Search Results for author:
Found 58 papers, 18 papers with code
Attention Heads of Large Language Models: A Survey
As a result, many researchers have begun exploring the potential internal mechanisms of LLMs, aiming to identify the essence of their reasoning bottlenecks, with most studies focusing on attention heads.
Xinyu: An Efficient LLM-based System for Commentary Generation
To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology.
$\text{Memory}^3$: Language Modeling with Explicit Memory
The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values).
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information.
DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning
Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given state, resulting in the extrapolation error issue.
Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning
Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs).
xFinder: Robust and Pinpoint Answer Extraction for Large Language Models
The continuous advancement of large language models (LLMs) has brought increasing attention to the critical issue of developing fair and reliable methods for evaluating their performance.
MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning
Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL).
DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training
In particular, by conducting graph sampling beforehand, DiskGNN acquires the node features that will be accessed by model computation, and such information is utilized to pack the target node features contiguously on disk to avoid read amplification.
Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving
Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems.
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG).
Debiasing Recommendation with Personal Popularity
Many methods have been proposed to reduce GP bias but they fail to notice the fundamental problem of GP, i. e., it considers popularity from a \textit{global} perspective of \textit{all users} and uses a single set of popular items, and thus cannot capture the interests of individual users.
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems.
Off-Policy Primal-Dual Safe Reinforcement Learning
Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint violation during training.
Grimoire is All You Need for Enhancing Large Language Models
In this paper, we propose a method SLEICL that involves learning from examples using strong language models and then summarizing and transferring these learned skills to weak language models for inference and application.
HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning
Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day.
RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems
The existing studies focus on dynamically allocating CRs in queue truncation scenarios (i. e., allocating the size of candidates), and formulate the CR allocation problem as an optimization problem with constraints.
CaVE: A Cone-Aligned Approach for Fast Predict-then-optimize with Binary Linear Programs
The end-to-end predict-then-optimize framework, also known as decision-focused learning, has gained popularity for its ability to integrate optimization into the training procedure of machine learning models that predict the unknown cost (objective function) coefficients of optimization problems from contextual instance information.
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
These techniques encompass the use of directed hallucination induction and strategies that deliberately alter authentic text to produce hallucinations.
Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
We propose a new MDR method named EDDA with two key components, i. e., embedding disentangling recommender and domain alignment, to tackle the two challenges respectively.
G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima
Deep neural networks (DNNs) have demonstrated promising results in various complex tasks.
AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning
Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner.
Safe Offline Reinforcement Learning with Real-Time Budget Constraints
Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years.
How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence
In general, a large scale of testing in simulation environment is conducted and then the learned driving knowledge is transferred to the real world, so how to adapt driving knowledge learned in simulation to reality becomes a critical issue.
Multi-Spectrally Constrained Low-PAPR Waveform Optimization for MIMO Radar Space-Time Adaptive Processing
This paper focuses on the joint design of transmit waveforms and receive filters for airborne multiple-input-multiple-output (MIMO) radar systems in spectrally crowded environments.
Co-Design for Spectral Coexistence between RIS-aided MIMO Radar and MIMO Communication Systems
Reconfigurable intelligent surface (RIS) refers to a signal reflection surface containing a large number of low-cost passive reflecting elements.
Constant-Modulus Waveform Design for Dual-Function Radar-Communication Systems in the Presence of Clutter
We investigate the constant-modulus (CM) waveform design for dual-function radar communication systems in the presence of clutter. To minimize the interference power and enhance the target acquisition performance, we use the signal-to-interference-plus-noise-ratio as the design metric. In addition, to ensure the quality of the service for each communication user, we enforce a constraint on the synthesis error of every communication signals. An iterative algorithm, which is based on cyclic optimization, Dinkinbach's transform, and alternating direction of method of multipliers, is proposed to tackle the encountered non-convex optimization problem. Simulations illustrate that the CM waveforms synthesized by the proposed algorithm allow to suppress the clutter efficiently and control the synthesis error of communication signals to a low level.
Connectivity-constrained Interactive Panoptic Segmentation
We address interactive panoptic annotation, where one segment all object and stuff regions in an image.
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.
AI Testing Framework for Next-G O-RAN Networks: Requirements, Design, and Research Opportunities
This article presents a general automated, distributed and AI-enabled testing framework to test AI models deployed in O-RAN in terms of their decision-making performance, vulnerability and security.
Waveform Design for Mutual Interference Mitigation in Automotive Radar
The mutual interference between similar radar systems can result in reduced radar sensitivity and increased false alarm rates.
BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion
During deployment, we combine the offline RL model with the LP model to generate a robust policy under the budget constraints.
PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming
PyEPO provides a simple interface for the definition of new optimization problems, the implementation of state-of-the-art predict-then-optimize training algorithms, the use of custom neural network architectures, and the comparison of end-to-end approaches with the two-stage approach.
Generalized Federated Learning via Sharpness Aware Minimization
Therefore, in this paper, we revisit the solutions to the distribution shift problem in FL with a focus on local learning generality.
A Probabilistic Model-Based Robust Waveform Design for MIMO Radar Detection
This paper addresses robust waveform design for multiple-input-multiple-output (MIMO) radar detection.
LoMar: A Local Defense Against Poisoning Attack on Federated Learning
Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network.
Face2Exp: Combating Data Biases for Facial Expression Recognition
To combat the mismatch between FR and FER data, Meta-Face2Exp uses a circuit feedback mechanism, which improves the base network with the feedback from the adaptation network.
Automatic Meta-Path Discovery for Effective Graph-Based Recommendation
Specifically, we define a vector encoding for meta-paths and design a policy network to extend meta-paths.
FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation
Federated Learning (FL) is a decentralized machine learning architecture, which leverages a large number of remote devices to learn a joint model with distributed training data.
Overcome Anterograde Forgetting with Cycled Memory Networks
This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.
BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market
Further, a novel offline reinforcement learning method and an off-policy evaluation algorithm are proposed for policy learning and policy evaluation, respectively.
Reviewing continual learning from the perspective of human-level intelligence
Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.
Learning by Active Forgetting for Neural Networks
This paper presents a learning model by active forgetting mechanism with artificial neural networks.
Vertex-Centric Visual Programming for Graph Neural Networks
Graph neural networks (GNNs) have achieved remarkable performance in many graph analytics tasks such as node classification, link prediction and graph clustering.
Interpretable performance analysis towards offline reinforcement learning: A dataset perspective
We make it open-source for fair and comprehensive competitions between offline RL algorithms with complete datasets and checkpoints being provided.
Constrained Radar Waveform Design for Range Profiling
Range profiling refers to the measurement of target response along the radar slant range.
Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients
Federated learning (FL) is a new machine learning framework which trains a joint model across a large amount of decentralized computing devices.
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference.
Connectivity-constrained interactive annotations for panoptic segmentation
Large-scale ground truth data sets are of crucial importance for deep learning based segmentation models, but annotating per-pixel masks is prohibitively time consuming.
Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?
In this paper, we incorporate the logic information with the help of the Natural Language Inference (NLI) task to the Story Cloze Test (SCT).
On the Recursive Teaching Dimension of VC Classes
This is the first upper bound for $RTD(C)$ that depends only on $VCD(C)$, independent of the size of the concept class $|C|$ and its~domain size $n$.
A Local Density-Based Approach for Local Outlier Detection
A Relative Density-based Outlier Score (RDOS) is introduced to measure the local outlierness of objects, in which the density distribution at the location of an object is estimated with a local KDE method based on extended nearest neighbors of the object.
Kernel-based Generative Learning in Distortion Feature Space
The recognition diversity indicates that a hybrid combination of the proposed generative classifier and the discriminative classifier could further improve the classification performance.
FSMJ: Feature Selection with Maximum Jensen-Shannon Divergence for Text Categorization
In this paper, we present a new wrapper feature selection approach based on Jensen-Shannon (JS) divergence, termed feature selection with maximum JS-divergence (FSMJ), for text categorization.
EEF: Exponentially Embedded Families with Class-Specific Features for Classification
In this letter, we present a novel exponentially embedded families (EEF) based classification method, in which the probability density function (PDF) on raw data is estimated from the PDF on features.
Toward Optimal Feature Selection in Naive Bayes for Text Categorization
Based on the JMH-divergence, we develop two efficient feature selection methods, termed maximum discrimination ($MD$) and $MD-\chi^2$ methods, for text categorization.
