Large language models

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

30,670 stories · RSS feed

arXiv AI

Jun 10

From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs

arXiv:2606. 10298v1 Announce Type: new Abstract: When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck.

By Runze Jiang, Taiqiang Wu, Yan Wang, Bingyu Zhu, Longtao Huang

llms

arXiv AI

Jun 10

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs

arXiv:2606. 10147v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can listen and see, but how do audio and visual signals actually travel through the network to shape an answer?

By Wish Suharitdamrong, Muhammad Awais, Xiatian Zhu, Sara Atito

llms multimodal safety

arXiv AI

Jun 10

Evaluating Research-Level Math Proofs via Strict Step-Level Verification

arXiv:2606. 10799v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs.

By Yifeng Sun

llms agents benchmarks safety

arXiv Machine Learning

Jun 10

Do LLMsMakeNeural Distinguishers Wise?

arXiv:2606. 10692v1 Announce Type: cross Abstract: Neural distinguishers are a cryptanalysis method for symmetric-key cryptography that trains machine learning models on pairs of plaintexts and ciphertexts with specific differences in order to recover a secret key.

By Tatsuya Sakagami, Masashi Hisai, Naoto Yanai

llms

arXiv AI

Jun 10

A Theory of Training Profit-Optimal LLMs

arXiv:2605. 16430v2 Announce Type: replace-cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure.

By Sophie Hao, William Merrill

llms

arXiv AI

Jun 10

Improving Topic Modeling by Distilling Soft Labels from Language Models

arXiv:2602. 17907v3 Announce Type: replace-cross Abstract: Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity.

By Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini

llms efficiency

arXiv Machine Learning

Jun 10

Time series forecasting from partial observations via Non-negative Matrix Factorization

arXiv:2102. 05314v2 Announce Type: replace Abstract: In modern time series problems, one aims at forecasting multiple time series with possible missing and noisy values.

By Yohann de Castro (ICJ, PSPM, CERMICS UMR 9032, ECL, IUF), Luca Mencarelli (CERMICS UMR 9032)

llms benchmarks

arXiv Machine Learning

Jun 10

Mechanistic Analysis of Alignment Algorithms in Language Models

arXiv:2606. 09850v1 Announce Type: new Abstract: Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations.

By Aarush Sinha, Ishan Garg, Veeraraju Elluru, Arth Singh, Kushal Garg

llms diffusion reinforcement-learning safety

arXiv Machine Learning

Jun 10

Operator Fusion for LLM Inference on the Tensix Architecture

arXiv:2606. 09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy that enhances data locality.

By Qingbo Wu, Ke Li, Wenzhu Wang, Jie Yu, Ruian Zhang, Lili Liu

llms

arXiv AI

Jun 10

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

arXiv:2606. 10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence.

By Zhi Zheng, Ziqiao Meng, Hao Luan, Wei Liu, Wee Sun Lee

llms rag nlp efficiency multimodal benchmarks

arXiv Machine Learning

Jun 10

DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction

arXiv:2606. 10243v1 Announce Type: new Abstract: Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems.

By Reazul Hasan Russel, Mingwei Tang, Rostam Shirani, Xinlong Liu, Navid Madani, Leo Ding, Yawen He, Xiangyu Wang, Mustafa Acar, Ashish Katiyar, Yuhai Li, Alan Yang, Metarya Ruparel, Derek Qiang Xu, Rupert Wu, Rui Yang, Liang Tao, Xinyi Zhao, Larry Zhang, Sri Reddy, Rob Malkin

llms rag

arXiv Machine Learning

Jun 10

PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning

arXiv:2606. 10369v1 Announce Type: cross Abstract: As large language models (LLMs) continue to scale, it becomes increasingly challenging to grow model capacity under fixed computation budgets.

By Xinyue Peng, Yi Qian, Jiaojiao Lin, Wenjian Shao, Yanming Liu

llms efficiency benchmarks

arXiv AI

Jun 10

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff

arXiv:2606. 09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training.

By Runze Liu, Jiashun Liu, Xu Wan, Yuqian Fu, Ling Pan

llms agents reinforcement-learning fine-tuning

arXiv AI

Jun 10

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning

arXiv:2606. 10532v1 Announce Type: new Abstract: Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks.

By Yunhan Jiang, Wenbin Duan, Shasha Guo, Liang Pang, Xiaoqian Sun, Huawei Shen

llms agents efficiency benchmarks

arXiv AI

Jun 10

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.

By Juncheng Diao, Zhicong Lu, Peiguang Li, Yongwei Zhou, Changyuan Tian, Qingbin Li, Rongxiang Weng, Jingang Wang, Xunliang Cai

llms agents nlp reinforcement-learning benchmarks

arXiv AI

Jun 10

Moonshine: An Autonomous Mathematical Research Agent Centered on Conjecture Generation

arXiv:2606. 10806v1 Announce Type: new Abstract: Moonshine is an autonomous agent whose central objective is to generate mathematical conjectures.

By Xiaoyang Chen, Xiang Jiang

llms agents

arXiv AI

Jun 10

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference

arXiv:2606. 09937v1 Announce Type: cross Abstract: We introduce RKSC (Reasoning-Aware KV Cache Sharing), a training-free inference framework that eliminates two structural redundancies in multi-branch LLM reasoning pipelines.

By Anirudh Sekar

llms fine-tuning efficiency benchmarks

arXiv AI

Jun 10

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

arXiv:2606. 11150v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data.

By Andrew Bo Liu, Samira Nedungadi, Bryce Cai, Alex Kleinman, Harmon Bhasin, Seth Donoughe

llms agents robotics benchmarks

arXiv AI

Jun 10

Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation

arXiv:2606. 10385v1 Announce Type: cross Abstract: On-policy distillation (OPD) has demonstrated strong empirical gains in enhancing complex reasoning in LLMs by aligning a student model with a teacher's predictive distribution over the student's own trajectories.

By Wenhao Zhang

llms fine-tuning efficiency

arXiv AI

Jun 10

Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community

arXiv:2606. 10159v1 Announce Type: cross Abstract: AI is increasingly used to support scientific peer review, from manuscript screening, reviewer assistance to editorial triage.

By Lin Li, Qi Zhang, Xander Davies, Jianing Qiu, Yarin Gal

llms robotics safety

Get the daily briefing