Binary hashing is a well-known approach for fast approximate nearest-neighbor search in information retrieval. Much work has focused on affinity-based objective functions involving the hash functions or binary codes. These objective functions encode neighborhood information between data points and are often inspired by manifold learning algorithms. They ensure that the hash functions differ from each other through constraints or penalty terms that encourage codes to be orthogonal or dissimilar across bits, but this couples the binary variables and complicates the already difficult optimization. We propose a much simpler approach: we train each hash function (or bit) independently from each other, but introduce diversity among them using techniques from classifier ensembles. Surprisingly, we find that not only is this faster and trivially parallelizable, but it also improves over the more complex, coupled objective function, and achieves state-of-the-art precision and recall in experiments with image retrieval.

Effective implementations of sampling-based probabilistic inference often require manually constructed, model-specific proposals. Inspired by recent progresses in meta-learning for training learning agents that can generalize to unseen environments, we propose a meta-learning approach to building effective and generalizable MCMC proposals. We parametrize the proposal as a neural network to provide fast approximations to block Gibbs conditionals. The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required. We explore several applications including open-universe Gaussian mixture models, in which our learned proposals outperform a hand-tuned sampler, and a real-world named entity recognition task, in which our sampler yields higher final F1 scores than classical single-site Gibbs sampling.

Presearch's "Doppelgänger" is trying to help people discover adult creators rather than use nonconsensual deepfakes. For three days in February, porn star Alix Lynx flew to Miami for her first exclusive creator gathering where she was in full grind mode: shooting Reels and talking strategy with other creators. "It was kind of like SoHo House for OnlyFans girls," she says of the experience, which is called The Circle and drew more than a dozen sex workers, including Remy LaCroix and Forrest Smith. Lynx, who is a former webcam model turned OnlyFans starlet, has a combined 2 million followers across Instagram, TikTok, and X . She joined OnlyFans in 2017 with "the luxury of having my own following," she says, but those numbers haven't always translated to subscriptions. It's why she was in Miami.

Our key insight is that the user's examination and click behavior

However, many previous works studied textual and relational retrieval tasks as separate topics.

An efficient two-staged approach is designed for exploring CSPG, with fast approaching and cross-partition expansion.