Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
arXiv:2607. 11643v1 Announce Type: cross Abstract: Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints.
arXiv:2607. 11081v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results.
arXiv:2607. 10617v1 Announce Type: new Abstract: The lineage graph of open-weight language models is self-reported: Hugging Face's base_model metadata field is optional and unverified, and over 60% of Hub models document no parentage at all.
arXiv:2607. 11177v1 Announce Type: new Abstract: In this paper, we propose deep learning based NeuroMem-FHP framework for estimating the parameters of the fractional Hawkes process (FHP), a self-exciting point process that captures long-range dependence through a fractional Mittag-Leffler excitation kernel.
arXiv:2607. 09822v1 Announce Type: cross Abstract: Recognition tells an agent what is in an image; personal memory affects what is worth looking up next.
arXiv:2607. 10057v1 Announce Type: cross Abstract: Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost?
arXiv:2607. 11193v1 Announce Type: cross Abstract: To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired.
arXiv:2607. 10784v1 Announce Type: cross Abstract: Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs.
arXiv:2607. 11138v1 Announce Type: new Abstract: The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously.
arXiv:2607. 09576v2 Announce Type: replace-cross Abstract: We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages, totaling 160 conventional expressions, the large majority of which are idiomatic.
arXiv:2601. 22146v2 Announce Type: replace-cross Abstract: Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data.
arXiv:2607. 10021v1 Announce Type: new Abstract: Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden.
arXiv:2604. 03922v2 Announce Type: replace Abstract: Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect.
arXiv:2509. 24148v3 Announce Type: replace-cross Abstract: Test-Driven Development (TDD) is a widely adopted practice that requires developers to create and execute tests alongside implementation.
arXiv:2607. 11734v1 Announce Type: cross Abstract: Differentiable simulators have advanced policy learning and model-based control, yet actuator dynamics remain an important source of sim-to-real error.
arXiv:2607. 11342v1 Announce Type: cross Abstract: Despite their central role in fault detection, test oracles remain challenging to construct effectively.
arXiv:2602. 02905v2 Announce Type: replace Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge.
arXiv:2603. 10725v3 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information.
arXiv:2604. 22770v2 Announce Type: replace-cross Abstract: Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency.