Research graph
References from Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI. Local targets link to admitted publications; unresolved targets remain external evidence.
Recurrent world models facilitate policy evolution
External reference
10.1007/s10462-024-10874-4
10.1007/s10462-024-10874-4 · External reference
10.1109/cvpr.2016.383
10.1109/cvpr.2016.383 · External reference
Interaction networks for learning about objects, relations and physics
2016 · External reference
10.52202/085713-3130
10.52202/085713-3130 · External reference
PHYRE: A new benchmark for physical reasoning
2019 · External reference
I-PHYRE: Interactive physical reasoning
External reference
10.52202/085713-3670
10.52202/085713-3670 · External reference
LLMPhy: Parameter-identifiable physical reasoning combining large language models and physics engines
External reference
10.1109/tpami.2025.3574322
10.1109/tpami.2025.3574322 · External reference
Semi-supervised classification with graph convolutional networks
External reference
Graph attention networks
External reference
Inductive representation learning on large graphs
2017 · External reference
Visual interaction networks: Learning a physics simulator from video
2017 · External reference
A compositional object-based approach to learning physical dynamics
External reference
10.52202/079017-3914
10.52202/079017-3914 · External reference
10.52202/085713-4091
10.52202/085713-4091 · External reference
A physics-guided multimodal transformer path to weather and climate sciences
2025 · External reference
10.1063/1.5116183
10.1063/1.5116183 · External reference
10.1016/j.cma.2019.112732
10.1016/j.cma.2019.112732 · External reference
10.52202/085713-2324
10.52202/085713-2324 · External reference
AlphaDrive: Unleashing the power of VLMs in autonomous driving via reinforcement learning and reasoning
2025 · External reference
AutoDrive-R$^{2}$2: Incentivizing reasoning and self-reflection capacity for VLA model in autonomous driving
External reference
Reinforcement learning meets large language models: A survey of advancements and applications across the LLM lifecycle
2025 · External reference
Causal modeling of dynamical systems
2018 · External reference
10.1007/978-981-99-8088-8_18
10.1007/978-981-99-8088-8_18 · External reference
10.1109/iros58592.2024.10802099
10.1109/iros58592.2024.10802099 · External reference
10.1145/3414685.3417795
10.1145/3414685.3417795 · External reference
Scalable differentiable physics for learning and control
2020 · External reference
GPT-4o system card
2024 · External reference
10.52202/075280-1516
10.52202/075280-1516 · External reference
OpenAI O1 system card
2024 · External reference
Qwen2.5-VL technical report
2025 · External reference
Physics SuperNova: AI agent matches elite gold medalists at IPhO 2025
2025 · External reference
Multimodal reasoning for science: Technical report and 1st place solution to the ICML 2025 SeePhys challenge
2025 · External reference
GAIA-1: A generative world model for autonomous driving
2023 · External reference
DriveDreamer: Towards real-world-driven world models for autonomous driving
2024 · External reference
OpenVLA: An open-source vision-language-action model
2025 · External reference
10.15607/rss.2025.xxi.010
10.15607/rss.2025.xxi.010 · External reference
10.1093/nsr/nwae403
10.1093/nsr/nwae403 · External reference
10.1016/j.inffus.2025.103575
10.1016/j.inffus.2025.103575 · External reference
10.1109/iros60139.2025.11246481
10.1109/iros60139.2025.11246481 · External reference
Probing perceptual constancy in large vision language models
2025 · External reference
From perception to cognition: A survey of vision-language interactive reasoning in multimodal large language models
2025 · External reference
10.1109/tpami.2025.3637037
10.1109/tpami.2025.3637037 · External reference
10.1109/access.2025.3649182
10.1109/access.2025.3649182 · External reference
10.24963/ijcai.2022/763
10.24963/ijcai.2022/763 · External reference
10.18653/v1/2023.findings-acl.67
10.18653/v1/2023.findings-acl.67 · External reference
Foundation model driven robotics: A comprehensive review
2025 · External reference
10.1140/epjc/s10052-025-14707-8
10.1140/epjc/s10052-025-14707-8 · External reference
10.1145/3746449
10.1145/3746449 · External reference
Generative physical AI in vision: A survey
2025 · External reference
Is SORA a world simulator? A comprehensive survey on general world models and beyond
2024 · External reference
3D and 4D world modeling: A survey
2025 · External reference
10.1126/science.aau0323
10.1126/science.aau0323 · External reference
From 2D to 3D cognition: A brief survey of general world models
2025 · External reference
A survey on world models grounded in acoustic physical information
2025 · External reference
From efficient multimodal models to world models: A survey
2024 · External reference
10.1109/tmech.2025.3574943
10.1109/tmech.2025.3574943 · External reference
10.1007/978-3-031-72775-7_13
10.1007/978-3-031-72775-7_13 · External reference
10.1109/ojvt.2025.3604823
10.1109/ojvt.2025.3604823 · External reference
10.1109/mcas.2025.3603693
10.1109/mcas.2025.3603693 · External reference
A survey: Learning embodied intelligence from physical simulators and world models
2025 · External reference
10.1007/s11704-024-40231-1
10.1007/s11704-024-40231-1 · External reference
Large model empowered embodied AI: A survey on decision-making and embodied learning
2025 · External reference
10.1007/s11633-025-1542-8
10.1007/s11633-025-1542-8 · External reference
Toward embodied AGI: A review of embodied AI and the road ahead
2025 · External reference
10.1109/tetci.2022.3141105
10.1109/tetci.2022.3141105 · External reference
A survey on robotics with foundation models: Toward embodied AI
2024 · External reference
10.3390/s23073762
10.3390/s23073762 · External reference
10.1109/iccv.2017.322
10.1109/iccv.2017.322 · External reference
10.1007/978-3-031-72970-6_3
10.1007/978-3-031-72970-6_3 · External reference
Qwen3-Omni technical report
2025 · External reference
10.1016/j.knosys.2024.112371
10.1016/j.knosys.2024.112371 · External reference
View-invariant pixelwise anomaly detection in multi-object scenes with adaptive view synthesis
2024 · External reference
10.1109/tsc.2024.3407588
10.1109/tsc.2024.3407588 · External reference
10.1177/02783649241297998
10.1177/02783649241297998 · External reference
10.1109/cvpr.2009.5206848
10.1109/cvpr.2009.5206848 · External reference
10.1007/978-3-319-10602-1_48
10.1007/978-3-319-10602-1_48 · External reference
10.1007/978-3-030-66096-3_39
10.1007/978-3-030-66096-3_39 · External reference
10.1109/cvpr52734.2025.02831
10.1109/cvpr52734.2025.02831 · External reference
10.1109/wacv61041.2025.00213
10.1109/wacv61041.2025.00213 · External reference
10.52202/085713-0457
10.52202/085713-0457 · External reference
Multi-SpatialMLLM: Multi-frame spatial understanding with multi-modal large language models
External reference
10.1007/978-3-032-37098-3_6
10.1007/978-3-032-37098-3_6 · External reference
10.1016/j.inffus.2022.08.014
10.1016/j.inffus.2022.08.014 · External reference
SpatialScore: Towards comprehensive evaluation for spatial intelligence
External reference
10.1145/3746027.3758219
10.1145/3746027.3758219 · External reference
MMSI-Bench: A benchmark for multi-image spatial intelligence
2026 · External reference
10.1109/cvpr52733.2024.00497
10.1109/cvpr52733.2024.00497 · External reference
10.1080/00405000.2020.1757296
10.1080/00405000.2020.1757296 · External reference
10.1109/cvpr52733.2024.01978
10.1109/cvpr52733.2024.01978 · External reference
Vision-based approach for food weight estimation from 2D images
2024 · External reference
10.24132/csrn.3401.24
10.24132/csrn.3401.24 · External reference
10.1109/icassp49660.2025.10889158
10.1109/icassp49660.2025.10889158 · External reference
SlotFormer: Unsupervised visual dynamics simulation with object-centric models
External reference
10.1145/3690624.3709168
10.1145/3690624.3709168 · External reference
Physion: Evaluating physical prediction from vision in humans and machines
2021 · External reference
10.1167/jov.23.9.5622
10.1167/jov.23.9.5622 · External reference
ContPhy: Continuum physical concept learning and reasoning from videos
2024 · External reference
10.1038/s41586-025-09422-z
10.1038/s41586-025-09422-z · External reference
UGPhysics: A comprehensive benchmark for undergraduate physics reasoning with large language models
External reference
10.52202/085713-0044
10.52202/085713-0044 · External reference
GPQA: A graduate-level Google-proof Q&A benchmark
2024 · External reference
10.18653/v1/2024.acl-long.211
10.18653/v1/2024.acl-long.211 · External reference
10.18653/v1/2025.acl-long.811
10.18653/v1/2025.acl-long.811 · External reference
10.1109/cvpr52733.2024.00913
10.1109/cvpr52733.2024.00913 · External reference
10.18653/v1/2025.acl-long.736
10.18653/v1/2025.acl-long.736 · External reference
10.52202/068431-1800
10.52202/068431-1800 · External reference
LOCA-R: Near-perfect performance on the chinese physics olympiad 2025
2025 · External reference
10.1103/physrevphyseducres.19.010132
10.1103/physrevphyseducres.19.010132 · External reference
Steps are all you need: Rethinking STEM education with prompt engineering
2024 · External reference
Symbolic or numerical? understanding physics problem solving in reasoning LLMs
2025 · External reference
Knowledge graphs are all you need: Leveraging KGs in physics question answering
2024 · External reference
10.18653/v1/2025.findings-ijcnlp.43
10.18653/v1/2025.findings-ijcnlp.43 · External reference
ABench-Physics: Benchmarking physical reasoning in LLMs via high-difficulty and dynamic physics problems
2025 · External reference
Grounding physical concepts of objects and events through dynamic visual reasoning
External reference
10.18653/v1/2026.eacl-long.166
10.18653/v1/2026.eacl-long.166 · External reference
P1-VL: Bridging visual perception and scientific reasoning in physics olympiads
2026 · External reference
CLEVRER: Collision events for video representation and reasoning
External reference
Learning neural causal models from unknown interventions
2020 · External reference
Dynamic visual reasoning by learning differentiable physics models from video and language
2021 · External reference
CAUSAL3D: A comprehensive benchmark for causal learning from visual data
2025 · External reference
10.52202/068431-0563
10.52202/068431-0563 · External reference
PhySense: Principle-based physics reasoning benchmarking for large language models
2025 · External reference
10.1007/s00707-025-04325-6
10.1007/s00707-025-04325-6 · External reference
A multi-agent framework for physical laws discovery
2024 · External reference
Contemporary symbolic regression methods and their relative performance
2021 · External reference
10.1109/tevc.2024.3423681
10.1109/tevc.2024.3423681 · External reference
Combining genetic algorithm and compressed sensing for features and operators selection in symbolic regression
2024 · External reference
Parsing the language of expression: Enhancing symbolic regression with domain-aware symbolic priors
2025 · External reference
10.1038/s41598-026-49762-y
10.1038/s41598-026-49762-y · External reference
10.1038/s41586-026-10265-5
10.1038/s41586-026-10265-5 · External reference
The AI Scientist-v2: Workshop-level automated scientific discovery via agentic tree search
2025 · External reference
Open source planning & control system with language agents for autonomous scientific discovery
2025 · External reference
10.1073/pnas.2414074122
10.1073/pnas.2414074122 · External reference
10.1017/flo.2025.10032
10.1017/flo.2025.10032 · External reference
Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange
2026 · External reference
From agent-only social networks to autonomous scientific research: Lessons from OpenClaw and Moltbook, and the architecture of ClawdLab and Beach.Science
2026 · External reference
ScienceAgentBench: Toward rigorous assessment of language agents for data-driven scientific discovery
External reference
10.52202/079017-0963
10.52202/079017-0963 · External reference
10.1145/3746449
10.1145/3746449 · External reference
10.1145/360825.360839
10.1145/360825.360839 · External reference
10.1145/357290.357293
10.1145/357290.357293 · External reference
10.1109/lra.2023.3270034
10.1109/lra.2023.3270034 · External reference
Unity: A general platform for intelligent agents
2018 · External reference
10.1109/tro.2023.3235591
10.1109/tro.2023.3235591 · External reference
10.1109/cvpr52688.2022.00541
10.1109/cvpr52688.2022.00541 · External reference
10.1109/iccv51070.2023.00014
10.1109/iccv51070.2023.00014 · External reference
GANs trained by a two time-scale update rule converge to a local Nash equilibrium
2017 · External reference
10.18653/v1/2021.emnlp-main.595
10.18653/v1/2021.emnlp-main.595 · External reference
10.1007/978-3-642-33715-4_54
10.1007/978-3-642-33715-4_54 · External reference
10.1109/cvprw63382.2024.00150
10.1109/cvprw63382.2024.00150 · External reference
10.1109/wacv61042.2026.00099
10.1109/wacv61042.2026.00099 · External reference
Towards world simulator: Crafting physical commonsense-based benchmark for video generation
2025 · External reference
VideoPhy: Evaluating physical commonsense for video generation
External reference
10.52202/085713-1834
10.52202/085713-1834 · External reference
Open-SORA: Democratizing efficient video production for all
2024 · External reference
CogVideoX: Text-tovideo diffusion models with an expert transformer
External reference
10.1007/s11263-024-02295-1
10.1007/s11263-024-02295-1 · External reference
10.1109/iccv51701.2025.01149
10.1109/iccv51701.2025.01149 · External reference
10.1007/978-3-031-73007-8_21
10.1007/978-3-031-73007-8_21 · External reference
ProPhy: Progressive physical alignment for dynamic world simulation
2025 · External reference
Think before you diffuse: LLMs-guided physics-aware video generation
2025 · External reference
10.52202/085713-5466
10.52202/085713-5466 · External reference
VideoPoet: A large language model for zero-shot video generation
External reference
Morpheus: Benchmarking physical reasoning of video generative models with real physical experiments
2025 · External reference
10.7551/mitpress/3877.003.0009
10.7551/mitpress/3877.003.0009 · External reference
10.1109/cvpr.2006.19
10.1109/cvpr.2006.19 · External reference
10.52202/079017-0810
10.52202/079017-0810 · External reference
Multiview neural surface reconstruction by disentangling geometry and appearance
2020 · External reference
10.1109/cvpr52734.2025.00153
10.1109/cvpr52734.2025.00153 · External reference
10.1109/cvpr52734.2025.01122
10.1109/cvpr52734.2025.01122 · External reference
10.1109/iros.2012.6386109
10.1109/iros.2012.6386109 · External reference
10.1109/cvpr.2014.59
10.1109/cvpr.2014.59 · External reference
10.1145/3072959.3073599
10.1145/3072959.3073599 · External reference
10.1109/cvpr.2017.272
10.1109/cvpr.2017.272 · External reference
Back to the features: DINO as a foundation for video world models
2025 · External reference
How far is video generation from world model: A physical law perspective
2025 · External reference
Brax–A differentiable physics engine for large scale rigid body simulation
2021 · External reference
NeoPhysix: An ultra fast 3D physical simulator as development tool for AI algorithms
2024 · External reference
10.1109/icra.2019.8794358
10.1109/icra.2019.8794358 · External reference
DEM-NeRF: A neuro-symbolic method for scientific discovery through physics-informed simulation
2025 · External reference
10.1109/cvpr52734.2025.02571
10.1109/cvpr52734.2025.02571 · External reference
LagNetViP: A Lagrangian neural network for video prediction
2020 · External reference
FusionForce: End-to-end differentiable neural-symbolic layer for trajectory prediction
2025 · External reference
PhyWorldBench: A comprehensive evaluation of physical realism in text-to-video models
2026 · External reference
Vision-language-action models: Concepts, progress, applications and challenges
2025 · External reference
A generalist agent
2022 · External reference
10.15607/rss.2023.xix.025
10.15607/rss.2023.xix.025 · External reference
RT-2: Vision-language-action models transfer web knowledge to robotic control
2023 · External reference
10.1109/lcsys.2021.3050609
10.1109/lcsys.2021.3050609 · External reference
Flow matching for generative modeling
External reference
10.1177/02783649241273668
10.1177/02783649241273668 · External reference
Open X-embodiment: Robotic learning datasets and RT-X models
2024 · External reference
World action models are zero-shot policies
2026 · External reference
World action verifier: Self-improving world models via forward-inverse asymmetry
2026 · External reference
10.1007/978-3-032-37718-0_19
10.1007/978-3-032-37718-0_19 · External reference
Active exploration for contact-rich tasks via online-adaptable models
2024 · External reference
Do as I can, not as I say: Grounding language in robotic affordances
2022 · External reference
Active visuo-tactile interactive robotic perception for object property-aware manipulation
2023 · External reference
EmbodiedBench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents
2025 · External reference
EMMOE: A comprehensive benchmark for embodied mobile manipulation in open environments
2025 · External reference
10.1109/lra.2020.2974707
10.1109/lra.2020.2974707 · External reference
RoboSuite: A modular simulation framework and benchmark for robot learning
2020 · External reference
ManiSkill2: A unified benchmark for generalizable manipulation skills
External reference
Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning
External reference
10.1109/lra.2022.3180108
10.1109/lra.2022.3180108 · External reference
BEHAVIOR: Benchmark for everyday household activities in virtual, interactive, and ecological environments
External reference
GraspNet-1Billion: A large-scale benchmark for general object grasping
2020 · External reference
Vision-and-language navigation today and tomorrow: A survey in the era of foundation models
2024 · External reference
Research on navigation methods based on LLMs
2025 · External reference
10.1109/tpami.2025.3554559
10.1109/tpami.2025.3554559 · External reference
Object goal navigation using goal-oriented semantic exploration
2020 · External reference
10.1109/iros55552.2023.10341827
10.1109/iros55552.2023.10341827 · External reference
10.1109/iros60139.2025.11247308
10.1109/iros60139.2025.11247308 · External reference
LGR: LLM-guided ranking of frontiers for object goal navigation
2025 · External reference
CL-CoTNav: Closed-loop hierarchical chain-of-thought for zero-shot object-goal navigation with vision-language models
2025 · External reference
10.1109/lra.2026.3655265
10.1109/lra.2026.3655265 · External reference
10.18653/v1/2020.acl-main.229
10.18653/v1/2020.acl-main.229 · External reference
10.1109/cvpr52688.2022.01496
10.1109/cvpr52688.2022.01496 · External reference
History aware multimodal transformer for vision-and-language navigation
2021 · External reference
10.18653/v1/n19-1268
10.18653/v1/n19-1268 · External reference
10.1109/cvpr52688.2022.01604
10.1109/cvpr52688.2022.01604 · External reference
10.1609/aaai.v38i7.28597
10.1609/aaai.v38i7.28597 · External reference
10.1609/aaai.v38i17.29858
10.1609/aaai.v38i17.29858 · External reference
10.15607/rss.2025.xxi.018
10.15607/rss.2025.xxi.018 · External reference
10.1109/cvpr42600.2020.01074
10.1109/cvpr42600.2020.01074 · External reference
10.18653/v1/2022.findings-emnlp.327
10.18653/v1/2022.findings-emnlp.327 · External reference
10.1609/aaai.v39i9.32974
10.1609/aaai.v39i9.32974 · External reference
UNMuTe: Unifying navigation and multimodal dialogue-like text generation
10.2139/ssrn.4777514 · 2024 · External reference
10.1007/978-981-95-0014-7_1
10.1007/978-981-95-0014-7_1 · External reference
Uncovering the fragility of trustworthy LLMs through chinese textual ambiguity
2025 · External reference
10.1109/icra55743.2025.11128692
10.1109/icra55743.2025.11128692 · External reference
10.1109/icra57147.2024.10610450
10.1109/icra57147.2024.10610450 · External reference
AI2-THOR: An interactive 3D environment for visual AI
2017 · External reference
10.1109/cvpr42600.2020.00323
10.1109/cvpr42600.2020.00323 · External reference
10.1109/lra.2020.2965078
10.1109/lra.2020.2965078 · External reference
10.1109/iros58592.2024.10802709
10.1109/iros58592.2024.10802709 · External reference
10.1109/cvpr.2018.00387
10.1109/cvpr.2018.00387 · External reference
10.18653/v1/2020.emnlp-main.356
10.18653/v1/2020.emnlp-main.356 · External reference
10.1007/978-3-030-58604-1_7
10.1007/978-3-030-58604-1_7 · External reference
10.1109/cvpr42600.2020.01000
10.1109/cvpr42600.2020.01000 · External reference
10.1109/cvpr.2019.01282
10.1109/cvpr.2019.01282 · External reference
The RobotSlang benchmark: Dialog-guided robot localization and navigation
2021 · External reference
Vision-and-dialog navigation
2020 · External reference
RoboRAN: A unified robotics framework for reinforcement learning-based autonomous navigation
2025 · External reference
A framework for automated driving system testable cases and scenarios
2018 · External reference
10.1002/rob.21918
10.1002/rob.21918 · External reference
10.177/0278364920917446
10.177/0278364920917446 · External reference
10.1109/tiv.2016.2578706
10.1109/tiv.2016.2578706 · External reference
End to end learning for self-driving cars
2016 · External reference
10.1103/physreve.62.1805
10.1103/physreve.62.1805 · External reference
Rapidly-exploring random trees: A new tool for path planning
1998 · External reference
10.1016/s0967-0661(02)00186-7
10.1016/s0967-0661(02)00186-7 · External reference
10.1177/027836498600500106
10.1177/027836498600500106 · External reference
10.15607/rss.2019.xv.031
10.15607/rss.2019.xv.031 · External reference
Maximum entropy inverse reinforcement learning
2008 · External reference
10.1109/tits.2021.3054625
10.1109/tits.2021.3054625 · External reference
10.1007/978-3-030-58536-5_32
10.1007/978-3-030-58536-5_32 · External reference
10.1109/icra48891.2023.10160609
10.1109/icra48891.2023.10160609 · External reference
10.1109/iccv51701.2025.02496
10.1109/iccv51701.2025.02496 · External reference
OccLLaMA: An occupancy-language-action generative world model for autonomous driving
2024 · External reference
10.1609/aaai.v39i9.33010
10.1609/aaai.v39i9.33010 · External reference
10.1109/icra48891.2023.10160890
10.1109/icra48891.2023.10160890 · External reference
DriveCoT: Integrating chain-of-thought reasoning with end-to-end driving
2024 · External reference
10.1109/cvprw67362.2025.00526
10.1109/cvprw67362.2025.00526 · External reference
10.1109/tnnls.2025.3626711
10.1109/tnnls.2025.3626711 · External reference
10.1109/iros60139.2025.11247360
10.1109/iros60139.2025.11247360 · External reference
10.1007/978-3-031-73347-5_17
10.1007/978-3-031-73347-5_17 · External reference
TeraSim-World: Worldwide safety-critical data synthesis for end-to-end autonomous driving
2025 · External reference
Cosmos-drive-dreams: Scalable synthetic driving data generation with world foundation models
2025 · External reference
10.1007/978-3-031-72995-9_9
10.1007/978-3-031-72995-9_9 · External reference
10.1038/s41586-025-08744-2
10.1038/s41586-025-08744-2 · External reference
10.1109/tits.2023.3259322
10.1109/tits.2023.3259322 · External reference
10.1109/ivs.2017.7995802
10.1109/ivs.2017.7995802 · External reference
10.1109/icra57147.2024.10610077
10.1109/icra57147.2024.10610077 · External reference
10.1109/cvpr42600.2020.01164
10.1109/cvpr42600.2020.01164 · External reference
10.1109/cvpr42600.2020.00252
10.1109/cvpr42600.2020.00252 · External reference
CARLA: An open urban driving simulator
2017 · External reference
10.1007/978-3-319-67361-5_40
10.1007/978-3-319-67361-5_40 · External reference
10.1109/lra.2022.3188435
10.1109/lra.2022.3188435 · External reference
10.52202/079017-0025
10.52202/079017-0025 · External reference
10.1038/s41597-025-06255-3
10.1038/s41597-025-06255-3 · External reference
10.3390/s18082678
10.3390/s18082678 · External reference
10.1109/cvpr42600.2020.01438
10.1109/cvpr42600.2020.01438 · External reference
Qwen2-VL: Enhancing vision-language model’s perception of the world at any resolution
2024 · External reference
Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids
External reference
Phi-4-Reasoning technical report
2025 · External reference
Attention over learned object embeddings enables complex visual reasoning
2021 · External reference
Class-balanced grouping and sampling for point cloud 3D object detection
2019 · External reference
10.1109/iccv51070.2023.00731
10.1109/iccv51070.2023.00731 · External reference
