Large language models

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

18,726 stories · RSS feed

arXiv Machine Learning

Aug 4

WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model

arXiv:2608. 01845v1 Announce Type: new Abstract: Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow.

By Leyang Chen, Junyi Wu, Shaoqiu Zhang, Yulun Zhang

llms diffusion

arXiv Machine Learning

Aug 4

Geometry-Guided Layerwise FFN Width Allocation in Transformers

arXiv:2608. 02064v1 Announce Type: new Abstract: Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth.

By Timur Mudarisov, Mikhail Burtsev, Radu State

llms

arXiv Machine Learning

Aug 4

MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation

arXiv:2608. 00195v1 Announce Type: cross Abstract: High-resolution 3D segmentation of hip and shoulder anatomy from CT and MRI is essential for surgical planning, yet frozen segmentation models often fail under domain shift.

By John Garcia Henao, Nicholas B\"unger, Benedikt Herzog, Cindy Guerrero Toro, Benjamin Vella, Matthias Biner, Rico Br\"utsch, Carmen Castroviejo Fernandez, Felix \"Ottl, Norman Juchler, Armando Hoch, Bettina Hochreiter, Sven Hirsch, Sebastiano Caprara

llms computer-vision benchmarks

arXiv Machine Learning

Aug 4

onepot-Bench 0: towards lab-aware in silico chemistry benchmarks

arXiv:2608. 02595v1 Announce Type: new Abstract: Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc analysis.

By Brandon Wang, Andrei S. Tyrin, Daniil A. Boiko

llms benchmarks safety

arXiv Machine Learning

Aug 4

Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams

arXiv:2608. 00012v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated.

By Fengxiang Wang, Qiuyang Yu, Yueying Li, Mingshuo Chen, Chengchi Fei, Kaiyi Xu, Lixin Gu, Wangxu Wei, Junchao Gong, Lipeng Ma, Jiong Wang, Fenghua Ling, Wenlong Zhang, Xue Yang, Wenjing Yang, Ben Fei, Long Lan

llms multimodal benchmarks

arXiv Machine Learning

Aug 4

GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMs

arXiv:2608. 00877v1 Announce Type: new Abstract: Remote-sensing multimodal large language models (MLLMs) often assert facts that imagery cannot establish, such as a facility's identity or function.

By Xuechen Li

llms multimodal safety

arXiv Machine Learning

Aug 4

Geometric Analysis of Token Selection in Multi-Head Attention

arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).

By Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova, Radu State

llms safety

arXiv Machine Learning

Aug 4

A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs

arXiv:2603. 07475v4 Announce Type: replace-cross Abstract: Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence denoising.

By Raghavv Goel, Risheek Garrepalli, Sudhanshu Agrawal, Chris Lott, Mingu Lee, Fatih Porikli

llms diffusion benchmarks safety

arXiv Machine Learning

Aug 4

HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses

arXiv:2608. 01918v1 Announce Type: new Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments.

By Luan Zhang, Ruochen Zhou, Dandan Song, Zhengyu Chen, Yuhang Tian, Jun Yang, Huipeng Ma, Chenhao Li, Guangyuan Feng, Xudong Li, Yizhou Jin, Yan Xu

llms agents

arXiv Machine Learning

Aug 4

Spatiotemporal Proximal Causal Inference under Hidden Confounding and Interference

arXiv:2608. 01352v1 Announce Type: new Abstract: Estimating causal effects from real-world spatiotemporal data is challenging due to hidden confounders and interference.

By Omar Faruque, Pavan Raj Ravi, Jianwu Wang

llms

arXiv Machine Learning

Aug 4

Unleashing the Potential of Large Language Models: A Blueprint for Real-Time, Enterprise-Ready Deployments

arXiv:2608. 00419v1 Announce Type: new Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback loops.

By Muhammad Faizan Raza (Luna), Shuo (Luna), Yang, Satish Mahadevan Srinivasan, Joanna F. DeFranco

llms rag reinforcement-learning safety

arXiv Machine Learning

Aug 4

MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents

arXiv:2608. 00007v1 Announce Type: cross Abstract: Equipping Large Language Models (LLMs) with human-like personas is crucial for agentic applications, such as role-play and user simulation.

By Bohan Tang, Yiwen Guo

llms agents

arXiv Machine Learning

Aug 4

Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models

arXiv:2608. 01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories.

By Leyan Xue, Feng Xiong, Mingjun Ma, Changqing Zhang

llms efficiency multimodal benchmarks

arXiv Machine Learning

Aug 4

SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models

arXiv:2608. 01899v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning.

By Jing Wu, Jianhua Wu, Jiayi Guan, Jiahong Chen, Jinghui Lu, Hangjun Ye, Bingzhao Gao, Long Chen

llms robotics fine-tuning multimodal

arXiv Machine Learning

Aug 4

Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer

arXiv:2608. 01585v1 Announce Type: cross Abstract: Language model benchmarking is a difficult task.

By Tyler Ashoff, Jordan Rodu

llms rag multimodal benchmarks safety

arXiv Machine Learning

Aug 4

(How) Learning Rates Regulate Catastrophic Overtraining

arXiv:2604. 13627v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant.

By Mark Rofin, Aditya Varre, Nicolas Flammarion

llms fine-tuning

arXiv Machine Learning

Aug 4

ReasonCast: Towards Explainable Time Series Forecasting with Reasoning

arXiv:2608. 01875v1 Announce Type: cross Abstract: Most time series (TS) models are specialized for a single task, either understanding (i.

By Seunghan Lee, Jun Seo, Jaehoon Lee, Junhyeok Kang, Sangjun Han, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Soonyoung Lee, Wonbin Ahn

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 4

SingLEM: Single-Channel Large EEG Model

arXiv:2509. 17920v2 Announce Type: replace Abstract: Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability.

By Jamiyan Sukhbaatar, Satoshi Imamura, Ibuki Inoue, Shoya Murakami, Kazi Mahmudul Hassan, Seungwoo Han, Ingon Chanpornpakdi, Toshihisa Tanaka

llms

arXiv Machine Learning

Aug 4

The Condition-Number Barrier in Sparse Least Squares

arXiv:2608. 02588v1 Announce Type: cross Abstract: In [AS21], Axiotis and Sviridenko conjectured that the linear dependence on the restricted condition number in sparse convex optimization cannot be improved by a polynomial-time algorithm.

By Honghao Lin, Vahab Mirrokni, David P. Woodruff

llms agents efficiency

arXiv Machine Learning

Aug 4

FAU at ImageCLEF 2026 Task on Multimodal Reasoning Robust Candidate Scoring and Concise Multilingual Visual Answering

arXiv:2608. 01664v1 Announce Type: cross Abstract: We present our ImageCLEF 2026 Multimodal Reasoning system for the Visual Multiple Choice Question Answering (Visual MCQ) and Visual Open Question Answering (Visual OpenQA) subtasks.

By Mohamed Basem, Vincent Christlein

llms nlp multimodal

Get the daily briefing