Search: “models”

arXiv:2607.06726v1 Announce Type: new Abstract: Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion fa

arXiv:2607.07708v1 Announce Type: cross Abstract: Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge

arXiv:2510.04547v5 Announce Type: replace-cross Abstract: Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-lang

arXiv:2211.14966v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are highly vulnerable to adversarial attacks. Ideally, a robust model should perform well on both perturbed training dat

arXiv:2512.11935v2 Announce Type: replace Abstract: Agentic AI systems increasingly connect large language models (LLMs) to external scientific tools, yet whether and when tool access improves predict

arXiv:2607.07538v1 Announce Type: new Abstract: Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics on the loss landscape, and a natural safety question is to

b9945 is a build-tagged release of llama.cpp, an open-source library that performs inference on large language models and is co-developed alongside the GGML tensor library. The llama.cpp project does

arXiv:2607.07267v1 Announce Type: cross Abstract: Claims about the universality of human concepts have been predominantly assessed through linguistic similarity across languages and cultures. However,

The race to build the fastest AI infrastructure is reshaping the semiconductor industry, with inference speed emerging as the defining competitive dimension of the AI era. As AI model wars intensify a

arXiv:2607.07129v1 Announce Type: new Abstract: Compositionality, by organizing complex behavior as combinations of simpler elements, enables robot learning that is scalable and data efficient. Levera

arXiv:2508.00554v4 Announce Type: replace-cross Abstract: In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy

arXiv:2607.07209v1 Announce Type: cross Abstract: Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interac

arXiv:2603.15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make in

arXiv:2607.06632v1 Announce Type: new Abstract: Adversarial attacks are crafted data manipulations that aim to deteriorate the outcomes of prediction or decision-making algorithms. In the energy syste

arXiv:2607.07178v1 Announce Type: cross Abstract: Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, exis

arXiv:2607.06648v1 Announce Type: cross Abstract: Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning

arXiv:2607.07478v1 Announce Type: cross Abstract: FFT-based spectral preprocessing of learned query-key (Q/K) projections substantially improves transformer attention on character-level language model

arXiv:2607.07321v1 Announce Type: new Abstract: Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks

arXiv:2607.06652v1 Announce Type: new Abstract: Rough path signatures are a universal feature map for continuous paths and, via the expected signature, characterise path distributions. These guarantee

arXiv:2607.07702v1 Announce Type: new Abstract: The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to d

arXiv:2607.06856v1 Announce Type: new Abstract: Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-a

Elon Musk announced progress updates on Grok, his AI assistant developed by xAI, likely highlighting improvements in the model's capabilities, training, or deployment. The post suggests ongoing develo

arXiv:2607.07233v1 Announce Type: new Abstract: Deep generative models offer a promising paradigm for topology optimization, enabling rapid design exploration. However, these approaches lack intrinsic

arXiv:2607.06972v1 Announce Type: new Abstract: Prompt-free adaptation of the Segment Anything Model (SAM) has emerged as a promising paradigm for automatic medical image segmentation. Existing method

Grok 4.5 is looking like a success with help from Cursor data but underneath the surface we expect future Grok/Cursor model training is likely to speed up in the coming months. We've spent several mon

arXiv:2304.03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural la

arXiv:2607.07034v1 Announce Type: cross Abstract: We introduce Intrinsic Green's Learning (IGL), a framework that models a target function on a manifold as the solution to a linear PDE whose source te

It seems like SpaceX/Grok and Meta/Muse have started to keep pace in the near-frontier category while also introducing a new category of cheap, fast & closed specialized coding models. Both were tied

arXiv:2607.06623v1 Announce Type: cross Abstract: Process industries rely on time-series forecasting and soft sensing to estimate quality variables that are hard to measure online. Labeled data are sc

arXiv:2607.06974v1 Announce Type: new Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in

arXiv:2607.07383v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic kn

Modal is a cloud computing platform that provides serverless infrastructure for running Python code at scale, enabling developers to execute functions, train machine learning models, and process data

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on @huggingface. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context

arXiv:2607.07368v1 Announce Type: cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single

Muse Spark 1.1 has been released and is now accessible through Vercel's AI Gateway, representing an update to the Muse Spark model or service. This release likely includes performance improvements, ne

arXiv:2607.06678v1 Announce Type: new Abstract: How can pretrained Vision-Language-Action (VLA) models retain long-horizon visual histories with high-frequency updates without sacrificing efficiency?

arXiv:2510.02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with

arXiv:2607.07023v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinfor

arXiv:2607.06655v1 Announce Type: cross Abstract: In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action pre

Unified identity security platform provider Permiso Security Inc. today launched the Risk Score Engine, a model that assigns continuous, multidimensional risk scores to every human, machine and artifi

arXiv:2503.15770v3 Announce Type: replace-cross Abstract: Depth foundation models (DFMs) offer strong learned priors for 3D perception from single RGB images but lack physical depth cues, leading to a

POV: you're in SF during a once-in-a-generation shift in technology. You just graduated, or you came out for the summer. AI billboards everywhere, models getting smarter every week, equal parts exciti

arXiv:2601.00086v3 Announce Type: replace Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or

arXiv:2607.06909v1 Announce Type: new Abstract: Despite rapid advances in chest X-ray (CXR) foundation models, most radiology report generation (RRG) systems still rely on heavily downsampled inputs (

arXiv:2603.00127v2 Announce Type: replace Abstract: X-Ray Computed Tomography (XCT) is a compelling tool in experimental mechanics, capable of non-destructively extracting information pertaining to th

arXiv:2607.06949v1 Announce Type: new Abstract: Training robust handwriting recognition (HTR) systems requires massive amounts of annotated data, which is often difficult to acquire. While synthetic h