Jiankang Deng

Assistant Professor@Imperial College London·英国·OpenReview

研究方向

Visual Language Learning · Multimodal Learning · 2D & 3D Generative Learning · Noise Learning · Long-tailed Learning · Polynomial Networks · Deep Face Analysis and Modelling (Detection · Alignment · Parsing · Reconstruction · Anti-spoofing · Recognition · Generation · Restoration)

Jiankang Deng

Dynamic Novel View Synthesis in High Dynamic Range

ReFocusEraser: Refocusing for Small Object Removal with Robust Context-Shadow Repair

RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models

CASteer: Cross-Attention Steering for Controllable Concept Erasure

Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

Optimal Affine Framework for Steering Generative Models

4D Mind Reading

Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution

UniViT: Unifying Image and Video Understanding in One Vision Encoder

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting

From Attention to Activation: Unraveling the Enigmas of Large Language Models

FRACTAL CALIBRATION FOR LONG-TAILED OBJECT DETECTION

Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension