Search Results for author:
Found 49 papers, 14 papers with code
机器音译研究综述(Survey on Machine Transliteration)
“机器音译是基于语音相似性自动将文本从一种语言转换为另一种语言的过程, 它是机器翻译的一个子任务, 侧重于语音信息的翻译。音译后可知道源单词在另一种语言中的发音, 使不熟悉源语言的人更容易理解该语言, 有益于消除语言和拼写障碍。机器音译在多语言文本处理、语料库对齐、信息抽取等自然语言应用中发挥着重要作用。本文阐述了目前机器音译任务中存在的挑战, 对主要的音译方法进行了剖析、分类和整理, 对音译数据集进行了罗列汇总, 并列出了常用的音译效果评价指标, 最后对该领域目前存在的问题进行了说明并对音译学的未来进行了展望。本文以期对进入该领域的新人提供快速的入门指南, 或供其他研究者参考。”
Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach
In this work, we propose a Group Relative Policy Optimization (GRPO) framework with a multi-label reward regression model to achieve safe and aligned language generation.
Output Length Effect on DeepSeek-R1's Safety in Forced Thinking
Large Language Models (LLMs) have demonstrated strong reasoning capabilities, but their safety under adversarial conditions remains a challenge.
Simplify RLHF as Reward-Weighted SFT: A Variational Method
More specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into a reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness.
Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor.
Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation
AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.
Morph: A Motion-free Physics Optimization Framework for Human Motion Generation
Human motion generation plays a vital role in applications such as digital humans and humanoid robot control.
Precision Knowledge Editing: Enhancing Safety in Large Language Models
Large language models (LLMs) have demonstrated remarkable capabilities, but they also pose risks related to the generation of toxic or harmful content.
Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs
To address these challenges, we introduce a self-instructed in-context learning framework that empowers LLMs to deliver more effective responses by generating reliable derived prompts to construct informative contextual environments.
VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Surprisingly, without further adaptation in the time-series domain, the proposed VisionTS could achieve superior zero-shot forecasting performance compared to existing TSF foundation models.
Atoxia: Red-teaming Large Language Models with Target Toxic Answers
Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM.
M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Third, M$^3$GPT learns to model the connections and synergies among various motion-relevant tasks.
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples.
PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning
However, current approaches typically either train adapters on individual tasks or distill shared knowledge from source tasks, failing to fully exploit task-specific knowledge and the correlation between source and target tasks.
Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques
This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL.
GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting
We introduce a novel large-scale scene reconstruction benchmark using the newly developed 3D representation approach, Gaussian Splatting, on our expansive U-Scene dataset.
Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained model.
Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features
Based on these analyzes, an SSD method based on temporal consistency and distribution of speaker features is proposed.
Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
Unbiased Learning to Rank (ULTR) aims to train unbiased ranking models from biased click logs, by explicitly modeling a generation process for user behavior and fitting click data based on examination hypothesis.
The Impact of Silence on Speech Anti-Spoofing
First, the reasons for the impact are explored, including the proportion of silence duration and the content of silence.
Visible and NIR Image Fusion Algorithm Based on Information Complementarity
Second, to generate the initial visible-NIR complementarity weight map, the difference maps of visible and NIR are filtered by the extend-DoG filter.
Towards Food Image Retrieval via Generalization-oriented Sampling and Loss Function Design
Therefore, it is challenging to study the generalization of the model in food image retrieval.
Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games.
Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification
Utilizing the large-scale unlabeled data from the target domain via pseudo-label clustering algorithms is an important approach for addressing domain adaptation problems in speaker verification tasks.
Self-Edit: Fault-Aware Code Editor for Code Generation
Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task.
Implant Global and Local Hierarchy Information to Sequence based Code Representation Models
Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.
EdgeYOLO: An Edge-Real-Time Object Detector
This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms.
Neural Episodic Control with State Abstraction
Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms.
Convolution-enhanced Evolving Attention Networks
To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps.
Poison Attack and Defense on Deep Source Code Processing Models
The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.
Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion
The overfitting of the model to the training set leads to extreme values of the scores and low correlation of the score distributions, which makes score fusion difficult.
Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification
Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set.
Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases
Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description.
SASV Based on Pre-trained ASV System and Integrated Scoring Module
Based on the assumption that there is a correlation between anti-spoofing and speaker verification, a Total-Divide-Total integrated Spoofing-Aware Speaker Verification (SASV) system based on pre-trained automatic speaker verification (ASV) system and integrated scoring module is proposed and submitted to the SASV 2022 Challenge.
Geometry-Based Stochastic Probability Models for the LoS and NLoS Paths of A2G Channels under Urban Scenario
Path probability prediction is essential to describe the dynamic birth and death of propagation paths, and build the accurate channel model for air-to-ground (A2G) communications.
Graph Enhanced Contrastive Learning for Radiology Findings Summarization
To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i. e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation.
Height-Dependent LoS Probability Model for A2G MmWave Communications under Built-up Scenarios
Based on the three-dimensional propagation characteristic under built-up scenarios, a height-dependent line-of-sight (LoS) probability model for air-to-ground (A2G) millimeter wave (mmWave) communications is proposed in this paper.
SDN Controller Load Balancing Based on Reinforcement Learning
Under the constraint of the best efficiency of migration in the whole and without migration conflict, selecting multiple sets of triples based on reinforcement learning, as the final migration of this round to attain the global optimal controller load balancing with minimum cost.
Networking and Internet Architecture
An Optimal-Transport-Based Reinforcement Learning Approach for Computation Offloading
With the mass deployment of computing-intensive applications and delay-sensitive applications on end devices, only adequate computing resources can meet differentiated services' delay requirements.
Edge-computing
Networking and Internet Architecture
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough
Limited by the definition of AP, such methods consider both negative and positive instances ranking before each positive instance.
Ranked #3 on
Vehicle Re-Identification
on VehicleID Large
Robust Handwriting Recognition with Limited and Noisy Data
Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved.
A Machine Learning Framework for Data Ingestion in Document Images
Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations.
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.
Kernelized Multiview Subspace Analysis by Self-weighted Learning
With the popularity of multimedia technology, information is always represented or transmitted from multiple views.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
Overcoming Catastrophic Forgetting by Soft Parameter Pruning
In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
