Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published 9 days ago • 207
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss Paper • 2410.17243 • Published Oct 22, 2024 • 90
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published 22 days ago • 129
Rank1: Test-Time Compute for Reranking in Information Retrieval Paper • 2502.18418 • Published 17 days ago • 25
GHOST 2.0: generative high-fidelity one shot transfer of heads Paper • 2502.18417 • Published 17 days ago • 63
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published 22 days ago • 162
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? Paper • 2502.14502 • Published 22 days ago • 85
view article Article Train 400x faster Static Embedding Models with Sentence Transformers Jan 15 • 159
The Differences Between Direct Alignment Algorithms are a Blur Paper • 2502.01237 • Published Feb 3 • 112
NanoBEIR 🍺 Collection A collection of smaller versions of BEIR datasets with 50 queries and up to 10K documents each. • 13 items • Updated Sep 11, 2024 • 13
view article Article KV Caching Explained: Optimizing Transformer Inference Efficiency By not-lain • Jan 30 • 36
Towards General Text Embeddings with Multi-stage Contrastive Learning Paper • 2308.03281 • Published Aug 7, 2023 • 2
Jasper and Stella: distillation of SOTA embedding models Paper • 2412.19048 • Published Dec 26, 2024 • 1
Facilitating large language model Russian adaptation with Learned Embedding Propagation Paper • 2412.21140 • Published Dec 30, 2024 • 18
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Paper • 1908.10084 • Published Aug 27, 2019 • 5
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published Dec 18, 2024 • 135
Tulu 3 Models Collection All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated about 21 hours ago • 93