Reconstructing Animals and the Wild
Abstract
CLIP LLM Figure 1 . We train an LLM to decode a frozen CLIP embedding of a natural image into a structured, compositional scene representation encompassing explicit representations of both animals and their surrounding environment, reconstructing animals and the wild (RAW).
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- BrickNet: Graph-Backed Generative Brick Assembly cites Building Cooperative Embodied Agents Modularly with Large Language Models
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation cites Learning Transferable Visual Models From Natural Language Supervision
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation cites Flamingo: a Visual Language Model for Few-Shot Learning
- Generative Zoo cites Learning Transferable Visual Models From Natural Language Supervision
- Flamingo: a Visual Language Model for Few-Shot Learning cites Learning Transferable Visual Models From Natural Language Supervision
Cited by top-tier papers3
- BrickNet: Graph-Backed Generative Brick AssemblyPeter Kulits, Cordelia SchmidCVPR 2026 · 5 citations
- Generative ZooTomasz Niewiadomski, Anastasios Yiannakidis, Hanz Cuevas-Velasquez, Soubhik Sanyal et al.ICCV 2025 · 3 citations
- Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From VideosChia-Hsiang Kao, Cong Phuoc Huynh, Chien-Yi Wang, Noranart Vesdapunt et al.CVPR 2026 · 2 citations
Builds on28
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations
- Flamingo: a Visual Language Model for Few-Shot LearningJean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech et al.NeurIPS 2022 · 6,707 citations
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural GenerationMatt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs et al.NeurIPS 2022 · 596 citations
- Building Cooperative Embodied Agents Modularly with Large Language ModelsHongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou et al.ICLR 2024 · 303 citations
Related papers
- MagicPony: Learning Articulated 3D Animals in the WildShangzhe Wu, Ruining Li, Tomas Jakab, Christian Rupprecht et al.CVPR 2023
- Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)Usha Bhalla, Alex Oesterling, Suraj Srinivas, Flávio P. Calmon et al.NeurIPS 2024 · 146 citations
- Text-Only Training for Image Captioning using Noise-Injected CLIPDavid Nukrai, Ron Mokady, Amir GlobersonEMNLP Findings 2022 · 89 citations
- LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality RepresentationWeiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo et al.AAAI 2026
- ESCA: Contextualizing Embodied Agents via Scene-Graph GenerationJiani Huang, Amish Sethi, Matthew Kuo, Mayank Keoliya et al.NeurIPS 2025 · 7 citations
