Large language models

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

31,598 stories · RSS feed

arXiv Computation and Language

Sep 21

I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance

arXiv:2609.21183v1 Announce Type: cross Abstract: Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM...

By Amit Kumar Singh Yadav, Ritvik Shrivastava, Xuan Zhang, Seungwhan Moon, Shashank Jain, Pinar Donmez, Babak Damavandi

llms

arXiv Computation and Language

Sep 21

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...

By Jintian Shao, Hongyi Huang, Jiayi Wu, YiMing Cheng, ZhiYu Wu, You Shan, MingKai Zheng

llms rag efficiency benchmarks

arXiv Computation and Language

Sep 21

Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model

arXiv:2601.06848v2 Announce Type: replace Abstract: Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, whi...

By Zhongzheng Wang, Yuanhe Tian, Hongzhi Wang, Yan Song

llms nlp fine-tuning multimodal

arXiv Computation and Language

Sep 21

MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery

arXiv:2606.24595v2 Announce Type: replace Abstract: Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, evolving understanding of the user that inter...

By Enze Ma, Yufan Zhou, Wei-Chieh Huang, Jie Yang, Huanhuan Ma, Zixuan Wang, Chengze Li, Chunyu Miao, Philip S. Yu, Zhen Wang

llms agents benchmarks

arXiv Computer Vision

Sep 21

ME-Dex 1.0: Bringing Heterogeneous Tactile Sensing into World Action Modeling

arXiv:2609.21449v1 Announce Type: new Abstract: World Action Models bring the predictive capabilities of video models into robot action generation, providing a rich foundation for modeling future vis...

By Xuancheng Zhang, Xuetao Liu, Qianying Tang, Jizhe Wang, Zhijing Cheng, Bochen Lin, Haoran Wen, Ming Li, Kun Zhan, Yu Liu

llms agents diffusion robotics

arXiv Computer Vision

Sep 21

DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

arXiv:2609.21675v1 Announce Type: new Abstract: Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural...

By Wan Xu, Yuanfan Guo, Kevin Han, LaLa Chen, Wangmeng Zuo

llms reinforcement-learning multimodal benchmarks safety

arXiv Computer Vision

Sep 21

Info3R: Information-Adaptive Test-Time Training for 3D Reconstruction

arXiv:2609.21938v1 Announce Type: new Abstract: Transformer-based models have recently achieved strong performance on 3D reconstruction from images, and recent works extend them to process video stre...

By Sunghyun Baek, Hanna Bae, Minchan Kwon, Junmo Kim

llms computer-vision safety

arXiv Computer Vision

Sep 21

MintAct: A Unified Visual Agent for Digital Environments

arXiv:2609.22083v1 Announce Type: new Abstract: We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual too...

By Mingfei Gao, Rui Tian, Haiming Gang, Bohan Zhai, Le Zhang, Yuanzheng Gong, Di Feng, Ege \"Ozsoy, Kaixin Ma, Vishwesh Kirthivasan, O\u{g}uzhan Fatih Kar, Roman Bachmann, Anders Boesen Lindbo Larsen, Afshin Dehghan

llms agents reinforcement-learning multimodal benchmarks

arXiv Computation and Language

Sep 21

From Discharge Notes to Patient Understanding: Persona-Grounded, Open-Ended Simulation of LLMs as Discharge Educators

arXiv:2609.20827v1 Announce Type: new Abstract: Hospital discharge education is an interactive teaching task: a clinician adapts a discharge plan to a patient's literacy, recall, and personality. Exi...

By Won Seok Jang, Zonghai Yao, Hong Yu

llms agents

arXiv Computation and Language

Sep 21

Reviser: Revision-Capable Text Generation via Autoregressive Cursor Actions

arXiv:2609.20830v1 Announce Type: new Abstract: Revision-capable generation is appealing because it can insert or revise earlier content, but many non-autoregressive and edit-based approaches obtain...

By Sean Diab

llms diffusion benchmarks

arXiv Computation and Language

Sep 21

From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News

arXiv:2609.20838v1 Announce Type: new Abstract: In this study, we examine how modern LLMs generate and detect fake news under controlled settings across four manipulation scenarios. These are open-en...

By Zeynep \"Ozdemir, Murat Osmano\u{g}lu, Sevgi Yi\u{g}it-Sert, \"Omer \"Ozg\"ur Tanr{\i}\"over, Y{\i}lmaz Ar

llms robotics

arXiv Computation and Language

Sep 21

COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training

arXiv:2609.20842v1 Announce Type: new Abstract: Text-to-SQL translates natural-language questions into executable SQL queries, but open-source large language models still require task-specific post-t...

By Qifeng Cai, Xuanguang Pan, Hao Liang, Chang Xu, Wentao Zhang

llms reinforcement-learning fine-tuning data-engineering

arXiv Computation and Language

Sep 21

Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER

arXiv:2609.21663v1 Announce Type: new Abstract: Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equal...

By Hritika Sharma, Thibault Ba\~neras-Roux, Alessandra Pinto, Petr Motlicek, Hyunggu Jung, Esa\'u Villatoro-Tello, Somang Nam

llms multimodal benchmarks

arXiv Computation and Language

Sep 21

Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction

arXiv:2609.21595v1 Announce Type: new Abstract: In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-OCR correction, yet its effectiveness for Devanag...

By Abhishek Bhandari, Gaurav Harit

llms computer-vision fine-tuning benchmarks

arXiv Computation and Language

Sep 21

PRISM-BN: A Controlled Corpus and Benchmark for Text-to-Parameterized Bayesian Network Extraction

arXiv:2609.21673v1 Announce Type: new Abstract: Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure and probabilistic parameters, making them natural...

By Amartya Bhattacharya, Nikhil Singh, Neeti Pokhriyal, Soroush Vosoughi

llms benchmarks safety

arXiv AI

Sep 21

Efficient Benchmarking in Production: A Study of an Evolving LLM Agent

arXiv:2609.21267v1 Announce Type: new Abstract: Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun. We study efficient recurring evaluation f...

By Yining She, Lei Lin

llms agents benchmarks

arXiv AI

Sep 21

LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers

arXiv:2609.21492v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely r...

By Jingyu Hu, Shu Yang, Weiru Liu, Di Wang

llms fine-tuning benchmarks

arXiv AI

Sep 21

The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

arXiv:2609.21509v1 Announce Type: new Abstract: When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How m...

By Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella, Samy Bengio

llms fine-tuning

arXiv AI

Sep 21

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

arXiv:2609.20886v1 Announce Type: cross Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tab...

By Chuxuan Hu, Yeye He, Penny Zhou, Wee Hyong Tok, Daniel Kang, Surajit Chaudhuri

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 21

How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach?

arXiv:2609.21058v1 Announce Type: cross Abstract: Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a front...

By Gaurav Agarwal, Ashish Garg, Isha Singhal

llms rag

Get the daily briefing