Model Releases
DLRMv4: The Next-Generation Recommendation MLPerf Training Benchmark
Evolving MLPerf Training from feature-interaction baselines to production-scale sequential recommendation with HSTU and the 560 GB Yambda-5B embedding benchmark. The post DLRMv4: The Next-Generation R
Evolving MLPerf Training from feature-interaction baselines to production-scale sequential recommendation with HSTU and the 560 GB Yambda-5B embedding benchmark. The post DLRMv4: The Next-Generation Recommendation MLPerf Training Benchmark appeared first on MLCommons.
Related
- A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems
- TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendation
- CAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation
- Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation
Source: MLCommons | 2026-10-01