-
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 158 -
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Paper • 2508.03680 • Published • 140 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 321 -
BitNet Distillation
Paper • 2510.13998 • Published • 59
Om Dehlan
immiscible-blade
AI & ML interests
LLMs and DDPMs
Organizations
None yet
Weekly1
-
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 158 -
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Paper • 2508.03680 • Published • 140 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 321 -
BitNet Distillation
Paper • 2510.13998 • Published • 59
models 0
None public yet
datasets 0
None public yet