Large language models

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

31,367 stories · RSS feed

arXiv AI

Jun 4

AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety

arXiv:2606. 04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.

By Yanjing Ren, Reza Ebrahimi, TengTeng Ma

llms robotics benchmarks safety

arXiv AI

Jun 4

Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning

arXiv:2605. 28829v2 Announce Type: replace-cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics.

By Ritvik Rastogi, Vishal Singh, Tejas Chaudhari, Sandeep Varma

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 4

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

arXiv:2606. 04302v1 Announce Type: cross Abstract: Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens.

By Haocheng Xia, Mihir Pamnani, Hanxi Fang, Supawit Chockchowwat, Yongjoo Park

llms rag efficiency benchmarks

arXiv Machine Learning

Jun 4

In-Context Graphical Inference

arXiv:2606. 05042v1 Announce Type: new Abstract: Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative approximations (Belief Propagation, variational methods) sacrifice convergence guarantees on frustrated topologies.

By Zehua Cheng, Wei Dai, Jiahao Sun

llms benchmarks safety

arXiv Machine Learning

Jun 4

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning

arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.

By Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah

llms efficiency multimodal benchmarks

arXiv Machine Learning

Jun 4

CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts

arXiv:2606. 04661v1 Announce Type: cross Abstract: Prompts tuned for accuracy often grow long, raising inference cost on every model call.

By Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata, Parag Agrawal, Yova Kementchedjhieva, Manish Gupta

llms benchmarks

arXiv AI

Jun 4

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data

arXiv:2601. 15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought).

By Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen

llms reinforcement-learning

arXiv AI

Jun 4

HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series

arXiv:2605. 11130v4 Announce Type: replace-cross Abstract: Critical events in multivariate time series, from turbine failures to cardiac arrhythmias, demand accurate prediction, yet labeled data is scarce because such events are rare and costly to annotate.

By Jonas Petersen, Gian-Alessandro Lombardi, Riccardo Maggioni, Camilla Mazzoleni, Federico Martelli, Philipp Petersen

llms rag benchmarks

arXiv AI

Jun 4

Stochastic Sparse Attention for Memory-Bound Inference

arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.

By Kyle Lee, Corentin Delacour, Kevin Callahan-Coray, Kyle Jiang, Can Yaras, Samet Oymak, Tathagata Srimani, Kerem Y. Camsari

llms efficiency

arXiv Machine Learning

Jun 4

Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning

arXiv:2601. 07408v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks.

By Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

Interfaze: The Future of AI is built on Task-Specific Small Models

arXiv:2602. 04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder through a shared embedding space.

By Harsha Vardhan Khurdula, Vineet Agarwal, Yoeven D Khemlani

llms rag computer-vision multimodal benchmarks

arXiv AI

Jun 4

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.

By Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang

llms safety

arXiv AI

Jun 4

Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification

arXiv:2606. 04037v1 Announce Type: new Abstract: Pre-deployment verification of enterprise artificial intelligence (AI) agents remains a critical gap between large language model (LLM) capability benchmarking and production deployment.

By Thanh Luong Tuan, Abhijit Sanyal

llms rag agents benchmarks safety

arXiv AI

Jun 4

Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs

arXiv:2506. 10630v3 Announce Type: replace-cross Abstract: To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures.

By Yitong Zhou, Yucong Luo, Mingyue Cheng, Qi Liu, Jiahao Wang, Daoyu Wang, Enhong Chen

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 4

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization

arXiv:2505. 11166v3 Announce Type: replace-cross Abstract: Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by data quality issues, training inefficiencies, and the lack of well-designed optimization objectives.

By Huashan Sun, Shengyi Liao, Yansen Han, Yu Bai, Yang Gao, Cheng Fu, Weizhou Shen, Fanqi Wan, Ming Yan, Ji Zhang, Fei Huang

llms benchmarks safety data-engineering

arXiv AI

Jun 4

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

arXiv:2606. 04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-width uniformly across all layers is sub-optimal in terms of both performance and accuracy.

By Giuseppe Franco, Ian Colbert, Pablo Monteagudo-Lago, Felix Marty, Nicholas Fraser

llms efficiency benchmarks

arXiv Machine Learning

Jun 4

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.

By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang

llms fine-tuning safety

arXiv Machine Learning

Jun 4

Bypassing Prompt Guards in Production with Controlled-Release Prompting

arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.

By Jaiden Fairoze, Sanjam Garg, Keewoo Lee, Mingyuan Wang

llms safety

arXiv AI

Jun 4

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data

arXiv:2606. 04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation.

By Devleena Das, Rajeev Patwari, Elliott Delaye, Ashish Sirasao

llms fine-tuning efficiency benchmarks

arXiv AI

Jun 4

Rollout-Level Advantage-Prioritized Experience Replay for GRPO

arXiv:2606. 04560v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards with GRPO is a standard approach for post-training reasoning LLMs.

By Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang, Ik-hwan Kim, Sungroh Yoon

llms reinforcement-learning benchmarks

Get the daily briefing