Search Results for author:
Found 35 papers, 15 papers with code
Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning
Aligning these distributions between corresponding regions from different tasks imparts higher flexibility and capacity to capture intra-region structures, accommodating a broader range of tasks.
Generalized Predictive Model for Autonomous Driving
In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline.
Embodied Understanding of Driving Scenarios
Hereby, we introduce the Embodied Language Model (ELM), a comprehensive framework tailored for agents' understanding of driving scenes with large spatial and temporal spans.
Hallucination Detection and Hallucination Mitigation: An Investigation
Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications.
GraphGPT: Graph Learning with Generative Pre-trained Transformers
We introduce \textit{GraphGPT}, a novel model for Graph learning by self-supervised Generative Pre-training Transformers.
Fully Sparse 3D Occupancy Prediction
Occupancy prediction plays a pivotal role in autonomous driving.
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines.
ReCo-Diff: Explore Retinex-Based Condition Strategy in Diffusion Model for Low-Light Image Enhancement
Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models.
AAMDM: Accelerated Auto-regressive Motion Diffusion Model
This paper introduces the Accelerated Auto-regressive Motion Diffusion Model (AAMDM), a novel motion synthesis framework designed to achieve quality, diversity, and efficiency all together.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies
Given a new task instance/context, the Elastic-GMM is transformed with Laplacian Editing and used to re-estimate the LPV-DS policy.
UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost.
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation.
Differentially-Private Decision Trees and Provable Robustness to Data Poisoning
By leveraging the better privacy-utility trade-off of PrivaTree we are able to train decision trees with significantly better robustness against backdoor attacks compared to regular decision trees and with meaningful theoretical guarantees.
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
Learning and Adapting Agile Locomotion Skills by Transferring Experience
Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running.
Graph-based Topology Reasoning for Driving Scenes
Understanding the road genome is essential to realize autonomous driving.
Ranked #5 on
3D Lane Detection
on OpenLane-V2 val
3D Data Augmentation for Driving Scenes on Camera
The proposed data augmentation approach contributes to a gain of 1. 7% and 1. 4% in terms of detection accuracy, on Waymo and nuScences respectively.
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Sequential Density Estimation via Nonlinear Continuous Weighted Finite Automata
Although WFAs have been extended to deal with continuous input data, namely continuous WFAs (CWFAs), it is still unclear how to approximate density functions over sequences of continuous random variables using WFA-based models, due to the limitation on the expressiveness of the model as well as the tractability of approximating density functions via CWFAs.
UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision
This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner.
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
UserBERT: Self-supervised User Representation Learning
This paper extends the BERT model to user data for pretraining user representations in a self-supervised way.
Connecting Weighted Automata, Tensor Networks and Recurrent Neural Networks through Spectral Learning
In this paper, we present connections between three models used in different research fields: weighted finite automata~(WFA) from formal languages and linguistics, recurrent neural networks used in machine learning, and tensor networks which encompasses a set of optimization techniques for high-order tensors used in quantum physics and numerical analysis.
Neural Representations in Hybrid Recommender Systems: Prediction versus Regularization
We also apply the NRP framework to a direct neural network structure which predicts the ratings without reconstructing the user and item information.
Learning to Profile: User Meta-Profile Network for Few-Shot Learning
1) Meta-learning model: In the context of representation learning with e-commerce user behavior data, we propose a meta-learning framework called the Meta-Profile Network, which extends the ideas of matching network and relation network for knowledge transfer and fast adaptation; 2) Encoding strategy: To keep high fidelity of large-scale long-term sequential behavior data, we propose a time-heatmap encoding strategy that allows the model to encode data effectively; 3) Deep network architecture: A multi-modal model combined with multi-task learning architecture is utilized to address the cross-domain knowledge learning and insufficient label problems.
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces
We propose a general framework for policy representation for reinforcement learning tasks.
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning.
Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model.
Bayesian Optimization in Variational Latent Spaces with Dynamic Compression
We propose a model and architecture for a sequential variational autoencoder that embeds the space of simulated trajectories into a lower-dimensional space of latent paths in an unsupervised way.
GRP Model for Sensorimotor Learning
Learning from complex demonstrations is challenging, especially when the demonstration consists of different strategies.
Deep Heterogeneous Autoencoders for Collaborative Filtering
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems.
Connecting Weighted Automata and Recurrent Neural Networks through Spectral Learning
In this paper, we unravel a fundamental connection between weighted finite automata~(WFAs) and second-order recurrent neural networks~(2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent.
Neural Network Based Nonlinear Weighted Finite Automata
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models.
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
