Skip to main content
GameDev.net gamedev.net

AI News

Artificial intelligence and machine learning in games

Physically Based Rendering in the Latent Space

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 …

Research arXiv cs.GR · 6 hours, 11 minutes ago
joining an AI doom panel discussion oh boy

Freya Holmér is joining an AI doom panel discussion, and she says she’ll argue that generative AI is an anti-humanity technology. The panel is hosted and moderated by Whick-TV, with …

Video Freya Holmér · 2 days, 13 hours ago
Sessions on managing AI impact, neurodivergent teams and personal resilience confirmed for GamesIndustry.biz HR Summit

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 HR …

News GamesIndustry.biz · 2 days, 18 hours ago
MiHoYo awarded $112,000 by Chinese court after AI voice service dupes Genshin Impact characters

Game Developer reports that miHoYo won about $112,000 in a Shanghai court case after an AI voice service imitated Genshin Impact characters. The ruling could become a useful signal for …

News Game Developer · 2 days, 18 hours ago
S4R: Scaling for Rigid-Body Interpenetration Resolution

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 shallow convex QP …

Research arXiv cs.GR · 3 days, 6 hours ago
PointGrade: Geometric Priors for Grading MoonBoard Problems

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 sequence-based predictor, the model …

Research arXiv cs.GR · 4 days, 6 hours ago
DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery

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 …

Research arXiv cs.GR · 4 days, 6 hours ago
ADLX 2.0: Extending graphics control to AI agents and agentic apps

AMD GPUOpen says ADLX 2.0 adds AI extensions and MCP servers so apps can monitor, manage, and optimize AMD graphics hardware. For game teams, that opens the door to agent-driven …

Official AMD GPUOpen · 5 days ago
EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation

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 backbone …

Research arXiv cs.GR · 5 days, 6 hours ago
HairCS: Reconstructing Strand-Based Hair from Hair Cards

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 scalp-rooted strands and even root …

Research arXiv cs.GR · 5 days, 6 hours ago
ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication

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 checks to improve …

Research arXiv cs.GR · 5 days, 6 hours ago
The Official Unity Plugin for Codex

Unity says its official Codex plugin is out now, pairing with GPT-6 Astra to speed up AI-assisted Unity work. The plugin ships 31 Unity-authored skills, checks projects before acting, and …

Official Unity · 5 days, 10 hours ago
ViFA-Council: Multi-Agent LLM Deliberation for Vietnamese Folk Art Generation

A new multi-agent LLM pipeline, ViFA-Council, uses GPT-4o, Gemini 3.1 Pro, and Claude Sonnet 4.6 to generate Vietnamese folk-art imagery and educational stories with tighter cultural control. The system adds …

Research arXiv cs.GR · 6 days, 6 hours ago
MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume Visualization

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 reasoning, …

Research arXiv cs.GR · 6 days, 6 hours ago
ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions

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 …

Research arXiv cs.GR · 6 days, 6 hours ago
KaiNinja: Extending Native 3D Generators to the Part Level

KaiNinja extends native 3D generation from whole objects to editable parts, targeting the pain point of fused meshes that are awkward to rig, simulate, or modify. Built on TRELLIS.2, it …

Research arXiv cs.GR · 6 days, 6 hours ago
TopoRig: Topology-Agnostic Facial Rigging via Multi-Source Supervision

arXiv cs.GR details TopoRig, a facial rigging system that keeps a character’s original mesh topology while predicting FACS-driven deformations. For teams building custom characters, the pitch is fewer transfer artifacts …

Research arXiv cs.GR · 6 days, 6 hours ago
A Variational Optimal Transport Operator on Incompressible Flow

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 teams, the …

Research arXiv cs.GR · 6 days, 6 hours ago
SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

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, albedo, and shading maps, aiming to replace …

Research arXiv cs.GR · 6 days, 6 hours ago
Level-5 CEO admits using generative AI in recent showcase

GamesIndustry.biz reports that Level-5 CEO Akihiro Hino apologized after confirming generative AI was used in a recent digital showcase. The studio says the games themselves are still human-made, but it …

News GamesIndustry.biz · 6 days, 14 hours ago
Page 1 of 43 Next