Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

15,495 stories · RSS feed

arXiv Machine Learning

Aug 13

Accelerating Time Series Foundation Models with Speculative Decoding

arXiv:2511. 18191v2 Announce Type: replace Abstract: Time series forecasting drives operational decisions under tight latency budgets, and autoregressive time series foundation models (TSFMs) increasingly deliver the most accurate forecasts.

By Pranav Subbaraman, Fang Sun, Jinxi Yu, Yue Yao, Huacong Tang, Xiao Luo, Yizhou Sun

llms efficiency

arXiv Machine Learning

Aug 13

Optimized Deferral for Imbalanced Settings

arXiv:2604. 27723v2 Announce Type: replace Abstract: Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost.

By Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong

llms computer-vision

arXiv Machine Learning

Aug 13

LLM Router: Rethinking Routing with Prefill Activations

arXiv:2603. 20895v3 Announce Type: replace-cross Abstract: Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty.

By Tanay Varshney, Annie Surla, Michelle Xu, Gomathy Venkata Krishnan, Maximilian Jeblick, David Austin, Neal Vaidya, Davide Onofrio

llms

arXiv AI

Aug 13

Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation

arXiv:2608. 12150v1 Announce Type: new Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions.

By Rodrigo Guedes de Souza, Alison R. Panisson

llms benchmarks

arXiv AI

Aug 13

From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation

arXiv:2608. 11493v1 Announce Type: new Abstract: Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale.

By Alireza S. Ziabari, Kat Ellis, Colleen Chan, Ding Tong

llms fine-tuning safety

arXiv AI

Aug 13

BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Model

arXiv:2608. 11244v1 Announce Type: new Abstract: Construction standards are critical for building safety and sustainability.

By Jia-Rui Lin, Junxi Guo, Keyin Chen, Peng Pan

llms nlp multimodal safety

arXiv AI

Aug 13

Clinical Feasibility of Low-Magnification Fluorescence Imaging for Breast Cancer Margin Detection Using Texture Analysis and Deep Learning

arXiv:2608. 11317v1 Announce Type: cross Abstract: High-resolution images of unprocessed surgical breast tissue can be obtained using microscopy with ultraviolet surface excitation (MUSE).

By Pouya Afshin, Tianling Niu, Tongtong Lu, David Helminiak, Julie Jorns, Mollie Patton, Tina Yen, Donghye Ye, Bing Yu

llms computer-vision

arXiv AI

Aug 13

Uncertainty-Aware and Explainable Ensemble Deep Learning Framework for Multi-Class Skin Lesion Classification

arXiv:2608. 11280v1 Announce Type: cross Abstract: Skin cancer diagnosis from dermoscopic images remains challenging due to high intra-class variability, inter-class similarity, class imbalance, and the limited interpretability of deep learning models.

By Rofiqul Islam, Lilatul Ferdouse

llms computer-vision safety

arXiv AI

Aug 13

TEMPER: Testing Emotional Perturbation in Quantitative Reasoning

arXiv:2604. 07801v2 Announce Type: replace-cross Abstract: Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language.

By Atahan Dokme, Benjamin Reichman, Larry Heck

llms benchmarks

arXiv AI

Aug 13

Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization

arXiv:2608. 11239v1 Announce Type: cross Abstract: Administering Database Management Systems (DBMS) instances requires Database Administrators (DBA) to balance performance in terms of Service Level Agreement (SLA) against resource usage, often prompting RAM over-allocation that wastes memory.

By Yifan Wang, Patrick Royer, Rapha\"el F\'eraud, David Delande

llms reinforcement-learning efficiency benchmarks

arXiv AI

Aug 13

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

arXiv:2608. 11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning.

By Archan Dutta, Vyanktesh Kanungo

llms rag diffusion multimodal

arXiv AI

Aug 13

Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs

arXiv:2608. 11573v1 Announce Type: cross Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs).

By Vu Duc Anh, Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen, Ponhvoan Srey, Luu Anh Tuan

llms reinforcement-learning

arXiv Machine Learning

Aug 13

Continuous-Latent Predictive Modeling with Semantic Alignment for EEG-Language Foundation Models

arXiv:2608. 11656v1 Announce Type: new Abstract: Recent advances in EEG foundation models have demonstrated the potential of large-scale pretraining to enable generalizable neural decoding across subjects, recording environments, and datasets.

By Myeong-Ju Cho, Hye-Bin Shin, Seo-Hyun Lee, Seong-Whan Lee

llms rag diffusion benchmarks safety

arXiv AI

Aug 13

How Organizations Use AI: Evidence from ChatGPT

arXiv:2608. 12236v1 Announce Type: cross Abstract: We study how organizations use frontier generative AI by linking ChatGPT Enterprise account records to usage, worker roles, task classifications, and public-company financial data through March 2026.

By Aaron Chatterji, David Holtz, Neel Rakholia, Prasanna Tambe, Gawesha Weeratunga

llms safety

arXiv AI

Aug 13

OpenAg: Democratizing Agricultural Intelligence

arXiv:2506. 04571v3 Announce Type: replace Abstract: Agriculture is undergoing a major transformation driven by artificial intelligence (AI), machine learning, and knowledge representation technologies.

By Srikanth Thudumu, Jason Fisher

llms rag agents fine-tuning

arXiv AI

Aug 13

CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D

arXiv:2509. 24528v4 Announce Type: replace-cross Abstract: Object retrieval from a scene has become a new trend of research due to its numerous applications.

By Mohamad Amin Mirzaei, Pantea Amoie, Ali Ekhterachian, Matin Mirzababaei, Babak Khalaj

llms rag computer-vision multimodal benchmarks

arXiv Machine Learning

Aug 13

Draw This First

arXiv:2608. 12064v1 Announce Type: cross Abstract: We invert the typical formulation of sketch generation: instead of drawing strokes in order, we predict a 2D field that defines the order in which strokes are drawn.

By Dazhi Zhong, Rowan Bradbury, Grant Davis

llms computer-vision

arXiv AI

Aug 13

Agent Safety Should Be a Runtime Contract

arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.

By Albus W. Ng, Yi Han, Jusheng Zhang, Wenhao Wang

llms agents reinforcement-learning safety

arXiv AI

Aug 13

Methodologies for Improving the Quality of AI Tutoring in K-12 Education

arXiv:2608. 11259v1 Announce Type: cross Abstract: Many AI tutors leverage large language models (LLMs) today.

By Tushar Udeshi, Anna Khazenzon, Kabir Khan, Nick Breen, RJ Corwin, Chris DiGiano, Kodi Weatherholtz, Marek Zaluski

llms agents

arXiv Machine Learning

Aug 13

Disentangling the Expressivity of RoPE

arXiv:2608. 11909v1 Announce Type: new Abstract: Two accounts recur in explanations of the success of rotary position embeddings (RoPE).

By Selim Jerad, Anej Svete, Jiaoda Li, Ryan Cotterell

llms rag safety

Get the daily briefing