Copertina

Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cao, Meng, Tang, Haoran, Zhao, Haoze, Han, Mingfei, Liu, Ruyang, Sun, Qiang, Chang, Xiaojun, Reid, Ian, Liang, Xiaodan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
di: Cao, Meng, et al.
Pubblicazione: (2024)

Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
di: Cao, Meng, et al.
Pubblicazione: (2025)

Video Spatial Reasoning with Object-Centric 3D Rollout
di: Tang, Haoran, et al.
Pubblicazione: (2025)

Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow
di: Liu, Ruyang, et al.
Pubblicazione: (2025)

MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval
di: Tang, Haoran, et al.
Pubblicazione: (2024)

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling
di: Cao, Meng, et al.
Pubblicazione: (2025)

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
di: Cao, Meng, et al.
Pubblicazione: (2024)

StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
di: Hu, Panwen, et al.
Pubblicazione: (2024)

Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos
di: Han, Mingfei, et al.
Pubblicazione: (2026)

LongVLM: Efficient Long Video Understanding via Large Language Models
di: Weng, Yuetian, et al.
Pubblicazione: (2024)

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
di: Han, Mingfei, et al.
Pubblicazione: (2023)

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
di: Han, Mingfei, et al.
Pubblicazione: (2024)

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
di: Wang, Yongxin, et al.
Pubblicazione: (2025)

Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
di: Cao, Meng, et al.
Pubblicazione: (2025)

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
di: Sun, Shangkun, et al.
Pubblicazione: (2024)

SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery
di: Cao, Meng, et al.
Pubblicazione: (2025)

World2Act: Latent Action Post-Training from World Model Dynamics
di: Vuong, An Dinh, et al.
Pubblicazione: (2026)

Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation
di: Jin, Minghao, et al.
Pubblicazione: (2026)

Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
di: Zhang, Kecheng, et al.
Pubblicazione: (2026)

Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video
di: Goel, Dave, et al.
Pubblicazione: (2025)

EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation
di: Wang, Yongxin, et al.
Pubblicazione: (2024)

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
di: Ma, Liang, et al.
Pubblicazione: (2025)

BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation
di: Hu, Panwen, et al.
Pubblicazione: (2025)

CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
di: Hao, Haihong, et al.
Pubblicazione: (2025)

JEUX Gameplay
di: Kukkonen, Karin, et al.
Pubblicazione: (2025)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
di: Hu, Pengfei, et al.
Pubblicazione: (2025)

Bridging Chaos Game Representations and $k$-mer Frequencies of DNA Sequences
di: He, Haoze, et al.
Pubblicazione: (2025)

Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models
di: Lu, Wentao, et al.
Pubblicazione: (2025)

Gameplay Highlights Generation
di: Edithal, Vignesh, et al.
Pubblicazione: (2025)

ST-LLM: Large Language Models Are Effective Temporal Learners
di: Liu, Ruyang, et al.
Pubblicazione: (2024)

GLaD: Geometric Latent Distillation for Vision-Language-Action Models
di: Guo, Minghao, et al.
Pubblicazione: (2025)

WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation
di: Wang, Jing, et al.
Pubblicazione: (2025)

Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models
di: Cao, Meng, et al.
Pubblicazione: (2024)

Reframing Pedagogical Practices Through the UTBO ‐ CLIL Framework in Art and Design Higher Education
di: Li Ruyang, et al.
Pubblicazione: (2026)

The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos
di: Cardoso, Igor, et al.
Pubblicazione: (2024)

Semantic, Orthographic, and Phonological Biases in Humans' Wordle Gameplay
di: Liang, Jiadong, et al.
Pubblicazione: (2024)

Volt Hockey Equipment and Gameplay
di: Avery Melam
Pubblicazione: (2026)

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
di: Wang, Yunzhe, et al.
Pubblicazione: (2026)

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
di: Sun, Mingfei
Pubblicazione: (2026)

BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay
di: Weaver, Catherine, et al.
Pubblicazione: (2024)