We have 7 of 26 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evaluations at inference. This has motivated extensive research on one-step generative modeling primarily built on diffusion and flow, though existing approaches often rely...
Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and reinforcement learning (RL) to this end. Conventional wisdom dictates that RL enables strong generalization on new tasks without losing existing capabilities, while SFT is...
This work studies blackboard intelligence: an inference-time perspective in which a model works on a fixed, revisable canvas and searches over candidate solution states rather than committing to a causal, left-to-right trajectory, and concludes that mean confidence, a simple model-internal quantity available from the s...
The Very Big Video Reasoning (VBVR) Dataset is introduced, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets.
An instantiation of flow matching that relies on a time-independent velocity field to exactly map between two distributions, so long as the target is singular, is proposed and supported on a lower-dimensional data manifold.
Equilibrium Forcing is introduced, a simplified framework for video denoising generative models without noise level conditioning that pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling.
This work introduces Explorative Modeling, a new paradigm that instead factors the training loop, exploring K candidate matches between model generations and data, and training on the best, so predictions commit to modes rather than blurring them, and establishes XMs as both a new pretraining axis for existing generati...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
