Tag
SMART is a framework that unlocks latent multi-vector capabilities in single-vector models for multimodal retrieval, improving state-of-the-art performance with reduced computational costs via contrastive training and late-interaction inference.
Releases a kernel on Hugging Face that accelerates MaxSim late-interaction retrieval by using tiled scoring with SIMD group matrix operations (Metal and WMMA), achieving 3–5× speedup over the naive implementation.
LightOn achieves GPT-5-level deep research retrieval performance using a 150M-parameter late-interaction model, a remarkable feat.
The article highlights how ColBERT models, despite being smaller and older, outperform larger models like Qwen3-embed-8B when coupled with late interaction techniques and minimal fine-tuning.
LightOn released Agent-ModernColBERT, a 149M parameter open-source retrieval model that achieves performance comparable to GPT-5 combined with Qwen3-Embed-8B by integrating agent reasoning traces into queries.
A new paper shows that late-interaction retrieval model representations can effectively replace raw document text in RAG tasks, extending their utility beyond retrieval.
A keynote recording argues that late interaction retrieval (e.g., ColBERT-style) is the most promising direction in AI-scale information retrieval research, contending that single-vector dense retrieval is fundamentally flawed and that the IR community must raise its ambitions significantly. The talk introduces the LIMIT benchmark as evidence of dense retrieval's generalization failures and calls for a paradigm shift by 2030.