Large language models

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

21,000 stories · RSS feed

arXiv AI

Jul 21

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

arXiv:2607. 17779v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images.

By Dongdong Yang, Deyue Zhang, Zhao Liu, Zonghao Ying, Wenzhuo Xu, Jiankai Jin, Xiangzheng Zhang, Quanchen Zou

llms diffusion multimodal benchmarks safety

arXiv Machine Learning

Jul 21

Backpropagation-Free Trunk Training via the Split Forward Gradients

arXiv:2607. 16612v1 Announce Type: cross Abstract: Backpropagation makes training deep networks memory intensive because it must store intermediate activations.

By Tian Qin, Wei-Min Huang

llms benchmarks

arXiv AI

Jul 21

From Intent to Infrastructure: LLM-Driven Agent Compilers for ISAC Networks

arXiv:2607. 16269v1 Announce Type: cross Abstract: Integrated sensing and communications (ISAC) is moving from proof-of-concept demonstrations to system-level deployment in sixth-generation (6G) networks.

By Lijie Zheng, Xudong Zhong, Baoquan Ren, Xiangwu Gong, Xinghui Zhu, Ji He

llms agents

arXiv AI

Jul 21

An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis

arXiv:2607. 16249v1 Announce Type: cross Abstract: Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management.

By Sreenath Vemula, Pierre Jehel, Fabrice Cotton, Filippo Gatti

llms agents

arXiv AI

Jul 21

RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants

arXiv:2607. 16243v1 Announce Type: cross Abstract: Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying.

By Anushiya Arunan, Xin Li, Yan Qin, U-Xuan Tan, Nhu Khue Vuong, Xiaoli Li, Chau Yuen

llms multimodal benchmarks safety

arXiv Machine Learning

Jul 21

Auditing Invisible Weight Updates with Reference Traces

arXiv:2607. 09800v2 Announce Type: replace Abstract: Master weights and stochastic rounding bypass invisible stored-weight updates but do not locate lost direct-storage proposals or parameters worth protecting.

By Zekai Shang

llms

arXiv Machine Learning

Jul 21

ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning

arXiv:2607. 16323v1 Announce Type: cross Abstract: Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR).

By Alexander Selivanov, Friederike Jungmann, Jan Kehrer, Karl-Ludwig Laugwitz, Eimo Martens, Daniel Rueckert

llms multimodal benchmarks

arXiv Machine Learning

Jul 21

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks

arXiv:2607. 18110v1 Announce Type: new Abstract: Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles.

By Tianzhu Ye, Li Dong, Guanheng Chen, He Zhu, Xun Wu, Shaohan Huang, Furu Wei

llms reinforcement-learning efficiency

arXiv AI

Jul 21

CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents

arXiv:2607. 16244v1 Announce Type: cross Abstract: Training multi-turn evidence-reading agents with outcome-only reinforcement learning is unstable because intermediate turns receive little direct credit.

By Hao Dou

llms agents reinforcement-learning

arXiv Machine Learning

Jul 21

The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture

arXiv:2607. 17146v1 Announce Type: cross Abstract: We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle $\calE = \calM \times \R^d$.

By Zhihua Liang

llms diffusion benchmarks

arXiv AI

Jul 21

OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs

arXiv:2607. 17963v1 Announce Type: new Abstract: Ontology extension refers to the process of enriching an existing ontology in response to emerging requirements, making it more complete.

By Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid, Simon Blattner, Robin Keskis\"arkk\"a, Aldo Gangemi, Eva Blomqvist, Andrea Giovanni Nuzzolese

llms rag

arXiv Machine Learning

Jul 21

Self-Evolving Just-In-Time Memory for Proactive Embodied Safety

arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.

By Bingrui Sima, Lizhong Wang, Xiaoya Lu, Kun He, Xiao Yang

llms agents robotics multimodal safety

arXiv AI

Jul 21

Short-Term Electricity Demand Forecasting for New England: A Comprehensive Machine Learning Benchmark with Weather, Calendar, and COVID-19 Indicators

arXiv:2606. 20918v2 Announce Type: replace-cross Abstract: Accurate short-term electricity demand forecasting is critical for reliable power system operation, energy market planning, and infrastructure optimization.

By Reza Ghanavati, Behrooz Mosallaei

llms benchmarks

arXiv AI

Jul 21

Trusting sovereign language models as scientific instruments: evidence from Portugal's AMALIA

arXiv:2607. 08731v2 Announce Type: replace-cross Abstract: National language models are becoming publicly funded epistemic infrastructure.

By Manuel Pita

llms

arXiv AI

Jul 21

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage

arXiv:2601. 03043v4 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency.

By Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

llms benchmarks

arXiv AI

Jul 21

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?

By Jiahe Fan, Yinghao Hou, Si Chen, Aiyuan Zhang, Hong Xie, Defu Lian

llms efficiency benchmarks safety

arXiv AI

Jul 21

Token-Level Cross-Modal Transformer with Contrastive Multi-Task Learning for Breast Cancer Subtype Classification and Survival Prediction

arXiv:2607. 16233v1 Announce Type: cross Abstract: Integrating heterogeneous genomic and clinical modalities for joint cancer subtype classification and survival prediction remains a key challenge in precision oncology.

By Suxing Liu Byungwon Min

llms multimodal

arXiv AI

Jul 21

Otap:Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories

arXiv:2607. 17082v1 Announce Type: new Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results.

By Babak Barazandeh, Subhabrata Majumdar, George Michailidis

llms agents benchmarks

arXiv Machine Learning

Jul 21

Perturbation is All You Need for Extrapolating Language Models

arXiv:2605. 04344v2 Announce Type: replace-cross Abstract: This paper develops a statistical theory of extrapolation for large language models, by reinterpreting them through pre-post-additive noise models.

By Zetai Cen, Jin Zhu, Xinwei Shen, Chengchun Shi

llms

arXiv AI

Jul 21

Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning

arXiv:2607. 16209v1 Announce Type: new Abstract: Context reranking and pruning have become essential for improving the efficiency of modern Retrieval-Augmented Generation (RAG) systems, yet an interpretable and unified framework remains underexplored.

By Yanqiao Chen, Dongsheng Hou, Yuhan Rui, Zhen Cao, Yepang Liu

llms rag fine-tuning efficiency benchmarks

Get the daily briefing