Large language models

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

24,907 stories · RSS feed

arXiv AI

Jul 7

A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition

arXiv:2204. 02803v2 Announce Type: replace-cross Abstract: Sign language recognition from monocular video or 2D pose sequences is challenging, both because 3D information must be inferred from 2D observations and because the signal is inherently spatiotemporal.

By Silvan Ferreira, Esdras Costa, Marcio Dahia, Jampierre Rocha

llms rag

arXiv AI

Jul 7

Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data

arXiv:2607. 03663v1 Announce Type: cross Abstract: The accurate estimation of Above-Ground Biomass (AGB) in mature tropical forests remains a critical challenge in remote sensing, primarily due to the saturation of Synthetic Aperture Radar (SAR) signals in high-density areas and persistent cloud cover affecting optical imagery.

By Luiz Felipe Parente Santiago (Institute of Computing, Brazilian Army Research Institute in the Amazon), Rosiane Rodrigues de Freitas (Institute of Computing), Daniel Rodrigues dos Santos (Military Institute of Engineering), Felipe Ferrari (Military Institute of Engineering)

llms computer-vision fine-tuning benchmarks

arXiv AI

Jul 7

On the Ability of Transformers to Verify Plans

arXiv:2603. 19954v2 Announce Type: replace Abstract: Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been limited.

By Yash Sarrof, Yupei Du, Katharina Stein, Alexander Koller, Sylvie Thi\'ebaux, Michael Hahn

llms

arXiv AI

Jul 7

TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios

arXiv:2607. 05131v1 Announce Type: new Abstract: Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interaction in real-world environments.

By Kailin Lyu, Di Wu, Long Xiao, Jianning Zeng, Jianwei He, Chang Lin, Lianyu Hu, Lin Shu, Jie Hao, Ce Hao

llms multimodal benchmarks safety

arXiv AI

Jul 7

PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving

arXiv:2607. 02525v1 Announce Type: cross Abstract: We present PEEK, a lightweight scheduling and eviction framework for both online (streaming) and offline (batch) LLM serving; this paper focuses on the online regime.

By Bing Xie, Zhipeng Wang, Masahiro Tanaka, Zheng Zhen

llms efficiency

arXiv AI

Jul 7

Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement

arXiv:2607. 04277v1 Announce Type: cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative?

By Jiang Zhang, Bing Yuan, Qian Zhang

llms agents safety

arXiv AI

Jul 7

DualView: Preventing Indirect Prompt Injection in Personal AI Agents

arXiv:2607. 03821v1 Announce Type: cross Abstract: Personal AI agents that run on the user's local machine, such as OpenClaw, automate daily tasks including web search, email, and file management.

By Juhee Kim, Woohyuk Choi, Taehyun Kang, Youngmin Kim, Byoungyoung Lee

llms agents benchmarks

arXiv AI

Jul 7

LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review

arXiv:2607. 05031v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct.

By Ali Hassaan Mughal, Muhammad Bilal

llms

arXiv AI

Jul 7

KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression

arXiv:2607. 01237v2 Announce Type: replace-cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.

By Shen Han, Yuyang Wu, Junpu Yu, Olexandr Isayev

llms efficiency

arXiv AI

Jul 7

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

arXiv:2607. 02637v1 Announce Type: cross Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models.

By Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin

llms computer-vision fine-tuning benchmarks safety

arXiv AI

Jul 7

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

arXiv:2607. 04438v1 Announce Type: cross Abstract: Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile.

By Lingao Xiao, Yalun Dai, Yangyu Huang, Qihao Zhao, Wenshan Wu, Hugo He, Ruishuo Chen, Jin Jiang, Qianli Ma, Jiahuan Zhang, Xin Zhang, Ying Xin, Yang Ou, Yan Xia, Scarlett Li, Longbo Huang, Zhipeng Zhang, Yang He, Yap Kim Hui, Yan Lu

llms agents multimodal benchmarks

arXiv AI

Jul 7

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

arXiv:2605. 28732v2 Announce Type: replace-cross Abstract: Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug.

By Xinle Deng, Ruobin Zhong, Hujin Peng, Xiaoben Lu, Yanzhe Wu, Guang Li, Buqiang Xu, Yunzhi Yao, Jizhan Fang, Haoliang Cao, Junjie Guo, Yuan Yuan, Ziqing Ma, Yuanqiang Yu, Rui Hu, Baohua Dong, Hangcheng Zhu, Ningyu Zhang

llms rag benchmarks

arXiv Machine Learning

Jul 7

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.

By Yueyang Wang, Baolong Bi, Shuo Lu, Jingyuan Zhang

llms fine-tuning multimodal

arXiv AI

Jul 7

Cultural Binding Heads in Language Models

arXiv:2605. 28543v2 Announce Type: replace Abstract: LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness.

By Avrile Floro, Luca Benedetto

llms benchmarks safety

arXiv AI

Jul 7

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents

arXiv:2607. 03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine outputs over many turns.

By Abhishek Kumar, Carsten Maple

llms agents benchmarks safety

arXiv Machine Learning

Jul 7

Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models

arXiv:2409. 16663v5 Announce Type: replace-cross Abstract: We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving.

By Alexander Popov, Alperen Degirmenci, David Wehr, Shashank Hegde, Ryan Oldja, Alexey Kamenev, Bertrand Douillard, David Nist\'er, Urs Muller, Ruchi Bhargava, Stan Birchfield, Nikolai Smolyanskiy

llms agents diffusion robotics

arXiv AI

Jul 7

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving

arXiv:2607. 02574v1 Announce Type: cross Abstract: The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor.

By Jie Li, Tongyang Wang, Yong Chen

llms efficiency

arXiv AI

Jul 7

SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images

arXiv:2208. 00657v2 Announce Type: cross Abstract: Building detection and change detection using remote sensing images can help urban and rescue planning.

By Amir Mohammadian, Foad Ghaderi

llms benchmarks

arXiv Machine Learning

Jul 7

GestaltMML: Enhancing Rare Genetic Disease Diagnosis through Multimodal Machine Learning Combining Facial Images and Clinical Text

arXiv:2312. 15320v3 Announce Type: replace-cross Abstract: Individuals with suspected rare genetic disorders often undergo multiple clinical evaluations, imaging studies, laboratory tests, and genetic tests over a prolonged period of time, a process commonly described as the diagnostic odyssey.

By Da Wu, Zhanliang Wang, Hongzhuo Chen, Jingye Yang, Cong Liu, Tzung-Chien Hsieh, Elaine Marchi, Justin Blair, Peter Krawitz, Chunhua Weng, Wendy Chung, Gholson J. Lyon, Ian D. Krantz, Jennifer M. Kalish, Kai Wang

llms multimodal benchmarks

arXiv Machine Learning

Jul 7

Geometric Causal Models

arXiv:2607. 05153v1 Announce Type: cross Abstract: Scientists often seek to draw causal inferences from structured data that is not independently and identically distributed, such as spatial data, network data, or molecular data.

By Eli N. Weinstein, David M. Blei

llms

Get the daily briefing