arXiv:2606. 01901v1 Announce Type: cross Abstract: We introduce the Image Reconstruction Game, a fully automated benchmark in which a vision-language model issues corrective instructions to an image generator across multiple turns, making accumulated common ground directly observable as a rendered image.
arXiv:2608. 00111v1 Announce Type: cross Abstract: Image restoration quality can be evaluated along three complementary facets: pixel-level fidelity, human perception, and downstream machine preference.
arXiv:2607. 16409v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation.
arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.
arXiv:2609.00663v1 Announce Type: new Abstract: Multimodal evaluations cannot say whether a vision-language model misread an image or misreasoned about it, because every existing method for separatin...
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
arXiv:2509. 07295v4 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture.
StateSight is a new benchmark designed to isolate and evaluate the ability of vision‑language models to reconstruct latent spatial structure from a single image. It consists of three procedurally generated task families—cube‑net opposite‑face reasoning, occluded cube‑tower counting, and 4‑neighbor connected‑component counting—each with 300 deterministic prompts and exact‑match scoring. The benchmark also includes a companion dataset, StateSight‑Steps, with 900 image‑text examples and 3,600 intermediate visual states to aid analysis of reconstruction errors.
Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface.
The paper introduces EgoGenEval, a new benchmark that assesses the physical consistency of visual generators under ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. Experiments on 16 pose‑free generators and two pose‑conditioned references show that current models struggle to maintain both camera motion and scene state simultaneously. A follow‑up study using EgoGen‑Train demonstrates that pairwise supervision does not effectively improve both metrics together, suggesting the need for a trajectory‑centric training paradigm.
RoboPhys-3D is a 3D‑grounded embodied world model benchmark built on RoboTwin 2.0, featuring 50 manipulation tasks, 5,000 episodes, and 25,000 multi‑view ground‑truth videos. It evaluates video world models by processing both generated and ground‑truth videos through the same 3D reconstruction pipeline, allowing the separation of reconstruction‑induced from generation‑induced errors. The benchmark defines 50 metrics across four sub‑dimensions—pixel fidelity, 3D geometry consistency, state understanding, and task completeness—and introduces the Average Full Score and RoboPhyscore for holistic assessment, with RoboPhyscore showing strong correlation with human judgments.
The paper introduces AttWarp, a lightweight technique that uses a multimodal large language model’s cross‑modal attention to perform rectilinear warping of input images at test time. By reallocating spatial resolution toward query‑relevant regions without altering model weights or architecture, AttWarp preserves global context while making small objects and subtle relationships easier for the model to read. Experiments on five benchmarks and four MLLMs show consistent accuracy gains, improved compositional reasoning, and reduced hallucinations compared to baseline image‑manipulation methods.
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.