Tencent is aggressively buying back its own shares on the Hong Kong Stock Exchange after its market capitalization lost $309 billion, driven by investor concerns over AI spending. The company repurcha…
ByteDance released Seedance 2.5, an AI video generation model capable of producing 30-second clips at 4K resolution with up to 50 multimodal references, setting a new benchmark for long-form AI video.…
ByteDance launched Seed Audio 1.0, an audio scene generation model that creates synchronized dialogue, ambient sound, and sound effects for AI video workflows at 18 cents per minute. The model analyze…
ByteDance's Seed Audio and Seedance models enable an audio-first video generation workflow, where users create an audio track first and use it as a reference for video generation. This approach improv…
Elastic acquired Jina AI in late 2025 and released jina-embeddings-v5-omni, a multimodal embedding model that handles text, images, audio, and video in a single vector space. The model achieves state-…
ByteDance's Seedance 2 Image to Video outperformed its predecessor Seedance V1.5 Pro in a head-to-head comparison, scoring 15.1 to 12.7. Seedance 2 demonstrated superior cinematic intent, shot grammar…
ByteDance aims to finalize the design of its next-generation in-house CPU by early next year, targeting mass production in the second half of 2027 to power its AI infrastructure. The company is collab…
DeepSeek, a Chinese AI lab, raised $7.4 billion in the largest first-time funding round by a Chinese startup, driven by US export restrictions and competition with Anthropic's Mythos model. China now …
ChangXin Memory Technologies (CXMT) has agreed to supply Tencent with roughly $3 billion of memory chips, according to sources, in a deal that would bind one of China's largest cloud operators to its …
ByteDance launched Seedance 2.5, a text-to-video model with 4K output and 30-second clips, alongside the Volcano Arc IP licensing platform that lets creators use licensed film assets with revenue shar…
A small Home Assistant blog received 18,209 AI crawler requests in nine days, accounting for 5.2% of total traffic. The majority came from ChatGPT-User (6,687 requests), which performs live fetches fo…
ByteDance's Volcano Arc platform and Seedance AI video model are addressing the IP problem in AI video generation by licensing real actor likenesses and film assets through a revenue-sharing model. Th…
ByteDance's Seed research team released Seedance 2.5, a video generation model that produces 30-second clips in 4K resolution with support for 50 multimodal references, addressing key limitations in A…
ByteDance open-sourced DeerFlow 2.0, a long-horizon agent runtime that orchestrates sub-agents, sandboxes, persistent memory, and an extensible skill system. The project reached 74,960 GitHub stars an…
ByteDance and Renmin University researchers released iLLaDA, an 8B diffusion language model that matches Qwen2.5 on base benchmarks but lags after fine-tuning. The model, trained from scratch on 12 tr…
Chuangxinzhong, a precision marketing subsidiary of Yeahka, became the top-ranked agency-tier partner of ByteDance's Jichuang 2.0 model by model consumption. The company reported a 116% year-on-year i…
Tencent is launching an AI assistant called Dayuan inside its enterprise collaboration tool WeCom, powered by DeepSeek's large language models. The tool can understand user requests and respond intell…
China's unicorn count rose to 381 in the 2026 Hurun Global Unicorn Index, up 38 from last year, with ByteDance ranking third globally behind OpenAI and Anthropic. The US leads with 806 unicorns, while…
Qualcomm unveiled the Dragonfly platform, a China-specific data center chip designed to comply with US export restrictions while serving a market that generates 46% of its revenue. The platform includ…
A developer filtered a list of 12 open-source AI projects down to seven that improve coding agent workflows, including ByteDance's DeerFlow for long-horizon tasks, Garry Tan's gstack for structured de…