Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Positional encoding is a fundamental component of Transformer-based generative recommendation models, where user histories are modeled as autoregressive item sequences. Most positional encoding methods are inherited from natural language processing and mainly represent discrete item order.
Existing speech retrieval systems rely on fixed similarity matching and cannot adapt to diverse user intents. We introduce INSPIRE, the first benchmark for instruction-aware speech retrieval, in which natural-language instructions dynamically specify relevance criteria, including semantic content, speaker identity, speaking style, environmental sounds, and their combinations.
LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known.
arXiv:2508. 16131v3 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context.
arXiv:2608. 14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.
arXiv:2512. 14732v3 Announce Type: replace-cross Abstract: Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines.
arXiv:2402. 01826v2 Announce Type: replace-cross Abstract: Current blood pressure (BP) technologies and standards were established decades ago, and these standards are still used worldwide today, often without adjusting BP readings for individual demographic factors such as sex and age.
arXiv:2402. 01591v4 Announce Type: replace-cross Abstract: Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound.
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.
arXiv:2603. 18871v2 Announce Type: replace Abstract: Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes the network topology.
arXiv:2503. 01236v3 Announce Type: replace-cross Abstract: This paper addresses fixed-graph terrain-aware path refinement, in which a global planner is restricted to a predefined route space and may remain optimal within that space while missing lower-cost terrain corridors available in the native-resolution map.
arXiv:1912. 08786v3 Announce Type: replace-cross Abstract: Three generations of software have transformed the role of artificial intelligence in society.
arXiv:2608. 01014v2 Announce Type: replace-cross Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified answers, human annotations, or external reward models.
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
arXiv:2608. 14370v1 Announce Type: cross Abstract: The modelling and analysis of secure business processes require the incorporation of security annotations into process models.
arXiv:2607. 28008v2 Announce Type: replace-cross Abstract: Representation engineering reads and steers capability directions in large language models, yet methods are typically evaluated on paper-specific synthetic data.
arXiv:2608. 14505v1 Announce Type: cross Abstract: Recipe data arises in domains such as materials synthesis, pharmaceutical formulation, and industrial manufacturing, where procedures are represented as ordered sequences of steps containing heterogeneous structured fields.
arXiv:2608. 14349v1 Announce Type: new Abstract: We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters.
arXiv:2608. 14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning.
arXiv:2608. 14286v1 Announce Type: cross Abstract: Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation.