Search Results for author: Hao Yin

Found 20 papers, 3 papers with code

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Address Multimodal Hallucination

no code implementations14 Apr 2025 Hao Yin, Guangzong Si, Zilei Wang

Contrastive decoding strategies are widely used to reduce hallucinations in multimodal large language models (MLLMs).

Hallucination

EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling

no code implementations3 Apr 2025 Hao Yin, Shi Guo, Xu Jia, Xudong Xu, Lu Zhang, Si Liu, Dong Wang, Huchuan Lu, Tianfan Xue

In this work, we propose a novel pipeline for non-contact sound recovery, fully utilizing spatial-temporal information from the event stream.

Mamba

Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference

1 code implementation17 Mar 2025 Hao Yin, Guangzong Si, Zilei Wang

Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs).

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models

1 code implementation17 Mar 2025 Hao Yin, Guangzong Si, Zilei Wang

However, these methods present two main limitations: (1) bluntly suppressing language priors can compromise coherence and accuracy of generated content, and (2) processing contrastive inputs adds computational load, significantly slowing inference speed.

Computational Efficiency Hallucination +1

A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions

no code implementations5 Feb 2025 Hao Yin, Paritosh Parmar, Daoliang Xu, Yang Zhang, Tianyou Zheng, Weiwei Fu

Action Quality Assessment (AQA) -- the ability to quantify the quality of human motion, actions, or skill levels and provide feedback -- has far-reaching implications in areas such as low-cost physiotherapy, sports training, and workforce development.

Action Quality Assessment Survey +1

Perturbation Ontology based Graph Attention Networks

no code implementations27 Nov 2024 Yichen Wang, Jie Wang, Fulin Wang, Xiang Li, Hao Yin, Bhiksha Raj

In recent years, graph representation learning has undergone a paradigm shift, driven by the emergence and proliferation of graph neural networks (GNNs) and their heterogeneous counterparts.

Graph Attention Graph Representation Learning +3

Navigating Spatial Inequities in Freight Truck Crash Severity via Counterfactual Inference in Los Angeles

no code implementations26 Nov 2024 Yichen Wang, Hao Yin, Yifan Yang, Chenyang Zhao, Siqin Wang

Freight truck-related crashes pose significant challenges, leading to substantial economic losses, injuries, and fatalities, with pronounced spatial disparities across different regions.

counterfactual Counterfactual Inference

Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation

no code implementations11 Jun 2024 Hanzhao Li, Liumeng Xue, Haohan Guo, Xinfa Zhu, YuanJun Lv, Lei Xie, Yunlin Chen, Hao Yin, Zhifei Li

The multi-codebook speech codec enables the application of large language models (LLM) in TTS but bottlenecks efficiency and robustness due to multi-sequence prediction.

Contraction analysis of time-varying DAE systems via auxiliary ODE systems

no code implementations11 Dec 2023 Hao Yin, Bayu Jayawardhana, Stephan Trenn

The first result pertains to the equivalence of the contraction of a DAE system and the uniform global exponential stability (UGES) of its variational DAE system.

Output contraction analysis of nonlinear systems

no code implementations11 Dec 2023 Hao Yin, Bayu Jayawardhana, Stephan Trenn

This paper introduce the notion of output contraction that expands the contraction notion to the time-varying nonlinear systems with output.

Learning for Semantic Knowledge Base-Guided Online Feature Transmission in Dynamic Channels

no code implementations30 Nov 2023 Xiangyu Gao, Yaping Sun, Dongyu Wei, Xiaodong Xu, Hao Chen, Hao Yin, Shuguang Cui

In this context, we address the problem of efficient remote object recognition by optimizing feature transmission between mobile devices and edge servers.

Autonomous Vehicles Decision Making +3

Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

1 code implementation10 May 2023 Lei Yuan, Zi-Qian Zhang, Ke Xue, Hao Yin, Feng Chen, Cong Guan, Li-He Li, Chao Qian, Yang Yu

Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity.

Diversity SMAC+

A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

no code implementations8 Sep 2022 Zeyu Liu, Yi Wang, Jing Wen, Yong Zhang, Hao Yin, Chao Guo, Zhongyu Wang

In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.

Segmentation

Multi-Access Point Coordination for Next-Gen Wi-Fi Networks Aided by Deep Reinforcement Learning

no code implementations22 Jun 2022 Lyutianyang Zhang, Hao Yin, Sumit Roy, Liu Cao

Meanwhile, a deep reinforcement learning channel access (DLCA) protocol is developed to replace the binary exponential backoff mechanism in DCF to enhance the network throughput by enabling the coordination of APs.

Deep Reinforcement Learning Fairness +2

Model Generation with Provable Coverability for Offline Reinforcement Learning

no code implementations1 Jun 2022 Chengxing Jia, Hao Yin, Chenxiao Gao, Tian Xu, Lei Yuan, Zongzhang Zhang, Yang Yu

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.

Offline RL Out-of-Distribution Generalization +3

Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks

no code implementations2 Mar 2021 Anwen Liao, Zhen Gao, Dongming Wang, Hua Wang, Hao Yin, Derrick Wing Kwan Ng, Mohamed-Slim Alouini

According to the proposed prior-aided iterative angle estimation algorithm, azimuth/elevation angles can be estimated, and these angles are adopted to achieve precise beam-alignment and refine GTTDU module for further eliminating delay-beam squint.

Information Theory Signal Processing Information Theory

Secret Key Generation for Intelligent Reflecting Surface Assisted Wireless Communication Networks

no code implementations14 Aug 2020 Zijie Ji, Phee Lep Yeoh, Deyou Zhang, Gaojie Chen, Yan Zhang, Zunwen He, Hao Yin, Yonghui Li

We propose and analyze secret key generation using intelligent reflecting surface (IRS) assisted wireless communication networks.

Higher-order clustering in networks

no code implementations12 Apr 2017 Hao Yin, Austin R. Benson, Jure Leskovec

Here we introduce higher-order clustering coefficients that measure the closure probability of higher-order network cliques and provide a more comprehensive view of how the edges of complex networks cluster.

Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.