Search Results for author:
Found 13 papers, 3 papers with code
UMoE: Unifying Attention and FFN with Shared Experts
Sparse Mixture of Experts (MoE) architectures have emerged as a promising approach for scaling Transformer models.
CodeCrash: Stress Testing LLM Reasoning under Structural and Semantic Perturbations
Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, yet their robustness in code comprehension and reasoning remains insufficiently explored.
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Addressing this concern, we introduce fully identical initialization (IDInit), a novel method that preserves identity in both the main and sub-stem layers of residual networks.
How Should We Build A Benchmark? Revisiting 274 Code-Related Benchmarks For LLMs
We propose How2Bench, which is comprised of a 55-criteria checklist as a set of guidelines to govern the development of code-related benchmarks comprehensively.
The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
Test cases are essential for validating the reliability and quality of software applications.
Learning to Ask: When LLM Agents Meet Unclear Instruction
Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone.
Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach
We further reveal that a focus on smaller visual segments can help multimodal large language models (MLLMs) mitigate these failures in the generation process.
XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
To address this issue, we present \tool, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models.
VRPTEST: Evaluating Visual Referring Prompting in Large Multimodal Models
With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems.
Split and Merge: Aligning Position Biases in LLM-based Evaluators
Specifically, PORTIA splits the answers into multiple segments, aligns similar content across candidate answers, and then merges them back into a single prompt for evaluation by LLMs.
No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence
Besides, the performance of fine-tuning strongly relies on the amount of downstream data, while in practice, the scenarios with scarce data are common.
Label-Aware Distribution Calibration for Long-tailed Classification
Real-world data usually present long-tailed distributions.
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods.
Ranked #7 on
Image Generation
on CelebA 256x256
(FID metric)
