view article Article Party is over: regularizing ColBERT models to fix efficient ANN methods lightonai • 18 days ago • 23
DenseOn & LateOn Collection A collection of open state-of-the-art single and multi-vector models • 8 items • Updated 10 days ago • 12
view article Article MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era MiniMax-AI • Jan 15, 2025 • 52
Mechanistic Analysis of Alignment Algorithms in Language Models Paper • 2606.09850 • Published May 9 • 2
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting Paper • 2606.09809 • Published 27 days ago • 4
view article Article **ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models?** lightonai • Feb 19 • 22
ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives Paper • 2603.20990 • Published 30 days ago • 1
ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models Paper • 2602.16609 • Published Feb 18 • 9
Bharat-NanoBEIR: Indian Language Retrieval Benchmarks Collection NanoBEIR retrieval benchmarks translated into 22 Indian languages across 13 datasets. • 22 items • Updated Dec 13, 2025 • 5
BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives Paper • 2511.08029 • Published Nov 11, 2025 • 4
view article Article Introducing RTEB: A New Standard for Retrieval Evaluation +4 fzliu, KennethEnevoldsen, Samoed, isaacchung, tomaarsen, fzoll • Oct 1, 2025 • 146
view article Article Welcome GPT OSS, the new open-source model family from OpenAI! +10 reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante • Aug 5, 2025 • 513
RLHN Datasets Collection RLHN: Cleaned Training Datasets with False Negatives Identified & Relabeled as ground truth. • 5 items • Updated May 23, 2025 • 4
Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval Paper • 2505.16967 • Published May 22, 2025 • 24
Natural Reasoning LMs Collection LMs fine tuned on natural reasoning by facebook • 2 items • Updated Mar 25, 2025 • 1
ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models Paper • 2411.10867 • Published Nov 16, 2024 • 9