AI Briefing#autoregressive-models
The latest AI and developer news about #autoregressive-models, with the original source and a short summary.
The latest AI and developer news about #autoregressive-models, with the original source and a short summary.
The framework scales group size quadratically with spatial compression to enable 32x compression while maintaining competitive performance on five text-to-image benchmarks.
A Jane Street intern project demonstrated that flow matching provides stable generation of synthetic order book events where DDPM diverged, though fully continuous diffusion struggles with the discrete nature of market microstructure.
A 201M-parameter SemanTok AR model matches or outperforms a VideoFlexTok AR model 3.4x its size.
JoyAI has released a 16B model that causally edits live video streams in real time based on natural language instructions.
Explorative Modeling adds an exploration axis to generative models to boost efficiency.
A study reveals that the Engram module functions as a simple architectural side-pathway rather than as memory retrieval in image generation.
By jointly training the tokenizer and the generative model, the approach achieved FID 1.48 on ImageNet 256x256.
I-DLM simultaneously boosts DLM quality and speed through introspective consistency.
A method that converts auto-regressive models into diffusion models to make them **more than 2x** faster.
LoRA, CFG, and chain-of-thought reduced accent leakage, hallucination, and truncation in LLM-based TTS.