NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model Paper • 2508.14444 • Published Aug 20, 2025 • 49
Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment Paper • 2406.17957 • Published Jun 25, 2024 • 2
Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Paper • 2604.19079 • Published Apr 21 • 1
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models Paper • 2504.03624 • Published Apr 4, 2025 • 19
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities Paper • 2505.08699 • Published May 13, 2025 • 3
Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction Paper • 2604.12398 • Published Apr 14 • 1
Speaker Attributed Automatic Speech Recognition Using Speech Aware LLMS Paper • 2604.11269 • Published Apr 13 • 2
Self-Speculative Decoding for LLM-based ASR with CTC Encoder Drafts Paper • 2603.11243 • Published Mar 11 • 1
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence Paper • 2502.09927 • Published Feb 14, 2025 • 1
Native and Compact Structured Latents for 3D Generation Paper • 2512.14692 • Published Dec 16, 2025 • 3
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation Paper • 2402.03216 • Published Feb 5, 2024 • 8
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT Paper • 2004.12832 • Published Apr 27, 2020 • 6