Kiran Kamble

Kiran Kamble on Hugging Face Daily Papers: 5 papers, 4 in the top 3 of their day, 611 upvotes.

1. Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning 186 upvotes, #1 of 2025-06-04
2. Expect the Unexpected: FailSafe Long Context QA for Finance 122 upvotes, #1 of 2025-02-12
3. Writing in the Margins: Better Inference Pattern for Long Context Retrieval 129 upvotes, #1 of 2024-08-28
4. OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web 25 upvotes, #5 of 2024-02-28
5. Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning 27 upvotes, #1 of 2023-07-10

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.