Search Results for author:
Found 28 papers, 9 papers with code
LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment
As large language models (LLMs) demonstrate exceptional performance across various domains, the deployment of these models on edge devices has emerged as a new trend.
Model Editing for LLMs4Code: How Far are We?
Despite that, a comprehensive study that thoroughly compares and analyzes the performance of the state-of-the-art model editing techniques for adapting the knowledge within LLMs4Code across various code-related tasks is notably absent.
Identifying Knowledge Editing Types in Large Language Models
However, there is a lack of effective measures to prevent the malicious misuse of this technology, which could lead to harmful edits in LLMs.
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning
First, we utilize the vulnerability patches to construct a vulnerability localization task.
DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking
Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base.
EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis
Achieving disentangled control over multiple facial motions and accommodating diverse input modalities greatly enhances the application and entertainment of the talking head generation.
FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization
Specifically, we develop a flow-based coefficient generator that encodes the dynamics of facial emotion into a multi-emotion-class latent space represented as a mixture distribution.
Say Anything with Any Style
To adapt to different speaking styles, we steer clear of employing a universal network by exploring an elaborate HyperStyle to produce the style-specific weights offset for the style branch.
Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style
Although automatically animating audio-driven talking heads has recently received growing interest, previous efforts have mainly concentrated on achieving lip synchronization with the audio, neglecting two crucial elements for generating expressive videos: emotion style and art style.
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Based on the distribution, we introduce a new metric Beyond, which computes a runtime-percentile-weighted Pass score to reflect functional correctness and code efficiency simultaneously.
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
In particular, local editing methods, which directly update model parameters, are more suitable for updating a small amount of knowledge.
From Static to Dynamic: A Continual Learning Framework for Large Language Models
The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks.
VicunaNER: Zero/Few-shot Named Entity Recognition using Vicuna
VicunaNER is a two-phase framework, where each phase leverages multi-turn dialogues with Vicuna to recognize entities from texts.
Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction
Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction.
EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation
During training, the emotion embedding and mouth features are used as keys, and the corresponding expression features are used as values to create key-value pairs stored in the proposed Motion Memory Net.
Span-based joint entity and relation extraction augmented with sequence tagging mechanism
On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE.
Joint Entity and Relation Extraction
named-entity-recognition
+3
A Two-Phase Paradigm for Joint Entity-Relation Extraction
An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task.
A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search
Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness.
Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes
Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples.
Topic-Grained Text Representation-based Model for Document Retrieval
Document retrieval enables users to find their required documents accurately and quickly.
SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder
However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with human scoring and inhibition of summary diversity.
Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
Previous research has demonstrated that the two paradigms have clear complementary advantages, but few models have attempted to leverage these advantages in a single NER model as far as we know.
Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism
To solve this problem, we pro-pose Sequence Tagging enhanced Span-based Network (STSN), a span-based joint extrac-tion network that is enhanced by token BIO label information derived from sequence tag-ging based NER.
Joint Entity and Relation Extraction
named-entity-recognition
+4
Temporal Difference Networks for Action Recognition
To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition.
TDN: Temporal Difference Networks for Efficient Action Recognition
To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition.
Ranked #18 on
Action Recognition
on Something-Something V1
Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations
Span-based joint extraction models have shown their efficiency on entity recognition and relation extraction.
TEA: Temporal Excitation and Aggregation for Action Recognition
Temporal modeling is key for action recognition in videos.
