Tianyu Huai

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

Tianyu Huai, Tingshuo Fan, Xinchi Chen, Yining Zheng et autres

As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmarks typically focus on static code generation, paper replication, or final answer correctness, but do not directly assess whether agents …

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

Tianyu Huai, Tingshuo Fan, Xinchi Chen, Yining Zheng et autres

As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmarks typically focus on static code generation, paper replication, or final answer correctness, but do not directly assess whether agents …

cn, cz (code pays fourni par la source)

Adaptive Momentum Mixture-of-Experts for Continual Visual Question Answering

Tianyu Huai, Jie Zhou, Qin Chen, Qingchun Bai et autres

Multimodal large language models (MLLMs) have attracted considerable attention for their impressive capabilities in understanding and generating visual-language content, particularly in tasks such as visual question answering (VQA). However, the rapid evolution of knowledge in real-world applications poses challenges for these models: …

cn (code pays fourni par la source)

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering

Tianyu Huai, Jie Zhou, Xingjiao Wu, Qin Chen et autres

Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid pace of knowledge updates in the real world makes offline training of …

cn (code pays fourni par la source)

Task-Core Memory Management and Consolidation for Long-term Continual Learning

Tianyu Huai, Jie Zhou, Yuxuan Cai, Qin Chen et autres

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human learning. Unlike traditional …

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering

Tianyu Huai, Jie Zhou, Xingjiao Wu, Qin Chen et autres

Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid pace of knowledge updates in the real world makes offline training of …

Efficiency is the rule: Domain adaptive semantic segmentation with minimal annotations

Tianyu Huai, Junhang Zhang, Xingjiao Wu, Jian Jin et autres

cn (code pays fourni par la source)

Recent Advances of Foundation Language Models-based Continual Learning: A Survey

Yutao Yang, Jie Zhou, Xuanwen Ding, Tianyu Huai et autres

Recently, foundation language models (LMs) have marked significant achievements in the domains of natural language processing and computer vision. Unlike traditional neural network models, foundation LMs obtain a great ability for transfer learning by acquiring rich common sense knowledge through pre-training on …

cn (code pays fourni par la source)

Enhancing Out-of-Distribution Generalization in VQA through Gini Impurity-guided Adaptive Margin Loss

Shuwen Yang, Tianyu Huai, Anran Wu, Xingjiao Wu et autres

In the Visual Question Answering (VQA) task context, most methods are influenced by language bias, resulting in poor performance on out-of-distribution data. Recently, some works attempted to use the adaptive margin loss to address this bias issue. However, these works typically consider …

cn (code pays fourni par la source)

Robust depth completion based on Semantic Aggregation

Zhichao Fu, Xin Li, Tianyu Huai, Weijie Li et autres

cn (code pays fourni par la source)

Debiased Visual Question Answering via the perspective of question types

Tianyu Huai, Shuwen Yang, Junhang Zhang, Jiabao Zhao et autres

cn (code pays fourni par la source)

EMID: An Emotional Aligned Dataset in Audio-Visual Modality

J.T. Zou, J. C. Mei, Guangze Ye, Tianyu Huai et autres

In this paper, we propose Emotionally paired Music and Image Dataset (EMID), a novel dataset designed for the emotional matching of music and images, to facilitate auditory-visual cross-modal tasks such as generation and retrieval. Unlike existing approaches that primarily focus on semantic …

cn (code pays fourni par la source)