AI Paper Atlas

Research map / Benchmarks / Beauty

Beauty leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Beauty. Best NDCG@10: 0.0698 (MIMAR-SRec, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Beauty · NDCG@10

14 papers, each with its best reported number for its own method; higher is better.

#NDCG@10 ↑MethodPaperTopic
10.0698MIMAR-SRecMulti-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
20.0657IOCLRecIntent Oriented Contrastive Learning for Sequential Recommendation
AAAI 2025 · Table 2
Recognition and long-tail
30.0604SIGMASIGMA: Selective Gated Mamba for Sequential Recommendation
AAAI 2025 · Overall performance table
Attention and transformers
40.0601FreqRec (P)Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
50.0557TGCL4SRTemporal Graph Contrastive Learning for Sequential Recommendation
AAAI 2024 · Table 2
Knowledge and temporal graphs
60.0537BirDRec
SASRec
Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation
NeurIPS 2023 · Table 3
Recognition and long-tail
70.0489FLASHRethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
NeurIPS 2026 · Table 1
Recognition and long-tail
80.0473HG-RecHyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy
ICML 2026 · Table 1
RNNs and normalization
90.0426SparseEnNet
Transformer
Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation
AAAI 2024 · Table 2
Certified and empirical robustness
100.0424ActionPieceActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation
ICML 2025 · Table: Performance comparison
Recognition and long-tail
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Beauty · NDCG@20

13 papers, each with its best reported number for its own method; higher is better.

#NDCG@20 ↑MethodPaperTopic
10.0799MIMAR-SRecMulti-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
20.0761IOCLRecIntent Oriented Contrastive Learning for Sequential Recommendation
AAAI 2025 · Table 2
Recognition and long-tail
30.0705TV-RecTV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation
NeurIPS 2025 · Table 1
CNN design
40.0703BSARecAn Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention
AAAI 2024 · Table 1
Attention and transformers
50.0702FENRec
ICSRec
Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec
AAAI 2025 · Table 1
Recognition and long-tail
60.0686FreqRec (P)Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
70.0648TGCL4SRTemporal Graph Contrastive Learning for Sequential Recommendation
AAAI 2024 · Table 2
Knowledge and temporal graphs
80.0568ADARec
ELCRec
De-collapsing User Intent: Adaptive Diffusion Augmentation with Mixture-of-Experts for Sequential Recommendation
AAAI 2026 · Table 1
Fast diffusion sampling
90.0568SRA-CL
Transformer
SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
NeurIPS 2025 · Table 1
Retrieval and knowledge
100.0512SparseEnNet
Transformer
Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation
AAAI 2024 · Table 2
Certified and empirical robustness
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Beauty · HR@20

10 papers, each with its best reported number for its own method; higher is better.

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.