影响力指数

65.81/100

前 3.4%

全站排名 #2,206

发表论文20 篇

平均评分5.0

年均产出6.7 篇/年

Di Huang

Full Professor@Beihang University·中国·OpenReview

研究方向

Visual Foundation Models · Geometry Deep Learning · Object Detection · Face Editing · Facial Expression Recognition · Face Recognition

6.0

PRO-MOF: Policy Optimization with Universal Atomistic Models for Controllable MOF Generation

ICLR 2026Poster

三作

4.0

DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning

ICLR 2026Rejected

三作

4.0

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration

ICLR 2026Withdrawn

通讯

4.0

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

ICLR 2026Rejected

通讯

3.0

Sieve Attention: Fusing Context-Aware Filtering and Sequential Allocation For Long Sequence

ICLR 2026Withdrawn

二作

7.0

Anomalies are Streaming: Continual Learning for Weakly Supervised Video Anomaly Detection

ICLR 2025Rejected

通讯

5.5

I4VGen: Image as Free Stepping Stone for Text-to-Video Generation

ICLR 2025Rejected

通讯

5.0

Text-Guided Visual Prompt Tuning for Vision-Language Models

ICLR 2025Rejected

通讯

4.8

Enhancing Video Understanding with Vision and Language Collaboration

ICLR 2025Rejected

通讯

4.8

$A^2$-DP: Annotation-aware Data Pruning for Object Detection

ICLR 2025Rejected

通讯

4.5

Unleashing the Potential of Unlabeled Data: Bidirectional Collaborative Semi-Supervised Active Learning for 3D Object Detection

ICLR 2025Rejected

通讯

4.4

Temporal Distribution-aware Quantization for Diffusion Models

ICLR 2025Rejected

4.2

Generalizable Transferability Estimation of Foundation Vision Models via Implicit Learning

ICLR 2025Withdrawn

通讯

3.0

CLIP-LAD: Unleash the Potential of CLIP for Few-shot Logical Anomaly Detection

合作者 (20)

Di Huang

PRO-MOF: Policy Optimization with Universal Atomistic Models for Controllable MOF Generation

DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

Sieve Attention: Fusing Context-Aware Filtering and Sequential Allocation For Long Sequence

Test-Time Adaptive Object Detection with Foundation Model

Implicit Modeling for Transferability Estimation of Vision Foundation Models

Progressive Parameter Efficient Transfer Learning for Semantic Segmentation

Anomalies are Streaming: Continual Learning for Weakly Supervised Video Anomaly Detection

I4VGen: Image as Free Stepping Stone for Text-to-Video Generation

Text-Guided Visual Prompt Tuning for Vision-Language Models

Enhancing Video Understanding with Vision and Language Collaboration

$A^2$-DP: Annotation-aware Data Pruning for Object Detection

Unleashing the Potential of Unlabeled Data: Bidirectional Collaborative Semi-Supervised Active Learning for 3D Object Detection

Temporal Distribution-aware Quantization for Diffusion Models

Generalizable Transferability Estimation of Foundation Vision Models via Implicit Learning

CLIP-LAD: Unleash the Potential of CLIP for Few-shot Logical Anomaly Detection