Paper rethinks positional encoding and interaction granularity for CTR prediction
_reachsumit · x · 2026-10-29
A new paper, Rethinking Positional Encoding and Interaction Granularity for CTR Prediction, proposes a CTR model that encodes each behavior's rank in the sequence and its time relative to the target item, and lets behaviors attend to each other within temporal groups, refining how positional information and interaction granularity are handled in user-behavior modeling.
More from Research
- AI Audit Finds 2,035 Errors in 138 Papers by Economists Saez and Zucman — sebkrier · 2026-10-29
- Granary-v2 open speech model expands to 48 languages with open data and pipeline — rdesh26 · 2026-10-29
- Tinker launches Dimuon, a Muon-based optimizer that beats AdamW on LoRA fine-tuning — xennygrimmato_ · 2026-10-29
- Six CUDA kernel optimizations squeeze another 1.78× speedup out of 3DGS training — gkopanas · 2026-10-29
- Cross-lingual LLM effects paper wins Outstanding Paper award at EMNLP 2026 — anas_ant · 2026-10-29
- Lie detector compiled into Qwen3.5 weights flags 91% of lies with zero false positives — teortaxesTex · 2026-10-29