view article Article Up to 3.2x Faster Inference with LFM2.5-DSpark LiquidAI • about 21 hours ago • 19
view article Article Grabette: an open system to record robot-manipulation data +4 SteveNguyen, chouziel, glannuzel, simheo, Jeremy-Pollen, etienne-pollen • Jul 21 • 56
view article Article mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench hotchpotch • 8 days ago • 7
view article Article LEMUR and Mean Centering for Late-Interaction Retrieval in txtai NeuML • 8 days ago • 8
view article Article Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers +1 tomaarsen, NohTow, raphaelsty • 4 days ago • 79
view article Article LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge LiquidAI • 9 days ago • 47
view article Article Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model CohereLabs • 9 days ago • 37
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval Paper • 2603.12824 • Published Mar 13 • 7
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Paper • 1908.10084 • Published Aug 27, 2019 • 17
view article Article FineBooks: are open OCR models good enough to unlock historical knowledge? finebooks • 11 days ago • 24
Muse Glimmer Collection Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated 11 days ago • 102
DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search Paper • 2607.27178 • Published 24 days ago • 6
view article Article GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval chungimungi • 13 days ago • 12
view article Article Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes erikkaum • 14 days ago • 19
view article Article Bekko Embedding: how small can a multilingual retrieval model be? hotchpotch • 23 days ago • 6