random's picture

random

fakerbaby

·

fakerbaby

AI & ML interests

NLP, RL, VLM

Recent Activity

upvoted a paper 3 days ago

Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch

upvoted a paper about 1 month ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

upvoted a paper about 1 month ago

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

View all activity

Organizations

Collections 1

Papers 9

arxiv:2403.07708

arxiv:2402.01391

arxiv:2401.11458

arxiv:2401.06080

spaces 2

Skywork R1V3

PaI

models 0

None public yet

datasets 0

None public yet