Large language models

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

23,269 stories · RSS feed

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 Machine Learning

Jul 7

Agentic Very Long Video Understanding

arXiv:2601. 18157v3 Announce Type: replace-cross Abstract: The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video.

By Aniket Rege, Arka Sadhu, Yuliang Li, Kejie Li, Ramya Korlakai Vinayak, Yuning Chai, Yong Jae Lee, Hyo Jin Kim

llms rag agents multimodal benchmarks

arXiv AI

Jul 7

Unified Audio Intelligence Without Regressing on Text Intelligence

arXiv:2607. 05196v1 Announce Type: cross Abstract: Audio intelligence involves understanding, reasoning about, and generating both audio and speech.

By Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang, Zihan Liu, Sungwon Kim, Yang Chen, Arushi Goel, Rajarshi Roy, Wenliang Dai, Zhuolin Yang, Yangyi Chen, Dongfu Jiang, Sreyan Ghosh, Tuomas Rintamaki, Andrew Tao, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

llms rag agents reinforcement-learning efficiency multimodal benchmarks safety

arXiv Machine Learning

Jul 7

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

arXiv:2604. 11943v3 Announce Type: replace-cross Abstract: An OS kernel that runs LLM inference internally can read the model's own next-token logit distribution before any text is generated, and act on it as a governance primitive.

By Daeyeon Son

llms agents fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions

arXiv:2604. 11730v4 Announce Type: replace-cross Abstract: Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that improve medical outcomes.

By Manuela Gonz\'alez-Gonz\'alez, Soufiane Belharbi, Muhammad Osama Zeeshan, Masoumeh Sharafi, Muhammad Haseeb Aslam, Lorenzo Sia, Nicolas Richet, Marco Pedersoli, Alessandro Lameiras Koerich, Simon L Bacon, Eric Granger

llms fine-tuning multimodal

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

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.

By Nicholas Tan Jerome, Frank Simon

llms fine-tuning benchmarks

arXiv AI

Jul 7

Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks

arXiv:2607. 03801v1 Announce Type: cross Abstract: We define Tiny Language Models (TLMs) as models below roughly 3B parameters that fit on mainstream consumer devices.

By Bhavesh Sood, Jaromir Savelka

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 7

Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs

arXiv:2607. 05013v1 Announce Type: cross Abstract: Although LLMs have made significant progress in mathematical reasoning, determining whether a mathematical problem is solvable remains a fundamental yet challenging capability.

By Nikolaos Xiros, Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos

llms robotics

arXiv Machine Learning

Jul 7

Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

arXiv:2607. 04819v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks.

By Ligong Han, Kai Xu, Hao Wang, Ruijiang Gao, Akash Srivastava

llms

arXiv AI

Jul 7

Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework

arXiv:2601. 06550v3 Announce Type: replace-cross Abstract: Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding.

By Pan Liao, Feng Yang, Di Wu, Jinwen Yu, Wang Zhao, Dingwen Zhang

llms multimodal benchmarks safety

arXiv AI

Jul 7

Agent Data Injection Attacks are Realistic Threats to AI Agents

arXiv:2607. 05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context.

By Woohyuk Choi, Juhee Kim, Taehyun Kang, Jihyeon Jeong, Luyi Xing, Byoungyoung Lee

llms agents

arXiv Machine Learning

Jul 7

Few-Step Diffusion Language Models via Trajectory Self-Distillation

arXiv:2602. 12262v4 Announce Type: replace-cross Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding.

By Tunyu Zhang, Xinxi Zhang, Ligong Han, Haizhou Shi, Xiaoxiao He, Zhuowei Li, Hao Wang, Kai Xu, Akash Srivastava, Chengzhi Mao, Hao Wang, Vladimir Pavlovic, Dimitris N. Metaxas

llms diffusion efficiency benchmarks

arXiv Machine Learning

Jul 7

Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B

arXiv:2607. 04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.

By Jaeyeon Kim, Jewon Lee, Bo-Kyeong Kim

llms diffusion efficiency

arXiv Machine Learning

Jul 7

Tile-Level Activation Overlap for Efficient LLM Inference

arXiv:2607. 02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.

By Abhinav Jangda, Tyler Sorensen, Sebastian Burckhardt, Jianlan YE, Chaoyin Li, Atul Gupta

llms

arXiv AI

Jul 7

A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements

arXiv:2607. 04436v1 Announce Type: cross Abstract: Natural language requirements (NLRs) are essential for bridging communication gaps among diverse stakeholders in software development.

By Pavithra PM Nair, Preethu Rose Anish

llms rag safety

arXiv AI

Jul 7

SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications

arXiv:2604. 14163v2 Announce Type: replace-cross Abstract: Maritime distress communications transmitted over very high frequency (VHF) radio are safety-critical voice messages used to report emergencies at sea.

By Tomer Atia, Yehudit Aperstein, Alexander Apartsin

llms multimodal safety

arXiv AI

Jul 7

Silicon Sampling via Cross-Survey Transfer

arXiv:2607. 03091v1 Announce Type: new Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research.

By Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Frank Cheng-shan Liu, I-Ling Cheng, Yihuang Kang

llms safety

arXiv AI

Jul 7

Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models

arXiv:2607. 02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information.

By Shengyi Hua, Kangzhe Hu, Conghui He, Xiaofan Zhang, Shaoting Zhang

llms rag agents reinforcement-learning

arXiv AI

Jul 7

FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection

arXiv:2506. 03162v3 Announce Type: replace-cross Abstract: The rapid proliferation of surveillance cameras has increased the demand for automated violence detection.

By Damith Chamalke Senadeera, Muhammad Awais, Shibo Li, Dimitrios Kollias, Gregory Slabaugh

llms benchmarks

Get the daily briefing