Search: “models”

Simultaneous Coverage and Efficiency Guarantee in Online Conformal Prediction

arXiv:2607.26577v1 Announce Type: new Abstract: Adaptive conformal inference (ACI) of Gibbs and Cand{es and its variants are the standard approach to online conformal prediction under distribution shi

Model Releases

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

DGX agent

arXiv:2607.26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a tw

model-releasesarxiv-cs-lg

30 Jul 2026

The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text

arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of in

safetyarxiv-cs-cl

Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs

arXiv:2607.27122v1 Announce Type: new Abstract: Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model must

safetyarxiv-cs-cv

Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection

arXiv:2607.27113v1 Announce Type: new Abstract: The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generat

safetyarxiv-cs-cv

When benchmark inferences do not compose: Projectibility in AI evaluation

arXiv:2607.26159v1 Announce Type: cross Abstract: An AI benchmark result rarely reaches a consequential claim in one step. Evaluators generalize it to further cases, interpret it as evidence of capabi

Why not Ollama Cloud for Opencode?

I see a lot of discussion here about best subscriptions or APIs to get. Most of them comes almost always back to DeepSeek API for Flash, Opencode Go and Codex Plus. I have the combo Ollama Cloud + Ope

model-releasesr-ollama

Yesterday I cohosted a dinner with @dexhorthy with a wonderful group of founders, to talk about agent loops and loop engineering. Some inter…

model-releasesjerry-liu--x

Yesterday I cohosted a dinner with @dexhorthy with a wonderful group of founders, to talk about agent loops and loop engineering. Some interesting insights: * Most of our group was *not* actively usin

Adding a custom MCP server to Claude and ChatGPT

model-releasessimon-willison

TIL: Adding a custom MCP server to Claude and ChatGPT Connecting a custom MCP server to Claude and ChatGPT's standard chat interfaces is possible, but can take quite a few steps. Tags: ai, generative-

Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings

arXiv:2607.24814v1 Announce Type: new Abstract: Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in

Tutorials

Analysis of the Shortcut Learning and Clever Hans Effect in CNN based ECG Image Classification

arXiv:2607.25117v1 Announce Type: cross Abstract: Deep learning models for ECG image classification may achieve high accuracy by exploiting non-physiological visual cues instead of ECG waveform morpho

tutorialsarxiv-cs-ai

Applications

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

arXiv:2607.25852v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best

applicationsarxiv-cs-cl

Automate data monitoring and root-cause analysis with Looker Agentic Workflows

model-releasesgoogle-cloud-ai

Traditional business intelligence alerts can only tell you that a metric changed, leaving data analysts to manually hunt through dashboards to figure out why. Today, we are introducing Looker Agentic

Automated Modernization of Machine Learning Engineering Notebooks for Reproducibility

arXiv:2602.07195v2 Announce Type: replace-cross Abstract: Interactive computational notebooks (e.g., Jupyter notebooks) are widely used in machine learning engineering (MLE) to program and share end-t

AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities

arXiv:2607.24821v1 Announce Type: cross Abstract: While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modali

b10181

model-releasesllama-cpp-releases

ggml-cuda : disable MMQ on devices with less than 48 KiB shared memory (#26141) ggml_cuda_should_use_mmq() selects MMQ purely from the quantization type. The current MMQ configurations are designed an

Balancing multiscale similarity and cartographic constraints: A similarity-driven optimization framework for line generalization

arXiv:2607.25474v1 Announce Type: new Abstract: Cartographic generalization is essential for generating multiscale map representations by balancing information preservation and cartographic readabilit

Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation

arXiv:2607.25622v1 Announce Type: new Abstract: Personalized person image generation requires preserving subject identity across both local facial details and broader appearance cues. Existing methods

Beyond 'What to Retrieve': Uncertainty in Retrieval-Augmented Code Generation

arXiv:2607.24884v1 Announce Type: cross Abstract: Repository-level code generation relies on heterogeneous evidence whose relevance, compatibility, and completeness are inherently uncertain. Similar-c

Local Ai

Bought a 5090 to escape API fees. Ended up building a mini datacenter. Sound familiar?

I bought an RTX 5090 last year just to run 27B models natively. I even fine-tuned it with my own data using LoRA, building RAGs and was pretty damn happy with the results at first. But, Q8 quantizatio

local-air-localllama

CD-RMOT-Bench: Benchmarking the Cross-Domain Referring Multi-Object Tracking

arXiv:2607.25239v1 Announce Type: new Abstract: Referring multi-object tracking (RMOT) extends tracking from category-driven perception to language-guided understanding by grounding object trajectorie

CogEEGAgent: Toward Autonomous Cognitive EEG Analysis with Grounded Execution and Selection-Aware Verification

arXiv:2607.25045v1 Announce Type: new Abstract: Electroencephalography (EEG) analysis in cognitive studies requires specialized expertise and involves many defensible choices over contrasts, channels,

DeepSeek V4 Flash isn't just for inference anymore. Fine-tune it on Fireworks with supervised fine-tuning, preference tuning, and combined p…

model-releasesfireworks-ai--x

DeepSeek V4 Flash isn't just for inference anymore. Fine-tune it on Fireworks with supervised fine-tuning, preference tuning, and combined preference optimization from the managed UI. Reinforcement le

DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome

arXiv:2511.09026v2 Announce Type: replace-cross Abstract: Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood. Despite recen

researcharxiv-cs-ai

DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization

arXiv:2607.24856v1 Announce Type: cross Abstract: Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response. Un

DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories

arXiv:2607.25864v1 Announce Type: new Abstract: Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs

researcharxiv-cs-lg

Applications

Explainable AI for Chronic Kidney Disease Prediction Using Simulated Federated Learning

arXiv:2607.25348v1 Announce Type: cross Abstract: Chronic Kidney Disease (CKD), characterized by the gradual loss of kidney function, remains a significant public health challenge. Early detection is

applicationsarxiv-cs-ai

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding

arXiv:2607.25266v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of

researcharxiv-cs-cv

Local Ai

i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the m…

i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and

local-ainous-research--x

Learning from 53.6K Real-World Developer Edits of AI-Generated Code

arXiv:2607.25130v1 Announce Type: cross Abstract: Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant

Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization

arXiv:2607.25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence se

Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension

arXiv:2607.24887v1 Announce Type: cross Abstract: Existing theories of neural-network width characterize asymptotic limits, but provide limited guidance on whether an expansion direction identified fr

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

arXiv:2607.25891v1 Announce Type: new Abstract: Evaluating AI agents in interactive environments is hindered by fragmented tasks, scaffolds, verifiers, and scoring rules. Existing efforts focus on nar

ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correction

arXiv:2607.25210v1 Announce Type: new Abstract: Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to signi

Local Ai

Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility

arXiv:2607.25148v1 Announce Type: new Abstract: Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water

local-aiarxiv-cs-lg

Predictive Control for Driving under Uncertain Road Geometry Estimated from Onboard Vision

arXiv:2508.02494v2 Announce Type: replace-cross Abstract: Autonomous vehicles driving on unknown roads must estimate the road geometry from onboard sensors and follow the resulting reference while res

safetyarxiv-cs-ro

Probabilistic Symbolic Regression for Equation Discovery via Operator-induced and Regularized Symbolic Forests

arXiv:2509.19710v2 Announce Type: cross Abstract: Symbolic regression has emerged as a powerful tool for artificial intelligence-driven scientific discovery by learning interpretable analytical expres

RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection

arXiv:2607.25392v1 Announce Type: new Abstract: We introduce RDVSv2, a large-scale benchmark for RGB-D video salient object detection (RGB-D VSOD) with dense frame-level annotations. Existing datasets

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension

arXiv:2512.06276v3 Announce Type: replace-cross Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Exis

Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes

arXiv:2601.20043v2 Announce Type: replace Abstract: Standard Bayesian Optimization (BO) assumes uniform smoothness across the search space an assumption violated in multi-regime problems such as molec

Research Report on Noise-Shaped One-Bit Coefficients in Discrete Polynomial Fourier Extension

model-releasesarxiv-cs-cl

arXiv:2607.24868v1 Announce Type: new Abstract: This report studies noise-shaped one-bit coefficients in normalized discrete polynomial Fourier extension. For first-order Sigma-Delta quantization, the

Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning

arXiv:2607.25299v1 Announce Type: cross Abstract: Optimization over the Stiefel manifold plays a significant role in various machine learning tasks. Existing methods either use the retraction operator

Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm

arXiv:2607.26001v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) aims to improve generalization by encouraging insensitivity to small, worst-case parameter perturbations. However, th

Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA

arXiv:2607.26052v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts k. Tokens differ in how uncertain the mod

The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance

arXiv:2607.24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant informa

researcharxiv-cs-ai

Agents

The LAIA Dataset: Labelled Attention for Intelligent Automobiles

arXiv:2607.25570v1 Announce Type: cross Abstract: The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of s

agentsarxiv-cs-ai

The number of times I have had to tell Opus 5 and Fable 5 to talk to me like an excited teenager and not a computer science phd is high. Was…

model-releasesallie-k--miller--x

The number of times I have had to tell Opus 5 and Fable 5 to talk to me like an excited teenager and not a computer science phd is high. Was going through a Google auth thing and got multiple paragrap

Thrilled to have @gabepereyra speak at our @sequoia event tmrw on OWN YOUR AI: how to build your own Lab as an application company. Also fea…

model-releasessonya-huang--x

Thrilled to have @gabepereyra speak at our @sequoia event tmrw on OWN YOUR AI: how to build your own Lab as an application company. Also featuring @FireworksAI_HQ @mercor_ai @LangChain @trajectorylabs