Pre-trained vision-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template engineering. Instead, current approaches to prompt optimization learn the prompts through gradient descent, where the prompts are treated as adjustable parameters. However, these methods tend to lead to overfitting of the base classes seen during training and produce prompts that are no longer understandable by humans. This paper introduces a simple but interpretable prompt optimizer (IPO), that utilizes large language models (LLMs) to generate textual prompts dynamically.

Cryo-Electron Microscopy (Cryo-EM) is an important imaging method which allows high-resolution reconstruction of the 3D structures of biomolecules. It produces highly noisy 2D images by projecting a molecule's 3D density from random viewing directions. Because the projection directions are unknown, estimating the images' poses is necessary to perform the reconstruction. We focus on this task and study it under the group synchronization framework: if the relative poses of pairs of images can be approximated from the data, an estimation of the images' poses is given by the assignment which is most consistent with the relative ones. In particular, by studying the symmetries of cryo-EM, we show that relative poses in the group O(2) provide sufficient constraints to identify the images' poses, up to the molecule's chirality. With this in mind, we improve the existing multi-frequency vector diffusion maps (MFVDM) method: by using O(2) relative poses, our method not only predicts the similarity between the images' viewing directions but also recovers their poses. Hence, we can leverage all input images in a 3D reconstruction algorithm by initializing the poses with our estimation rather than just clustering and averaging the input images. We validate the recovery capabilities and robustness of our method on randomly generated synchronization graphs and a synthetic cryo-EM dataset.

Some definitions might overlap with the notations in the main paper. We denote the input random variable with X and the category random variable with C. The category code random variable, which we define as the embedding sequence of input X The length of each sequence z, which we show with l(z), equals the number of digits present in that sequence. It measures the randomness of values of X when we only have knowledge about its distribution P. It also measures the minimum number of bits required on average to transmit or encode the values drawn from this probability distribution [1, 2]. The conditional entropy of a random variable X given random variable Z is shown by H(X|Z), which states the amount of randomness we expect to see from X after observing Z. Note that contrary to H(X|Z), mutual information is symmetric. Similar to Shannon's information theory, Kolmogorov Complexity or Algorithmic Information Theory[3-5] measures the shortest length to describe an object. Their difference is that Shannon's information considers that the objects can be described by the characteristic of the source that produces them, but Kolmogorov Complexity considers that the description of each object in isolation can be used to describe it with minimum length.

In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category?

Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process. To overcome this limitation, we introduce ProtoDiff, a novel framework that leverages a task-guided diffusion model during the meta-training phase to gradually generate prototypes, thereby providing efficient class representations. Specifically, a set of prototypes is optimized to achieve per-task prototype overfitting, enabling accurately obtaining the overfitted prototypes for individual tasks. Furthermore, we introduce a task-guided diffusion process within the prototype space, enabling the meta-learning of a generative process that transitions from a vanilla prototype to an overfitted prototype. ProtoDiff gradually generates taskspecific prototypes from random noise during the meta-test stage, conditioned on the limited samples available for the new task. Furthermore, to expedite training and enhance ProtoDiff's performance, we propose the utilization of residual prototype learning, which leverages the sparsity of the residual prototype. We conduct thorough ablation studies to demonstrate its ability to accurately capture the underlying prototype distribution and enhance generalization.

Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relates to generalization error utilizing PAC Bayesian analysis for equivariant networks, where the transformation laws of feature spaces are determined by group representations. By using perturbation analysis of equivariant networks in Fourier domain for each layer, we derive norm-based PAC-Bayesian generalization bounds. The bound characterizes the impact of group size, and multiplicity and degree of irreducible representations on the generalization error and thereby provide a guideline for selecting them. In general, the bound indicates that using larger group size in the model improves the generalization error substantiated by extensive numerical experiments.

Cryo-Electron Microscopy (Cryo-EM) is an important imaging method which allows high-resolution reconstruction of the 3D structures of biomolecules. It produces highly noisy 2D images by projecting a molecule's 3D density from random viewing directions. Because the projection directions are unknown, estimating the images' poses is necessary to perform the reconstruction. We focus on this task and study it under the group synchronization framework: if the relative poses of pairs of images can be approximated from the data, an estimation of the images' poses is given by the assignment which is most consistent with the relative ones. In particular, by studying the symmetries of cryo-EM, we show that relative poses in the group O(2) provide sufficient constraints to identify the images' poses, up to the molecule's chirality. With this in mind, we improve the existing multi-frequency vector diffusion maps (MFVDM) method: by using O(2) relative poses, our method not only predicts the similarity between the images' viewing directions but also recovers their poses. Hence, we can leverage all input images in a 3D reconstruction algorithm by initializing the poses with our estimation rather than just clustering and averaging the input images. We validate the recovery capabilities and robustness of our method on randomly generated synchronization graphs and a synthetic cryo-EM dataset.

This paper focuses on Bayesian Optimization (BO) for objectives on combinatorial search spaces, including ordinal and categorical variables. Despite the abundance of potential applications of Combinatorial BO, including chipset configuration search and neural architecture search, only a handful of methods have been proposed. We introduce COMBO, a new Gaussian Process (GP) BO.

As Robots become ever more important in our daily lives there's growing need for understanding how they're perceived by people. This study aims to investigate how the user perception of robots is influenced by displays of personality. Using LLMs and speech to text technology, we designed a within-subject study to compare two conditions: a personality-driven robot and a purely task-oriented, personality-neutral robot. Twelve participants, recruited from Socially Intelligent Robotics course at Vrije Universiteit Amsterdam, interacted with a robot Nao tasked with asking them a set of medical questions under both conditions. After completing both interactions, the participants completed a user experience questionnaire measuring their emotional states and robot perception using standardized questionnaires from the SRI and Psychology literature.

California lawmakers passed roughly 1,200 bills last year, including some that resulted in unforeseeable wins by Republicans, promising protections for consumers and small strides for those in the entertainment industry. In the end, Gov. Gavin Newsom signed about 84% of the bills he received. Many of those laws take effect today, Jan. 1, as California rings in a new year. Cannabis cafes are legal: You can now hang out at dispensaries like you would a restaurant or cafe, thanks to AB 1775. The new law brings an Amsterdam-style approach to marijuana use, by allowing cannabis retailers to make and sell food and nonalcoholic beverages at what will be known as cannabis cafes or lounges.