Hugging Face's logo
VIDRAFT_LAB's picture
🔄 In a Training Loop

VIDRAFT_LAB

SeaWolf-AI
119 43 250
SpyC0der77's profile picture leaan88's profile picture mac1e2's profile picture
·
https://www.vidraft.net

AI & ML interests

Contact: arxivgpt@gmail.com

Recent Activity

reacted to theirpost with 🤗 about 13 hours ago
🧬 Darwin-180B-RSI — an AI that learns from itself and knows when it's right 👉 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🧬 Darwin — crossbreed and evolve the parent Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots — producing a child stronger than its parents. Father model: Qwen3.8-Flash-Next (180B MoE). 🔧 Rewired paths 🔹 12 full-attention layers · 🔹 36 linear-attention layers · 🔹 48 shared-expert layers — precision-strengthened 🔒 512 routed experts · router · vision encoder — untouched → Only 0.02% of the weights changed. 🔁 RSI × 🏛️ ZTC RSI (recursive self-improvement): solve → verify against real answers → learn only the correct reasoning → repeat. ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right — zero extra tokens. Returns answer + confidence as JSON. {"answer": "...", "confidence": 0.97, "truncated": false} ✨ Synergy: ZTC finds where the model wavers → RSI learns exactly there → confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers. ⚡ Same accuracy, 11% shorter reasoning — faster and cheaper. 📄 https://arxiv.org/abs/2605.14386 🤗 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🏛️ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems 🏆 The result — #1 on five Hugging Face official leaderboards 🥇 AIME 2026 100% (first perfect score on the board) 🥇 HMMT Feb 2026 100% (first perfect score on the board) 🥇 GPQA Diamond 94.44% 🥇 MMLU-Pro 88.12% 🥇 MMMU-Pro 79.48% 📏 131K-token thinking budget · bf16 · samples per benchmark listed on the model card. 🚀 #Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
reacted to theirpost with 👀 about 13 hours ago
🧬 Darwin-180B-RSI — an AI that learns from itself and knows when it's right 👉 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🧬 Darwin — crossbreed and evolve the parent Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots — producing a child stronger than its parents. Father model: Qwen3.8-Flash-Next (180B MoE). 🔧 Rewired paths 🔹 12 full-attention layers · 🔹 36 linear-attention layers · 🔹 48 shared-expert layers — precision-strengthened 🔒 512 routed experts · router · vision encoder — untouched → Only 0.02% of the weights changed. 🔁 RSI × 🏛️ ZTC RSI (recursive self-improvement): solve → verify against real answers → learn only the correct reasoning → repeat. ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right — zero extra tokens. Returns answer + confidence as JSON. {"answer": "...", "confidence": 0.97, "truncated": false} ✨ Synergy: ZTC finds where the model wavers → RSI learns exactly there → confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers. ⚡ Same accuracy, 11% shorter reasoning — faster and cheaper. 📄 https://arxiv.org/abs/2605.14386 🤗 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🏛️ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems 🏆 The result — #1 on five Hugging Face official leaderboards 🥇 AIME 2026 100% (first perfect score on the board) 🥇 HMMT Feb 2026 100% (first perfect score on the board) 🥇 GPQA Diamond 94.44% 🥇 MMLU-Pro 88.12% 🥇 MMMU-Pro 79.48% 📏 131K-token thinking budget · bf16 · samples per benchmark listed on the model card. 🚀 #Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
reacted to theirpost with 🚀 about 13 hours ago
🧬 Darwin-180B-RSI — an AI that learns from itself and knows when it's right 👉 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🧬 Darwin — crossbreed and evolve the parent Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots — producing a child stronger than its parents. Father model: Qwen3.8-Flash-Next (180B MoE). 🔧 Rewired paths 🔹 12 full-attention layers · 🔹 36 linear-attention layers · 🔹 48 shared-expert layers — precision-strengthened 🔒 512 routed experts · router · vision encoder — untouched → Only 0.02% of the weights changed. 🔁 RSI × 🏛️ ZTC RSI (recursive self-improvement): solve → verify against real answers → learn only the correct reasoning → repeat. ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right — zero extra tokens. Returns answer + confidence as JSON. {"answer": "...", "confidence": 0.97, "truncated": false} ✨ Synergy: ZTC finds where the model wavers → RSI learns exactly there → confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers. ⚡ Same accuracy, 11% shorter reasoning — faster and cheaper. 📄 https://arxiv.org/abs/2605.14386 🤗 https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 🏛️ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems 🏆 The result — #1 on five Hugging Face official leaderboards 🥇 AIME 2026 100% (first perfect score on the board) 🥇 HMMT Feb 2026 100% (first perfect score on the board) 🥇 GPQA Diamond 94.44% 🥇 MMLU-Pro 88.12% 🥇 MMMU-Pro 79.48% 📏 131K-token thinking budget · bf16 · samples per benchmark listed on the model card. 🚀 #Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
View all activity

Organizations

FINAL_Bench's profile picture Gemma Challenge's profile picture PPALLI's profile picture