Search Results for author:
Found 27 papers, 14 papers with code
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model to extract visual information and generate text outputs via attention mechanisms.
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
Distinct from previous adaptive testing methods that rely on static datasets with limited difficulty, GETA incorporates an iteratively-updated item generator which infers each LLM's moral boundaries and generates difficulty-tailored testing items, accurately reflecting the true alignment extent.
DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
Despite the remarkable achievements of language models (LMs) across a broad spectrum of tasks, their propensity for generating toxic outputs remains a prevalent concern.
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns.
ToViLaG: Your Visual-Language Generative Model is Also An Evildoer
Warning: this paper includes model outputs showing offensive content.
Text2Bundle: Towards Personalized Query-based Bundle Generation
Bundle generation aims to provide a bundle of items for the user, and has been widely studied and applied on online service platforms.
Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets
Furthermore, our in-depth analysis verifies that the advanced selection of review subsets and the two-stage training scheme are vital to boosting the summarization performance.
Towards Multi-Subsession Conversational Recommendation
Therefore, we propose a novel conversational recommendation scenario named Multi-Subsession Multi-round Conversational Recommendation (MSMCR), where user would still resort to CRS after several subsessions and might preserve vague interests, and system would proactively ask attributes to activate user interests in the current subsession.
Data-Augmented Counterfactual Learning for Bundle Recommendation
In this paper, we propose a novel graph learning paradigm called Counterfactual Learning for Bundle Recommendation (CLBR) to mitigate the impact of data sparsity problem and improve bundle recommendation.
CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Story generation has emerged as an interesting yet challenging NLP task in recent years.
LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT
LightHuBERT outperforms the original HuBERT on ASR and five SUPERB tasks with the HuBERT size, achieves comparable performance to the teacher model in most tasks with a reduction of 29% parameters, and obtains a $3. 5\times$ compression ratio in three SUPERB tasks, e. g., automatic speaker verification, keyword spotting, and intent classification, with a slight accuracy loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Temporal aware Multi-Interest Graph Neural Network For Session-based Recommendation
Session-based recommendation (SBR) is a challenging task, which aims at recommending next items based on anonymous interaction sequences.
Intention Adaptive Graph Neural Network for Category-aware Session-based Recommendation
Session-based recommendation (SBR) is proposed to recommend items within short sessions given that user profiles are invisible in various scenarios nowadays, such as e-commerce and short video recommendation.
Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation
As a result, we first propose a more realistic CRS learning setting, namely Multi-Interest Multi-round Conversational Recommendation, where users may have multiple interests in attribute instance combinations and accept multiple items with partially overlapped combinations of attribute instances.
Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
Finally, we apply an answer selection model on the full KSG and the top-ranked sub-KSGs respectively to validate the effectiveness of our proposed graph-augmented learning to rank method.
Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks
Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to generate a text sequence.
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+8
Multi-View Self-Attention Based Transformer for Speaker Recognition
In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition.
Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation
In this work, we propose an end-to-end heterogeneous global graph learning framework, namely Graph Learning Augmented Heterogeneous Graph Neural Network (GL-HGNN) for social recommendation.
Multi-behavior Graph Contextual Aware Network for Session-based Recommendation
Based on the global graph, MGCNet attaches the global interest representation to final item representation based on local contextual intention to address the limitation (iii).
Interpretable Compositional Convolutional Neural Networks
The reasonable definition of semantic interpretability presents the core challenge in explainable AI.
Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation
Additionally, existing personalized session-based recommenders capture user preference only based on the sessions of the current user, but ignore the useful item-transition patterns from other user's historical sessions.
Improved Instance Discrimination and Feature Compactness for End-to-End Person Search
Our method achieves comparable performance on two benchmarks, CUHK-SYSU and PRW, and achieves 91. 96% of mAP and 93. 34% of rank1 accuracy on CUHK-SYSU.
EfficientTDNN: Efficient Architecture Search for Speaker Recognition
Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition.
Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020
In this report, we discribe the submission of Tongji University undergraduate team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 2020.
3D-Rotation-Equivariant Quaternion Neural Networks
This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs).
Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing
In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures.
