Search Results for author:
Found 40 papers, 15 papers with code
Adaptive Unsupervised Self-training for Disfluency Detection
Supervised methods have achieved remarkable results in disfluency detection.
KAN 2.0: Kolmogorov-Arnold Networks Meet Science
The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs).
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling
New candidate tokens from the decoding process are then used to update the matrix.
RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing
Tactile feedback is critical for understanding the dynamics of both rigid and deformable objects in many manipulation tasks, such as non-prehensile manipulation and dense packing.
Improving Grammatical Error Correction via Contextual Data Augmentation
Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity.
Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training
To address this problem, we propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model.
Exploring Backdoor Attacks against Large Language Model-based Decision Making
Specifically, we propose three attack mechanisms and corresponding backdoor optimization methods to attack different components in the LLM-based decision-making pipeline: word injection, scenario manipulation, and knowledge injection.
Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer
The study explores mitigating overconfidence bias in LLMs to improve their reliability.
Variational Delayed Policy Optimization
In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL).
KAN: Kolmogorov-Arnold Networks
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs).
LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction
In this light, we propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
Progress and Opportunities of Foundation Models in Bioinformatics
Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments.
S$^{2}$-DMs:Skip-Step Diffusion Models
On the CIFAR10 dataset, models trained using our algorithm showed an improvement of 3. 27% to 14. 06% over models trained with traditional methods across various sampling algorithms (DDIMs, PNDMs, DEIS) and different numbers of sampling steps (10, 20, ..., 1000).
Single-Cell RNA-seq Synthesis with Latent Diffusion Model
The single-cell RNA sequencing (scRNA-seq) technology enables researchers to study complex biological systems and diseases with high resolution.
Empowering Autonomous Driving with Large Language Models: A Safety Perspective
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly in out-of-distribution and uncertain data.
Multi-view learning for automatic classification of multi-wavelength auroral images
Finally, to highlight the discriminative information between auroral classes, we propose a lightweight attention feature enhancement module called LAFE.
State-Wise Safe Reinforcement Learning With Pixel Observations
In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations.
D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation
These fields capture the dynamics of the underlying 3D environment and encode both semantic features and instance masks.
Kinematics-aware Trajectory Generation and Prediction with Latent Stochastic Differential Modeling
However, it remains a challenging problem for these methods to ensure that the generated/predicted trajectories are physically realistic.
Dynamic-Resolution Model Learning for Object Pile Manipulation
Prior works typically assume representation at a fixed dimension or resolution, which may be inefficient for simple tasks and ineffective for more complicated tasks.
CSED: A Chinese Semantic Error Diagnosis Corpus
Our experiments show that powerful pre-trained models perform poorly on this corpus.
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions.
Fourier Continuation for Exact Derivative Computation in Physics-Informed Neural Operators
The physics-informed neural operator (PINO) is a machine learning architecture that has shown promising empirical results for learning partial differential equations.
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs
The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network.
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions.
A Tool for Neural Network Global Robustness Certification and Training
Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.
Second Order Ensemble Langevin Method for Sampling and Inverse Problems
We propose a sampling method based on an ensemble approximation of second order Langevin dynamics.
E2Efold-3D: End-to-End Deep Learning Method for accurate de novo RNA 3D Structure Prediction
When E2Efold-3D is coupled with the experimental techniques, the RNA structure prediction field can be greatly advanced.
Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions
Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations.
Joint Differentiable Optimization and Verification for Certified Reinforcement Learning
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e. g., safety, stability) under the learned controller.
CLMB: deep contrastive learning for robust metagenomic binning
Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data.
Learning-based Framework for Sensor Fault-Tolerant Building HVAC Control with Model-assisted Learning
As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption.
POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems
We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs).
Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
To address this issue, we propose a novel semi-supervised transfer learning framework based on optimal transport theory and self-paced ensemble for Sepsis early detection, called SPSSOT, which can efficiently transfer knowledge from the source hospital (with rich labeled data) to the target hospital (with scarce labeled data).
Verification in the Loop: Correct-by-Construction Control Learning with Reach-avoid Guarantees
Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching.
Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
Data quantity and quality are crucial factors for data-driven learning methods.
Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator
Data quantity and quality are crucial factors for data-driven learning methods.
Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints
In order to manipulate a deformable object, such as rope or cloth, in unstructured environments, robots need a way to estimate its current shape.
Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market.
