-
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 34 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 43 -
BitNet Distillation
Paper • 2510.13998 • Published • 62 -
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
Paper • 2510.19430 • Published • 55
🔄 In a Training Loop
Keylhan Paumard--André
keypa
QEntanglement's profile picture
webbrain-4b7f2a9c's profile picture
ShatteredManoj's profile picture·
AI & ML interests
Efficient deep learning, LLM fine-tuning, inference optimization, model compression, distributed training, GPU systems, open-source AI infrastructure
Recent Activity
liked a model 3 days ago
nvidia/NVIDIA-Nemotron-Labs-Teacher-Competition-Coding upvoted an article 3 days ago
MOPD: how frontier labs merge RL experts into one model and how to do it using TRL liked a model 6 days ago
migtissera/Tess-4.5-27B-GGUFOrganizations
-
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 34 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 43 -
BitNet Distillation
Paper • 2510.13998 • Published • 62 -
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
Paper • 2510.19430 • Published • 55
models 17
keypa/vision-adapter-probe-checkpoints
Updated • 1
keypa/minecraft-world-jepa-ckpts
Updated
keypa/MoonViT-V2-Standalone
Image Feature Extraction • Updated
keypa/oracle-gemma4-12b-lora
Text Generation • Updated • 8
keypa/oracle-gemma4-12b-GGUF
Text Generation • 12B • Updated • 21
keypa/oracle-gemma4-12b
Text Generation • 12B • Updated • 7
keypa/soren-9b-stage-0-0_identity_v1
9B • Updated • 6
keypa/soren-9b-stage-1-1_reasoning_warmup
9B • Updated • 4
keypa/qwen36-27b-adapters-suite
Updated
keypa/Qwen3.5-9B-Claude-Opus-4.7
Image-Text-to-Text • 10B • Updated • 185 • 4
datasets 10
keypa/vision-adapter-manifests
Updated • 113
keypa/vision-adapter-embeddings
Viewer • Updated • 139k • 777
keypa/vision-adapter-images
Viewer • Updated • 139k • 80
keypa/reap-calibration-v1-filtered
Viewer • Updated • 21k • 19
keypa/reap-calibration-v1-full
Viewer • Updated • 23.1k • 32
keypa/reaper-calibration
Viewer • Updated • 790k • 53 • 2
keypa/gpt-oss-calibration-data
Viewer • Updated • 15.6k • 39
keypa/mls-french-whisper-final
Viewer • Updated • 258k • 48 • 1
keypa/common_voice_23
Viewer • Updated • 27.1k • 244
keypa/common_voice_22
Viewer • Updated • 625k • 214