-
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Paper • 2602.05885 • Published • 28 -
hkust-nlp/drkernel-14b
Text Generation • 15B • Updated • 102 • • 6 -
hkust-nlp/drkernel-8b
Text Generation • 8B • Updated • 191 • • 4 -
hkust-nlp/drkernel-14b-coldstart
Text Generation • 0.5B • Updated • 411 •
HKUST NLP Group
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
-
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Paper • 2602.05885 • Published • 28 -
hkust-nlp/drkernel-14b
Text Generation • 15B • Updated • 102 • • 6 -
hkust-nlp/drkernel-8b
Text Generation • 8B • Updated • 191 • • 4 -
hkust-nlp/drkernel-14b-coldstart
Text Generation • 0.5B • Updated • 411 •
models 66
hkust-nlp/drkernel-8b-coldstart
Text Generation • 0.3B • Updated • 277 •
hkust-nlp/drkernel-14b-coldstart
Text Generation • 0.5B • Updated • 411 •
hkust-nlp/drkernel-14b
Text Generation • 15B • Updated • 102 • • 6
hkust-nlp/drkernel-8b
Text Generation • 8B • Updated • 191 • • 4
hkust-nlp/WebExplorer-8B
Image-Text-to-Text • 8B • Updated • 23.7k • • 14
hkust-nlp/Qwen-2.5-7B-Verifier-general-verifier
Reinforcement Learning • 8B • Updated • 3
hkust-nlp/Qwen-2.5-7B-Verifier-R1-Qwen-1.5B
Reinforcement Learning • 8B • Updated • 1
hkust-nlp/Qwen-2.5-7B-Verifier-HF
Reinforcement Learning • 8B • Updated • 9
hkust-nlp/R1-Distill-Verifier-1.5B
2B • Updated • 1 • 1
hkust-nlp/Qwen-2.5-7B-Verifier-R1-Verifier-1.5B
Reinforcement Learning • 8B • Updated • 2 • 1
datasets 32
hkust-nlp/drkernel-validation-data
Viewer • Updated • 100 • 77 • 1
hkust-nlp/drkernel-rl-data
Viewer • Updated • 72k • 132
hkust-nlp/drkernel-coldstart-8k
Viewer • Updated • 8.92k • 82 • 2
hkust-nlp/Toolathlon-Trajectories
Preview • Updated • 4.29k • 21
hkust-nlp/WebExplorer-QA
Viewer • Updated • 100 • 79 • 7
hkust-nlp/CodeIO-PyEdu-Reasoning-Raw
Updated • 104 • 2
hkust-nlp/CodeIO-PyEdu-Reasoning
Preview • Updated • 184 • 57
hkust-nlp/rl-verifier-pitfalls_hacking_data
Viewer • Updated • 6.12k • 38 • 1
hkust-nlp/deepscaler_simplelr
Viewer • Updated • 40.3k • 215
hkust-nlp/Laser-Deepscaler-Dataset
Viewer • Updated • 40.8k • 292