2 citations · 5 across the 47 of their papers we have counts for
52 papers
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
Zhefan Rao, Meng Chu, Xuan Zhang +80
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction require…
GameDirector: Decoupling Gameplay Logic from Rendering for Player-Configurable Game World Models
Zijun Lin, Zhiyang Deng, Yuzhe Wu +2
Recent game world models support realistic visual simulation and interactive gameplay based on player inputs. However, they typically learn environment dynamics from pixel-level su…
BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data
Wei Zhang, Xin Li, Peishu Shi +4
Video virtual try-on (VVT) aims to generate realistic videos of a person wearing a target garment. Recent methods leverage a keyframe-driven video generation paradigm to improve in…
Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving
Zhaoxin Fan, Tianbao Zhang, Wenjun Wu +5
World models offer a promising paradigm for autonomous driving by predicting how traffic scenes may evolve and using such predictions to support action generation. However, existin…
H3-World: Turning Language Understanding into World Control
Danze Chen, Zeqing Wang, Ziyue Lin +2
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become…
WorldMind: Decoupled Game World Model for State-Aware NPC Behavior
Zhiyang Deng, Boran Zhang, Danze Chen +1
Game world models have recently demonstrated promising capabilities in generating visually coherent and action-controllable gameplay videos. However, non-player character (NPC) beh…
StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation
Zijun Lin, Zeqing Wang, Cheston Tan +2
Recent game world models can generate visually realistic and interactive environments conditioned on player actions. However, games are not defined by pixels alone; they are govern…
STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching
Hao Wang, Haoran Geng, Xiaotong Yang +7
Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, c…
MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation
Yinhan Zhang, Dingwei Tan, Xianghao Kong +3
Large-scale video diffusion models deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-effic…
Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis
Chenghao Qian, Nedko Savov, Lingdong Kong +7
Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion. The key limitation of existing methods is the lack of diversit…
CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
Haoyu Zhao, Jiaxi Gu, Haoran Chen +11
Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera param…
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
Zizhao Tong, Yeying Jin, Hongfeng Lai +11
Interactive world models for first-person shooter (FPS) games must resolve high-frequency overlapping control signals at every frame without disrupting unaffected regions. Existing…
ReactiveGWM: Flexible Control and NPC Reactivity in Game World Models
Zeqing Wang, Danze Chen, Zhaohu Xing +4
Existing game world models typically adopt role-specific interactions, where player and NPC roles are bound to fixed characters. This limits their flexibility in multi-character ga…
NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Suhang Yao +95
This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this c…
Elucidating Representation Degradation Problem in Diffusion Model Training
Zhipeng Yao, Dazhou Li, Zitong Zhang +6
Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As nois…
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Shangwen Zhu, Qianyu Peng, Zhao Pu +12
Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace th…
Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
Yinghao Chen, Yeying Jin, Xiang Chen +3
Unsupervised deraining has attracted attention for its ability to learn the real-world distribution of rain without paired supervision. However, the lack of strong constraints make…
LoViF 2026 The First Challenge on Weather Removal in Videos
Chenghao Qian, Xin Li, Yeying Jin +23
This paper presents a review of the LoViF 2026 Challenge on Weather Removal in Videos. The challenge encourages the development of methods for restoring clean videos from inputs de…
NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results
Xin Li, Jiachao Gong, Xijun Wang +75
This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-…
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin +47
As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that ma…
InstanceAnimator: Multi-Instance Sketch Video Colorization
Yinhan Zhang, Yue Ma, Bingyuan Wang +5
We propose InstanceAnimator, a novel Diffusion Transformer framework for multi-instance sketch video colorization. Existing methods suffer from three core limitations: inflexible u…
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
Nanxiang Jiang, Zhaoxin Fan, Baisen Wang +8
Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures…
UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
Wei Zhang, Yeying Jin, Xin Li +5
Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework…
Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
Nanxiang Jiang, Zhaoxin Fan, Enhan Kang +6
Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to pro…