The Recurrent Looped Transformer (RLT) divides its layers into a parallel causal encoder and a recurrent decoder, allowing the computation path to grow with sequence length while keeping a fixed per-token cost. Experiments on six algorithmic tasks show that RLT outperforms a standard eight‑layer Transformer, achieving perfect generalization on parity up to 256 bits and high accuracy on swap‑based permutation tracking and modular arithmetic beyond training lengths. Ablation studies confirm that the recurrent feedback is essential for these gains, with chunked updates preserving performance on parity but reducing accuracy on permutation tracking.
By Yifan Zhang, Jichen Feng, Shihan Qin
Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior. Examples include robots working in a warehouse and agents mo...
Simon Willison comments on EmbeddingGemma 2, noting its Apache 2.0 license and expressing preference for open‑weight models over proprietary, hosted‑only options. He argues that embedding models are often used to generate and store large numbers of vectors, and a closed model could force costly re‑embedding if the vendor discontinues service. Willison prefers a hosted solution that allows him to switch to the open‑weight version if needed.
The rapid expansion of text-to-music generative models challenges traditional paradigms of music creation and intellectual property. Plagiarism in this context is rarely an absolute mathematical binar...
We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings such as suicide prevention, whe...
Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses regions within a slide as internal controls to estimate and correct acquisition...
While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA inference using techniques like action chunking and vi...
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-inter...
Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to generalize across downstream tasks. While deep learni...
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum E...
We report on an approach to teaching logic to mixed groups of computer science, mathematics, and philosophy students, based on the logico-pluralistic LogiKEy methodology, used for more than a decade i...
Speech-LLMs often exhibit prompt overfitting, where models solely trained on automatic speech recognition (ASR) instruction fail to generalize to new instructions such as speech translation and contin...
Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skill content and evaluate downstrea...
In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism of agentic medical question-answering systems. Wh...
The paper introduces a dataset‑free approach to generate planar graph embeddings that meet strict structural and geometric constraints. By integrating parametric graph grammars with safe reinforcement learning, the authors formulate the task as a constrained Markov decision process and use action projection to keep actions within safe sets. Their method consistently outperforms classical and deep generative baselines on a new benchmark suite for constrained, goal‑directed planar graph generation.
The paper presents a lightweight on‑device personalization method for ECG monitoring called prototype‑only head adaptation. It freezes a small 1‑D CNN feature extractor and adapts only class prototypes in a 32‑dimensional embedding space, eliminating costly back‑propagation and requiring only a single forward pass per support beat. The approach boosts inter‑patient macro‑F1 scores from 0.635–0.646 to 0.731–0.797 across 1/5/10‑shot scenarios and runs efficiently on a PSoC 6 microcontroller with minimal memory and latency.
The paper demonstrates that a pretrained symbolic music transformer already encodes jazz pianist identity sufficiently for accurate classification across two benchmarks. By adding cross‑attention over learned pianist embeddings, the model can generate music conditioned on a specific artist’s style, and evaluation protocols confirm that the generated continuations are correctly attributed to the intended pianist. Additionally, the classifier is repurposed to identify the most characteristic moments in a performance, revealing the musical gestures that distinguish each pianist’s voice.
By Drew Edwards, Akira Maezawa, Simon Dixon
The paper introduces a unified multitask learning framework for Music Emotion Recognition that simultaneously handles categorical and dimensional emotion labels, enabling training across multiple datasets. It leverages musical features such as key and chords, MERT embeddings, and employs knowledge distillation from teacher models to a student model to improve generalization. Experiments on MTG‑Jamendo, DEAM, PMEmo, and EmoMusic show that this approach outperforms state‑of‑the‑art models, including the top MediaEval 2021 entry.
By Jaeyong Kang, Dorien Herremans
The paper introduces a method for approximate vector search in ultrametric (infinity-metric) spaces by using a projection operator that transforms arbitrary dissimilarity functions into ultrametric ones while preserving nearest neighbors. It extends this approach to q-metric spaces, where triangle inequalities involve q-th powers, and learns an efficient approximation of the projected distances. Experiments show that higher q values speed up search at the cost of recall, yet the proposed methods remain competitive with existing search techniques.
By Antonio Pariente, Ignacio Hounie, Santiago Segarra, Alejandro Ribeiro