Search Results for author:
Found 26 papers, 9 papers with code
Exemplar-Free Class Incremental Learning via Incremental Representation
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i. e., samples).
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms.
Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the searching space.
Boximator: Generating Rich and Controllable Motions for Video Synthesis
Its robust motion controllability is validated by drastic increases in the bounding box alignment metric.
GenEM: Physics-Informed Generative Cryo-Electron Microscopy
To address this, we introduce physics-informed generative cryo-electron microscopy (GenEM), which for the first time integrates physical-based cryo-EM simulation with a generative unpaired noise translation to generate physically correct synthetic cryo-EM datasets with realistic noises.
Make Pixels Dance: High-Dynamic Video Generation
Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence.
Ranked #3 on
Text-to-Video Generation
on UCF-101
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?
However, the performance of these models heavily relies on design choices such as network structures, training data, and training strategies, and these choices have not been extensively discussed in the literature, making it difficult to quantify progress in this field.
eTag: Class-Incremental Learning with Embedding Distillation and Task-Oriented Generation
Most successful CIL methods incrementally train a feature extractor with the aid of stored exemplars, or estimate the feature distribution with the stored prototypes.
CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations
Cryo-electron microscopy (cryo-EM) allows for the high-resolution reconstruction of 3D structures of proteins and other biomolecules.
A Survey on Causal Reinforcement Learning
While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability.
Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks
X-FM has one language encoder, one vision encoder, and one fusion encoder, as well as a new training method.
Ranked #3 on
Visual Grounding
on RefCOCO+ test B
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
Vision language pre-training aims to learn alignments between vision and language from a large amount of data.
Ranked #1 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks.
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
To this end, the cross-view language modeling framework considers both multi-modal data (i. e., image-caption pairs) and multi-lingual data (i. e., parallel sentence pairs) as two different views of the same object, and trains the model to align the two views by maximizing the mutual information between them with conditional masked language modeling and contrastive learning.
VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models
We release the VLUE benchmark to promote research on building vision-language models that generalize well to more diverse images and concepts unseen during pre-training, and are practical in terms of efficiency-performance trade-off.
Vietnamese Language Models
Vietnamese Natural Language Understanding
+1
ULSA: Unified Language of Synthesis Actions for Representation of Synthesis Protocols
This work is an important step towards creating a synthesis ontology and a solid foundation for autonomous robotic synthesis.
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Most existing methods in vision language pre-training rely on object-centric features extracted through object detection and make fine-grained alignments between the extracted features and texts.
Ranked #1 on
Image Retrieval
on Flickr30K 1K test
(using extra training data)
A probabilistic deep learning approach to automate the interpretation of multi-phase diffraction spectra
Autonomous synthesis and characterization of inorganic materials requires the automatic and accurate analysis of X-ray diffraction spectra.
Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking
However, in such a stacked encoder-decoder structure, the operation prediction objective only affects the BERT encoder and the value generation objective mainly affects the RNN decoder.
Ranked #2 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Open-Domain Dialogue Generation Based on Pre-trained Language Models
These results show that discrepancies is an important factor to consider when we use a pre-trained model, and a reduction in discrepancies can lead to improved performance.
Multi-Domain Dialogue State Tracking based on State Graph
Existing approaches usually concatenate previous dialogue state with dialogue history as the input to a bi-directional Transformer encoder.
Ranked #5 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation
Conditioned dialogue generation suffers from the scarcity of labeled responses.
Causal Discovery with Multi-Domain LiNGAM for Latent Factors
In this paper, we propose Multi-Domain Linear Non-Gaussian Acyclic Models for Latent Factors (MD-LiNA), where the causal structure among latent factors of interest is shared for all domains, and we provide its identification results.
Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models
Words are annotated in fine-grained and coarse-grained labels.
Ranked #17 on
Sentiment Analysis
on SST-5 Fine-grained classification
