MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 4 items • Updated about 3 hours ago • 11
Towards More Effective and Economic Sparsely-Activated Model Paper • 2110.07431 • Published Oct 14, 2021 • 2
Query of CC: Unearthing Large Scale Domain-Specific Knowledge from Public Corpora Paper • 2401.14624 • Published Jan 26, 2024 • 1
Turn Waste into Worth: Rectifying Top-$k$ Router of MoE Paper • 2402.12399 • Published Feb 17, 2024 • 2
Balanced Data Sampling for Language Model Training with Clustering Paper • 2402.14526 • Published Feb 22, 2024
WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset Paper • 2402.19282 • Published Feb 29, 2024
VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks Paper • 2412.18194 • Published Dec 24, 2024 • 1
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems Paper • 2506.16381 • Published Jun 19, 2025 • 4
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning Paper • 2506.23127 • Published Jun 29, 2025 • 2
XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs Paper • 2506.23325 • Published Jun 29, 2025
World-aware Planning Narratives Enhance Large Vision-Language Model Planner Paper • 2506.21230 • Published Jun 26, 2025 • 1
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance Paper • 2510.00499 • Published Oct 1, 2025 • 21
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models Paper • 2510.13626 • Published Oct 15, 2025 • 47