影响力指数

61.81/100

前 4.4%

全站排名 #2,803

发表论文15 篇

平均评分5.1

年均产出5.0 篇/年

Cheng Deng

Full Professor@Xidian University·中国·OpenReview

研究方向

Multimodal LLM · visual content generation · visual-and-language · deep learning · multimodal learning · cross-modal retrieval

4.5

Perceive, Reflect and Understand Long Video: Progressive Multi-Granular Clue Exploration with Interactive Agents

ICLR 2026Rejected

通讯

4.5

COME: Advancing Representation Learning and Generative Modeling for High-Quality Text-to-Motion Generation

ICLR 2026Rejected

通讯

4.0

A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages

ICLR 2026Rejected

通讯

4.0

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space

ICLR 2026Withdrawn

通讯

4.0

Towards Interpretable Steering for Hallucination Mitigation in Large Vision–Language Models

ICLR 2026Rejected

通讯

3.5

MetaDCSeg: Robust Medical Image Segmentation via Meta Dynamic Center Weighting

ICLR 2026Withdrawn

通讯

7.6

Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling

NeurIPS 2025Poster

通讯

7.3

Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams

NeurIPS 2025Poster

通讯

7.0

Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization

ICLR 2025Poster

通讯

6.5

CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback Disentanglement

合作者 (20)

Cheng Deng

Perceive, Reflect and Understand Long Video: Progressive Multi-Granular Clue Exploration with Interactive Agents

COME: Advancing Representation Learning and Generative Modeling for High-Quality Text-to-Motion Generation

A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space

Towards Interpretable Steering for Hallucination Mitigation in Large Vision–Language Models

MetaDCSeg: Robust Medical Image Segmentation via Meta Dynamic Center Weighting

Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling

Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams

Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization

CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback Disentanglement

Hierarchical Multi-Grained Reasoning for Object Concept Learning

Manifold K-means with $\ell_{2,p}$-Norm Maximization

Discrete Tensorized Label Learning with Anchor Graphs