Search Results for author:
Found 50 papers, 19 papers with code
LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery
We further design an adaptive weight assignment approach that balances the generalization ability of the LLM and the domain expertise of the old CL model.
An Autonomous Large Language Model Agent for Chemical Literature Data Mining
The proposed approach marks a significant advancement in automating chemical literature extraction and demonstrates the potential for AI to revolutionize data management and utilization in chemistry.
SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning
Sign language recognition (SLR) plays a vital role in facilitating communication for the hearing-impaired community.
Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis
Recent AI research plots a promising future of automatic chemical reactions within the chemistry society.
DISCO: Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
Large-scale well-annotated datasets are of great importance for training an effective object detector.
Delete: Deep Lead Optimization Enveloped in Protein Pocket through Unified Deleting Strategies and a Structure-aware Network
Drug discovery is a highly complicated process, and it is unfeasible to fully commit it to the recently developed molecular generation methods.
Decompose and Realign: Tackling Condition Misalignment in Text-to-Image Diffusion Models
The ``Decompose'' phase separates conditions based on pair relationships, computing the result individually for each pair.
Highly accurate and efficient deep learning paradigm for full-atom protein loop modeling with KarmaLoop
Protein loop modeling is the most challenging yet highly non-trivial task in protein structure prediction.
Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning
Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers).
DPPMask: Masked Image Modeling with Determinantal Point Processes
In particular, we evaluate our method on two representative MIM frameworks, MAE and iBOT.
Traj-MAE: Masked Autoencoders for Trajectory Prediction
Specifically, our Traj-MAE employs diverse masking strategies to pre-train the trajectory encoder and map encoder, allowing for the capture of social and temporal information among agents while leveraging the effect of environment from multiple granularities.
PointPatchMix: Point Cloud Mixing with Patch Scoring
With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86. 3% accuracy on ScanObjectNN and 94. 1% accuracy on ModelNet40.
DR-Label: Improving GNN Models for Catalysis Systems by Label Deconstruction and Reconstruction
Reversely, the model Reconstructs a more robust equilibrium state prediction by transforming edge-level predictions to node-level with a sphere-fitting algorithm.
Initial Structure to Relaxed Energy (IS2RE), Direct
Property Prediction
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
To address this problem, we propose a novel method, Fisher Information-based Evidential Deep Learning ($\mathcal{I}$-EDL).
RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction
In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures.
G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e. g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora.
Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation
The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based Single-Atom Alloy Catalysts for CO2 Reduction Reaction
Graph neural networks (GNNs) have drawn more and more attention from material scientists and demonstrated a high capacity to establish connections between the structure and properties.
A Survey on Generative Diffusion Model
Deep generative models are a prominent approach for data generation, and have been used to produce high quality samples in various domains.
MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails
In high-throughput experimentation (HTE) datasets, the average yield of our methodology's top 10 high-yield reactions is relatively close to the results of ideal yield selection.
Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations
Concretely, for trusty representation learning, we propose to incorporate pseudo labels to instruct the pair selection, obtaining more reliable representation pairs for pixel contrast.
Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation
Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos and then employs a translation module to translate glosses into spoken sentences.
Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels.
LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction
Precise congestion prediction from a placement solution plays a crucial role in circuit placement.
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning
The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones.
RetroPrime: A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictions
RetroPrime achieves the Top-1 accuracy of 64. 8% and 51. 4%, when the reaction type is known and unknown, respectively, in the USPTO-50 K dataset.
Ranked #12 on
Single-step retrosynthesis
on USPTO-50k
Balancing Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning
Fairness in recommendation has attracted increasing attention due to bias and discrimination possibly caused by traditional recommenders.
Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction
Value function is the central notion of Reinforcement Learning (RL).
Noise against noise: stochastic label noise helps combat inherent label noise
The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect, previously studied in optimization by analyzing the dynamics of parameter updates.
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption. The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN).
Ranked #45 on
Image Classification
on Clothing1M
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
For validation, we prove that a noisy validation set is reliable, addressing the critical demand of model selection in scenarios like hyperparameter-tuning and early stopping.
A Rotation-Invariant Framework for Deep Point Cloud Analysis
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations.
Towards Disentangling Non-Robust and Robust Components in Performance Metric
Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.
PMD: An Optimal Transportation-based User Distance for Recommender Systems
Collaborative filtering, a widely-used recommendation technique, predicts a user's preference by aggregating the ratings from similar users.
Wasserstein Collaborative Filtering for Item Cold-start Recommendation
We further adopt the idea of CF and propose Wasserstein CF (WCF) to improve the recommendation performance on cold-start items.
Spectral-based Graph Convolutional Network for Directed Graphs
Our approach can work directly on directed graph data in semi-supervised nodes classification tasks.
Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small.
Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work.
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.
Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates.
Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed.
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels.
Ranked #37 on
Image Classification
on mini WebVision 1.0
Log Hyperbolic Cosine Loss Improves Variational Auto-Encoder
In Variational Auto-Encoder (VAE), the default choice of reconstruction loss function between the decoded sample and the input is the squared $L_2$.
Cascaded Feature Network for Semantic Segmentation of RGB-D Images
Our approach is to use the available depth to split the image into layers with common visual characteristic of objects/scenes, or common "scene-resolution".
Ranked #72 on
Semantic Segmentation
on NYU Depth v2
Learning to Aggregate Ordinal Labels by Maximizing Separating Width
While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users.
From Noise Modeling to Blind Image Denoising
This paper addresses this problem and proposes a novel blind image denoising algorithm which can cope with real-world noisy images even when the noise model is not provided.
Blind Image Denoising via Dependent Dirichlet Process Tree
This paper addresses this problem and proposes a novel blind image denoising algorithm to recover the clean image from noisy one with the unknown noise model.
Online Prediction of Dyadic Data with Heterogeneous Matrix Factorization
We further develop a novel online learning approach for Variational inference and use it for the online learning of HeMF, which can efficiently cope with the important large-scale DDP problem.
An Efficient Statistical Method for Image Noise Level Estimation
In this paper, we address the problem of estimating noise level from a single image contaminated by additive zero-mean Gaussian noise.
