Lutalica's picture

Lutalica

Lutalica

·

https://github.com/RewindL

RewindL

AI & ML interests

Multimodal LLMs, LLM Reasoning, Reinforcement Learning, Efficient Inference

Recent Activity

commented on a paper 4 days ago

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

commented on a paper 10 days ago

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

upvoted a paper 10 days ago

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

View all activity

Organizations

upvoted a paper 10 days ago

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

Paper • 2603.04800 • Published 11 days ago • 20

upvoted a paper about 1 month ago

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Paper • 2602.02160 • Published Feb 2 • 13

upvoted a paper 8 months ago

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14, 2025 • 90

upvoted a paper 11 months ago

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published Apr 18, 2025 • 139