Yi Li

papers

864

total citations

papers (24)

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

AAAI 2024arXiv

192

citations

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

CVPR 2024arXiv

citations

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

ECCV 2022arXiv

citations

SViTT: Temporal Learning of Sparse Video-Text Transformers

CVPR 2023arXiv

citations

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

NEURIPS 2022arXiv

citations

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

ECCV 2020arXiv

citations

BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning

ICCV 2021arXiv

citations

Token Activation Map to Visually Explain Multimodal LLMs

ICCV 2025arXiv

citations

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

ICML 2024arXiv

citations

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

ICLR 2024arXiv

citations

Community-Centric Graph Unlearning

AAAI 2025arXiv

citations

Faster Approximation Algorithms for k-Center via Data Reduction

ICML 2025arXiv

citations

Split Adaptation for Pre-trained Vision Transformers

CVPR 2025arXiv

citations

Improving Video Model Transfer With Dynamic Representation Learning

CVPR 2022

citations

Zeitgebers-Based User Experience Analysis and Time Perception Modeling via Transformer in VR

ISMAR 2025

citations

Background Data Resampling for Outlier-Aware Classification

CVPR 2020

citations

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

AAAI 2025arXiv

citations

Artistic Style Discovery With Independent Components

CVPR 2022

citations

Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal

CVPR 2022

citations

Yi Li

papers (24)

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

Learning Representations from Audio-Visual Spatial Alignment

Pseudo-Mask Matters in Weakly-Supervised Semantic Segmentation

Cross-Spectral Face Hallucination via Disentangling Independent Factors

VALHALLA: Visual Hallucination for Machine Translation

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

SViTT: Temporal Learning of Sparse Video-Text Transformers

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning

Token Activation Map to Visually Explain Multimodal LLMs

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

Community-Centric Graph Unlearning

Faster Approximation Algorithms for k-Center via Data Reduction

Split Adaptation for Pre-trained Vision Transformers

Improving Video Model Transfer With Dynamic Representation Learning

Zeitgebers-Based User Experience Analysis and Time Perception Modeling via Transformer in VR

Background Data Resampling for Outlier-Aware Classification

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

Artistic Style Discovery With Independent Components

Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal

papers (24)

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

Learning Representations from Audio-Visual Spatial Alignment

Pseudo-Mask Matters in Weakly-Supervised Semantic Segmentation

Cross-Spectral Face Hallucination via Disentangling Independent Factors

VALHALLA: Visual Hallucination for Machine Translation

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

SViTT: Temporal Learning of Sparse Video-Text Transformers

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning

Token Activation Map to Visually Explain Multimodal LLMs

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

Community-Centric Graph Unlearning

Faster Approximation Algorithms for k-Center via Data Reduction

Split Adaptation for Pre-trained Vision Transformers

Improving Video Model Transfer With Dynamic Representation Learning

Zeitgebers-Based User Experience Analysis and Time Perception Modeling via Transformer in VR

Background Data Resampling for Outlier-Aware Classification

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

Artistic Style Discovery With Independent Components

Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal