At the first epoch, learning rate is warmed up gradually fromlrinit = 1 10 5 to lrpeak. Figure A and B demonstrate the performances of the baseline and rejection sampling by varying hyperparameterssuchastop-k,softmaxtemperature,andacceptanceratio.Forthebaselinesampling in ImageNet, the hyperparameter setting withk = 2048 and temperaturet = 0.95 achieves the best FID performance in the small and medium models and the second-best performance in the large model. Figure C: Examples of reconstructed images using HQ-VAE with the learnable down-and upsampling layers. B.3 PredictionHeadTransformer(PHT) Wepropose locally hierarchical decoding inPHT contrary tothestandard sequential approach by assuming the conditional independence among bottom codes given a top code. We use pixel-shuffle and -unshuffle for resizing operations as illustrated in (a) while recursively quantizing hierarchical feature maps to acquire three-levelcodes--top,middle,andbottom.

The team even extracted DNA from a tiny 100-year-old butterfly leg. Breakthroughs, discoveries, and DIY tips sent every weekday. When you think of butterflies, chances are you imagine unmistakable insects with bright, bold wings. But it turns out that individual butterfly species are sometimes shockingly difficult to tell apart. "Thanks to the genetic revolution and the collaboration of researchers and museums in various countries led by London's Natural History Museum, century-old butterflies are now speaking to us," Christophe Faynel, an entomologist at the Société entomologique Antilles Guyane, said in a statement .

Feedback is entertained by the commotion at the International Association for Cryptologic Research's recent elections, where results could not be decrypted after an honest but unfortunate human mistake The phrase "you couldn't make it up", Feedback feels, is often misunderstood. It doesn't mean there are limits to the imagination, but rather that there are some developments you can't include in a fictional story because people would say "oh come on, that would never happen". The trouble is, those people are wrong, because real life is frequently ridiculous. In the world of codes and ciphers, one of the more important organisations is the International Association for Cryptologic Research, described as " a non-profit organization devoted to supporting the promotion of the science of cryptology ". The IACR recently held elections to choose new officers and directors and to tweak its bylaws.

Foundation models have demonstrated a remarkable ability to learn rich, transferable representations across diverse modalities such as images, text, and audio. In modern machine learning pipelines, these representations often replace raw data as the primary input for downstream tasks. In this paper, we address the challenge of adapting a pre-trained foundation model to inject domain-specific knowledge, without retraining from scratch or incurring significant computational costs. To this end, we introduce BotaCLIP, a lightweight multimodal contrastive framework that adapts a pre-trained Earth Observation foundation model (DOFA) by aligning high-resolution aerial imagery with botanical relevés. Unlike generic embeddings, BotaCLIP internalizes ecological structure through contrastive learning with a regularization strategy that mitigates catastrophic forgetting. Once trained, the resulting embeddings serve as transferable representations for downstream predictors. Motivated by real-world applications in biodiversity modeling, we evaluated BotaCLIP representations in three ecological tasks: plant presence prediction, butterfly occurrence modeling, and soil trophic group abundance estimation. The results showed consistent improvements over those derived from DOFA and supervised baselines. More broadly, this work illustrates how domain-aware adaptation of foundation models can inject expert knowledge into data-scarce settings, enabling frugal representation learning.

The proof, known to be so hard that a mathematician once offered 10 martinis to whoever could figure it out, uses number theory to explain quantum fractals. In 1974, five years before he wrote his Pulitzer Prize-winning book, Douglas Hofstadter was a graduate student in physics at the University of Oregon. When his doctoral adviser went on sabbatical to Regensburg, Germany, Hofstadter tagged along, hoping to practice his German. The pair joined a group of brilliant theoretical physicists who were agonizing over a particular problem in quantum theory. They wanted to determine the energy levels of an electron in a crystal grid placed near a magnet. Hofstadter was the odd one out, unable to follow the others' line of thought. "Part of my luck was that I couldn't keep up with them," he said.

The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion objectives. We present SONAR-LLM, a decoder-only transformer that "thinks" in the same continuous SONAR embedding space, yet is supervised through token-level cross-entropy propagated via the frozen SONAR decoder. This hybrid objective retains the semantic abstraction of LCM while eliminating its diffusion sampler and restoring a likelihood-based training signal. Across model sizes from 39M to 1.3B parameters, SONAR-LLM attains competitive generation quality. We report scaling trends, ablations, benchmark results, and release the complete training code and all pretrained checkpoints to foster reproducibility and future research.

Multi-grade deep learning (MGDL) has been shown to significantly outperform the standard single-grade deep learning (SGDL) across various applications. This work aims to investigate the computational advantages of MGDL focusing on its performance in image regression, denoising, and deblurring tasks, and comparing it to SGDL. We establish convergence results for the gradient descent (GD) method applied to these models and provide mathematical insights into MGDL's improved performance. In particular, we demonstrate that MGDL is more robust to the choice of learning rate under GD than SGDL. Furthermore, we analyze the eigenvalue distributions of the Jacobian matrices associated with the iterative schemes arising from the GD iterations, offering an explanation for MGDL's enhanced training stability.

Butterflies, or 4-cycles in bipartite graphs, are crucial for identifying cohesive structures and dense subgraphs. While agent-based data mining is gaining prominence, its application to bipartite networks remains relatively unexplored. We propose distributed, agent-based algorithms for \emph{Butterfly Counting} in a bipartite graph $G((A,B),E)$. Agents first determine their respective partitions and collaboratively construct a spanning tree, electing a leader within $O(n \log λ)$ rounds using only $O(\log λ)$ bits per agent. A novel meeting mechanism between adjacent agents improves efficiency and eliminates the need for prior knowledge of the graph, requiring only the highest agent ID $λ$ among the $n$ agents. Notably, our techniques naturally extend to general graphs, where leader election and spanning tree construction maintain the same round and memory complexities. Building on these foundations, agents count butterflies per node in $O(Δ)$ rounds and compute the total butterfly count of $G$ in $O(Δ+\min\{|A|,|B|\})$ rounds.