Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
Generative recommendation for large-scale advertising
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.IR 3years
2026 3roles
dataset 1polarities
background 1representative citing papers
CapsID uses probabilistic capsule routing and confidence-based termination to generate variable-length semantic IDs, improving recall by 9.6% over strong baselines with half the latency of dual-representation systems.
UniVA unifies value alignment in generative recommendation via a Commercial SID tokenizer, eCPM-aware RL decoder, and personalized beam search, reporting 37% offline Hit Rate gains and 1.5% online GMV lift on Tencent WeChat Channels.
citing papers explorer
-
Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation
Releases TencentGR-1M and TencentGR-10M datasets with baselines for all-modality generative recommendation in advertising, including weighted evaluation for conversions.
-
CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation
CapsID uses probabilistic capsule routing and confidence-based termination to generate variable-length semantic IDs, improving recall by 9.6% over strong baselines with half the latency of dual-representation systems.
-
Unified Value Alignment for Generative Recommendation in Industrial Advertising
UniVA unifies value alignment in generative recommendation via a Commercial SID tokenizer, eCPM-aware RL decoder, and personalized beam search, reporting 37% offline Hit Rate gains and 1.5% online GMV lift on Tencent WeChat Channels.