Mistral Large 3 Collection A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 95
Devstral 2 Collection A couple of agentic LLMs for software engineering tasks, excelling at using tools to explore codebases, edit multiple files, and power SWE Agents. • 2 items • Updated 13 days ago • 47
V_{0.5}: Generalist Value Model as a Prior for Sparse RL Rollouts Paper • 2603.10848 • Published 3 days ago • 9
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling Paper • 2509.12201 • Published Sep 15, 2025 • 107
CodePercept: Code-Grounded Visual STEM Perception for MLLMs Paper • 2603.10757 • Published 4 days ago • 11
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs Paper • 2509.09677 • Published Sep 11, 2025 • 37
EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion Paper • 2507.16535 • Published Jul 22, 2025 • 23
FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System Paper • 2603.10420 • Published 4 days ago • 4
RoboBrain-Dex Collection Dexterous VLA utilizing human ego data training • 2 items • Updated 1 day ago • 3
Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding Paper • 2510.08668 • Published Oct 9, 2025 • 11
LeVo: High-Quality Song Generation with Multi-Preference Alignment Paper • 2506.07520 • Published Jun 9, 2025 • 8
Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment Paper • 2406.17957 • Published Jun 25, 2024 • 1
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published 8 days ago • 104
FireRedASR2S Collection FireRedASR2S is a SOTA, industrial-grade, all-in-one ASR system with ASR, VAD, LID, and Punc module. All modules achieve SOTA performance. • 7 items • Updated 1 day ago • 8