with self-supervised learning.
Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
Specifically, for an utterance, we generate its future context with pre-trained language models, potentially containing extra beneficial knowledge in a conversational form homogeneous with the historical ones.
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
To ensure the reliability of PandaLM, we collect a diverse human-annotated test dataset, where all contexts are generated by humans and labels are aligned with human preferences.
PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
Furthermore, we present a comprehensive analysis to understand the mystery behind prompt robustness and its transferability.
Cross-Lingual Paraphrase Identification
Machine Translation
+5
GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework
Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.
Exploiting Pseudo Image Captions for Multimodal Summarization
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives.
Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives.
Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness
The capability of Large Language Models (LLMs) like ChatGPT to comprehend user intent and provide reasonable responses has made them extremely popular lately.
Exploring Vision-Language Models for Imbalanced Learning
However, their performance on imbalanced dataset is relatively poor, where the distribution of classes in the training dataset is skewed, leading to poor performance in predicting minority classes.
Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
End-to-end generation-based approaches have been investigated and applied in task-oriented dialogue systems.
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective
In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective.
BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.
In this paper, we propose a Bottom-Up Patch Summarization approach named BUS which is inspired by the Document Summarization Task in NLP to learn a concise visual summary of lengthy visual token sequences, guided by textual semantics.
Sequence Generation with Label Augmentation for Relation Extraction
Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models.
Ranked #1 on
Relation Extraction
on sciERC-sent
Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction
Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them.
Ranked #2 on
Relation Extraction
on TACRED-Revisited
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
As a pioneering exploration that expands event detection to the scenarios involving informal and heterogeneous texts, we propose a new large-scale Chinese event detection dataset based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.
Consistent Direct Time-of-Flight Video Depth Super-Resolution
We believe the methods and dataset are beneficial to a broad community as dToF depth sensing is becoming mainstream on mobile devices.
DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows.
Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation
A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the typically long music sequences (e. g., over 10, 000 tokens), and the existing models have shortcomings in generating musical repetition structures.
Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs
Answering natural language questions on knowledge graphs (KGQA) remains a great challenge in terms of understanding complex questions via multi-hop reasoning.
Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets
Beyond classification, Conv-Adapter can generalize to detection and segmentation tasks with more than 50% reduction of parameters but comparable performance to the traditional full fine-tuning.
USB: A Unified Semi-supervised Learning Benchmark for Classification
We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning.
Multi-scale Wasserstein Shortest-path Graph Kernels for Graph Classification
However, the existing R-convolution graph kernels cannot resolve both of the two challenges: 1) Comparing graphs at multiple different scales, and 2) Considering the distributions of substructures when computing the kernel matrix.
A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example
Though widely used in industry, traditional task-oriented dialogue systems suffer from three bottlenecks: (i) difficult ontology construction (e. g., intents and slots); (ii) poor controllability and interpretability; (iii) annotation-hungry.
Incorporating Heterophily into Graph Neural Networks for Graph Classification
Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily, which means connected nodes tend to have different class labels and dissimilar features.
Graph Neural Diffusion Networks for Semi-supervised Learning
To solve these two issues, we propose a new graph neural network called GND-Nets (for Graph Neural Diffusion Networks) that exploits the local and global neighborhood information of a vertex in a single layer.
Modeling Human-AI Team Decision Making
AI and humans bring complementary skills to group deliberations.
Frequency-Aware Contrastive Learning for Neural Machine Translation
Inspired by the observation that low-frequency words form a more compact embedding space, we tackle this challenge from a representation learning perspective.
Temporally Consistent Online Depth Estimation in Dynamic Scenes
We present a framework named Consistent Online Dynamic Depth (CODD) to produce temporally consistent depth estimates in dynamic scenes in an online setting.
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs.
Ranked #28 on
Semantic Segmentation
on Cityscapes val
Deep Embedded K-Means Clustering
To this end, we discard the decoder and propose a greedy method to optimize the representation.
Ranked #1 on
Deep Clustering
on MNIST
Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation
This paper proposes a sophisticated neural architecture to incorporate bilingual dictionaries into Neural Machine Translation (NMT) models.
Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
Legal judgment prediction(LJP) is an essential task for legal AI.
Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE).
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval
The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field.
Multi-Hop Transformer for Document-Level Machine Translation
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information.
Multi-view Inference for Relation Extraction with Uncertain Knowledge
Knowledge graphs (KGs) are widely used to facilitate relation extraction (RE) tasks.
Ranked #32 on
Relation Extraction
on DocRED
(using extra training data)
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach
Code summaries are brief natural language descriptions of source code pieces.
SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint
Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction
Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relational facts.
Learning Deep Graph Representations via Convolutional Neural Networks
The learned deep representation for a graph is a dense and low-dimensional vector that captures complex high-order interactions in a vertex neighborhood.
Incorporating User's Preference into Attributed Graph Clustering
In contrast to global clustering, local clustering aims to find only one cluster that is concentrating on the given seed vertex (and also on the designated attributes for attributed graphs).
Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning
Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance.
Tree++: Truncated Tree Based Graph Kernels
At the heart of Tree++ is a graph kernel called the path-pattern graph kernel.
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data
In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class.
PKUSE at SemEval-2019 Task 3: Emotion Detection with Emotion-Oriented Neural Attention Network
This paper presents the system in SemEval-2019 Task 3, {``}EmoContext: Contextual Emotion Detection in Text{''}.
Deep Dynamic Boosted Forest
Specically, we propose to measure the quality of each leaf node of every decision tree in the random forest to determine hard examples.
