Chun Yuan

27

Papers

334

Total Citations

Papers (27)

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting

CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

FlatQuant: Flatness Matters for LLM Quantization

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models

Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

Identification of Causal Structure in the Presence of Missing Data with Additive Noise Model

Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework

Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution

Deep Homography Estimation for Visual Place Recognition

FREE: Faster and Better Data-Free Meta-Learning

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

DFD: Distilling the Feature Disparity Differently for Detectors

ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

Text-guided Visual Prompt DINO for Generic Segmentation

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition

Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models

Aligning Composed Query with Image via Discriminative Perception from Negative Correspondences

IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis