PaperHub

Chang Xu

~Chang_Xu4

27
论文总数
13.5
年均投稿
5.7
平均评分
接收情况15/27
会议分布
ICLR
20
NeurIPS
4
ICML
3

发表论文 (27 篇)

202522

7.3
3

Representative Guidance: Diffusion Model Sampling with Coherence

ICLR 2025Spotlight
4.2
5

Compress Guidance in Conditional Diffusion Sampling

ICLR 2025withdrawn
6.5
4

Learning Mask Invariant Mutual Information for Masked Image Modeling

ICLR 2025Poster
7.0
4

Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention

ICLR 2025Poster
7.3
3

Exploring Local Memorization in Diffusion Models via Bright Ending Attention

ICLR 2025Spotlight
7.5
4

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models

ICLR 2025Spotlight
6.1
4

Beyond One-Hot Labels: Semantic Mixing for Model Calibration

ICML 2025Poster
4.0
5

RED: Efficiently Boosting Ensemble Robustness via Random Sampling Inference

ICLR 2025withdrawn
4.4
5

The Devil is in the Word: Video-Conditioned Text Representation Refinement for Text-to-Video Retrieval

ICLR 2025withdrawn
3.7
3

Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors

ICLR 2025withdrawn
7.8
4

SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning

NeurIPS 2025Poster
4.3
4

Weak-to-Strong Enhanced Vision Model

ICLR 2025withdrawn
4.0
4

Investigating Memorization in Video Diffusion Models

ICLR 2025withdrawn
7.2
4

Adversarial Robustness via Deformable Convolution with Stochasticity

ICML 2025Poster
7.2
5

Anti-Exposure Bias in Diffusion Models

ICLR 2025Spotlight
6.4
4

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching

NeurIPS 2025Poster
5.7
3

SAN-Diff: Structure-aware noise for super-resolution diffusion model

ICLR 2025Rejected
4.0
4

Exploring the Design Space of Autoregressive Models for Efficient and Scalable Image Generation

ICLR 2025withdrawn
4.0
4

FusionSAM: Visual Multimodal Learning with Segment Anything Model

ICLR 2025withdrawn
7.2
4

Stable Fair Graph Representation Learning with Lipschitz Constraint

ICML 2025Poster
5.0
5

Empirical Study on Enhancing Efficiency in Masked Image Modeling Pre-training

ICLR 2025Rejected
4.5
4

Training-free Long Video Generation with Chain of Diffusion Model Experts

ICLR 2025withdrawn