Research map / Probabilistic and scientific modeling / Variational and generative sampling
Sequence-to-Set Generative Models
Longtao Tang, Ying Zhou, Yu Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add size-bias trick (ablation) | Benchmark · TMALL | average l1-distance: 0.95 -> 0.91 | Improved |
| add size-bias trick (ablation) | DCM · TMALL | average l1-distance: 1.00 -> 0.94 | Improved |
| add size-bias trick (ablation) | MRW · TMALL | average l1-distance: 1.02 -> 0.92 | Improved |
| add size-bias trick (ablation) | SetNN · TMALL | average l1-distance: 0.96 -> 0.88 | Improved |
| add size-bias trick (ablation) | GRU2Set · TMALL | average l1-distance: 0.97 -> 0.87 | Improved |
| add size-bias trick (ablation) | Benchmark · HKTVMALL | average l1-distance: 0.83 -> 0.80 | Improved |
| add size-bias trick (ablation) | DCM · HKTVMALL | average l1-distance: 0.86 -> 0.81 | Improved |
| add size-bias trick (ablation) | MRW · HKTVMALL | average l1-distance: 0.88 -> 0.82 | Improved |
| add size-bias trick (ablation) | SetNN · HKTVMALL | average l1-distance: 0.88 -> 0.79 | Improved |
| add size-bias trick (ablation) | GRU2Set · HKTVMALL | average l1-distance: 0.88 -> 0.78 | Improved |
| use DCM or MRW instead of histogram benchmark | DCM, MRW · TMALL, HKTVMALL | l1-distance: 0.95 -> 1.00 | Hurt |
| GRU2Set with size bias vs benchmark | GRU2Set + Size Bias · TMALL | l1-distance: 4% | Improved |
Closest papers by meaning
- A Sequential Set Generation Method for Predicting Set-Valued Outputs (AAAI 2019 · similarity 0.84)
- LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data (ICML 2025 · similarity 0.82)
- Order-Independence Without Fine Tuning (NeurIPS 2024 · similarity 0.82)
- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective (NeurIPS 2026 · similarity 0.82)
- Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability (ICML 2024 · similarity 0.82)
- Set-LLM: A Permutation-Invariant LLM (NeurIPS 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
