Large language models

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

21,300 stories · RSS feed

arXiv AI

Jul 20

Verbalizable Representations Form a Global Workspace in Language Models

arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.

By Wes Gurnee, Nicholas Sofroniew, Adam Pearce, Mateusz Piotrowski, Isaac Kauvar, Runjin Chen, Anna Soligo, Paul Bogdan, Euan Ong, Rowan Wang, Ben Thompson, David Abrahams, Subhash Kantamneni, Emmanuel Ameisen, Joshua Batson, Jack Lindsey

llms safety

arXiv AI

Jul 20

CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations

arXiv:2607. 15847v1 Announce Type: cross Abstract: Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation.

By Suzan Awinat, Alfonso Ortega del Puente

llms rag benchmarks

arXiv Machine Learning

Jul 20

CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach

arXiv:2607. 16028v1 Announce Type: new Abstract: This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data.

By Andrei Neagu, Eeham Khan, Leila Kosseim

llms agents reinforcement-learning

arXiv Machine Learning

Jul 20

A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods

arXiv:2607. 15705v1 Announce Type: new Abstract: Accurate load forecasting at multiple grid levels is essential for future smart grids, ranging from aggregated control area forecasts for balancing supply and demand to forecasts of individual end-consumer loads for demand-side management and energy management systems.

By Matthias Hertel, Sebastian P\"utz, Jonathan Kolar, Benjamin Sch\"afer, Ralf Mikut, Veit Hagenmeyer

llms benchmarks

arXiv AI

Jul 20

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching

arXiv:2607. 15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent).

By Yan Song

llms rag benchmarks

arXiv Machine Learning

Jul 20

Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models

arXiv:2607. 15655v1 Announce Type: cross Abstract: Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding.

By Yingqian Cui, Wei Deng, Lantao Mei, Hang Li, Charu C. Aggarwal, Hui Liu, Yue Xing

llms diffusion benchmarks

arXiv AI

Jul 20

An Exam for Active Observers

arXiv:2607. 16165v1 Announce Type: cross Abstract: Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot.

By Jiarui Zhang, Muzi Tao, Shangshang Wang, Ollie Liu, Xuezhe Ma, Willie Neiswanger

llms multimodal benchmarks

arXiv AI

Jul 20

From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation

arXiv:2607. 15552v1 Announce Type: cross Abstract: Generating personalized trip itineraries is a complex planning task and involves a tension between hard combinatorial feasibility and soft latent desirability.

By Himel Dev, Tanmoy Sen, Madhusudan Basak, Bashima Islam

llms reinforcement-learning

arXiv Machine Learning

Jul 20

Cost-efficient generative AI summarization for scalable automated essay scoring in educational assessment

arXiv:2607. 15829v1 Announce Type: cross Abstract: Automated essay scoring (AES) enables scalable assessment and timely feedback but remains challenged by transformer input-length limitations, which can cause information loss when processing long essays.

By Haowei Hua

llms nlp benchmarks safety

arXiv AI

Jul 20

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.

By Bo-An Chang, Yu-Chih Chen

llms diffusion nlp reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Jul 20

Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention

arXiv:2607. 15449v1 Announce Type: new Abstract: Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained MLP residual-stack fixed point and ask whether it constitutes a relevant, marginal, or irrelevant operator.

By Parviz Haggi-Mani, Irina Rish

llms

arXiv AI

Jul 20

Perceived AGI: Believability as Dimensional Completeness, Not Capability

arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.

By Sebastian Cochinescu

llms agents robotics benchmarks

arXiv AI

Jul 20

Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts

arXiv:2607. 15647v1 Announce Type: new Abstract: LEED v4.

By Aritro De (The University of Texas at Austin), Juliana Felkner (The University of Texas at Austin)

llms multimodal benchmarks

arXiv AI

Jul 20

Human-Inspired Neuro-Symbolic World Modeling and Logic Reasoning for Interpretable Safe UAV Landing Site Assessment

arXiv:2510. 22204v3 Announce Type: replace-cross Abstract: Reliable assessment of safe landing sites in unstructured environments is essential for deploying Unmanned Aerial Vehicles (UAVs) in real-world applications such as delivery, inspection, and surveillance.

By Weixian Qian, Tianyi Yang, Sebastian Schroder, Yao Deng, Jiaohong Yao, Xiao Cheng, Richard Han, Xi Zheng

llms computer-vision safety

arXiv AI

Jul 20

Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving

arXiv:2607. 15621v1 Announce Type: cross Abstract: Large language models bring instruction following and scene reasoning to end-to-end driving, but their inference latency collides with the control rate a vehicle requires.

By Yun Li, Jiachen Gong, Simon Thompson, Ehsan Javanmardi, Qunli Zhang, Zifan Zeng, Shiming Liu, Peng Wang, Zixuan Guo, Manabu Tsukada

llms agents efficiency multimodal benchmarks

arXiv AI

Jul 20

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.

By Xintong Li, Sha Li, Yuwei Zhang, Changlong Yu, Rongmei Lin, Hongye Jin, Shuyi Guan, Xin Liu, Linwei Li, Qingyu Yin, Jingbo Shang

llms agents reinforcement-learning

arXiv AI

Jul 20

What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers

arXiv:2604. 15010v2 Announce Type: replace-cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it?

By \'Eric Jacopin

llms

arXiv AI

Jul 20

AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots

arXiv:2607. 15620v1 Announce Type: cross Abstract: Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop.

By Priyanka V. Setty, Arvind Ramanathan, Ian Foster, Rick Stevens

llms computer-vision robotics multimodal benchmarks

arXiv Machine Learning

Jul 20

SODA: Semi On-Policy Black-Box Distillation for Large Language Models

arXiv:2604. 03873v4 Announce Type: replace Abstract: Black-box knowledge distillation for large language models presents a strict trade-off.

By Xiwen Chen, Jingjing Wang, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Yueyue Deng, Hejian Sang, Zhipeng Wang, Alborz Geramifard, Feng Luo

llms efficiency benchmarks safety

arXiv AI

Jul 20

FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment

arXiv:2604. 23786v2 Announce Type: replace Abstract: In recent years, the integration of multimodal machine learning in wellbeing assessment has offered transformative potential for monitoring mental health.

By Sophie Chiang, Tom Brennan, Fethiye Irmak Dogan, Jiaee Cheong, Hatice Gunes

llms multimodal safety

Get the daily briefing