Applying image processing algorithms independently toeachvideo frame often leads to temporal inconsistencyin the resulting video.

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best network within a functional neighborhood of the original network that includes a diverse set of candidate network structures. By using Taylor approximation, the optimal network structure in the neighborhood can be found with a greedy selection procedure. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures that avoid catastrophic forgetting in continual learning. Empirically, firefly descent achieves promising results on both neural architecture search and continual learning. In particular, on a challenging continual image classification task, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.

Large language models promise a broad set of functions, but when not given a specific objective, they default to milquetoast results such as drafting emails littered with cliches. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular objective, enables LLMs to produce tools, interfaces, and responses that are more responsive and desired. We contribute an architecture for automatically inducing just-in-time objectives by passively observing user behavior, then steering downstream AI systems through generation and evaluation against this objective. Inducing just-in-time objectives (e.g., "Clarify the abstract's research contribution") enables automatic generation of tools, e.g., those that critique a draft based on relevant HCI methodologies, anticipate related researchers' reactions, or surface ambiguous terminology. In a series of experiments (N=14, N=205) on participants' own tasks, JIT objectives enable LLM outputs that achieve 66-86% win rates over typical LLMs, and in-person use sessions (N=17) confirm that JIT objectives produce specialized tools unique to each participant.

Clarity: 1. clarify if \varepsilon and \delta are learnable parameters the same as model parameters or they are just learnable during the architecture descent. In Line 116, when optimizing \varepsilon and \delta, are neural network weights also updated? 2. "measured by the gradient magnitude", magnitude of full-batch or a few mini-batches? A small number? 5. Make use the legend labels "Random (split)" and "RandSearFh" in Figure 1(a) are exactly the same with those appeared in the text ("RandSearch (split)" and "RandSearch (split new)"). In Figure 1(a), a should-have simple baseline: add one neuron and randomly initialize new weights. In Figure 3(b), If the splitting and growing happen at the same time, the number of neurons (markers along x-axis) should have a gap larger than 1.

Looking over the reviews, rebuttal and discussion afterwards, I think this paper is of interest to the community. However there are several ambiguities and issues in the presentation of the work that had been noted by the reviewers (e.g. R3) which does hamper how well the work can be understood. So I *urge* the authors to make sure all the points raised by the reviewers are considered (as mentioned in the rebuttal) and incorporated in the main text and make sure the text is clear and easy to parse. I do believe the rebuttal addresses most of the issues brought up, in particular I think the replies given to the issues raised by R1 are valid, including additional experiments that were required by the reviewer.

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best network within a functional neighborhood of the original network that includes a diverse set of candidate network structures. By using Taylor approximation, the optimal network structure in the neighborhood can be found with a greedy selection procedure. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures that avoid catastrophic forgetting in continual learning. Empirically, firefly descent achieves promising results on both neural architecture search and continual learning.

Shneiderman's mantra, "Overview first, zoom and filter, then details-on-demand", highlights the importance of giving readers a high-level overview before offering detail. We apply this idea to generate an overview of sets of objects, hypothesising that an overview will be beneficial to readers who want to understand the set. Previously we investigated the domain of consumer products, focusing on descriptions of products (such as TVs) which are intended to help readers decide which specific products to buy. Now we aim to generalise the techniques we have developed, by looking at a very different type of domain, namely bibliographical references in academic papers.

"Topographic" mappings occur frequently in the brain. A pop(cid:173) ular approach to understanding the structure of such mappings is to map points representing input features in a space of a few dimensions to points in a 2 dimensional space using some self(cid:173) organizing algorithm. We argue that a more general approach may be useful, where similarities between features are not con(cid:173) strained to be geometric distances, and the objective function for topographic matching is chosen explicitly rather than being spec(cid:173) ified implicitly by the self-organizing algorithm. We investigate analytically an example of this more general approach applied to the structure of interdigitated mappings, such as the pattern of ocular dominance columns in primary visual cortex.

We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-image generation scenarios. (i) When a bank of images is available, we retrieve and condition on a related image (Retrieve&Fuse), resulting in significant improvements on the MS-COCO benchmark, gaining a state-of-the-art FID score of 6.65 in zero-shot settings. (ii) When cropped-object images are at hand, we utilize them and perform subject-driven generation (Crop&Fuse), outperforming the textual inversion method while being more than x100 faster. (iii) Having oracle access to the image scene (Scene&Fuse), allows us to achieve an FID score of 5.03 on MS-COCO in zero-shot settings. Our experiments indicate that X&Fuse is an effective, easy-to-adapt, simple, and general approach for scenarios in which the model may benefit from additional visual information.

The European Council has adopted its common position ('general approach') on the Artificial Intelligence Act. Its aim is to ensure that artificial intelligence (AI) systems placed on the EU market and used in the Union are safe and respect existing law on fundamental rights and Union values. The proposal follows a risk-based approach and lays down a uniform, horizontal legal framework for AI that aims to ensure legal certainty. It promotes investment and innovation in AI, enhances governance and effective enforcement of existing law on fundamental rights and safety, and facilitates the development of a single market for AI applications. It goes hand in hand with other initiatives, including the Coordinated Plan on Artificial Intelligence which aims to accelerate investment in AI in Europe. The adoption of the general approach will allow the Council to enter negotiations with the European Parliament ('trilogues') once the latter adopts its own position with a view to reaching an agreement on the proposed regulation.