Search Results for author:
Found 91 papers, 31 papers with code
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications.
Practical Implementation of KalmanNet for Accurate Data Fusion in Integrated Navigation
The extended Kalman filter has been widely used in sensor fusion to achieve integrated navigation and localization.
Latent Space Imaging
Digital imaging systems have classically been based on brute-force measuring and processing of pixels organized on regular grids.
Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems.
Scalable Differentiable Causal Discovery in the Presence of Latent Confounders with Skeleton Posterior (Extended Version)
Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs.
End-to-End Hybrid Refractive-Diffractive Lens Design with Differentiable Ray-Wave Model
Hybrid refractive-diffractive lenses combine the light efficiency of refractive lenses with the information encoding power of diffractive optical elements (DOE), showing great potential as the next generation of imaging systems.
Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games.
Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
The common goal is an achievable state with high value, which is obtained by sampling from the distribution of future states.
An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
Recent researches reveal that simple divide-and-conquer prompting strategy, i. e. simply dividing the input sequence to multiple sub-inputs, can also substantially improve LLM's performance in some specific tasks such as misinformation detection.
Enhance Reasoning for Large Language Models in the Game Werewolf
This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents.
More Agents Is All You Need
We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated.
Affordable Generative Agents
The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents.
Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e. g., winning games).
TAROT: A Hierarchical Framework with Multitask Co-Pretraining on Semi-Structured Data towards Effective Person-Job Fit
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation.
Limitations of Data-Driven Spectral Reconstruction -- Optics-Aware Analysis and Mitigation
Hyperspectral imaging empowers machine vision systems with the distinct capability of identifying materials through recording their spectral signatures.
Mean-field underdamped Langevin dynamics and its spacetime discretization
We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures.
Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy.
Professional Network Matters: Connections Empower Person-Job Fit
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions.
Diversity from Human Feedback
DivHF learns a behavior descriptor consistent with human preference by querying human feedback.
Text-to-Image Generation for Abstract Concepts
Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts.
PSGformer: Enhancing 3D Point Cloud Instance Segmentation via Precise Semantic Guidance
The model achieves a more comprehensive feature representation by the features which connect global and local features.
RLTF: Reinforcement Learning from Unit Test Feedback
The goal of program synthesis, or code generation, is to generate executable code based on given descriptions.
Maximum Entropy Heterogeneous-Agent Reinforcement Learning
We embed cooperative MARL problems into probabilistic graphical models, from which we derive the maximum entropy (MaxEnt) objective for MARL.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering
Graph CF has attracted more and more attention in recent years due to its effectiveness in leveraging high-order information in the user-item bipartite graph for better recommendations.
Future-conditioned Unsupervised Pretraining for Decision Transformer
While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data.
Image Quality Is Not All You Want: Task-Driven Lens Design for Image Classification
Experimental results demonstrate the designed image classification lens (``TaskLens'') exhibits higher accuracy compared to conventional imaging-driven lenses, even with fewer lens elements.
Skill-Based Few-Shot Selection for In-Context Learning
Few-shot selection -- selecting appropriate examples for each test instance separately -- is important for in-context learning.
Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention
Recent years have witnessed the great potential of attention mechanism in graph representation learning.
How Do In-Context Examples Affect Compositional Generalization?
Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence.
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.
Aberration-Aware Depth-from-Focus
Computer vision methods for depth estimation usually use simple camera models with idealized optics.
Does Deep Learning Learn to Abstract? A Systematic Probing Framework
Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context.
Robust Mid-Pass Filtering Graph Convolutional Networks
Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks.
Homophily-oriented Heterogeneous Graph Rewiring
To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN.
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse.
Curriculum Learning for ab initio Deep Learned Refractive Optics
Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective.
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
In more detail, penultimate layer outputs on the training set are considered as the representations of in-distribution (ID) data.
Ranked #11 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
We show that, despite such state distribution shift, the policy gradient estimation bias can be reduced in the following three ways: 1) a small learning rate; 2) an adaptive-learning-rate-based optimizer; and 3) KL regularization.
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.
DGI: Easy and Efficient Inference for GNNs
In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution.
DIGMN: Dynamic Intent Guided Meta Network for Differentiated User Engagement Forecasting in Online Professional Social Platforms
Furthermore, based on the dynamic user intent representations, we propose a meta predictor to perform differentiated user engagement forecasting.
Revisiting Discrete Soft Actor-Critic
We study the adaption of soft actor-critic (SAC) from continuous action space to discrete action space.
Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement learning.
Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach
Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data.
Ranked #6 on
Node Classification
on Squirrel
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.
Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima
Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training.
MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors.
Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL).
Making Large Language Models Better Reasoners with Step-Aware Verifier
Few-shot learning is a challenging task that requires language models to generalize from limited examples.
Ranked #45 on
Arithmetic Reasoning
on GSM8K
Sparse Optical Flow-Based Line Feature Tracking
To achieve this goal, an efficient two endpoint tracking (TET) method is presented: first, describe a given line feature with its two endpoints; next, track the two endpoints based on SOF to obtain two new tracked endpoints by minimizing a pixel-level grayscale residual function; finally, connect the two tracked endpoints to generate a new line feature.
Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models
This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations, leading to a more effective way to adapt unfamiliar inputs to frozen PLMs.
HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction
The Temporal Link Prediction task of WSDM Cup 2022 expects a single model that can work well on two kinds of temporal graphs simultaneously, which have quite different characteristics and data properties, to predict whether a link of a given type will occur between two given nodes within a given time span.
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.
Reasoning Like Program Executors
Reasoning over natural language is a long-standing goal for the research community.
Ranked #2 on
Question Answering
on DROP Test
(using extra training data)
JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.
Efficient Exploration
Hierarchical Reinforcement Learning
+4
Snapshot HDR Video Construction Using Coded Mask
This paper study the reconstruction of High Dynamic Range (HDR) video from snapshot-coded LDR video.
Source Free Unsupervised Graph Domain Adaptation
To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph.
Neuron with Steady Response Leads to Better Generalization
Based on the analysis results, we articulate the Neuron Steadiness Hypothesis: the neuron with similar responses to instances of the same class leads to better generalization.
GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
For node-level tasks, GNNs have strong power to model the homophily property of graphs (i. e., connected nodes are more similar) while their ability to capture the heterophily property is often doubtful.
Learning Diverse Policies in MOBA Games via Macro-Goals
Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.
Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.
Diffractive lensless imaging with optimized Voronoi-Fresnel phase
Here we report a diffractive lensless camera with spatially-coded Voronoi-Fresnel phase to achieve superior image quality.
Neural Étendue Expander for Ultra-Wide-Angle High-Fidelity Holographic Display
As a result, modern holographic displays possess low \'{e}tendue, which is the product of the display area and the maximum solid angle of diffracted light.
Neuron Campaign for Initialization Guided by Information Bottleneck Theory
Initialization plays a critical role in the training of deep neural networks (DNN).
A Miniature Biological Eagle-Eye Vision System for Small Target Detection
Small target detection is known to be a challenging problem.
A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging
We present a thorough investigation of these state-of-the-art spectral reconstruction methods from the widespread RGB images.
Active-set algorithms based statistical inference for shape-restricted generalized additive Cox regression models
In this paper, we introduce the shape-restricted inference to the celebrated Cox regression model (SR-Cox), in which the covariate response is modeled as shape-restricted additive functions.
Boosting Offline Reinforcement Learning with Residual Generative Modeling
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment
In this paper, we propose a cooperative MARL method with sequential credit assignment (SeCA) that deduces each agent's contribution to the team's success one by one to learn better cooperation.
MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.
Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging
We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures.
Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking
Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN).
Multispectral Illumination Estimation Using Deep Unrolling Network
This paper examines the problem of illumination spectra estimation in multispectral images.
Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.
Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
Towards Playing Full MOBA Games with Deep Reinforcement Learning
However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.
PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
This paper presents PL-VINS, a real-time optimization-based monocular VINS method with point and line features, developed based on the state-of-the-art point-based VINS-Mono \cite{vins}.
Fast ORB-SLAM without Keypoint Descriptors
ORB-SLAM2 \cite{orbslam2} is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe.
Robotics Computational Geometry I.4.0; I.4.9
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
Real time backbone for semantic segmentation
The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding.
Optimizing Controller Placement for Software-Defined Networks
In comparison to communication delay, existing literature on the CPP assumes that the influence of controller workload distribution on network performance is negligible.
Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
In the Federated Learning paradigm, a master machine learning model is distributed to user clients, the clients use their locally stored data and model for both inference and calculating model updates.
Hierarchical Macro Strategy Model for MOBA Game AI
In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.
Catadioptric HyperSpectral Light Field Imaging
In this paper, we present a single camera hyperspectral light field imaging solution that we call Snapshot Plenoptic Imager (SPI).
Noise Robust IOA/CAS Speech Separation and Recognition System For The Third 'CHIME' Challenge
This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Calibration of Multiple Fish-Eye Cameras Using a Wand
Fish-eye cameras are becoming increasingly popular in computer vision, but their use for 3D measurement is limited partly due to the lack of an accurate, efficient and user-friendly calibration procedure.
Bethe-ADMM for Tree Decomposition based Parallel MAP Inference
We present a parallel MAP inference algorithm called Bethe-ADMM based on two ideas: tree-decomposition of the graph and the alternating direction method of multipliers (ADMM).
Scan-based Compressed Terahertz Imaging and Real-Time Reconstruction via the Complex-valued Fast Block Sparse Bayesian Learning Algorithm
Compressed Sensing based Terahertz imaging (CS-THz) is a computational imaging technique.
Fast Marginalized Block Sparse Bayesian Learning Algorithm
One typical correlation structure is the intra-block correlation in block sparse signals.
The Annealing Sparse Bayesian Learning Algorithm
The performance such as NMSE and F-measure can be greatly improved due to the annealing technique.
