arXiv AI
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 15
PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction
arXiv:2610.17288v1 Announce Type: new Abstract: Building physical simulations from video requires coding agents to translate observations into executable models and refine them through tool use. We i...
arXiv Computer Vision
Oct 1
Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction
arXiv:2609.39960v1 Announce Type: new Abstract: 4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations. Despite substan...
arXiv AI
Jun 19
CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
arXiv:2605. 10873v2 Announce Type: replace-cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics.
arXiv AI
Jun 29
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
arXiv:2606. 28215v1 Announce Type: cross Abstract: Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs.
arXiv Computer Vision
Oct 21
AEON: Unifying Video and 3D World Models
arXiv:2610.28631v1 Announce Type: new Abstract: Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate rea...
Hugging Face Trending Papers
Jun 2
NewtPhys: Do Foundation Models Understand Newtonian Physics?
Previous work has evaluated physics reasoning in foundation models using synthetic or semi-synthetic scenes and visual question-answering tasks. However, these benchmarks emphasize high-level events and lack the visual fidelity required to assess true low-level Newtonian understanding.