Search Results for author:
Found 46 papers, 14 papers with code
Context Shift Reduction for Offline Meta-Reinforcement Learning
In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets.
Collaborative Large Language Model for Recommender Systems
Recently, there is a growing interest in developing next-generation recommender systems (RSs) based on pretrained large language models (LLMs), fully utilizing their encoded knowledge and reasoning ability.
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world.
Polarization Multi-Image Synthesis with Birefringent Metasurfaces
In contrast to previous work on incoherent opto-electronic filtering that can realize only one spatial filter, our approach can realize a continuous family of filters from a single capture, with filters being selected from the family by adjusting the post-capture digital summation weights.
Pushing the Limits of Machine Design: Automated CPU Design with AI
By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours.
Online Prototype Alignment for Few-shot Policy Transfer
Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment.
Path-Specific Counterfactual Fairness for Recommender Systems
But since sensitive features may also affect user interests in a fair manner (e. g., race on culture-based preferences), indiscriminately eliminating all the influences of sensitive features inevitably degenerate the recommendations quality and necessary diversities.
Flew Over Learning Trap: Learn Unlearnable Samples by Progressive Staged Training
Unlearning techniques are proposed to prevent third parties from exploiting unauthorized data, which generate unlearnable samples by adding imperceptible perturbations to data for public publishing.
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation
This imperceptible protective noise makes the data almost unlearnable for diffusion models, i. e., diffusion models trained or fine-tuned on the protected data cannot generate high-quality and diverse images related to the protected training data.
ANPL: Towards Natural Programming with Interactive Decomposition
We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together.
Ranked #4 on
Code Generation
on HumanEval
Conceptual Reinforcement Learning for Language-Conditioned Tasks
Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments.
Ultra-low Precision Multiplication-free Training for Deep Neural Networks
The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications.
Online Symbolic Regression with Informative Query
Symbolic regression, the task of extracting mathematical expressions from the observed data $\{ \vx_i, y_i \}$, plays a crucial role in scientific discovery.
Quantized Distributed Training of Large Models with Convergence Guarantees
Communication-reduction techniques are a popular way to improve scalability in data-parallel training of deep neural networks (DNNs).
Dual Class-Aware Contrastive Federated Semi-Supervised Learning
To our knowledge, we are the first to present an FSSL method that utilizes only 10\% labeled clients, while still achieving superior performance compared to standard federated supervised learning, which uses all clients with labeled data.
StereoISP: Rethinking Image Signal Processing for Dual Camera Systems
Conventional image signal processing (ISP) frameworks are designed to reconstruct an RGB image from a single raw measurement.
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Object-Category Aware Reinforcement Learning
Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL.
Multivariate Hawkes-based Models in LOB: European, Spread and Basket Option Pricing
In this paper, we consider pricing of European options and spread options for Hawkes-based model for the limit order book.
Remote Work Optimization with Robust Multi-channel Graph Neural Networks
Introducing a brand new workplace type naturally leads to the cold-start problem, which is particularly more common for less active job seekers.
FedMCSA: Personalized Federated Learning via Model Components Self-Attention
Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data.
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection.
Neural Program Synthesis with Query
In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4% on the ImageNet dataset, largely pushing the certified defenses for practical use.
Learning Controllable Elements Oriented Representations for Reinforcement Learning
Deep Reinforcement Learning (deep RL) has been successfully applied to solve various decision-making problems in recent years.
Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment
In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (Zero-Shot)
on CMRC 2018
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+18
Improving Dialogue Breakdown Detection with Semi-Supervised Learning
In ablations on DBDC4 data from 2019, our semi-supervised learning methods improve the performance of a baseline BERT model by 2\% accuracy.
DeText: A Deep Text Ranking Framework with BERT
Ranking is the most important component in a search system.
MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method
Most modern Multi-Object Tracking (MOT) systems typically apply REID-based paradigm to hold a balance between computational efficiency and performance.
Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network
Predicting Origin-Destination (OD) flow is a crucial problem for intelligent transportation.
DWM: A Decomposable Winograd Method for Convolution Acceleration
In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers.
Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned
LinkedIn Talent Solutions business contributes to around 65% of LinkedIn's annual revenue, and provides tools for job providers to reach out to potential candidates and for job seekers to find suitable career opportunities.
Towards Deep and Representation Learning for Talent Search at LinkedIn
In this paper, we present the results of our application of deep and representation learning models on LinkedIn Recruiter.
Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras.
BENCHIP: Benchmarking Intelligence Processors
The variety of emerging intelligence processors requires standard benchmarks for fair comparison and system optimization (in both software and hardware).
Focal Track: Depth and Accommodation With Oscillating Lens Deformation
The focal track sensor is a monocular and computationally efficient depth sensor that is based on defocus controlled by a liquid membrane lens.
Towards thinner convolutional neural networks through Gradually Global Pruning
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices.
Attribute-controlled face photo synthesis from simple line drawing
In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion.
Every Filter Extracts A Specific Texture In Convolutional Neural Networks
We also demonstrate that style of images could be a combination of these texture primitives.
A Generic Inverted Index Framework for Similarity Search on the GPU - Technical Report
We propose a novel generic inverted index framework on the GPU (called GENIE), aiming to reduce the programming complexity of the GPU for parallel similarity search of different data types.
Sliding-Window Optimization on an Ambiguity-Clearness Graph for Multi-object Tracking
Multi-object tracking remains challenging due to frequent occurrence of occlusions and outliers.
Intelligent Health Recommendation System for Computer Users
The time people spend in front of computers has been increasing steadily due to the role computers play in modern society.
Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition
Firstly, we divide the feature space into several subspaces using the decomposition method proposed in this paper.
