PaperHub

Shouhong Ding

~Shouhong_Ding3

20
论文总数
10.0
年均投稿
5.6
平均评分
接收情况12/20
会议分布
ICLR
10
NeurIPS
6
ICML
4

发表论文 (20 篇)

202516 篇

5.5
4

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration

ICML 2025Poster
4.3
3

YouCLIP: Advancing Multilingual Cross-Modal Learning with Efficient Training.

ICLR 2025Rejected
6.0
4

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts

ICLR 2025Poster
4.0
4

TAS: Distilling Arbitrary Teacher and Student via a Hybrid Assistant

ICLR 2025withdrawn
7.8
4

Large Continual Instruction Assistant

ICML 2025Poster
5.3
3

LLaCA: Multimodal Large Language Continual Assistant

ICLR 2025Rejected
4.7
7

CTV-FAS: Compensate Texts with Visuals for Generalizable Face Anti-spoofing

ICLR 2025withdrawn
4.2
5

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals

ICML 2025Poster
4.8
4

Hallucination in LVLMs: Fictitious Presupposition Questions, Benchmark, and Solution

ICLR 2025withdrawn
6.0
3

UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition

ICLR 2025Poster
4.5
4

Exploring the Collaborative Advantage of Low-level Information on Generalizable AI-generateted Image Detection

ICLR 2025withdrawn
4.8
4

Decoupled Data Augmentation for Improving Image Classification

ICLR 2025withdrawn
8.3
4

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

ICML 2025Oral
6.4
4

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes

NeurIPS 2025Poster
6.4
4

Switchable Token-Specific Codebook Quantization For Face Image Compression

NeurIPS 2025Poster
7.3
4

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

NeurIPS 2025Spotlight
合作者 (20)