Author name cluster

Yihang Chen

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.

9 papers

1 author row

EAAI Journal 2026 Journal Article

Lightweight multi-classification pear fruit high-precision detection model in complex orchard scenes

Shaohua Liu
Jinlin Xue
Tianyu Zhang
Pengfei Lv
Tianxing Zhao
Han Sun
ruikai liu
Yihang Chen

Obstacle occlusion in modern orchards significantly reduces the operational efficiency of pear-picking robots. To address this issue, a lightweight multi-classification pear fruit high-precision detection model, named MultiPL-YOLO (You Only Look Once), is proposed, which employs an anchor-based detection algorithm. Firstly, the network structure is adjusted to enhance feature extraction while reducing parameters and complexity. Additionally, the target anchor boxes are redesigned using the k-means algorithm. These modifications optimize the model for better feature extraction of multi-classification pear targets. Secondly, a redesigned C3 (CSP Bottleneck with 3 convolutions) module, incorporating Coordinate Attention and Efficient Multi-Head Convolution (C3-CAEMHC), is introduced to capture multi-scale features and expand the receptive field. Finally, Efficient Intersection over Union (EIoU) loss function is used in the head network to accelerate convergence and improve detection accuracy. Test results show that our model achieves a streamlined design with only 2, 499, 072 parameters, a 64. 4% reduction compared to the original model, and a model size of 5. 9 MB (MegaBytes), representing a 59. 0% decrease. Its feature extraction ability under complex environments is significantly improved, with precision of 96. 1%, recall of 92. 6%, and mAP@50 (mean Average Precision at IoU threshold of 50%) of 97. 0%, marking improvements of 0. 8, 2. 1, and 2. 0 percentage points over the original model, respectively. Furthermore, our model demonstrates superior detection performance on embedded industrial computers with limited computational resources. This study highlights the role of artificial intelligence in strengthening the perception and autonomous decision-making of agricultural robots, thereby facilitating intelligent fruit harvesting under challenging orchard conditions.

Details DOI

TMLR Journal 2026 Journal Article

Multi-Step Alignment as Markov Games: An Optimistic Online Mirror Descent Approach with Convergence Guarantees

Yongtao Wu
Luca Viano
Kimon Antonakopoulos
Yihang Chen
Zhenyu Zhu
Quanquan Gu
Volkan Cevher

Reinforcement Learning from Human Feedback (RLHF) has been highly successful in aligning large language models with human preferences. While prevalent methods like DPO have demonstrated strong performance, they frame interactions with the language model as a bandit problem, which limits their applicability in real-world scenarios where multi-turn conversations are common. Additionally, DPO relies on the Bradley-Terry model assumption, which does not adequately capture the non-transitive nature of human preferences. In this paper, we address these challenges by modeling the alignment problem as a two-player constant-sum Markov game, where each player seeks to maximize their winning rate against the other across all steps of the conversation. Our approach Optimistic Multi-step Preference Optimization (OMPO) is built upon the optimistic online mirror descent algorithm~\citep{rakhlin2013online,joulani17a}. Theoretically, we provide a rigorous analysis for the convergence of OMPO and show that OMPO requires $\mathcal{O}(\epsilon^{-1})$ policy updates to converge to an $\epsilon$-approximate Nash equilibrium. We also validate the effectiveness of our method on multi-turn conversations dataset and math reasoning dataset.

PDF Details

AAAI Conference 2026 Conference Paper

PCGS: Progressive Compression of 3D Gaussian Splatting

Yihang Chen
Mengyao Li
Qianyi Wu
Weiyao Lin
Mehrtash Harandi
Jianfei Cai

3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practical applications. While many compression techniques have been proposed, they fail to efficiently utilize existing bitstreams in on-demand applications due to their lack of progressivity, leading to a waste of resource. To address this issue, we propose PCGS (Progressive Compression of 3D Gaussian Splatting), which adaptively controls both the quantity and quality of Gaussians (or anchors) to enable effective progressivity for on-demand applications. For quantity, we introduce a progressive masking strategy that incrementally incorporates new anchors while refining existing ones to enhance fidelity. For quality, we propose a progressive quantization approach that gradually reduces quantization step sizes to achieve finer modeling of Gaussian attributes. Furthermore, to compact the incremental bitstreams, we leverage existing quantization results to refine probability prediction, improving entropy coding efficiency across progressive levels. PCGS achieves progressivity while maintaining compression performance comparable to SoTA non-progressive methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

Tsai Hor Chan
Feng Wu
Yihang Chen
Guosheng Yin
Lequan Yu

Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while learning cross-modal interactions. Previous approaches primarily focus on the cross-modal alignment, while over-emphasis on the alignment of marginal distributions of modalities may impose excess regularization and obstruct meaningful representations within each modality. The Dirichlet process (DP) mixture model is a powerful Bayesian non-parametric method that can amplify the most prominent features by its richer-gets-richer property, which allocates increasing weights to them. Inspired by this unique characteristic of DP, we propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment. Specifically, we assume that each modality follows a mixture of multivariate Gaussian distributions and further adopt DP to calculate the mixture weights for all the components. This paradigm allows DP to dynamically allocate the contributions of features and select the most prominent ones, leveraging its richer-gets-richer property, thus facilitating multimodal feature fusion. Extensive experiments on several multimodal datasets demonstrate the superior performance of our model over other competitors. Ablation analysis further validates the effectiveness of DP in aligning modality distributions and its robustness to changes in key hyperparameters. Code is anonymously available at https: //github. com/HKU-MedAI/DPMM. git

PDF Details

NeurIPS Conference 2025 Conference Paper

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

Jiaben Chen
Zixin Wang
Ailing Zeng
Yang Fu
Xueyang Yu
Siyuan Cen
Julian Tanke
Yihang Chen

In this work, we present TalkCuts, a large-scale dataset designed to facilitate the study of multi-shot human speech video generation. Unlike existing datasets that focus on single-shot, static viewpoints, TalkCuts offers 164k clips totaling over 500 hours of high-quality 1080P human speech videos with diverse camera shots, including close-up, half-body, and full-body views. The dataset includes detailed textual descriptions, 2D keypoints and 3D SMPL-X motion annotations, covering over 10k identities, enabling multimodal learning and evaluation. As a first attempt to showcase the value of the dataset, we present Orator, an LLM-guided multi-modal generation framework as a simple baseline, where the language model functions as a multi-faceted director, orchestrating detailed specifications for camera transitions, speaker gesticulations, and vocal modulation. This architecture enables the synthesis of coherent long-form videos through our integrated multi-modal video generation module. Extensive experiments in both pose-guided and audio-driven settings show that training on TalkCuts significantly enhances the cinematographic coherence and visual appeal of generated multi-shot speech videos. We believe TalkCuts provides a strong foundation for future work in controllable, multi-shot speech video generation and broader multimodal learning.

PDF Details

NeurIPS Conference 2024 Conference Paper

Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement

Yanyan Huang
Weiqin Zhao
Yihang Chen
Yu Fu
Lequan Yu

Whole slide image (WSI) analysis is gaining prominence within the medical imaging field. Recent advances in pathology foundation models have shown the potential to extract powerful feature representations from WSIs for downstream tasks. However, these foundation models are usually designed for general-purpose pathology image analysis and may not be optimal for specific downstream tasks or cancer types. In this work, we present Concept Anchor-guided Task-specific Feature Enhancement (CATE), an adaptable paradigm that can boost the expressivity and discriminativeness of pathology foundation models for specific downstream tasks. Based on a set of task-specific concepts derived from the pathology vision-language model with expert-designed prompts, we introduce two interconnected modules to dynamically calibrate the generic image features extracted by foundation models for certain tasks or cancer types. Specifically, we design a Concept-guided Information Bottleneck module to enhance task-relevant characteristics by maximizing the mutual information between image features and concept anchors while suppressing superfluous information. Moreover, a Concept-Feature Interference module is proposed to utilize the similarity between calibrated features and concept anchors to further generate discriminative task-specific features. The extensive experiments on public WSI datasets demonstrate that CATE significantly enhances the performance and generalizability of MIL models. Additionally, heatmap and umap visualization results also reveal the effectiveness and interpretability of CATE.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Tieyuan Chen
Huabin Liu
Tianyao He
Yihang Chen
Chaofan Gan
Xiao Ma
Cheng Zhong
Yang Zhang

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5. 7% and 4. 1%, respectively.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Membership Inference Attacks against Large Vision-Language Models

Zhan Li
Yongtao Wu
Yihang Chen
Francesco Tonin
Elias Abad Rocamora
Volkan Cevher

Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential inclusion of sensitive information, such as private photos and medical records, in their training datasets. Detecting inappropriately used data in VLLMs remains a critical and unresolved issue, mainly due to the lack of standardized datasets and suitable methodologies. In this study, we introduce the first membership inference attack (MIA) benchmark tailored for various VLLMs to facilitate training data detection. Then, we propose a novel MIA pipeline specifically designed for token-level image detection. Lastly, we present a new metric called MaxRényi-K%, which is based on the confidence of the model output and applies to both text and image data. We believe that our work can deepen the understanding and methodology of MIAs in the context of VLLMs. Our code and datasets are available at https: //github. com/LIONS-EPFL/VL-MIA.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

Jingtong Su
Yihang Chen
Tianle Cai
Tianhao Wu
Ruiqi Gao
Liwei Wang
Jason D. Lee

Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation. Conventional wisdom of pruning algorithms suggests that: (1) Pruning methods exploit information from training data to find good subnetworks; (2) The architecture of the pruned network is crucial for good performance. In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call initial tickets''), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance. These findings inspire us to choose a series of simple \emph{data-independent} prune ratios for each layer, and randomly prune each layer accordingly to get a subnetwork (which we call random tickets''). Experimental results show that our zero-shot random tickets outperforms or attains similar performance compared to existing initial tickets''. In addition, we identify one existing pruning method that passes our sanity checks. We hybridize the ratios in our random ticket with this method and propose a new method called hybrid tickets'', which achieves further improvement.

PDF Details