Rishabh Tiwari

rishabh2k1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

upvoted a paper 24 days ago

Learning, Fast and Slow: Towards LLMs That Adapt Continually

authored a paper about 2 months ago

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

View all activity

Organizations

Papers 12

arxiv:2605.12484

arxiv:2604.07725

arxiv:2603.04304

arxiv:2602.21371

models 4

rishabh2k1/qwen3_reasoning_sft

Updated Dec 19, 2025

rishabh2k1/qwen_reasoning_sft

Updated Dec 19, 2025

rishabh2k1/Qwen2.5-Math-PRM-7B-v1

7B • Updated Apr 21, 2025 • 3

rishabh2k1/Qwen2.5-Math-7B-Instruct-PRM-v1

Updated Apr 21, 2025

datasets 5

rishabh2k1/qwen3_instruct_sft_2196031

Viewer • Updated Dec 19, 2025 • 1 • 75

rishabh2k1/qwen3_instruct_sft_2196030

Viewer • Updated Dec 19, 2025 • 1 • 70

rishabh2k1/openthoughts_dataset_variants

Preview • Updated Dec 19, 2025 • 3

rishabh2k1/qwen3_reasoning_sft_2111879

Viewer • Updated Dec 19, 2025 • 1 • 181

rishabh2k1/qwen3_reasoning_sft_2111685

Viewer • Updated Dec 19, 2025 • 1 • 68