Search Results for author:
Found 8 papers, 5 papers with code
Unleashing Vecset Diffusion Model for Fast Shape Generation
To address these challenges, we present FlashVDM, a systematic framework for accelerating both VAE and DiT in VDM.
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint.
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs.
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
Our experiments reveal these LLMs' coding abilities in real-world code repositories.
DevEval: Evaluating Code Generation in Practical Software Projects
Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e. g., real program distributions, sufficient dependencies, and enough-scale project contexts.
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred.
AceCoder: Utilizing Existing Code to Enhance Code Generation
A key question is how to make prompts (i. e., Prompting Techniques).
Integrating Tree Path in Transformer for Code Representation
Learning distributed representation of source code requires modelling its syntax and semantics.
