We have 11 of 33 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.
Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic programs from a language model, running approximate inference on each, and averaging them with weights proportional to an exponentiated evidence bound. We show that this weighting depends on how a model is written. The...
Stream-level flow matching replaces the linear interpolant of conditional flow matching (CFM) by a Gaussian-process (GP) stream connecting each source--target pair, and reports lower sample error than \icfm{} on 2-Gaussian, MNIST and CIFAR-10 benchmarks. We ask what such a stream model actually contributes. Three resul...
Consist-Retinex is proposed, which first uses a Retinex Transformer Decomposition Network to obtain paired reflectance and illumination maps, then trains two conditional consistency models with a Retinex-aware dual objective and adaptive noise-emphasized fixed-point sampling.
The results suggest that bridge-anchored generative paths provide a general mechanism for strengthening conditional stochastic function modeling.
Agentic video-generation systems close a loop between a generator and a verifier: an LLM plans shots, calls a text-to-video model, and a multimodal judge decides whether the result satisfies the request. To diagnose where a long workflow fails, recent harnesses deliberately show the judge more than the video-the agent'...
It is argued that detection of missing mass is a strictly easier problem than sampling it: detection needs one point per missed basin plus a local curvature estimate, whereas correction needs the sampler retrained, whereas correction needs the sampler retrained.
A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction $s$ is known by design the total edge count follows from $\hat e=e_s/s^2$ and no model is needed. We treat the case where $s$ is unknown and the population size is known. Our main result is a...
It is proved that counterfactual invariance is necessary and sufficient to identify the causal predictor, and the mechanism from feature-vector SCMs to procedural pixel video, real images with spectrogram audio, moving real digits, and a conditional generator is verified.
Adaptive Momentum Langevin Dynamics (AMLD), a practical stochastic correction kernel that introduces a momentum variable into the annealed posterior sampling framework and equips it with an annealing-aware momentum retention schedule, is proposed.
A PAC-Bayesian account in which quantum policy design is reframe around an entanglement--generalization trade-off rather than expressivity alone is given, where entangled circuits consistently generalize worse than non-entangled circuits of equal parameter count.
The contribution is accordingly not a better estimator but a characterization of \emph{when prior-based correction is justified}, plus designs that supply the missing information when it is not, plus designs that supply the missing information when it is not.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
