rishabh

rishabh-ranjan's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in stanford-star/relbench-leaderboard 28 days ago

Add leaderboard entry: RelBench GNN

#13 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: LightGBM (tabular features)

#12 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: LightGBM (tabular features)

#11 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: ID-GNN

#10 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: RelBench GNN

#9 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: RelBench Baseline (heuristics)

#8 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: RelBench Baseline (heuristics)

#7 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: Hybrid GNN + tabular

#6 opened 28 days ago by

rishabh-ranjan

Add leaderboard entry: LightGBM (tabular features)

#5 opened 28 days ago by

rishabh-ranjan

New activity in stanford-star/relbench-leaderboard 29 days ago

Add leaderboard entry: RelBench Baseline (heuristics)

#4 opened 29 days ago by

rishabh-ranjan

Add leaderboard entry: RelBench Baseline (heuristics)

#3 opened 29 days ago by

rishabh-ranjan

Add leaderboard entry: RT

#2 opened 29 days ago by

rishabh-ranjan

Add leaderboard entry: PluRel

#1 opened 29 days ago by

rishabh-ranjan

New activity in stanford-star/rt-plurel about 2 months ago

RelBench leaderboard checkpoints + README (flat layout) Checkpoints behind the PluRel rows on https://relbench.stanford.edu/leaderboard/: - cntd-pretrain_<db>_<task>.pt: synthetic+real continued pretraining (leave-one-DB-out per RelBench database incl rel-event; per-task best; val-NMAE selection for regression) - finetune_<db>_<task>.pt: per-task fine-tune from the matching cntd-pretrain checkpoint - README section documenting both. Full official test splits.

#5 opened about 2 months ago by

rishabh-ranjan

RelBench leaderboard checkpoints + README Adds the checkpoints behind the PluRel rows on https://relbench.stanford.edu/leaderboard/: - cntd-pretrain_<db>_<task>.pt: synthetic+real continued pretraining (leave-one-DB-out per RelBench database incl rel-event, per-task best, val-NMAE selection for regression) - leaderboard-finetuned/finetune_<db>_<task>.pt: per-task fine-tunes from the matching cntd-pretrain checkpoint - README section documenting both. Full official test splits; protocols in the README.

1

#4 opened about 2 months ago by

rishabh-ranjan

README: document RelBench leaderboard checkpoints

1

#3 opened about 2 months ago by

rishabh-ranjan

RelBench leaderboard checkpoints: synth+real continued-pretraining (7 leave-one-DB runs) + 21 fine-tuned ckpts (NMAE selection); see LEADERBOARD.md

1

#2 opened about 2 months ago by

rishabh-ranjan

New activity in stanford-star/rt-v1 5 months ago

Add model card for Relational Transformer

#1 opened 5 months ago by

nielsr