Search: “index”

GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAs

arXiv:2608.04510v1 Announce Type: cross Abstract: Diffusion-based vision-language-action (VLA) policies can generate plausible actions even when their predictions are weakly grounded in the visual and

nvidia/NVIDIA-Nemotron-Parse-2.0 · Hugging Face

DGX agent

NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information. Given a Red, Green, Blu

model-releasesr-localllama

6 Aug 2026

RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

arXiv:2608.03487v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a wid

researcharxiv-cs-ai

Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals

arXiv:2607.21597v2 Announce Type: replace Abstract: Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event

local-aiarxiv-cs-ai

SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models

arXiv:2608.04975v1 Announce Type: cross Abstract: SciCode is the standard measure of the scientific-coding ability of language models: research-level problems that demand both frontier scientific theo

The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing

arXiv:2608.04432v1 Announce Type: cross Abstract: On two-sided content platforms, symmetric two-sided isolation (assigning matched fractions of creators and viewers to isolated treatment and control s

applicationsarxiv-cs-lg

Hardware

A Deployment-Friendly Foundational Framework for Efficient Computational Pathology

arXiv:2602.14010v2 Announce Type: replace-cross Abstract: Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image anal

hardwarearxiv-cs-ai

Agent memory layers don't need an LLM deciding what to remember

Most agent memory setups run a model call on the way in. Something reads the turn, decides whether it's worth keeping, rewrites it into a 'memory', tags it with a type and an importance score. That's

local-air-localllama

Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation

model-releasesarxiv-cs-lg

arXiv:2608.03990v1 Announce Type: new Abstract: Synthetic histopathology image generation has emerged as an approach that may address data scarcity in computational pathology, yet current evaluation m

Building a Fully Local PDF Read-Aloud & PDF-to-Audiobook Desktop App with Kokoro 82M, Qwen, and llama.cpp

model-releasesr-localllama

Hey everyone, I’ve been building Speechfony - a desktop app for reading PDFs (and EPUBs) with offline text-to-speech. Open a document, listen sentence-by-sentence with highlighting, or export selected

Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation

arXiv:2608.03647v1 Announce Type: cross Abstract: Out-of-distribution (OOD) recommendation is vulnerable to preference shifts induced by a latent environment. Existing methods can infer latent states

DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units

arXiv:2608.03127v1 Announce Type: cross Abstract: Hand motion carries the finest-grained information in human activity, yet the representations behind hand generation, understanding, and robot learnin

researcharxiv-cs-ai

Fast Object Removal Attacks on Safety-Critical Video-based Perception Systems

arXiv:2608.02806v1 Announce Type: cross Abstract: By leveraging data from video-based perception systems, intelligent transportation systems (ITS) support safety-critical applications that improve roa

safetyarxiv-cs-cv

In-Context Pure Exploration in Continuous Decision Spaces

arXiv:2602.17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to ident

Tutorials

Measuring Explainer Stability via Attribution Separability

arXiv:2608.02697v1 Announce Type: cross Abstract: Attribution methods (AMs) assign an importance score to each feature and are widely adopted to explain black-box models. However, most methods can pro

tutorialsarxiv-cs-ai

Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue

arXiv:2608.03142v1 Announce Type: cross Abstract: We study contextual dynamic pricing with arbitrary covariate sequences and bounded, possibly nonbinary purchase quantities. Demand follows a semiparam

MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning

arXiv:2608.03882v1 Announce Type: cross Abstract: Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logis

One-shotting a Raccoon Heist game using Claude Fable 5

model-releasessimon-willison

Back in 2024 I tweeted screenshots of a game concept generated by GPT-3 and some concept 'art' created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5

pi-Attention: Online Efficient Sparse Transformers for Long-Context Modeling

arXiv:2511.10696v3 Announce Type: replace-cross Abstract: Sparse attention is crucial in long-context Transformers, which restricts each token to a limited neighborhood and thereby reduces the quadrat

researcharxiv-cs-ai

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

arXiv:2608.03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than pro

SocietyBench: Forecasting Counterfactual Social-World Evolution

arXiv:2608.04009v1 Announce Type: new Abstract: Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a b

SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference

arXiv:2608.03335v1 Announce Type: new Abstract: Video diffusion transformers (vDiTs) generate high quality but pay quadratic self-attention cost, making inference prohibitive at video-token scales. Th

safetyarxiv-cs-cv

Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI

arXiv:2608.03762v1 Announce Type: cross Abstract: Uterine peristalsis is a key physiological phenomenon responsible for various functions across the menstrual cycle, intimately linked to uterine wall

researcharxiv-cs-cv

When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives

arXiv:2608.03722v1 Announce Type: new Abstract: Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capa

AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery

arXiv:2608.01303v1 Announce Type: new Abstract: Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it. Generat

safetyarxiv-cs-lg

An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting

arXiv:2608.02088v1 Announce Type: new Abstract: Reliable photovoltaic (PV) forecasts are needed for low-carbon energy systems, but newly deployed sites often have short, imperfect records. This makes

safetyarxiv-cs-lg

AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization

arXiv:2608.01997v1 Announce Type: new Abstract: Single-optimizer training is a poor fit for the distinct phases of deep network optimization: adaptive methods handle noisy early gradients well but ove

Celty: SpMspV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference

arXiv:2608.01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weigh

local-aiarxiv-cs-lg

CORTIVA: Candidate-Score Fusion of Complementary Visual Teachers for EEG- and MEG-to-Image Retrieval

model-releasesarxiv-cs-cv

arXiv:2608.01355v1 Announce Type: new Abstract: Decoding visual experience from non-invasive brain activity is central to neuroscience and brain-computer interfaces. Functional magnetic resonance imag

Douyin Multimodal Embedding Model Technical Report

arXiv:2608.02148v1 Announce Type: cross Abstract: Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial search

applicationsarxiv-cs-cl

Emergence Invariance: From Symbolized Thought to Interface Refinement

model-releasesarxiv-cs-lg

arXiv:2608.01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition. Large lan

Estimating SSIM from MSE for DCT-Based Compressed Images

arXiv:2608.02549v1 Announce Type: cross Abstract: Efficient and perceptually meaningful quality assessment is a fundamental requirement for image and video processing, compression, and streaming syste

researcharxiv-cs-cv

FastGFDs: Efficient Validation of Graph Functional Dependencies with Desbordante

arXiv:2608.02321v1 Announce Type: cross Abstract: Graph functional dependencies (GFD) are a recently-developed concept aimed at capturing both topological structures in graphs and functional dependenc

Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning

model-releasesarxiv-cs-lg

arXiv:2608.01917v1 Announce Type: new Abstract: Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates re

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

arXiv:2608.00065v1 Announce Type: cross Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and

Passing Coarse Marginal Checks Can Be Cheap: Persona Mixtures and Imprecise Treatment-Response Estimates in an LLM Persona Panel

arXiv:2608.00979v1 Announce Type: cross Abstract: Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble hu

RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings

arXiv:2608.01311v1 Announce Type: new Abstract: Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constrain

local-aiarxiv-cs-cl

Robust Bayesian Optimization via Tempered Posteriors

arXiv:2601.07094v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquis

Running fast is not enough, you need fast AND correct An excellent addition from @ArtificialAnlys to make sure that the flashy speed numbers…

model-releasesfireworks-ai--x

Running fast is not enough, you need fast AND correct An excellent addition from @ArtificialAnlys to make sure that the flashy speed numbers are backed by 100% matching accuracy Announcing the Artific

Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generation

arXiv:2608.00658v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The for

researcharxiv-cs-cl

Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct

arXiv:2608.00285v1 Announce Type: new Abstract: Sixteen language models drawn from ten families produced, on average, the semantic diversity of 1.69 distinct formulations of a psychotherapeutic case,

researcharxiv-cs-cl

SSR: Similarity-Shift Refinement for Training-Free Object-Centric Masks

arXiv:2608.01103v1 Announce Type: new Abstract: Object-centric models often produce fragmented masks, boundary leakage, and incorrect region merging. We introduce Similarity-Shift Refinement (SSR), a

applicationsarxiv-cs-cv

Stabilized Best-of-K Training for Neural Combinatorial Optimization

arXiv:2608.00296v1 Announce Type: new Abstract: Leader Reward modifies POMO training to emphasize the best trajectory produced by repeated inference. We test a narrow extension: replace its binary lea

Statistical comparisons of time-series feature sets on classification tasks

arXiv:2608.01586v1 Announce Type: cross Abstract: In recent years, numerous open-source software libraries have been developed for computing sets of features from univariate time series. The type and

Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation

arXiv:2608.01666v1 Announce Type: new Abstract: However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open q

TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention

arXiv:2608.02050v1 Announce Type: new Abstract: Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the

Agents

V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory

arXiv:2608.01543v1 Announce Type: cross Abstract: Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either

agentsarxiv-cs-cl

VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval

arXiv:2608.01211v1 Announce Type: new Abstract: Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and ret

applicationsarxiv-cs-cv