Search Results for author:
Found 9 papers, 3 papers with code
On the Semantics of LM Latent Space: A Vocabulary-defined Approach
In response, we introduce a pioneering method called vocabulary-defined semantics, which establishes a reference frame within the LM latent space, ensuring disentangled semantic analysis grounded in LM vocabulary.
Neuron-level LLM Patching for Code Generation
In this paper, we propose a novel and effective model editing approach, \textsc{MENT}, to patch LLMs in coding tasks.
Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables
To systematically explore the potential improvements of code generation, we let it participate in the whole top-down development from \emph{expressibles} to \emph{executables}, which is possible in limited scopes.
Efficient Virtual View Selection for 3D Hand Pose Estimation
3D hand pose estimation from single depth is a fundamental problem in computer vision, and has wide applications. However, the existing methods still can not achieve satisfactory hand pose estimation results due to view variation and occlusion of human hand.
Ranked #1 on
Hand Pose Estimation
on ICVL Hands
Assemble Foundation Models for Automatic Code Summarization
Thereby, we propose a flexible and robust approach for automatic code summarization, based on neural models.
Ranked #1 on
Source Code Summarization
on ParallelCorpus-Python
Multimodal Representation for Neural Code Search
In this paper, to improve the vector space, we introduce tree-serialization methods on a simplified form of AST and build the multimodal representation for the code data.
Ranked #1 on
Code Search
on CodeSearchNet - Ruby
Interpretable Foreground Object Search As Knowledge Distillation
As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds.
LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
Finally, we provide a variety of experimental results to show that the proposed framework is able to achieve state-of-the-art accuracy with significantly reduced computational cost, which are the key properties for enabling real-time applications in low-cost commercial devices such as mobile devices and AR/VR headsets.
Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other.
