Filter
Exclude
Time range
-
Near
Mar 4
🚀 Even Elon Musk is Impressed! How Qwen 3.5 is Redefining "Small but Mighty." "Impressive intelligence density!" — Just yesterday, Elon Musk personally weighed in to praise Alibaba’s newly released Qwen 3.5 Small Model Series. Spanning from 0.8B to 9B parameters, this lineup officially shatters the myth that "size is everything" in AI: • Punching Above Its Weight: The 9B model’s performance rivals legacy models ten times its size, dominating benchmarks in logic, math, and multilingual tasks. • Native Multimodal: No more "bolt-on" vision. With ground-up image integration, OCR and UI navigation are now lightning-fast. • The On-Device Revolution: The 4B model flies on standard laptops, enabling offline AI assistants on smartphones—balancing privacy with peak speed. • Powered by Scaled RL: Thanks to advanced Reinforcement Learning, these small models have learned to "think," delivering rock-solid reasoning via Chain-of-Thought (CoT). Chinese LLMs have entered the "Refinement Era": It’s no longer about scaling up—it’s about leveling up the IQ! Do you think the era of small models has truly arrived? Qwen 3.5 vs Grok — which one are you more bullish on? Tell me in the comments! 🚀 If you found this useful, repost it to your friends~ #AI #ElonMusk #Qwen3 #Alibaba #SmallModel #Grok
4
3
153
11 Nov 2025
⭐ VibeThinker-1.5B — SOTA reasoning in a tiny model. 🚀 Performance: Highly competitive on AIME24/25 & HMMT25 — surpasses DeepSeek R1-0120 on math, and outperforms same-size models in competitive coding. ⚡ Efficiency: Only 1.5B params — 100-600× smaller than giants like Kimi K2 & DeepSeek R1. 💰 Cost: Full post-training for just $7.8K — 30-60× cheaper than DeepSeek R1 or MiniMax-M1. 🧠 Innovation: Powered by our Spectrum-to-Signal Principle (SSP) and MGPO framework. Model : huggingface.co/WeiboAI/VibeT… Github: github.com/WeiboAI/VibeThink… Arxiv : arxiv.org/abs/2511.06221 #AI #LLM #Reasoning #OpenSource #SmallModel
28
58
382
111,032
まだVSync取って無くて、最終的にはVSyncでバッファスイッチ。 SGPは描画完了時に割り込み掛けられるんで、間に合って無ければ1Frame遅らせるとかかね。 ハードスプライトも同列に扱える様整備中(表示は出来てる) SmallModelだとメモリが厳しい。 でも全部Far*になるのも嫌だなぁ_(┐「ε:)_
1
1
14
649
🚀 We’re excited to share our latest work! Welcome to the first successful "aha moment" on multimodal reasoning. "Aha moment" is featured by improved response length & performance. It emerges during RL of an unaligned base model on multimodal tasks. Aha moment for language reasoning was originally observed on DeepSeek-R1-Zero. 🔍 Key Findings: 1. Directly applying GRPO on an unaligned 2B base model could elicit the multimodal “aha moment”: thinking capability marked by spontaneous reasoning strategy and increased reasoning length 2. Visual-centric task could benefit from long Chain-of-Thoughts 💻 Discover more on our notion blog and project page! Detailed Research Blog: Follow our complete journey and technical insights at our Notion Blog: 🔗turningpointai.notion.site/t… Reproduce Our Results: Access and build upon our implementation at GitHub: 🔗github.com/turningpoint-ai/V… Presented by: TurningPointAI Team 🔗turningpoint-ai.com/ #turningpointai #Smallmodel #MultimodalR1 #DeepseekR1 #R1 #Deepseek #AI #MultimodalReasoning #Qwen #QwenVL #DeepSeekR1zero
3
11
3,634
Every #rwa should have this kind of arrangement for members of society who serve us day and night. #smallmodel brilliantly executed in my neighborhood. For #social_family with #SocialDistancing #foreveryone
3
13
15 Jan 2016
#smallmodel #natualschool model and natural schoolplayground together
1