How C2LLM Redefines Code Retrieval with Attention‑Based Pooling

Introducing C2LLM, a contrastive code LLM series that replaces mean and EOS pooling with a multi‑head attention pooling module, achieving top scores on the MTEB‑Code benchmark across 12 tasks and demonstrating cost‑effective, high‑precision code retrieval for both production and AI agent applications.

MTEB-CodeRetrieval Augmented Generationattention pooling

0 likes · 8 min read

How C2LLM Redefines Code Retrieval with Attention‑Based Pooling

AI Frontier Lectures

May 21, 2025 · Artificial Intelligence

How BGE’s New Code and Multimodal Vector Models Set New Retrieval Benchmarks

The article introduces three BGE vector models—BGE‑Code‑v1, BGE‑VL‑v1.5, and BGE‑VL‑Screenshot—detailing their architectures, open‑source resources, benchmark results on CoIR, Code‑RAG, MMEB, and MVRB, and their impact on code and multimodal retrieval research.

AI researchMultimodal AIOpen-source models

0 likes · 8 min read

How BGE’s New Code and Multimodal Vector Models Set New Retrieval Benchmarks

Kuaishou Large Model

Nov 29, 2024 · Artificial Intelligence

How OASIS Achieves State‑of‑the‑Art Code Search with Just 5M Tokens

Fast.ai's Kwaipilot team unveiled OASIS, a 1.3B‑parameter code‑embedding model that, using only 5 million tokens, outperforms larger OpenAI embeddings across CodeSearchNet, CoSQA and AdvTest benchmarks, thanks to repository‑level program analysis, synthetic data generation, and a fused loss function.

AI modelBenchmarkcode embedding

0 likes · 8 min read