The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

The paper evaluates the performance of Vision-Language Models (VLMs) in a collaborative dialogue task requiring spatial reconstruction, finding that while detailed text representations improve results…

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

The paper introduces the Image Reconstruction Game, a benchmark showing that the quality of the descriptive model is the primary determinant of image reconstruction success, while the generator's role…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes a visual program synthesis framework using a VLM to generate accurate training data for semiconductor inspection, mitigating the sim-to-real gap by applying input binarization to st…

SimuScene introduces a novel compositional 3D reconstruction pipeline that integrates physics simulation directly into the shape and layout estimation process to generate stable, simulation-ready 3D s…

The paper reframes industrial visual sim-to-real transfer as a domain-gap problem categorized by the availability of explicit object geometry (CAD), arguing that the required prior evidence dictates t…

The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating re…

The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…

PatchPoison introduces a lightweight dataset-poisoning method that injects small, high-frequency adversarial patches into multi-view image datasets to systematically corrupt feature matching and degra…

GeM-NR proposes a novel, training-free framework to achieve general multi-view image editing, enabling consistent edits that drastically change both the geometry and appearance of a nonrigid scene.

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence fro…

The paper proposes MindDiffuser, a two-stage framework that significantly improves image reconstruction from brain activity by combining semantic guidance from text-to-image models with structural ref…

Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…

The paper addresses the challenge of multi-turn view planning for VLMs by proposing an iterative framework that uses self-exploration and view graph distillation, significantly improving planning perf…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…