model releases

common/peg : suppress incomplete escape sequences (#26780) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iO

model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r

arXiv:2608.07873v1 Announce Type: new Abstract: We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived obj

arXiv:2608.09231v1 Announce Type: new Abstract: Diffusion caching is a lightweight strategy that accelerates Diffusion Transformers (DiTs) by reusing intermediate features across denoising steps, but

arXiv:2608.08191v1 Announce Type: new Abstract: Multi-organ ultrasound segmentation remains challenging when anatomically adjacent structures must be delineated jointly, as localized boundary errors c

arXiv:2608.09617v1 Announce Type: new Abstract: Symbolic regression is the problem of finding an algebraic expression describing a stochastic dependence of a target variable on a set of inputs. Unlike

arXiv:2608.09888v1 Announce Type: cross Abstract: We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuou

arXiv:2511.22130v2 Announce Type: replace Abstract: To navigate ever-shifting real-world environments, agents must grapple with incomplete knowledge and adapt their strategies through experience. Howe

arXiv:2508.16481v3 Announce Type: replace Abstract: Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit. In this pa

arXiv:2608.09140v1 Announce Type: cross Abstract: Recent work on protecting privacy during user-LLM interactions often focuses on direct, explicit identifiers: the personally-identifiable information

arXiv:2608.09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expecte

arXiv:2512.05098v2 Announce Type: replace-cross Abstract: In recent years, Image Quality Assessment (IQA) for AI-generated images (AIGI) has advanced rapidly; however, existing methods primarily targe

arXiv:2508.04412v3 Announce Type: replace Abstract: The advent of large language models (LLMs) has sparked an evolution of autonomous web browsing agents: given a web browsing task and serialised user

arXiv:2608.08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs. We study wheth

arXiv:2603.12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge an

arXiv:2608.08459v1 Announce Type: cross Abstract: Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domain

arXiv:2608.09292v1 Announce Type: cross Abstract: Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. H

arXiv:2604.03159v2 Announce Type: replace-cross Abstract: Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive fi

arXiv:2608.09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effe

arXiv:2608.08182v1 Announce Type: cross Abstract: Machine learning models for MALDI-TOF mass spectrometry have shown considerable promise for clinical microbiology tasks such as microbial identificati

Security operations platform startup Blumira Inc. today launched Hearth, a vendor-agnostic artificial intelligence command center that lets security teams investigate and act across their existing too

arXiv:2603.24084v2 Announce Type: replace Abstract: Empirical evaluation in multi-objective search (MOS) has historically suffered from fragmentation, relying on heterogeneous problem instances with i

arXiv:2608.09510v1 Announce Type: cross Abstract: Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and re

Building Agent Skills and testing them is hard, but it doesn't have to be. Listen to Arjun Patel demo Cultivar, an open source tool developed at Pinecone to help benchmark agent skills in sandboxes. T

arXiv:2608.09296v1 Announce Type: new Abstract: A CAD model is not engineering-grade merely because it looks correct. It must satisfy design requirements, respond predictably to parameter changes, sup

Hi! I'm really obsessed with LLM hallucinations for the last 6 days 😭 I started by designing system prompts to attack hallucinations but failed, obviously. Now I tried reading logprobs and... I think

arXiv:2608.08536v1 Announce Type: new Abstract: Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient

arXiv:2608.08160v1 Announce Type: cross Abstract: The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. Howev

arXiv:2608.08634v1 Announce Type: new Abstract: Open-weight language models from Chinese AI labs caught up on benchmarks relative to proprietary frontier models in recent months. Yet their reliability

arXiv:2608.08744v1 Announce Type: cross Abstract: The carbon footprint of any deployed Large Language Model (LLM) accumulates during inference, where repeated use of the model substantially exceeds th

arXiv:2608.08392v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven

arXiv:2608.07809v1 Announce Type: new Abstract: A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong. We study both ha

arXiv:2603.24304v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) deliver strong performance on graph tasks, but their accuracy drops significantly under out-of-distribution (OOD)

For the 14th time, a Google product has hit 1 billion users. Google CEO Sundar Pichai posted on X that a billion people are using Gemini every month, and that Gemini is Google's fastest-growing produc

arXiv:2608.09124v1 Announce Type: new Abstract: Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job complet

arXiv:2608.09164v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms.

arXiv:2608.08336v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become the de facto standard for adapting Vision Transformers (ViTs) to downstream tasks. While parameter cou

arXiv:2608.09374v1 Announce Type: new Abstract: Electrical circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent topology, sel

Anthropic has pledged to start marking Claude-generated text and images with machine-readable data, in an effort to comply with European rules for AI transparency. 'Generated text will carry embedded

Claude's watermark probably doesn't work how you think. As the CTO of GPTZero, I'll explain how Anthropic, Google and OpenAI are building text watermarking in this brief explainer and whether it can b

arXiv:2608.07796v1 Announce Type: new Abstract: Large language models perform strongly on medical knowledge benchmarks, but reliable clinical deployment requires agents to conduct defensible investiga

arXiv:2608.09030v1 Announce Type: cross Abstract: What should a machine learning model learn when data is missing during training? We look at the learning process from a dynamical systems perspective,

arXiv:2608.07621v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primari

arXiv:2608.09139v1 Announce Type: new Abstract: Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly opt

arXiv:2608.09282v1 Announce Type: new Abstract: Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise

arXiv:2608.07570v1 Announce Type: cross Abstract: Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred. Existing crop-and-