SIGNAL
Tracking the global AI frontier — labs · research · agents · policy
Frontier Signal
✦

Create

Release-by-release coverage of the AI creation stack: video, image, music, voice, design and code generation tools.

Release-by-release coverage of the AI creation stack: video, image, music, voice, design and code generation tools.

Latest in Create

30 stories
GPT-5.6 is now the preferred model in Microsoft 365 Copilot
Labs

GPT-5.6 is now the preferred model in Microsoft 365 Copilot

Learn how GPT-5.6 powers Microsoft 365 Copilot with stronger AI capabilities across Word, Excel, PowerPoint, Chat, and Cowork for faster, higher-quality work.…
Grok x Cursor
Briefing

Grok x Cursor

More Fable, GPT-5.6 and new ChatGPT voice…
Introducing GPT-Live
Labs

Introducing GPT-Live

A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.…
Muse Image is technically impressive, but Meta's use of Instagram photos raises questions
Briefing

Muse Image is technically impressive, but Meta's use of Instagram photos raises questions

Meta's Superintelligence Labs ships Muse Image, its first image generation model. Like OpenAI's GPT Image 2, it works as an agent, using tools like code executi…
Responses are the Easy Part: What We’ve Learned Building Real-time Voice Experiences at Scale
Labs

Responses are the Easy Part: What We’ve Learned Building Real-time Voice Experiences at Scale

Timing, interruption, silence and recovery shape the experience as much as words…
Copilot goes cheap as Microsoft phases out OpenAI and Anthropic models to cut costs
Briefing

Copilot goes cheap as Microsoft phases out OpenAI and Anthropic models to cut costs

Microsoft is replacing AI models from OpenAI and Anthropic with its own MAI models in products like Excel and Outlook. Tens of thousands of queries per week alr…
Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents
Briefing

Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents

Microsoft reportedly plans to merge its consumer and enterprise Copilot apps into a single app in August. Rarely used features like Copilot Podcasts are getting…
Chinese AI video maker Kling raises $2 billion as it gears up for Hong Kong IPO
Briefing

Chinese AI video maker Kling raises $2 billion as it gears up for Hong Kong IPO

Kuaishou has raised about $2 billion from investors for its AI video division, Kling. The article Chinese AI video maker Kling raises $2 billion as it gears up …
Google launches Nano Banana 2 Lite for fast AI images and Gemini Omni Flash for video via API
Briefing

Google launches Nano Banana 2 Lite for fast AI images and Gemini Omni Flash for video via API

Google adds two new generative AI models. Nano Banana 2 Lite generates images in four seconds at $0.034 a pop. Gemini Omni Flash brings video generation and edi…
Bringing speed and strong cost performance to the market with Gemini Omni Flash and Nano Banana 2 Lite
Practice

Bringing speed and strong cost performance to the market with Gemini Omni Flash and Nano Banana 2 Lite

Great creative happens when your tools move at the speed of your ideas. To help you create rich, reliable experiences while reducing regeneration time and costs…
Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
Research

Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting

Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhea…
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data
Research

OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data

Music-driven dance video generation aims to synthesize expressive human motion that is temporally aligned with music while maintaining high visual fidelity. Des…
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
Research

SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic align…
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Research

UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception

Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches …
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
Research

ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation

ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation witho…
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Research

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt followin…
Generative Relightable Avatars
Research

Generative Relightable Avatars

We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body hum…
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
Research

OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis

Generic text-to-video models can be used as rich open-world scene priors. Despite the high quality of today's generated videos, they do not directly yield relia…
Cage-based Texture Transfer with Geometric Filtering
Research

Cage-based Texture Transfer with Geometric Filtering

Real-time texture transfer expands the creative horizon for interactive applications, enabling seamless detail projection in scenarios that range from digital c…
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
Research

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chin…
Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization
Research

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available…
Semantic Browsing: Controllable Diversity for Image Generation
Research

Semantic Browsing: Controllable Diversity for Image Generation

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend…
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Research

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation

Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have…
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Research

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent…
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Research

Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks

Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discr…
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
Research

Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation

Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Comp…
VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Research

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where…
OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning
Research

OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning

Reinforcement Learning (RL) has enabled LLMs to excel in objective reasoning tasks such as mathematics and code generation. However, applying RL to open-ended t…
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
Research

MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation

Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelity with r…
Build a healthcare appointment agent with Amazon Nova 2 Sonic
Practice

Build a healthcare appointment agent with Amazon Nova 2 Sonic

In this post, you will learn how to build a voice agent that handles appointment reminder conversations using Amazon Nova 2 Sonic and Amazon Bedrock AgentCore. …