Search Results for author:
Found 35 papers, 9 papers with code
Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
In response, we propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL, termed Gradient-based Estimation (GBE), which relies on the analytic gradient derived along trajectories.
Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting
Despite recent advances in improving surface reconstruction accuracy, the reconstructed results still exhibit bias and suffer from inefficiency in storage and training.
Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs
Autism spectrum disorder(ASD) is a pervasive developmental disorder that significantly impacts the daily functioning and social participation of individuals.
Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions
To provide future directions toward building energy-efficient large SNN models, we present a survey of existing methods for developing deep spiking neural networks, with a focus on emerging Spiking Transformers.
Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation
Although recent advancements in text-to-3D generation have significantly improved generation quality, issues like limited level of detail and low fidelity still persist, which requires further improvement.
Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
In this paper, we propose an off-policy policy gradient method with the optimal action-dependent baseline (Off-OAB) to mitigate this variance issue.
Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo
Natural Light Uncalibrated Photometric Stereo (NaUPS) relieves the strict environment and light assumptions in classical Uncalibrated Photometric Stereo (UPS) methods.
Learning to Manipulate Artistic Images
Recent advancement in computer vision has significantly lowered the barriers to artistic creation.
Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images
However, in the case of inputting sparse Low Dynamic Range (LDR) panoramic images, NeRF often degrades with under-constrained geometry and is unable to reconstruct HDR radiance from LDR inputs.
$\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning
Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system.
Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation
A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs).
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
However, due to the quantization error and accumulating error, it often requires lots of time steps (high inference latency) to achieve high performance, which negates SNN's advantages.
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
Although the ambiguity is alleviated on non-Lambertian objects, the problem is still difficult to solve for more general objects with complex shapes introducing irregular shadows and general materials with complex reflectance like anisotropic reflectance.
ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model
Overall, LLMs have the potential to revolutionize dental diagnosis and treatment, which indicates a promising avenue for clinical application and research in dentistry.
Evaluating the Efficacy of Skincare Product: A Realistic Short-Term Facial Pore Simulation
In this paper, we propose the first simulation model to reveal facial pore changes after using skincare products.
NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo
Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by unknown light.
TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources
In this work, we propose TinyLight, the first DRL-based ATSC model that is designed for devices with extremely limited resources.
Automatic Facial Skin Feature Detection for Everyone
We present an automatic facial skin feature detection method that works across a variety of skin tones and age groups for selfies in the wild.
DiLiGenT102: A Photometric Stereo Benchmark Dataset With Controlled Shape and Material Variation
Evaluating photometric stereo using real-world dataset is important yet difficult.
Single Image Reflection Removal With Absorption Effect
In this paper, we consider the absorption effect for the problem of single image reflection removal.
Panoramic Image Reflection Removal
This paper studies the problem of panoramic image reflection removal, aiming at reliving the content ambiguity between reflection and transmission scenes.
Indoor Lighting Estimation Using an Event Camera
Image-based methods for indoor lighting estimation suffer from the problem of intensity-distance ambiguity.
On Convergence of Gradient Expected Sarsa($λ$)
We study the convergence of $\mathtt{Expected~Sarsa}(\lambda)$ with linear function approximation.
Sample Complexity of Policy Gradient Finding Second-Order Stationary Points
However, due to the inherent non-concavity of its objective, convergence to a first-order stationary point (FOSP) can not guarantee the policy gradient methods finding a maximal point.
Object Properties Inferring from and Transfer for Human Interaction Motions
In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.
What Does Plate Glass Reveal About Camera Calibration?
This paper aims to calibrate the orientation of glass and the field of view of the camera from a single reflection-contaminated image.
Emotion recognition with 4kresolution database
Human emotion can be classified as one of the basic emotion types like being angry, happy or dimensional emotion with valence and arousal values.
Gradient Q$(σ, λ)$: A Unified Algorithm with Function Approximation for Reinforcement Learning
To address above problem, we propose a GQ$(\sigma,\lambda)$ that extends tabular Q$(\sigma,\lambda)$ with linear function approximation.
Expected Sarsa($λ$) with Control Variate for Variance Reduction
In this paper, for reducing the variance, we introduce control variate technique to $\mathtt{Expected}$ $\mathtt{Sarsa}$($\lambda$) and propose a tabular $\mathtt{ES}$($\lambda$)-$\mathtt{CV}$ algorithm.
Policy Optimization with Stochastic Mirror Descent
Improving sample efficiency has been a longstanding goal in reinforcement learning.
Contribution of Radio Halos to the Foreground for SKA EoR Experiments
The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.
Cosmology and Nongalactic Astrophysics
SPLINE-Net: Sparse Photometric Stereo through Lighting Interpolation and Normal Estimation Networks
This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net).
Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics.
Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
In this paper, we propose a general framework to combine DQN and most of the return-based reinforcement learning algorithms, named R-DQN.
A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning
Results show that, with an intermediate value of $\sigma$, $Q(\sigma ,\lambda)$ creates a mixture of the existing algorithms that can learn the optimal value significantly faster than the extreme end ($\sigma=0$, or $1$).
