Zhibo Chen

Embodied Navigation Foundation Model

AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation

Q&C: When Quantization Meets Cache in Efficient Generation

CP4D: Compositional physics-aware 4D scene generation

AR4D: Autoregressive 4D Generation from Monocular Videos

AnyAvatar: Dynamic and Consistent Audio-Driven Human Animation for Multiple Characters

IQA-Octopus: Unified Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring

LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents

OmniQuality-R: Advancing Reward Models through All-Encompassing Quality Assessment

OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior

Training-free Camera Control for Video Generation

Q-Adapt: Adapting LMM for Visual Quality Perceiver with Progressive Instruction Tuning

Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models

LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents

Alternating Optimized Stochastic Vector Quantization in Neural Compression

VideoDiT: Bridging Image Diffusion Transformers for Streamlined Video Generation