The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate…

The paper introduces BilliardPhys-Bench, a new benchmark that demonstrates that current multimodal LLMs struggle with complex physical reasoning and predicting object dynamics in simulated environment…

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

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 introduces SchGen, the first large language model capable of generating editable PCB schematics from natural language by using a novel semantically grounded code representation.

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper introduces MUSE, a comprehensive benchmark that evaluates Text-to-CAD generation by assessing complex assemblies based on functionality, manufacturability, and assemblability, moving beyond…

DiagramRAG is a lightweight retrieval-augmented framework that uses reference diagrams to guide the completion of scientific diagrams from incomplete user sketches, achieving high performance on stand…

SSR3D-LLM introduces a structured spatial reasoning interface for unified 3D-LLMs, allowing fine-grained object grounding by generating and processing sequential latent spatial steps.

The paper introduces WorldCoder-Bench, a comprehensive benchmark and evaluation protocol for testing LLMs' ability to autonomously generate complex, physically grounded, and interactive 3D web worlds.

The paper introduces OmniMatBench, a comprehensive, human-calibrated multimodal reasoning benchmark covering 19 materials science subfields, revealing that current multimodal language models (MLLMs) h…

pcbGPT is a grounded system that automatically generates editable KiCad PCB schematics from natural language requirements, achieving high accuracy on complex embedded design tasks.

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

The paper introduces APEIRIA, a neuro-symbolic 3D Multi-modal LLM that bridges the gap between interpretable symbolic reasoning and flexible, open-vocabulary 3D understanding.

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on th…

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…

The paper introduces Geometric Latent Reasoning (GLR), a method that models reasoning as continuous paths in the embedding space, showing that this continuous approach allows LLMs to solve problems us…

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) ar…