Vignesh Kothapalli
kvignesh1420
AI & ML interests
Deep learning
Recent Activity
liked a model about 24 hours ago
nvidia/Kumo-Relational upvoted a paper about 24 hours ago
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement upvoted an article 2 days ago
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular PredictionOrganizations
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 4 months ago
by 
rishabh-ranjan
Add pipeline tag and link to original Relational Transformer paper
#1 opened 7 months ago
by 
nielsr