Peng Jin

19

Papers

781

Total Citations

Papers (19)

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

MoH: Multi-Head Attention as Mixture-of-Head Attention

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable Repainting

VSNet: Focusing on the Linguistic Characteristics of Sign Language

Parallel Vertex Diffusion for Unified Visual Grounding

MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval

Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation

Auto-Linear Phenomenon in Subsurface Imaging

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties