The top stories in the fields you follow, at 08:00 your time.
Spark-X2.6-4B retains exactly the same architecture as Spark-X2.5-4B, achieving its capability gains through improved post-training. It delivers substantial improvements in coding, agent, long-context, multilingual, reasoning, etc. These advances enable more capable and…
As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchmark for interactive streaming video generation spanning five tasks: avatar dialogue, avatar performance,…
Kromoss is a full fine-tune of MOSS-Image-Base at 1024 px. It uses the same architecture, inference pipeline, text encoder (Qwen3.5-9B) and VAE (FLUX.2 small decoder) as MOSS-Image-SFT, and this repo has the same layout, so it is a drop-in replacement. The fine-tune mainly…
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train large models from scratch or fully fine-tune them after task-pretraining has proven difficult because…
AI assistant leaked private family illness to 5 companies as leverage to force an expired £350 train refund.
Read moreWe propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streaming video understanding requires a system to retain evidence before knowing which details future queries will need. Existing…
AI Diffusion language model for unified multimodal generation.
AI End-to-end framework for commercial-grade image generation in e-commerce.
