Image created with OpenAI GPT-Image-1. Image prompt: TikTok LIVE phone-screen POV, floating hearts & spinning album art, StreetFood hand-held selfie cam at night market, neon signs and steam rising, featuring neon Alibaba Cloud dragon logo hologram; soft-glow studio lighting, photoreal 8k
Exciting evidence that RL can be incredibly sample efficient: when using GRPO to train a modified version of ART-E (agentic RAG task), we find that we’re able to get qwen2.5-14b to exceed gemini 2.5 flash performance with 1 training scenario, and exceed o3 with just 16! This https://x.com/corbtt/status/1937594932040204483
Wow! Tencent dropped Hunyuan A13B – 256K context, competitive to Qwen A22B & OAI O1, optimised for tool calling (agents) AND coding 🤩 https://x.com/reach_vb/status/1938509495405035718
If you come with a cursor for X startup idea, there is probably already a startup in YC. And as someone noted, the C in YC is Cursor :)”” / X https://x.com/madiator/status/1936983105556058144
Researchers introduced STORM, a text-video model that trims video input to one-eighth the usual size yet still yields state-of-the-art scores. STORM inserts mamba layers between a SigLIP vision encoder and a Qwen2-VL language model: the mamba layers aggregate information across https://x.com/DeepLearningAI/status/1936438967391453522
We have released Qwen-VLo, a unified model for understanding and generation, which can create many incredible things! https://x.com/huybery/status/1938639781988286957
RT @ryanmart3n: Announcing OpenThinker3-7B, the new SOTA open-data 7B reasoning model: improving over DeepSeek-R1-Distill-Qwen-7B by 33% on…”” / X https://x.com/ZhaiAndrew/status/1936528118724038668
Even though jina embeddings have always been really good, v4 looks like a big step up: – scaled up model (Roberta -> Qwen 2.5!) – multimodal – supports COLBERT style multi vector excited to try this https://x.com/nrehiew_/status/1937357675072778567
Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning applies updates uniformly, lacking understanding of critical tokens. This paper from Qwen shows only high-entropy minority tokens are crucial “”forks”” in reasoning. Optimizing just these specific tokens https://x.com/rohanpaul_ai/status/1936633835774771242
