Skip to content

Author

Haoyang Huang

We have 21 of 45 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

FactoSR is presented, a factorized reinforcement learning framework that explicitly interpret the dimensions collapsed by visual projection, and suggests that reinforcing explicit, factorized 4D consistency is a critical step toward evolving VLMs into robust, world-aware reasoners.

Yi-Jun Yang, Shenghe Zheng, Wen-Bo Li et al. · 0 citations
Preprint Aug 2026

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

This work introduces ZimaBlue, a scalable framework for learning generalizable World Action Models (WAMs) from large-scale video, and adopts an asynchronous Slow-Fast dual-system architecture to make generative WAMs practical for real-time control.

Xiong-Hao Wu, Yi-Jun Yang, Shi-Long Zhou et al. · 5 citations
Preprint Aug 2026

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

The method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation, and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift.

Yi-Cheng Xiao, Wenxun Dai, Xinran Qin et al. · 5 citations
Jul 2026

Self Gradient Forcing: Native Long Video Extrapolation

Self Gradient Forcing (SGF), a two-pass training strategy that restores this missing memory-writing supervision within the native autoregressive training objective, using losses on future video latents to train the model to encode context into more effective causal memory.

Junhao Zhuang, Shiyi Zhang, Yuxuan Bian et al. · 5 citations
Jul 2026

Perceptual Flow Matching for Few-Step Generative Modeling

Perceptual Flow Matching supervises flow matching in a perceptual feature space using pretrained perceptual models, which substantially improves the few-step generation capability of flow-matching models, reducing the number of sampling steps from 35-50 to 4-8 while preserving generation quality.

Chuyang Zhao, Yifei Song, Hongfa Wang et al. · 2 citations
Preprint Aug 2026

Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

Results indicate that memory, geometric control, and rollout-aware training provide a practical foundation for generating coherent stories and continuously evolving interactive worlds.

Nan Duan, Hao-Yang Huang, Wei-Yang Jin et al. · 4 citations · ⚡1
Preprint Jul 2026

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models

Geo3R is proposed, a training-free, plug-and-play framework that incorporates geometric evidence and structured 3D reasoning to mitigate spatial reasoning hallucination and substantially reduces spatial reasoning hallucination across diverse MLLMs without additional training, outperforming existing models and methods.

Mingyu Wang, Weilin Jin, Wenbo Li et al. · 0 citations
Jul 2026

HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models

Fine-grained hallucination diagnosis for MLLMs is proposed, a new unified task that jointly performs hallucination detection, classification, and interpretable explanation generation and feedback experiments show that the fine-grained diagnostic explanations produced by the model effectively guide target models to corr...

Weilin Jin, Mingyu Wang, Wenbo Li et al. · 0 citations
Jul 2026

Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs

A lightweight linear detector is built on top of Role-Break that requires no fine-tuning of the VLM, whose feature dimension stays below 5,000 and reaches an average AUROC of 93.23 across six VLMs and four benchmarks.

Mingyu Wang, Weilin Jin, Wenbo Li et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.