Large language models

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

32,584 stories · RSS feed

arXiv AI

Sep 15

EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse

arXiv:2609.15161v1 Announce Type: cross Abstract: Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strate...

By Dongsheng Shi, Yue Li, Xin Yi, Linlin Wang

llms agents benchmarks

arXiv Computer Vision

Sep 15

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

arXiv:2609.13814v1 Announce Type: new Abstract: Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and li...

By Ruixiang Zhao, Hualei Wang, Renhe Sun, Enzhi Zhou, Jincenzi Wu, Xujie Song, Kexin Shi, Zihang Liu, Pengcheng Zhu, Jiayi Zhou, Baoyue Zhang, Changhao Zhang, Zitong Wang, Jinhong Wang, Tong Niu, Jingjing Liu, Junan Lin, Haolin He, Hengshuo Chu, Yuhui Chen, Jian Liu, Yuge Huang, Junliang Xing, Yuntao Wang, Weiqiang Wang, Chun Yu, Yuanchun Shi

llms nlp multimodal benchmarks

arXiv Computer Vision

Sep 15

StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models

arXiv:2609.13804v1 Announce Type: new Abstract: Visual prefixes account for a major portion of the per-layer computation in multimodal large language models (MLLMs), making visual-token pruning a dir...

By Hansen Zhang, Landi He, Mingde Yao, Lijian Xu

llms efficiency multimodal

arXiv Computer Vision

Sep 15

DiVA: Enabling Interactive Digital Life Simulation via Video Models

arXiv:2609.13830v1 Announce Type: new Abstract: We present DiVA, a deeply interactive digital life simulator pioneering a new paradigm for long-term, open-ended interactive experiences within digital...

By Cheng Chen, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Wen Wang, Yihao Meng, Hanlin Wang, Yixuan Li, Jiacheng Wei, Zhenshan Tan, Yanhong Zeng, Yujun Shen, Guosheng Lin, Fayao Liu

llms multimodal

arXiv Computer Vision

Sep 15

Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding

arXiv:2609.13991v1 Announce Type: new Abstract: Reconstructing 3D objects from brain signals offers a promising avenue for understanding human visual cognition. While prior work has shown initial suc...

By Yongyi Lu, Xiongfeng Huang, Zhijing Yang

llms diffusion benchmarks safety

arXiv Computer Vision

Sep 15

Parameter-Efficient Fine-Tuning of Foundation Models for Liver Tumor Segmentation in CT

arXiv:2609.14106v1 Announce Type: new Abstract: We evaluated parameter-efficient fine-tuning (PEFT) of the Segment Anything Model (SAM) for liver tumor segmentation in abdominal CT of colorectal live...

By Ramtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples, Richard K. G. Do, Amber L. Simpson

llms computer-vision fine-tuning efficiency

arXiv AI

Sep 15

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception

arXiv:2609.15215v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal percept...

By Yanfeng Shi, Yan Song, Junhui Li, Tinggan Huang, Wu Guo, Haoyu Song, Ian McLoughlin

llms benchmarks

arXiv Computer Vision

Sep 15

SPARK: Representation-Level KV Memory Alignment for Safer Vision-Language Models

arXiv:2609.14258v1 Announce Type: new Abstract: Vision-language models (VLMs) remain vulnerable to jailbreaks that distribute harmful intent across text and images, making unimodal safety mechanisms...

By Mohd Azfar, Izhar Dad Khan

llms multimodal safety data-engineering

arXiv Computer Vision

Sep 15

Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education

arXiv:2609.14284v1 Announce Type: new Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Th...

By Md Khalid Syfullah, Asif Hasan Tonmoy, Saad Ahmed, S. M. Jahangir Alam

llms fine-tuning multimodal

arXiv Computer Vision

Sep 15

Two-Stage Mixture-of-LoRA for Multi-Task Medical Vision-Language Learning

arXiv:2609.14350v1 Announce Type: new Abstract: Medical vision-language models (VLMs) allow a single model to perform clinical image analysis tasks ranging from diagnosis classification to report gen...

By Zhanghao Chen, Yuanyuan Li, Zhenyu Lu, Shuo Gao, Guangquan Zhou, Yikun Zhang

llms fine-tuning multimodal

arXiv Computer Vision

Sep 15

From Density to Biopsy Decisions and Malignancy Prediction: A Benchmark Study of Multimodal Large Language Models Against Radiologists in Digital and Contrast-Enhanced Mammography

arXiv:2609.14676v1 Announce Type: new Abstract: Purpose: To compare four multimodal large language models (MLLMs) with radiologists of varying expertise in breast density assessment, BI-RADS assessme...

By Ali Abbasian Ardakani, Afshin Mohammadi, Taha Yusuf Kuzan, Beyza Nur Kuzan, Alisa Mohebbi, Masume Behruzi, Hamid Khorshidi, Ashkan Ghorbani, Elham Asadiara, Zeinab Khorshidi Lotfi, Ansar Rahman, Nedim Christoph Beste, U. Rajendra Acharya, Sepideh Hatamikia

llms multimodal benchmarks data-engineering

arXiv Computer Vision

Sep 15

Zero-shot video highlight detection based on text descriptions and synthetic images

arXiv:2609.14790v1 Announce Type: new Abstract: Detecting video highlights, the most informative or engaging moments in a video, is important for applications such as video summarization and content...

By Michal Byra, Alberto Presta, Grzegorz Stefanski, Krzysztof Arendt

llms diffusion nlp

arXiv Computer Vision

Sep 15

Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed Cameras

arXiv:2609.15032v1 Announce Type: new Abstract: Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either r...

By Hanzhang Tu, Zhanfeng Liao, Wei Min, Jiajun Zhang, Yebin Liu

llms efficiency benchmarks safety

arXiv Computer Vision

Sep 15

V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments

arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particu...

By Ziqian Fan, Shibo Xu, Junjie Li, Xiangyu Zhao, Shengyuan Ding, Yifan Yang, Zhenjie Yang, Haodong Duan, Yue Zhou, Zhihang Zhong, Xue Yang

llms agents multimodal benchmarks

arXiv Computer Vision

Sep 15

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

arXiv:2609.15810v1 Announce Type: new Abstract: Diffusion Transformers deliver state-of-the-art video generation, but their long spatiotemporal sequences make attention the dominant deployment cost,...

By Xingyang Li, Dongyun Zou, Shining Zhang, Jiacheng Chen, Haocheng Xi, Lvmin Zhang, Jun-Yan Zhu, Song Han, Zhekai Zhang, Yujun Lin, Muyang Li

llms diffusion efficiency benchmarks

arXiv Computer Vision

Sep 15

UniqueShip: Mitigating Data Leakage in Acoustic Ship Classification Benchmark Datasets

arXiv:2609.13659v1 Announce Type: cross Abstract: Underwater Acoustic Target Recognition (UATR) of ships is well-suited for machine learning, yet its progress is hindered by the lack of large, divers...

By Connor Hashemi, Trevor Stout, Anthony Hoogs, Jason Parham

llms benchmarks

arXiv Computer Vision

Sep 15

Multi4D: an end-to-end neural network for structural determination at complex material interfaces

arXiv:2609.14348v1 Announce Type: cross Abstract: Heterogeneous interfaces dictate the performance and degradation of functional materials, making it essential to link local structural variations wit...

By Haoran Zhang, Zian Mao, Shufen Chu, Xiaoya He, Yuyan Guan, Antong Yang, Mingze Li, Xiaoqin Zeng, Yujun Xie

llms diffusion

arXiv AI

Sep 15

Enemray: Toward Capable Language Models for Hassaniya

arXiv:2609.14829v1 Announce Type: cross Abstract: We introduce Enemray, a Hassaniya-centric language model that enables general-purpose interaction in Hassaniya. Enemray is trained around a stability...

By Cheikh Ahmed

llms agents safety

arXiv AI

Sep 15

An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

The paper introduces a modular correction framework for large language models that uses Activated LoRA adapters and a context-aware routing mechanism to mitigate harmful outputs. By allowing expert adapters to activate mid-sequence without invalidating the KV cache, the system achieves low-latency, targeted correction during generation. Experiments show improved alignment on safety benchmarks while maintaining task performance, presenting a lightweight, scalable approach to safer LLM deployments.

By Roberto Campbell, Momin Abbass, Muneeza Azmat, Michal Ulewicz, Raya Horesh, Kristjan Greenewald, Rog\'erio Abreu de Paula, Nathalie Baracaldo

llms fine-tuning efficiency benchmarks safety

arXiv AI

Sep 15

A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrolled Mandarin Kinship Speech Dataset

arXiv:2609.14145v1 Announce Type: cross Abstract: Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTR...

By Qiyang Sun, Langqing Zhang, Yupei Li, Bj\"orn Schuller

llms multimodal benchmarks

Get the daily briefing