Xiangxiang Chu

Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools

AutoDrive-R²: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

FASA: FREQUENCY-AWARE SPARSE ATTENTION

NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation

Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models

Tree Search for LLM Agent Reinforcement Learning

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-Training

Decomposing Policy Optimization into Proxy Objective and Knowledge Distillation for Long-context Reasoning

Don't Lose Sight: Visually-Grounded Credit Assignment for Multimodal Reasoning

IntSR: An Integrated Generative Framework for Search and Recommendation

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective

Effective Probabilistic Time Series Forecasting with Fourier Adaptive Noise-Separated Diffusion

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

Trash to Treasure: Paving a New Way for Improving Video Understanding via Counterfactual Video Generation

From Editor to Dense Geometry Estimator

MIGA: Make Train-Free Infinite Frame Generation Great Again for Consistent Long Videos

Acceleration-Aware Sampling for Few-Step Rectified Flow Models

Reflection from Retrieval: MLLM-Guided Iterative Reasoning for Zero-Shot Composed Image Retrieval

AnyLayout: Versatile Advertising Poster Layout Generation with MLLMs

StoryCtrl: Customized Story Visualization with Fine-Grained Control

FLOWDREAMER: EXPLORING HIGH FIDELITY TEXT-TO-3D GENERATION VIA RECTIFIED FLOW

Powering Neural Architecture Search with Robust Masked Autoencoders