Author name cluster

Yida Yin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

ICLR Conference 2025 Conference Paper

A Coefficient Makes SVRG Effective

Yida Yin
Zhiqiu Xu
ZhiYuan Li
Trevor Darrell
Zhuang Liu 0003

Stochastic Variance Reduced Gradient (SVRG), introduced by Johnson & Zhang (2013), is a theoretically compelling optimization method. However, as Defazio & Bottou (2019) highlight, its effectiveness in deep learning is yet to be proven. In this work, we demonstrate the potential of SVRG in optimizing real-world neural networks. Our empirical analysis finds that, for deeper neural networks, the strength of the variance reduction term in SVRG should be smaller and decrease as training progresses. Inspired by this, we introduce a multiplicative coefficient $\alpha$ to control the strength and adjust it through a linear decay schedule. We name our method $\alpha$-SVRG. Our results show $\alpha$-SVRG better optimizes models, consistently reducing training loss compared to the baseline and standard SVRG across various model architectures and multiple image classification datasets. We hope our findings encourage further exploration into variance reduction techniques in deep learning. Code is available at github.com/davidyyd/alpha-SVRG.

Details

ICML Conference 2025 Conference Paper

Idiosyncrasies in Large Language Models

Mingjie Sun
Yida Yin
Zhiqiu Xu
J. Zico Kolter
Zhuang Liu 0003

In this work, we unveil and study idiosyncrasies in Large Language Models (LLMs) – unique patterns in their outputs that can be used to distinguish the models. To do so, we consider a simple classification task: given a particular text output, the objective is to predict the source LLM that generates the text. We evaluate this synthetic task across various groups of LLMs and find that simply fine-tuning text embedding models on LLM-generated texts yields excellent classification accuracy. Notably, we achieve 97. 1% accuracy on held-out validation data in the five-way classification problem involving ChatGPT, Claude, Grok, Gemini, and DeepSeek. Our further investigation reveals that these idiosyncrasies are rooted in word-level distributions. These patterns persist even when the texts are rewritten, translated, or summarized by an external LLM, suggesting that they are also encoded in the semantic content. Additionally, we leverage LLM as judges to generate detailed, open-ended descriptions of each model’s idiosyncrasies. Finally, we discuss the broader implications of our findings, including training on synthetic data, inferring model similarity, and robust evaluation of LLMs.

Details

ICRA Conference 2025 Conference Paper

In-Context Learning Enables Robot Action Prediction in LLMs

Yida Yin
Zekai Wang
Yuvan Sharma
Dantong Niu
Trevor Darrell
Roei Herzig

Recently, Large Language Models (LLMs) have achieved remarkable success using in-context learning (ICL) in the language domain. However, leveraging the ICL capabilities within LLMs to directly predict robot actions remains largely unexplored. In this paper, we introduce RoboPrompt, a frame-work that enables off-the-shelf text-only LLMs to directly predict robot actions through ICL without training. Our approach first heuristically identifies keyframes that capture important moments from an episode. Next, we extract end-effector actions from these keyframes as well as the estimated initial object poses, and both are converted into textual descriptions. Finally, we construct a structured template to form ICL demonstrations from these textual descriptions and a task instruction. This enables an LLM to directly predict robot actions at test time. Through extensive experiments and analysis, RoboPrompt shows stronger performance over zero-shot and ICL baselines in simulated and real-world settings. Our project page is available at https://davidyyd.github.io/roboprompt.

Details

ICLR Conference 2024 Conference Paper

Initializing Models with Larger Ones

Zhiqiu Xu
Yanjie Chen
Kirill Vishniakov
Yida Yin
Zhiqiang Shen
Trevor Darrell
Lingjie Liu
Zhuang Liu 0003

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers new opportunities for tackling this classical problem of weight initialization. In this work, we introduce weight selection, a method for initializing smaller models by selecting a subset of weights from a pretrained larger model. This enables the transfer of knowledge from pretrained weights to smaller models. Our experiments demonstrate that weight selection can significantly enhance the performance of small models and reduce their training time. Notably, it can also be used together with knowledge distillation. Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era.

Details

ICRA Conference 2024 Conference Paper

MATRIX: Multi-Agent Trajectory Generation with Diverse Contexts

Zhuo Xu
Rui Zhou
Yida Yin
Huidong Gao
Masayoshi Tomizuka
Jiachen Li 0001

Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications. However, collecting massive and annotated real-world human datasets has been a laborious task, especially for highly interactive scenarios. On the other hand, algorithmic data generation methods are usually limited by their model capacities, making them unable to offer realistic and diverse data needed by various application users. In this work, we study trajectory-level data generation for multi-human or human-robot interaction scenarios and propose a learning-based automatic trajectory generation model, which we call Multi-Agent TRajectory generation with dIverse conteXts (MATRIX). MATRIX is capable of generating interactive human behaviors in realistic diverse contexts. We achieve this goal by modeling the explicit and interpretable objectives so that MATRIX can generate human motions based on diverse destinations and heterogeneous behaviors. We carried out extensive comparison and ablation studies to illustrate the effectiveness of our approach across various metrics. We also presented experiments that demonstrate the capability of MATRIX to serve as data augmentation for imitation-based motion planning.

Details

NeurIPS Conference 2024 Conference Paper

Understanding Bias in Large-Scale Visual Datasets

Boya Zeng
Yida Yin
Zhuang Liu

A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a framework to identify the unique visual attributes distinguishing these datasets. Our approach applies various transformations to extract semantic, structural, boundary, color, and frequency information from datasets, and assess how much each type of information reflects their bias. We further decompose their semantic bias with object-level analysis, and leverage natural language methods to generate detailed, open-ended descriptions of each dataset's characteristics. Our work aims to help researchers understand the bias in existing large-scale pre-training datasets, and build more diverse and representative ones in the future. Our project page and code are available at boyazeng. github. io/understand_bias.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Knowledge-Graph Augmented Word Representations for Named Entity Recognition

Qizhen He
Liang Wu
Yida Yin
Heming Cai

By modeling the context information, ELMo and BERT have successfully improved the state-of-the-art of word representation, and demonstrated their effectiveness on the Named Entity Recognition task. In this paper, in addition to such context modeling, we propose to encode the prior knowledge of entities from an external knowledge base into the representation, and introduce a Knowledge-Graph Augmented Word Representation or KAWR for named entity recognition. Basically, KAWR provides a kind of knowledge-aware representation for words by 1) encoding entity information from a pre-trained KG embedding model with a new recurrent unit (GERU), and 2) strengthening context modeling from knowledge wise by providing a relation attention scheme based on the entity relations defined in KG. We demonstrate that KAWR, as an augmented version of the existing linguistic word representations, promotes F1 scores on 5 datasets in various domains by +0.46∼+2.07. Better generalization is also observed for KAWR on new entities that cannot be found in the training sets.

PDF Details