arxiv:2510.02263
Anikait Singh
Asap7772
AI & ML interests
Deep Learning, Reinforcement Learning, Robotics
Recent Activity
published
a dataset
5 days ago
Asap7772/arc-barc-processed-direct-80k-solutions-all
published
a dataset
6 days ago
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step80
published
a dataset
6 days ago
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step120
Organizations
models
176
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
2
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.01-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
2
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-7-beta-0.1-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
2
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.05-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
4
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.01-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
5
Asap7772/Qwen3-4B-second-stage-DPO-lr-1e-6-beta-0.1-loss-sigmoid-rpo-1.0-ckpt-135
196k
•
Updated
•
4
Asap7772/qwen3-4b-arc-second-stage-awr-sftinit-lr1e-6-0908
Text Generation
•
4B
•
Updated
•
8
Asap7772/qwen3-4b-arc-second-stage-star-sftinit-lr1e-6-0908
Text Generation
•
4B
•
Updated
•
7
Asap7772/qwen3-4b-arc-second-stage-star-sftinit-lr1e-5-0908
Text Generation
•
4B
•
Updated
•
4
Asap7772/qwen3-4b-arc-second-stage-awr-sftinit-lr1e-5-0908
Text Generation
•
4B
•
Updated
•
9
datasets
2,775
Asap7772/arc-barc-processed-direct-80k-solutions-all
Updated
•
4
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step80
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step120
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step160
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step100
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step140
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step40
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step60
Updated
•
5
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-valclassifiersft1e-5-step20
Updated
•
6
Asap7772/arc-agi-impabs-dpolr1e-7-beta0.01-classifiersft5e-6
Preview
•
Updated
•
30