AI & Machine Learning

arXiv cs.GR details an edge-centric brain transformer that models rs-fMRI connectivity as connections, not just regions. The framework uses edge time-series, a line graph, and a structure-aware...

arXiv cs.GR details MoSAT, a motion-synthesis model that uses spatial audio plus text to drive full-body animation. The team pairs it with STAM, a new dataset of motion sequences, directional sound,...

arXiv cs.GR details ChemXRG, a DSL pipeline that turns 3D chemical reaction animation into executable programs. The team pairs persistent atom IDs with bond, charge, and grouping operations, then...

arXiv cs.GR details a causal study showing audio-video generators can latch onto visual shortcuts instead of the event that actually causes a sound. The authors found that cross-attention and...

arXiv cs.GR details LINGO, a 3D Gaussian Splatting pipeline for sparse-view X-ray novel view synthesis and CT reconstruction. The method uses latent mask-space initialization and dynamic gradient...

arXiv cs.GR details ProxyBuild, a text-guided 3D building system that aims to produce editable structures instead of single baked meshes. The method uses mesh-anchored procedural proxies to separate...

arXiv cs.GR details VISTA, a two-stage text-to-animation system that blends prompt-driven motion structure with style pulled from reference video. For teams building character animation tools, the...

arXiv cs.GR details a method that pushes physically based rendering into the latent space used by diffusion models. The approach aims to make image generation more controllable by simulating light...

GamesIndustry.biz has confirmed the first HR Summit sessions for next month in London, with AI, neurodiversity and people-leader resilience at the center. For studios, the agenda points to practical...

arXiv cs.GR details S4R, a scale-continuation method that repairs rigid-body interpenetration in large procedural scenes. It shrinks bodies to a collision-free state, then restores full size through...

arXiv cs.GR details LYRIC, a physics-based character controller that turns free-form language into contact-rich whole-body interactions. For game teams, the interesting part is the split between a...

arXiv cs.GR details PointGrade, a machine-learning method that grades MoonBoard bouldering problems by sampling point clouds from pre-scanned hold meshes. By folding geometric priors into a...

arXiv cs.GR details DSD, a diffusion-based skill discovery method that learns a wider set of reusable humanoid motor skills. For game teams building animation or AI-driven characters, the pitch is...

EMODY Flow tackles a common failure in audio-driven character animation: emotion labels get ignored, and motion collapses toward the same result. The 35M-parameter system couples a frozen Qwen-3 Omni...

HairCS turns hair-card assets into strand-based hairstyles, aiming to keep the original silhouette while adding finer geometric detail. The pipeline also enforces production-friendly constraints like...

ViCo is a new training framework aimed at making AI-generated charts look and read more like human-made figures. It combines self-reflection, multi-step reinforcement learning, and automated visual...

MedVA tackles a stubborn bottleneck in medical volume visualization: turning a clinician’s intent into the right ROI and making it visible without endless manual tuning. The system combines symbolic...

A new pipeline turns text prompts into physically consistent dynamic 3D scenes that can run in Unreal Engine. The system builds an Evolutive Scene Graph, then optimizes layout and motion with...

A new neural operator called VIOT predicts divergence-free transport fields for incompressible density flow, turning what was an hour-scale solve into seconds per pair. For graphics and simulation...

SyntheticDoc brings 1,000,000 procedurally generated, high-resolution training images to document unwarping and illumination correction. The dataset pairs each sample with pixel-perfect UV, normal,...