14 papers
SignGPT: Toward LLM-Mediated Sign Language Interaction through Gloss-Free Translation and Generation
Ronghui Li, Jun Dong, Zhongyuan Hu +8
Large language models (LLMs) provide limited support for sign language interaction. Unifying sign language translation (SLT) and generation (SLG) to enable sign language as both in…
VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics
Bowei Liu, Zheng Lu, Yuhan Bian +8
Recent advances in video generation models have significantly improved the realism of synthetic videos, blurring the boundary between generated and authentic content and raising co…
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models
Bin Hu, Yanwen Ma, Jiehui Huang +14
Recent game world models can synthesize visually plausible, action-conditioned rollouts. However, their interaction behaviors often remain limited to exploratory or wandering traje…
UltraVR: A Diagnostic Ultra-Resolution Image-VQA Benchmark for Evidence-Grounded Reasoning
Gexin Huang, Yanting Yang, Myeongkyun Kang +6
Vision-language models (VLMs) excel on visual question answering and multimodal reasoning benchmarks. Yet their capability on ultra-resolution images - where critical evidence is t…
Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation
Haocheng Luo, Jiahui Liu, Ruicheng Zhang +8
While Vision-Language Models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this limitation to a perception--reasoning mo…
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
Ruicheng Zhang, Guangyu Chen, Zunnan Xu +5
Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models (EWMs) offer promise through ima…
MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds
Xiangzuo Wu, Chengwei Ren, Jun Zhou +2
Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view…
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
Ruicheng Zhang, Mingyang Zhang, Jun Zhou +6
Scalable embodied intelligence is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video world models in this domain are limited to synthesi…
Controllable Layer Decomposition for Reversible Multi-Layer Image Generation
Zihao Liu, Zunnan Xu, Shi Shu +4
This work presents Controllable Layer Decomposition (CLD), a method for achieving fine-grained and controllable multi-layer separation of raster images. In practical workflows, des…
Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time Training
Ruicheng Zhang, Jun Zhou, Zunnan Xu +5
Trajectory-Guided image-to-video (I2V) generation aims to synthesize videos that adhere to user-specified motion instructions. Existing methods typically rely on computationally ex…
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
Jiaqi Huang, Zunnan Xu, Jun Zhou +6
Leveraging multimodal large models for image segmentation has become a prominent research direction. However, existing approaches typically rely heavily on manually annotated datas…
Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
Fa-Ting Hong, Zunnan Xu, Zixiang Zhou +5
Talking head synthesis is vital for virtual avatars and human-computer interaction. However, most existing methods are typically limited to accepting control from a single primary…
FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
Jun Zhou, Jiahao Li, Zunnan Xu +6
Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs)…
HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
Zunnan Xu, Zhentao Yu, Zixiang Zhou +10
We introduce HunyuanPortrait, a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation. Given a sing…