Search: “models”

Role Steering of Language Models for Social Simulations

arXiv:2608.00023v1 Announce Type: new Abstract: Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated populat

4 Aug 2026

Self-Improving Large Language Models via Progressive Experience Evolution

DGX agent

arXiv:2608.02139v1 Announce Type: new Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transformin

safetyarxiv-cs-cl

4 Aug 2026

A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging

arXiv:2607.28858v1 Announce Type: cross Abstract: Automatic brain tumor segmentation from magnetic resonance imaging (MRI) has become a fundamental task in computer-assisted diagnosis, treatment plann

COSI-Lab: Conference Living Lab for Modeling Multi-Perspective Multimodal Social Intention

arXiv:2607.28649v1 Announce Type: cross Abstract: COSI-Lab presents a multimodal, multi-sensor dataset of an interdisciplinary scientific workshop containing 32 academics at an international conferenc

Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations

model-releasesarxiv-cs-lg

arXiv:2607.28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. AC

Tutorials

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

arXiv:2607.29235v1 Announce Type: cross Abstract: Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands

tutorialsarxiv-cs-ai

Ling-3.0-flash is another potential model to test before qwen3.8 27b

model-releasesr-localllama

I tested Ling-3.0-flash with hard bugs and it fixed bugs that qwen3.6-27b could not. This models speed faster than deepseek v4 flash but almost the same level as (old) deepseek v4 flash. Note: hard bu

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structured data directly from your PDFs: form fiel…

model-releasesllamaindex--x

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structured data directly from your PDFs: form field values, checkbox states, annotations, embedded images, vec

Industry

Instead of limiting the progress of AI companies or preventing them from releasing models as proposed in the bipartisan AI Kill Switch Act, …

Instead of limiting the progress of AI companies or preventing them from releasing models as proposed in the bipartisan AI Kill Switch Act, Hugging Face CEO Clément Delague says he would rather see Co

industryclem-delangue--x

2 Aug 2026

LLMs can know a task is impossible and still optimize it anyway. Ask whether to walk or drive to a car wash 50 meters away, and some models …

LLMs can know a task is impossible and still optimize it anyway. Ask whether to walk or drive to a car wash 50 meters away, and some models focus on distance while missing that the car itself must rea

safetygary-marcus--x

2 Aug 2026

Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation

model-releasesarxiv-cs-cv

arXiv:2607.27856v1 Announce Type: new Abstract: Few-shot medical image segmentation (FS-MIS) aims to segment novel regions of interest (ROIs) from a few annotated support examples. Despite rapid progr

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars c…

model-releasesnous-research--x

**DeepSeek V4 Flash 0731 Performance Test** On July 31 2026, a single prompt executed via the Hermes Agent on DeepSeek V4 Flash 0731 completed in 32 minutes and incurred an estimated cost of 0.07 USD.

Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models

arXiv:2607.26588v1 Announce Type: new Abstract: The rapid development of large language models (LLMs) has renewed interest in agent-based modeling (ABM). However, current LLM-based ABM research faces

safetyarxiv-cs-ai

I have trained a model to predict my blood sugar [P]

model-releasesr-machinelearning

It's an encoder-only transformer that consumes past(blood glucose + carbs + insulin) and future(carbs + insulin) and predicts future blood glucose for the next 2 hours. Announced meals and boluses/bas

ORCA-bench: How Ready Are Language Model Agents for Oncall?

arXiv:2607.28545v1 Announce Type: new Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics,

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

arXiv:2607.28362v1 Announce Type: new Abstract: We present ShadowDancer, a novel approach to any-action, frame-level control of interactive video world models. The obstacle is representational: existi

researcharxiv-cs-cv

Sources: OpenAI demoed a new 'Astra' AI model family to US policymakers and regulators this week, touting its improved abilities to complete long-running tasks (The Information)

The Information: Sources: OpenAI demoed a new “Astra” AI model family to US policymakers and regulators this week, touting its improved abilities to complete long-running tasks — OpenAI is preparing t

model-releasestechmeme

(Towards) Scalable Reliable Automated Evaluation with Large Language Models

arXiv:2607.28282v1 Announce Type: new Abstract: Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive. Existing automated

researcharxiv-cs-cl

We've gotten some great medium sized models lately (DSV4 Flash 0731, Inkling Small, Laguna S 2.1, Step 3.7 Flash) but does anybody else want to see some new 70-80b contenders?

model-releasesr-localllama

I can run the mediums, but sometimes I want a faster option that's smarter than Qwen 27B/35B. On my hardware I get like 500 to 800 tok/s prefill and 16 to 22 tok/s gen on ~120B class models, which is

Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering

arXiv:2607.26411v1 Announce Type: new Abstract: Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture, yet it remains unclear whether these capabi

safetyarxiv-cs-cv

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

arXiv:2607.27077v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often

researcharxiv-cs-lg

GPT-5.6 found optimizations that 'reduced end-to-end serving costs by 20%' for OpenAI to serve that model Presumably that's billions of doll…

model-releasessimon-willison--x

GPT-5.6 found optimizations that 'reduced end-to-end serving costs by 20%' for OpenAI to serve that model Presumably that's billions of dollars a month in savings at this point? Codex analysed product

Local Ai

MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

arXiv:2607.26554v1 Announce Type: new Abstract: Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images gene

local-aiarxiv-cs-cv

one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infr…

one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel

safetyfireworks-ai--x

WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models

model-releasesarxiv-cs-cv

arXiv:2607.26203v1 Announce Type: new Abstract: Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data. Despite its imp

Local Ai

Beyond Counts: A Distributional Robustness Margin For Pathology Foundation Models

arXiv:2607.25497v1 Announce Type: cross Abstract: Pathology foundation models are approaching clinical deployment, yet remain vulnerable to systematic non-biological variation across centres. Differen

local-aiarxiv-cs-ai

BREAKING: Grok 4.5 just claimed the top spot on the new HighWalk Benchmark. The independent test measures how well AI models update real tec…

model-releaseselon-musk--x

BREAKING: Grok 4.5 just claimed the top spot on the new HighWalk Benchmark. The independent test measures how well AI models update real technical specifications from 46 Laravel commits — heavy on cod

Applications

Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?

arXiv:2607.25929v1 Announce Type: cross Abstract: Deep generative models (DGMs) are widely used for complex high-dimensional data and increasingly applied to spatial and spatio-temporal modeling. Thei

applicationsarxiv-cs-lg

Diffusion Model-based Parameter Estimation in Dynamic Power Systems

arXiv:2411.10431v3 Announce Type: replace Abstract: Parameter estimation, which represents a classical inverse problem, is often ill-posed as different parameter combinations can yield identical outpu

Dual-Domain Manifold Modeling for Hyperspectral Image Fusion

arXiv:2607.25338v1 Announce Type: new Abstract: Achieving a coherent integration of spectral richness and spatial fidelity remains a central objective in hyperspectral image fusion. However, existing

Forensic Reproducibility Audit of a Radiology Vision-Language Model Benchmark: From Intended Protocol to Released Artifact

arXiv:2607.25589v1 Announce Type: cross Abstract: Medical-imaging AI benchmarks combine datasets, DICOM rendering, prompts, provider APIs, automated labels, statistical code, manuscripts, and reposito

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context

arXiv:2607.25375v1 Announce Type: new Abstract: India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recogniz

Medical world models in healthcare: foundations, applications, and challenges for trustworthy clinical translation

arXiv:2607.25242v1 Announce Type: new Abstract: Medical world models offer a framework for extending medical artificial intelligence beyond static prediction by representing evolving patient states an

safetyarxiv-cs-cv

Memory for Large Language Models

arXiv:2607.25380v1 Announce Type: new Abstract: Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an implicit byproduct of computation to a

MyoCardBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios

arXiv:2607.25186v1 Announce Type: new Abstract: Background: Most medical large language model (LLM) benchmarks focus on examination knowledge or isolated tasks and may not reflect the longitudinal, mu

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

model-releasesarxiv-cs-cv

arXiv:2607.24957v1 Announce Type: new Abstract: We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Model

RDQ: Residual Distribution Quantization for Large Language Models

model-releasesarxiv-cs-lg

arXiv:2607.10137v2 Announce Type: replace Abstract: Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision. We identify the root cause as residual stream dist

RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation

arXiv:2607.24810v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on general remote sensing tasks. However, their capability for rare scenes remains insuff

Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models

arXiv:2603.05147v2 Announce Type: replace Abstract: Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through reasoning techniques. While effect

researcharxiv-cs-cv

Concept-based Visual Counterfactual Explanations with Diffusion Models

arXiv:2607.22544v1 Announce Type: new Abstract: Visual counterfactual explanations aim to answer 'what minimal change to this image would flip the model's prediction?', and are increasingly important

safetyarxiv-cs-ai

Local Ai

Development of Vision-Language Model-based GNSS Spoofing Detection for Autonomous Vehicle Navigation

arXiv:2607.23962v1 Announce Type: new Abstract: Autonomous vehicles (AVs) depend on Global Navigation Satellite Systems (GNSS) for localization and navigation, making them vulnerable to spoofing attac

local-aiarxiv-cs-cv

Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions

arXiv:2507.07008v2 Announce Type: replace Abstract: Used as priors for Bayesian inverse problems, diffusion models have recently attracted considerable attention in the literature. Their flexibility a

researcharxiv-cs-lg

Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration

arXiv:2607.23538v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), their ability to generate empathetic mental health counseling responses in low-resource languag

How OpenAI hacked HuggingFace. What we know. Hugging Face proved that open platforms and open models can still win those battles when the al…

model-releasesclem-delangue--x

How OpenAI hacked HuggingFace. What we know. Hugging Face proved that open platforms and open models can still win those battles when the alternative is locked-down systems that refuse to assist their

Hybrid AI-Physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study

arXiv:2504.08909v2 Announce Type: replace Abstract: Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit syst

safetyarxiv-cs-ai

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data

arXiv:2607.24422v1 Announce Type: new Abstract: This paper presents a summary of the Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data (AFMFR), held at the 2

safetyarxiv-cs-cv

LEDOM: Reverse Language Model

arXiv:2507.01335v4 Announce Type: replace-cross Abstract: Autoregressive language models are trained exclusively left-to-right. We explore the complementary factorization, training right-to-left at sc

researcharxiv-cs-ai

LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models

arXiv:2411.00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as