All entries

From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization

arXiv:2608.09595v1 Announce Type: new Abstract: Compressing large language models to two bits or fewer is increasingly feasible through block-wise post-training quantization; cross-block variants reco

From token probabilities to calibrated confidence: An empirical study of mathematical question answering

DGX agent

arXiv:2608.07827v1 Announce Type: cross Abstract: Confidence estimation for large language models (LLMs) aims to estimate the probability that a generated answer is correct, while calibration aligns t

researcharxiv-cs-cl

11 Aug 2026

Tutorials

From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents

arXiv:2608.05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajector

tutorialsarxiv-cs-ai

From Uncertainty to Failure Attribution: Self-Diagnosing Models for Failure Attribution under Distribution Shift

arXiv:2608.07953v1 Announce Type: new Abstract: Distribution shift poses a significant challenge to the robustness of machine learning models, but the current solutions only aim to detect out-of-distr

researcharxiv-cs-lg

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

arXiv:2608.09925v1 Announce Type: cross Abstract: Large language models are increasingly being deployed in governmental settings, yet few existing evaluation frameworks jointly reflect the values of p

From vision to reality: a unified AI solver for the grid

GENCO is an AI‑driven neural solver released by IBM Research and partners that unifies three core electrical‑grid analysis tasks within the GridFM Development Framework. It runs on Linux Foundation En

researchibm-research

From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification

arXiv:2603.02270v2 Announce Type: replace Abstract: Automated animal identification is a practical task for reuniting lost pets with their owners, yet current systems often struggle due to limited dat

Industry

Frontier AI raises the cybersecurity bar: Why prediction must become prevention

Artificial intelligence is a double-edged sword when it comes to cybersecurity. It is giving defenders new ways to sift through vast amounts of telemetry, identify anomalous behavior and automate rout

industrysiliconangle

FSTC-Encoder: Feature--Spatial--Temporal Correlation Learning for Generalizable RF Sensing

arXiv:2608.08439v1 Announce Type: cross Abstract: Heterogeneous RF sensing differs substantially in feature structure, spatial layout, and temporal scale, making existing models difficult to reuse acr

Full-bandwidth transformer

arXiv:2608.08888v1 Announce Type: new Abstract: Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth. Dense attention gives each

Full-Feature versus Limited-Input Machine Learning for Residential Energy Estimation: A Comparative Analysis of RECS and ResStock Under Realistic Input Constraints

arXiv:2608.09255v1 Announce Type: new Abstract: Residential energy estimates are often needed before detailed envelope characteristics, equipment efficiencies, infiltration, sensor, or billing data ar

researcharxiv-cs-lg

Fusion Training for Mathematical Generalization in Large Language Models

arXiv:2608.09893v1 Announce Type: cross Abstract: Thinking Mode Fusion (TMF) enables large language models to support both concise responses and long-form reasoning by unifying a non-thinking mode and

GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices

arXiv:2608.08968v1 Announce Type: cross Abstract: Microservice root cause analysis (RCA) requires correlating failures across heterogeneous telemetry within complex service dependency graphs. Existing

Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure

arXiv:2608.08722v1 Announce Type: cross Abstract: Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim. We document this concretely

Gated Spatial Redundancy Projection for Pathology Transformer Attentions

arXiv:2608.08374v1 Announce Type: new Abstract: Transformer models are increasingly used for whole-slide image analysis in computational pathology. Yet, WSIs differ fundamentally from natural images:

GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis

arXiv:2608.09921v1 Announce Type: new Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power s

General OOD Detection via Model-aware and Subspace-aware Variable Priority

arXiv:2512.13003v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is essential for determining when a supervised model encounters inputs that differ meaningfully from its t

local-aiarxiv-cs-lg

Generalized Convexity and Smoothness via Conjugate Duality: Optimization Theory for Deep Neural Networks

arXiv:2608.09523v1 Announce Type: new Abstract: Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimiza

safetyarxiv-cs-lg

Generalizing deep reinforcement learning across cable-driven parallel robot configurations with actuator-level policies

arXiv:2608.07546v1 Announce Type: cross Abstract: Cable-driven parallel robots (CDPRs) present diverse configurations and complex control challenges, which can be addressed by deep reinforcement learn

safetyarxiv-cs-ai

Tutorials

Generative Models: Principles, Architectures, and Applications

arXiv:2608.08101v1 Announce Type: new Abstract: Generative AI has emerged as one of the most transformative forces in modern artificial intelligence, reshaping how we create, imagine, and interact wit

tutorialsarxiv-cs-ai

GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association

arXiv:2608.09581v1 Announce Type: new Abstract: Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene. Deterministic approaches,

Applications

GeoAI-based post-segmentation quality validation of building footprints via spatial feature engineering

arXiv:2608.09048v1 Announce Type: new Abstract: Deep learning-based building footprint extraction from high-resolution imagery often produces topologically inconsistent vectors unfit for direct GIS da

applicationsarxiv-cs-cv

Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real

arXiv:2608.07579v1 Announce Type: cross Abstract: The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting; depth

GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models

arXiv:2608.09325v1 Announce Type: new Abstract: Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency r

GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction

model-releasesarxiv-cs-cv

arXiv:2608.09493v1 Announce Type: new Abstract: Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains chal

Tutorials

Ghost Features and Spooky Transfer Learning for Hypercomplex-Valued Neural Networks

arXiv:2608.07735v1 Announce Type: new Abstract: Hypercomplex numbers extend the concept of complex numbers by introducing additional imaginary components. Besides increasing dimensionality, operations

tutorialsarxiv-cs-cv

GLocFM: A Geometry-Aware Foundation Model for 3D Indoor Wireless Localization

arXiv:2608.09285v1 Announce Type: cross Abstract: Learning-based wireless localizers often fail to utilize geometric information about the propagation environment, limiting their ability to exploit no

Goal-oriented Navigation Instruction Generation with Tour Video Priors

model-releasesarxiv-cs-cv

arXiv:2608.08596v1 Announce Type: new Abstract: Navigation Instruction Generation (NIG) aims to produce step-by-step natural language instructions for navigation guidance. Existing studies primarily t

Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification

arXiv:2603.19329v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations

Google’s Gemini AI app passes 1 billion monthly active users

model-releasessiliconangle

Google LLC’s Gemini artificial intelligence app has passed 1 billion monthly active users, making it the 14th product in the company’s history to reach that mark. The company announced the milestone t

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding

arXiv:2604.02047v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward p

Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

arXiv:2608.09225v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests.

GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering

arXiv:2608.07881v1 Announce Type: new Abstract: Clustering mixed tabular data requires a unified metric space to bridge the inherent heterogeneity between continuous numerical measurements and discret

safetyarxiv-cs-ai

Gradient Under Microscope: Benchmarking Resource Utilization of Memory-Efficient Gradient Computation Methods

model-releasesarxiv-cs-lg

arXiv:2608.08961v1 Announce Type: new Abstract: AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training o

Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning

arXiv:2608.09484v1 Announce Type: new Abstract: Many diffusion-based planners enforce safety through inference-time guidance, but such interleaved trajectory deformations often degrade kinematic feasi

safetyarxiv-cs-ro

GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning

arXiv:2608.07905v1 Announce Type: new Abstract: Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environment

Agents

GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum

arXiv:2603.28533v3 Announce Type: replace Abstract: Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both t

agentsarxiv-cs-cl

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views

arXiv:2608.09270v1 Announce Type: cross Abstract: Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and

Applications

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

arXiv:2608.08010v1 Announce Type: cross Abstract: Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pre

applicationsarxiv-cs-ai

Guardian Crawler: Retrieval-First Knowledge Discovery with Bounded LLM Augmentation for Noisy Web Intelligence

arXiv:2608.08994v1 Announce Type: cross Abstract: Retrieving relevant evidence from noisy web data is challenging, particularly in sensitive domains containing incomplete reports, heterogeneous langua

Agents

Guixu: Valuation-Driven Data Discovery for Autonomous AI Agents with On-Chain Attestation

arXiv:2608.07949v1 Announce Type: new Abstract: Autonomous agents increasingly rely on external data to complete downstream tasks such as model training and decision support. However, existing data di

agentsarxiv-cs-ai

GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning

arXiv:2608.07619v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but often degrade under visual and environmental shifts. Latent worl

local-aiarxiv-cs-ro

Applications

H2: A Dual Hybrid Semantic Data Lake Architecture for Medical Data Harmonization with Human-In-the-Loop verified, LLM Driven Metadata Annotation System

arXiv:2608.08056v1 Announce Type: new Abstract: Medical data, by its nature, exhibit a high degree of heterogeneity on multiple levels ranging from (a) different modalities like images, text and time

applicationsarxiv-cs-ai

Agents

Had so much fun giving this talk at @sequoia about @harvey’s moneyball approach to building a research lab. The biggest mistake I made in th…

Had so much fun giving this talk at @sequoia about @harvey’s moneyball approach to building a research lab. The biggest mistake I made in the early days of Harvey was trying to play the Yankees baseba

agentssonya-huang--x

Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching

arXiv:2608.09654v1 Announce Type: new Abstract: GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on

Hallucinations and Constraints : Regulating surgical workflow recognition beyond accuracy

arXiv:2608.09332v1 Announce Type: new Abstract: Hallucinations are a major concern for the integration of artificial intelligence into medicine, although less explored in the realm of medical image pr

researcharxiv-cs-lg

Halpern Iteration Achieves ilde{O}(epsilon^{-1/p}) pth-Order Oracle Complexity for Monotone Variational Inequalities

arXiv:2608.08463v1 Announce Type: cross Abstract: We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) show

HandSplatter: Automated Digital Goniometry from Neural Rendering

arXiv:2608.09735v1 Announce Type: new Abstract: Hand and finger disorders are leading contributors to musculoskeletal disability, creating a clinical need for precise methods to quantify joint motion.