Seedream 4.5
PulseAugur coverage of Seedream 4.5 — every cluster mentioning Seedream 4.5 across labs, papers, and developer communities, ranked by signal.
-
New VLM Tampering Detection Framework Achieves State-of-the-Art Results
Researchers have developed a new framework for detecting pixel-level image tampering in modern vision-language models (VLMs). The approach focuses on domain generalization to ensure robustness across different VLM-gener…
-
Open-source text-to-image models rapidly advance, but editing and video lag
The open-source community is seeing rapid advancements in text-to-image generation models, with Krea 2 and Ideogram 4.0 closing the gap with closed-source alternatives. However, models like Qwen2511 and Klein9B still la…
-
SenseTime open-sources SenseNova U1, unifying multimodal understanding and generation
SenseTime has officially released and open-sourced its SenseNova U1 series of native unified models for understanding and generation. These models, built on the NEO-unify architecture, integrate multimodal understanding…