AI intelligence feed

TELEGRAM HUGGINGFACEPAPERSJul 3, 2026Highlight

Morphing into Hybrid Attention Models

The paper proposes FlashMorph, a method to convert standard Transformers into hybrid attention models by formulating layer selection as a budget-constrained optimization problem. It uses morphable models and linearization regularization to decide which layers keep full attention and which switch to linear attention, considering global interdependencies. This approach outperforms heuristic selection strategies, discovering efficient configurations that maintain strong long-context recall and overall performance. FlashMorph also reduces the computational cost of layer selection itself, making it scalable.

TELEGRAM HUGGINGFACEPAPERSJun 29, 2026Highlight

Qwen-Image-2.0-RL Technical Report

Researchers present Qwen-Image-2.0-RL, a method that enhances image generation and editing diffusion models via reinforcement learning. It combines RLHF and on-policy distillation, fine-tunes vision-language models, and constructs task-specific reward models within a scalable RL training framework. A hybrid classifier-free guidance strategy and per-category reward weight calibration further boost performance. The approach achieves notable gains in visual quality, instruction following, and editing accuracy across multiple evaluation metrics.

AI signal, minus the noise.

Morphing into Hybrid Attention Models

Qwen-Image-2.0-RL Technical Report