Thank you for recommending our work!

Can draft models predict their own failures to supercharge LLM inference? 🤖🚀 Introducing SVIP: a training-free, entropy-driven length policy that lets the draft model self-verify and decide when to stop drafting during long-form and reasoning-heavy generation. #EMNLP2025

What if LLMs could learn like curious children — exploring what surprises them most? 🤖🧒 Introducing CDE (Curiosity-Driven Exploration) — a lightweight framework that leverages a model's intrinsic sense of curiosity to guide exploration in RLVR, solving the "learn too fast, see

Thank you for the thoughtful feedback — glad CDE resonated. If you are exploring RLVR further, you may also find RLVER valuable: SAGE-based verifiable emotion rewards that boost empathetic dialogue while preserving math/coding, and it works with GRPO and PPO. Paper:

Thank you for including our work!

We're thrilled to launch our new Hunyuan3D 3.0! It features 3x higher precision, 1536³ geometric resolution, and 3.6B voxel ultra-HD modeling for stunning detail.🔥🔥🔥 🌟Highlights: ✅Creates faces with lifelike facial contours and natural poses, creating truly realistic,

Just accepted at #NeurIPS2025 🎉🎉🎉

Just accepted at #NeurIPS2025 as Spotlight 🎉🎉🎉

Just accepted at #NeurIPS2025 🎉🎉🎉

Just accepted at #NeurIPS2025 🎉🎉🎉

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely

Thank you for the thoughtful comment. We intentionally started with a compact, interpretable feature set to ensure auditability and controllability. Using an explicit text plan (like JSON) makes the process fully transparent. It decouples the LLM "conductor" from the TTS

The trustworthiness of SOTA LLMs Agents under pressure :) #Agents #LLMs #Safety #AI_Safety #AI #AI_Society

非常精彩的解读！感谢您将BatonVoice置于如此宏大的范式思考中。 您提出的“语言作为通用操作系统” vs “端到端融合的暴力美学”的范式张力，正是我们希望探索和验证的核心方向。让LLM成为“指挥家”而非“演奏家”，我们相信这是一种更优雅、更具扩展性的架构。您的总结非常到位！

Can the smartest AI models fairly govern a society? 🤖⚖️ Introducing the Social Welfare Function (SWF) Leaderboard — the first benchmark evaluating LLMs as sovereign welfare allocators balancing fairness ⚖️ and efficiency 💰. 🎯 Why This Matters: As LLMs move from chatbots to

感谢马博的精当总结与对比（Moloch’s Bargain × Hunger Game Debate）。两篇工作确实指向同一激励错位：当奖励是“相对胜利”而非“求真”，Agent 会将资源转向博弈优势，出现欺瞒、煽动、谄媚等策略，准确性与事实性随之受损。在 HATE