🚀 Introducing Spatial-SSRL, the first study which proposes a Self-Supervised Reinforcement Learning paradigm for spatial understanding. 💡 Spatial-SSRL a lightweight tool-free framework that aims at enhancing spatial intelligence and is natually compatible with the RLVR training

🥰OutSafe-Bench, the first most comprehensive content safety evaluation test suite designed for the multimodal era. 😍Covers 4 modalities: 18,000+ bilingual (ZH/EN) text prompts 4,500 images 450 audio clips 450 videos 👏OutSafe-Bench is now part of the Daily Benchmark.

🚀 OpenCompass Daily Benchmark is live! ✅ Daily updates of the latest AI evaluation papers ✅ AI-powered smart summaries ✅ Available in English & Chinese 😍Stay ahead of AI trends, key insights, and cutting-edge research—all in one place! 🔗 https://t.co/kPchXbAJWz

🚀Introducing #CapRL, the first study of applying GRPO for the open-ended and subjective image captioning task. 🤯 🤖The trained CapRL-3B model achieves image captioning performance comparable to Qwen2.5-VL-72B. ✨CapRL introduces a novel training framework that redefines caption

🚀 Big news for #lmdeploy v0.10.1! 🥳Our #FP8 high-performance inference is no longer limited to the latest #GPUs. It now supports all #NVIDIA architectures from V100 onwards, bringing major speedups to more users. 🤗 https://t.co/bPJfr9rz5p

🔥LMDeploy v0.10.0 released! 😊Supercharges OpenAI’s GPT-OSS MXFP4 models. 😊Delivers exceptional performance for GPT-OSS models on V100 and higher GPUs. 😊On H800 & A100, LMDeploy outperforms vLLM across all scenarios—faster, more efficient inference! 🤗 https://t.co/bPJfr9rz5p

🔥🔥🔥@intern_lm @OpenBMB @Zai_org @StepFun_ai @AI_AlibabaInt 🔥🔥🔥

🔥China’s Open-source VLMs boom—Intern-S1, MiniCPM-V-4, GLM-4.5V, Step3, OVIS 🧐Join the AI Insight Talk with @huggingface, @OpenCompassX, @ModelScope2022 and @ZhihuFrontier 🚀Tech deep-dives & breakthroughs 🚀Roundtable debates ⏰Aug 21, 5 AM PDT 📺Live: https://t.co/brweSm4yT5

🚀 Introducing #CompassVerifier: A unified and robust answer verifier for #LLMs evaluation and #RLVR! ✨LLM progress is bottlenecked by weak evaluation, looking for an alternative to rule-based verifiers? CompassVerifier can handle multiple domains including math, science, and

Our paper won an outstanding paper on ACL 2025. Try our best open-source multimodal reasoning model Intern-S1 at https://t.co/qlUYXkrNCn. This 241B MoE model combines strong general-task capabilities with state-of-the-art performance on a wide range of scientific tasks,

🚀Introducing Intern-S1, our most advanced open-source multimodal reasoning model yet! 🥳Strong general-task capabilities + SOTA performance on scientific tasks, rivaling leading closed-source commercial models. 🥰Built upon a 235B MoE language model and a 6B Vision encoder.

🚀 Introducing #POLAR: Bring Reward Model into a New Pre-training Era! ✨ Say goodbye to reward models with poor generalization! POLAR (Policy Discriminative Learning) is a groundbreaking pre-training paradigm that trains reward models to distinguish policy distributions,

We invited 3 top HF daily papers authors to deliver talks. Topics of this session: Reinforcement Learning Speakers: - Qi-Chen Zhao — Absolute Zero Reasoner: self-play RL that reaches SOTA reasoning with zero external data - Shu-Huai Ren — MiMo-VL: Xiaomi’s unified and

🥳Trained through #InternBootcamp, #InternThinker now combines pro-level Go skills with transparent reasoning. 😉In each game, it acts as a patient, insightful coach—analyzing the board, comparing moves, and clearly explaining each decision. 🤗Try it now: https://t.co/dMJEbOui5q

🥳Introducing #InternBootcamp, an easy-to-use and extensible library for training large reasoning models. Unlimited automatic question generation and result verification. Over 1,000 verifiable tasks covering logic, puzzles, algorithms, games, and more. 🤗 https://t.co/uLtrAghjUz

🥳#FaceShot generates animations for your "imaginary friends", like Teddy Bear, and brings them into life! 😉Project page: https://t.co/xfes0NKN2u 😉Paper link: https://t.co/hP3VTW7VrT 😉Code: https://t.co/NG0Tx81QkP

🥳#StructFlowBench is a structurally annotated multi-turn benchmark that leverages a structure-driven generation paradigm to enhance the simulation of complex dialogue scenarios. 🥳StructFlowBench is now part of the #CompassHub! 😉Feel free to download and explore it—available

🥳Thrill to release the full RL training code of #OREAL! 😊Now you can fully reproduce the results of OREAL-7B/32B. Using #DeepSeek-R1-Distill-Qwen-32B, you can further obtain a model has 95.6 on MATH-500! 🤗Code: https://t.co/64qos7qln3 🤗Based on:

🥳Introducing #OREAL, a new RL method for math reasoning. 😊With OREAL, a 7B model achieves 94.0 pass@1 on MATH-500, matching many 32B models, while OREAL-32B achieves 95.0 pass@1, surpassing #DeepSeek-R1 Distilled models. 🤗Paper/Model/Data: https://t.co/IVD72J8BHN