My latest work got accepted to #ICLR2026! I am really grateful for my co-authors!!
We propose an alternative approach to end-to-end backpropagation!
1/
We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required.
Open-source, lightweight, and incredibly fast. 🧵👇
🚀 Excited to share our work at Bytedance Seed!
Knapsack RL: Unlocking Exploration of LLMs via Budget Allocation 🎒
Exploration in LLM training is crucial but expensive.
Uniform rollout allocation is wasteful:
✅ Easy tasks → always solved → 0 gradient
❌ Hard tasks → always fail → 0 gradient
💡 Our idea: treat exploration as a knapsack problem → allocate rollouts where they matter most.
✨ Results:
🔼 +20–40% more non-zero gradients
🧮 Up to 93 rollouts for hard tasks (w/o extra compute)
📈 +2–4 avg points, +9 peak gains on math benchmarks
💰 ~2× cheaper than uniform allocation
📄 Paper: https://t.co/3HbOwV2tLL
自身のモチベーション維持のために論文読みの記録を残すことにしました。data/papers.ymlを編集してpushすると自動でREADMEが更新されるはず。
超簡易的なツールですがUse this templateから二次利用していただいても構いません。
https://t.co/Hd1ICpdZ5N
🎙️ Meet Qwen3-ASR — the all-in-one speech recognition model!
✅ High-accuracy EN/CN + 9 more languages: ar, de, en, es, fr, it, ja, ko, pt, ru, zh
✅ Auto language detection
✅ Songs? Raps? Voice with BGM? No problem. <8% WER
✅ Works in noise, low quality, far-field
✅ Custom context? Just paste ANY text — names, jargon, even gibberish 🧠
✅ One model. Zero hassle.Great for edtech, media, customer service & more.
API:https://t.co/bB64vHbE1f
ModelScope Demo: https://t.co/B4qoprpbeS
Hugging Face Demo: https://t.co/CHofDumZnM
Blog:https://t.co/V9zOPfGxfp
自身のモチベーション維持のために論文読みの記録を残すことにしました。data/papers.ymlを編集してpushすると自動でREADMEが更新されるはず。
超簡易的なツールですがUse this templateから二次利用していただいても構いません。
https://t.co/Hd1ICpdZ5N
1)Hi all, glad to share some demos of our SpeechGPT2. It can can perceive and express emotions, and provide appropriate voice responses in various styles such as rap, drama, robot, funny, and whisper
project page: https://t.co/KM8fE1tUS8