XIAOJUAN QI

UniTok: a Unified Tokenizer for Visual Generation and Understanding

EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes

Understanding Data Influence in Reinforcement Finetuning

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Scaling RL to Long Videos

Mixture Compressor for Mixture-of-Experts LLMs Gains More

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Diff-In: Data Influence Estimation with Differential Approximation

Data Pruning by Information Maximization

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Multimodal Context-Aware Transformer with Visual Guidance for Automated 3D Annotation

POC: Preventing the Over-Collapse of Classes for Class-Incremental Learning

Rethinking Out-of-Distribution Detection in Vision Foundation Models

Granularity Matters in Long-Tail Learning

An Image is Worth $K$ Slots: Data-efficient Scaling of Self-supervised Visual Pre-training

Text-to-3D with Classifier Score Distillation

Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting

What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights

Splatter a Video: Video Gaussian Representation for Versatile Processing

Decoupled Kullback-Leibler Divergence Loss

Decoupled Kullback-Leibler Divergence Loss

Diffusion-based Data Generation for Out-of-Distribution Object Detection