No article text was recorded for this version.
physical common sense
Version 1 of 1186 papers247 conceptsfrozen 2026-10-04
Papers in this version
- Blog: PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
- Blog: Physion: Evaluating Physical Prediction from Vision in Humans and Machines
- Blog: PACS: A Dataset for Physical Audiovisual CommonSense Reasoning
- Blog: Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought
- Blog: Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
- Blog: NEWTON: Are Large Language Models Capable of Physical Reasoning?
- Blog: Probing Mechanical Reasoning in Large Vision Language Models
- Blog: Benchmarking Counterfactual Reasoning Abilities about Implicit Physical Properties
- Blog: Physion: Evaluating Physical Prediction from Vision in Humans and Machines
- Blog: PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
- Blog: Vision Language Models Know Law of Conservation without Understanding More-or-Less
- Blog: I-PHYRE: Interactive Physical Reasoning
- Blog: Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos
- Blog: Naive
- Blog: Invariant representation of physical stability in the human brain
- Blog: A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories
- Blog: GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs
- Blog: A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
- Blog: Perception Test 2025: Challenge Summary and a Unified VQA Extension
- Blog: LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models
- Blog: Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties
- Blog: CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
- Blog: GRASP: A Novel Benchmark for Evaluating Language GRounding and Situated Physics Understanding in Multimodal Language Models
- Blog: CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
- Blog: EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
- Blog: Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics
- Blog: AIBIRDS: The Angry Birds Artificial Intelligence Competition
- Blog: VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
- Blog: X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
- Blog: Visual Grounding of Learned Physical Models.
- Blog: Generalizable Features From Unsupervised Learning
- Blog: Embodied AI Agents: Modeling the World
- Blog: Benchmarking Progress to Infant-Level Physical Reasoning in AI
- Blog: The Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research
- Blog: A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
- Blog: SlotPi: Physics-informed Object-centric Reasoning Models
- Blog: DOoM: Difficult Olympiads of Math
- Blog: PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
- Blog: Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties
- Blog: OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Blog: NEWTON: Are Large Language Models Capable of Physical Reasoning?
- Blog: PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
- Blog: PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
- Blog: Visual cognition in multimodal large language models
- Blog: Flexible neural representation for physics prediction
- Blog: Physics-Based Interaction with 3D Objects via Video Generation
- Blog: Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
- Blog: Evaluating Object Permanence in Embodied Agents using the Animal-AI Environment
- Blog: MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
- Blog: Theoretical physics benchmark (TPBench) - a dataset and study of AI reasoning capabilities in theoretical physics
- Blog: Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models
- Blog: Who is Mistaken?
- Blog: CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
- Blog: Evaluating visual "common sense" using fine-grained classification and captioning tasks
- Blog: Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
- Blog: Learning VIsual Predictive Models of Physics for Playing Billiards Katerina Fragkiadaki
- Blog: Embodied AI: From LLMs to World Models
- Blog: Solving Physics Puzzles by Reasoning about Paths
- Blog: AGI-Elo: How Far Are We From Mastering A Task?
- Blog: MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting
Showing 60 of 186 papers.
History & citation
Current · Permanent link
- Physical Commonsense and Intuitive Physics in AI merged into this direction (87% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_physical_common_sense_ce951a05,
title = {physical common sense},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/physical-common-sense/rdr_ce951a058021474299bd0a35fe7813b7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_physical_common_sense_ce951a05_v1,
title = {physical common sense},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/physical-common-sense/rdr_ce951a058021474299bd0a35fe7813b7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}