Search Results for author:
Found 50 papers, 13 papers with code
VisualLens: Personalization through Visual History
We hypothesize that a user's visual history with images reflecting their daily life, offers valuable insights into their interests and preferences, and can be leveraged for personalization.
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
Datasets play a pivotal role in training visual models, facilitating the development of abstract understandings of visual features through diverse image samples and multidimensional attributes.
A Controlled Study on Long Context Extension and Generalization in LLMs
Broad textual understanding and in-context learning require language models that utilize full document contexts.
DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech
In recent years, speech diffusion models have advanced rapidly.
Smart Multi-Modal Search: Contextual Sparse and Dense Embedding Integration in Adobe Express
As user content and queries become increasingly multi-modal, the need for effective multi-modal search systems has grown.
Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?
Currently, Audio Language Models (ALMs) are rapidly advancing due to the developments in large language models and audio neural codecs.
ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation
The results indicate that the ASRRL method significantly outperforms traditional fine-tuning approaches, achieving higher speaker similarity and better overall speech quality with limited reference speeches.
Zero-Shot Long-Form Video Understanding through Screenplay
The Long-form Video Question-Answering task requires the comprehension and analysis of extended video content to respond accurately to questions by utilizing both temporal and contextual information.
A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge
The objective of the challenge is to establish a multi-speaker, multi-lingual Indic Text-to-Speech system with voice cloning capabilities, covering seven Indian languages with both male and female speakers.
MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation
Despite advancements in AIGC technologies for text and image generation, the foley audio dubbing remains rudimentary due to difficulties in cross-modal scene matching and content correlation.
Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio
To effectively detect LLM-based deepfake audio, we focus on the core of the generation process, the conversion from neural codec to waveform.
The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio
With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods.
Paintings and Drawings Aesthetics Assessment with Rich Attributes for Various Artistic Categories
This dataset solely comprises overall scores for high-quality artistic images.
Identifying Causal Effects under Kink Setting: Theory and Evidence
This paper develops a generalized framework for identifying causal impacts in a reduced-form manner under kinked settings when agents can manipulate their choices around the threshold.
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
The generated demos strategically interpolate between existing demos and the given query, transforming the query from OOD to ID.
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks.
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks.
Interpreting and Improving Attention From the Perspective of Large Kernel Convolution
These findings highlight the effectiveness of LKCA in bridging local and global feature modeling, offering a practical and robust solution for real-world applications with limited data and resources.
Making Harmful Behaviors Unlearnable for Large Language Models
Specifically, we introduce ``security vectors'', a few new parameters that can be separated from the LLM, to ensure LLM's responses are consistent with the harmful behavior.
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model.
COGEDAP: A COmprehensive GEnomic Data Analysis Platform
The analyses can be done by running these auto-generated scripts with the software containers.
Joint RIS Calibration and Multi-User Positioning
Reconfigurable intelligent surfaces (RISs) are expected to be a key component enabling the mobile network evolution towards a flexible and intelligent 6G wireless platform.
Nonparametric Decoding for Generative Retrieval
The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed.
The Short-term Impact of Congestion Taxes on Ridesourcing Demand and Traffic Congestion: Evidence from Chicago
To this end, this study applies difference-in-differences (i. e., a regression-based causal inference approach) to empirically evaluate the effects of the congestion tax policy on ridesourcing demand and traffic congestion in Chicago.
DePS: An improved deep learning model for de novo peptide sequencing
De novo peptide sequencing from mass spectrometry data is an important method for protein identification.
Active Learning Over Multiple Domains in Natural Language Tasks
Studies of active learning traditionally assume the target and source data stem from a single domain.
C+1 Loss: Learn to Classify C Classes of Interest and the Background Class Differentially
We figure out that the background class should be treated differently from the classes of interest during training.
Joint Positioning and Tracking via NR Sidelink in 5G-Empowered Industrial IoT: Releasing the Potential of V2X Technology
The fifth generation (5G) mobile networks with enhanced connectivity and positioning capabilities play an increasingly important role in the development of automated vehicle-to-everything (V2X) and other advanced industrial Internet of Things (IoT) systems.
The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering
In the context of question answering, we investigate competing hypotheses for the existence of MPPIs, including poor posterior calibration of neural models, lack of pretraining, and "dataset bias" (where a model learns to attend to spurious, non-generalizable cues in the training data).
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets.
ContourRend: A Segmentation Method for Improving Contours by Rendering
A good object segmentation should contain clear contours and complete regions.
Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT
Materials and Methods In this retrospective and multi-center study, a deep learning model, COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT exams for the detection of COVID-19.
Graph-FCN for image semantic segmentation
Then we apply graph convolutional network to solve this graph node classification problem.
An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering
To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation.
NCUEE at MEDIQA 2019: Medical Text Inference Using Ensemble BERT-BiLSTM-Attention Model
This study describes the model design of the NCUEE system for the MEDIQA challenge at the ACL-BioNLP 2019 workshop.
DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction
The proposed method generates well-positioned centerlines, exhibiting lower number of missing branches and is more robust in the presence of minor imperfections of the object segmentation mask.
Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding
In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end.
Residual Attention based Network for Hand Bone Age Assessment
The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians.
UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation
This paper describes the acquisition of a large scale and high quality parallel corpora for English and Chinese.
