arxiv:2511.10492
Qiang
zhangtemplar
·
AI & ML interests
computer vision, machine learning, deep learning, multimodality learning, face modeling
Recent Activity
new activity about 12 hours ago
google/gemma-4-31B-it:RuntimeError: FlashAttention forward only supports head dimension at most 256 upvoted a paper about 2 months ago
Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation commentedon a paper about 2 months ago
Principled Synthetic Data Enables the First Scaling Laws for LLMs in RecommendationOrganizations
models 11
zhangtemplar/rl_course_vizdoom_health_gathering_supreme
Reinforcement Learning • Updated
zhangtemplar/LunarLander-v2-newppo
Reinforcement Learning • Updated
zhangtemplar/a2c-PandaReachDense-v3
Reinforcement Learning • Updated • 2
zhangtemplar/Pyramids
Reinforcement Learning • Updated • 9
zhangtemplar/ppo-SnowballTarget
Reinforcement Learning • Updated • 3
zhangtemplar/Reinforce-Pixelcopter-PLE-v0
Reinforcement Learning • Updated
zhangtemplar/Reinforce-CartPole8
Reinforcement Learning • Updated
zhangtemplar/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning • Updated • 5
zhangtemplar/Taxi-v3
Reinforcement Learning • Updated
zhangtemplar/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
datasets 0
None public yet