pathwise gradient
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Oct 2026
3 papers in the last two months, against 0 in the two before.
Start here
Two papers to read first, in the order they came out- 1Backpropagating verifier rewards improves reasoning in continuous flow language models
A critic predicting per-token values lets continuous flow language models improve reasoning through backpropagated verifier rewards.
Oct 2026 - 2Quadrotors learn to fly through moving gaps using differentiable simulation
A quadrotor can learn to fly through a moving narrow gap using only onboard cameras and a differentiable simulator, without pre-training.
Oct 2026
How fast it is moving
Often studied with
diffusion language modelA language model that generates text by iteratively denoising a latent or discrete representation.1 togetherdistribution matching distillationA training method that aligns student and teacher output distributions to compress many-step generative models into efficient few-step versions.1 togetherreinforcement learningA machine learning method where an agent learns to make sequences of decisions by receiving rewards or penalties for its actions.1 togetherThe papers
Most central to this idea first, not most recent.
- Academiccs.RO
Quadrotors learn to fly through moving gaps using differentiable simulation
A quadrotor can learn to fly through a moving narrow gap using only onboard cameras and a differentiable simulator, without pre-training.
University of Zurich · Oct 2026
- Academiccs.LG
Backpropagating verifier rewards improves reasoning in continuous flow language models
A critic predicting per-token values lets continuous flow language models improve reasoning through backpropagated verifier rewards.
Tufts University · Oct 2026
- AI Startupcs.LG
Distributional distillation cuts diffusion language model sampling steps by half or more
Two distribution matching distillation methods reduce network evaluations for continuous diffusion language models by up to 49% and 20% at similar generation quality.
Inria, PSL Research University · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.