Hugging Face Daily PapersRuihan Yu, Yu-Ju Tsai, Muyao NiuOct 1, 20261 min readpaperadvanced

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Summary

EditHero is a new benchmark for long‑horizon, part‑level 3D editing that supplies natural‑language instructions, geometry and texture targets, and a deterministic engine that produces the exact result after each edit. Using it, the authors show that bottom‑up LLM/VLM agents preserve unchanged parts better than top‑down non‑agentic methods, though they run slower (minutes per edit).

EditHero provides sequences of part‑level 3D edits with NL instructions and target images for both geometry and texture.
A deterministic assembly engine can generate the exact target after every edit, and all sequences are hand‑reviewed for correctness.
Top‑down non‑agentic methods often modify regions that should stay fixed, while LLM/VLM agents follow instructions more faithfully.
LLM/VLM agents preserve unedited parts well but each edit takes minutes, highlighting a speed‑accuracy trade‑off.

Researchers building iterative 3D editing tools, especially those leveraging LLM/VLM agents, need realistic benchmarks to evaluate reliability and performance.

6/10

llm graphics computer vision benchmark vlm

Related reading

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design arxiv.org
CADWorld is a new benchmark suite of 200 long‑horizon mechanical CAD tasks in FreeCAD, covering sketching, part modeling, assembly, CAM, FEM, and more. Agents interact via screenshots and GUI actions; success is checked by executable validation of the saved CAD artifacts. Seven existing agents achieve at most 17.5 % success versus an 87 % expert baseline, highlighting the gap between GUI competen…
Hugging Face Daily Papersarxiv.orgZihan Dong, Yuanzhe Liu, Zhiyuan Ma21d1 minpaper
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay arxiv.org
The paper presents GameHorizon, a unified suite comprising an automated annotation pipeline, a 5,000‑hour multi‑horizon gameplay dataset from 21 AAA titles, and reproducible offline and online benchmarks. Using it, the authors evaluate 47 models, exposing a hierarchy of task difficulty and gaps in long‑term planning.
Hugging Face Daily Papersarxiv.orgYiran Wang, Xingyilang Yin, Junfu Pu14d1 minpaper
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations arxiv.org
FAMOS is a feed-forward model that predicts 3D articulation, including movable-part segmentation and joint parameters, from sparse, unordered point clouds. It leverages multiple observations through a Multi-state Articulation Transformer and a novel observed articulation span objective, outperforming existing baselines.
Hugging Face Daily Papersarxiv.orgKevin Qu, Tao Sun, Massimiliano Viola18d1 minpaper
LongLive-Plug: Once-for-All Distillation for Video Generation arxiv.org
LongLive-Plug introduces a once-for-all distillation framework for video generation models. It learns reusable capabilities as LoRAs on a base model, enabling training-free, plug-and-play deployment to 54 diverse downstream models.
Hugging Face Daily Papersarxiv.orgShuai Yang, Luozhou Wang, Wei Huang6d1 minpaper
EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks arxiv.org
EMem‑Bench is a new benchmark of 2,554 long‑horizon embodied episodes that explicitly tests an agent’s ability to construct, update, and reuse memory across four defined challenges. The authors also release EMem, a spatial‑event‑scene external memory, and an 8B policy (EMem‑8B) that together achieve the strongest performance, highlighting persistent gaps in current multimodal LLM agents.
Hugging Face Daily Papersarxiv.orgLizhou Liang, Xinyu Zhong, Miao Pan12d1 minpaper
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation arxiv.org
Ego2Act introduces a new benchmark for evaluating goal-directed manipulation in egocentric video generation, featuring 2,640 videos across 110 real-world tasks. It reveals that current video generation models struggle with multi-step physical reasoning, often skipping steps and failing at fine-grained object manipulation and persistent world modeling.
Hugging Face Daily Papersarxiv.orgPatrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana4d1 minpaper

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Summary

Related reading

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Designarxiv.org

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplayarxiv.org

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observationsarxiv.org

LongLive-Plug: Once-for-All Distillation for Video Generationarxiv.org

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasksarxiv.org

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generationarxiv.org

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design arxiv.org

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay arxiv.org

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations arxiv.org

LongLive-Plug: Once-for-All Distillation for Video Generation arxiv.org

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks arxiv.org

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation arxiv.org