Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2604. 13899v3 Announce Type: replace-cross Abstract: Instruction-tuned LLMs can annotate thousands of instances at low cost.
arXiv:2606. 17678v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference.
arXiv:2606. 18193v1 Announce Type: cross Abstract: We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.
arXiv:2606. 18181v1 Announce Type: cross Abstract: Illegal, unreported, and unregulated fishing (IUU) traditionally refers to fishing activities that violate applicable laws or occur in areas that lack applicable laws.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
Large language models (LLMs) are increasingly deployed in hiring workflows, yet most research on gender bias in LLM hiring decisions has focused on English-language, Western-format resumes. This study examines whether pro-female gender bias extends to a Japanese corporate context and evaluates two practical mitigation strategies.
Recent advancements in Large Language Models (LLMs) have empowered home assistants with natural language interaction capabilities. However, current assistants overlook the progressive omission that occurs in human dialogue as shared context accumulates, leading to more elliptical expressions for efficient communication.
Natural language understanding often depends on meanings that are implied rather than explicitly stated, requiring pragmatic reasoning. Despite strong performance on math and logical reasoning, large language models (LLMs) still struggle with making pragmatic inferences, often choosing literal interpretations.
Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability.
Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from visual cues. To overcome this, we propose a novel retrieval-augmented image captioning framework that generates captions with deeper insights, such as object attributes, event context, and underlying significance, by leveraging external knowledge.
Domain adaptation remains a central challenge in 3D vision, especially for multimodal foundation models that align 3D point clouds with visual and textual data. While these models demonstrate strong general capabilities, adapting them to downstream domains with limited data often leads to overfitting and catastrophic forgetting.
Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity.
Caregivers often turn to online communities for informational and emotional support. In these spaces, peer supporters frequently draw on personal narratives to respond to emotionally complex caregiving situations.
Tired of your monthly API bill? Follow this tested guide to set up a high-performance local LLM on your Mac Mini without the headaches.
LLM rate limits don't just interrupt agent pipelines—they can silently corrupt structured outputs when fallback models receive incompatible payloads. I built a recovery layer that classifies failures, adapts payloads across model tiers, preserves execution state, and maintains schema integrity during provider swaps.
Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and compositional features across layers. In language modeling, \textbf{transformers} have emerged as the dominant architecture, with early layers capturing local syntactic patterns and later layers encoding more complex clause-level dependencies.
Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging. We present an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine (AIE), mapping dense and multi-head attention (MHA) layers to AIE tiles.
arXiv:2606. 15615v1 Announce Type: new Abstract: Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps.
arXiv:2606. 16723v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers.
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.