All entries

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

researcharxiv-cs-lg

Model Releases

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving

DGX agent

arXiv:2608.00881v1 Announce Type: new Abstract: Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step. As

model-releasesarxiv-cs-lg

4 Aug 2026

Appreciate it! High performance, low cost. Try it out today. 💻

Appreciate it! High performance, low cost. Try it out today. 💻 Qwen 3.8 Max is available on AI Gateway. It scores mid-pack on the DeepsecBench cybersecurity leaderboard at one of the lowest costs per

model-releasesqwen--x

ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification

arXiv:2608.01291v1 Announce Type: new Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syrian, E

Applications

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

arXiv:2607.02252v2 Announce Type: replace Abstract: The deployment of Industrial Anomaly Detection (IAD) in real-world manufacturing frequently encounters a challenging cold-start bottleneck, in which

applicationsarxiv-cs-cv

ARM: Detector-Agnostic Changepoint Attribution with Finite-Sample Error Control

arXiv:2608.01691v1 Announce Type: cross Abstract: Detecting a change in a multivariate series answers only the first of two questions; the operational question is which coordinates changed. Existing a

researcharxiv-cs-cv

ARMOR: A Robust Self-Supervised Framework for Root Cause Analysis in Microservices under Missing Modality

arXiv:2603.25538v3 Announce Type: replace Abstract: Automated incident management is critical for microservice reliability. While recent unified frameworks leverage multimodal data for joint optimizat

safetyarxiv-cs-lg

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

arXiv:2506.22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physica

safetyarxiv-cs-lg

Agents

ArmorCode targets runaway AI costs with four new remediation agents

Exposure management startup ArmorCode Inc. today used Black Hat USA 2026 in Las Vegas to detail an expansion of its agentic artificial intelligence platform, adding four planned agents and three new s

agentssiliconangle

AROpt: An Optimization Method for Autoregressive Time Series Forecasting

arXiv:2602.02288v3 Announce Type: replace Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly b

researcharxiv-cs-lg

Artificial Intelligence for the Characterization of Particles and Fibers by Optical Microscopy

arXiv:2608.00361v1 Announce Type: new Abstract: Optical microscopy of particle and fiber dispersions involves interpreting subtle visual cues influenced by specimen morphology, chemical composition, m

researcharxiv-cs-cv

Hardware

As AI Increases Demands on Memory, Storage Steps Up

Surging AI demands are driving the need for massive datasets and context windows that burst past the confines of system memory. But rising needs aren’t met by simply adding more storage capacity. What

hardwarenvidia-blog

Asleep at the Wheel: JEPA's Limitations in Evaluating Novel Driving Data

model-releasesarxiv-cs-cv

arXiv:2608.01336v1 Announce Type: new Abstract: Modern autonomous-driving fleets record far more video than human reviewers can inspect. This motivates the need for an automatic clip triage mechanism,

Applications

Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagery

arXiv:2608.01906v1 Announce Type: new Abstract: Rapid and accurate post-disaster building damage assessment is essential, yet remains a challenging task. Unmanned Aerial Vehicle (UAV) imagery offers a

applicationsarxiv-cs-cv

Local Ai

Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning

arXiv:2608.02250v1 Announce Type: new Abstract: Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally up

local-aiarxiv-cs-lg

Assistant Placement Aria: A Benchmark for Egocentric Placement Assistance

model-releasesarxiv-cs-ro

arXiv:2608.00652v1 Announce Type: new Abstract: Human assistance in robotics spans around several tasks such as navigation, object manipulation, and placement, where a key challenge is selecting targe

ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment

arXiv:2608.02006v1 Announce Type: new Abstract: Dynamic 3D scene reconstruction has achieved remarkable success under the assumption of strictly synchronized multi-camera inputs. However, in real-worl

safetyarxiv-cs-cv

Tutorials

Astrolabe: Spherical-Map Guidance Across Diffusion Pipelines for Full-Body Capture from Unconstrained Images

arXiv:2608.01276v1 Announce Type: new Abstract: Full-body capture from unconstrained photographs requires global correspondence across arbitrary views, poses, crops, and occlusions. Yet pose, geometry

tutorialsarxiv-cs-cv

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization

arXiv:2608.01078v1 Announce Type: new Abstract: We propose ScaleQ-1.58, a scalable ternary post-training quantization (PTQ) framework for reasoning LLMs. Its core insight stems from an empirical findi

researcharxiv-cs-cl

Attention-Steered Vision-Language Models for Sign Language Translation

arXiv:2608.00235v1 Announce Type: new Abstract: Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language

researcharxiv-cs-cv

AttnLink: Turning Attention into Schema Links for Text-to-SQL

arXiv:2608.00693v1 Announce Type: new Abstract: Schema linking is a critical component of Text-to-SQL systems, but existing approaches often trade off contextual modeling capacity, score-based control

Auditable Release Control for Pedagogical Leakage in LLM Tutors

arXiv:2608.00515v1 Announce Type: cross Abstract: Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized. We formalize

Augmented Inverse Hybrid Weighting: Robust Inference under Deterministic and Random Distribution Shifts

model-releasesarxiv-cs-lg

arXiv:2608.00701v1 Announce Type: cross Abstract: Reweighting source samples to match a target covariate distribution is a standard response to distribution shift when generalizing evidence from one p

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

arXiv:2608.02602v1 Announce Type: new Abstract: Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation

AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery

arXiv:2608.00198v1 Announce Type: new Abstract: Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adeq

researcharxiv-cs-lg

Automated ECG Interval Measurement and Wave Delineation Using Fast Fourier Convolution ResNet

arXiv:2608.00058v1 Announce Type: cross Abstract: Accurate measurement of ECG intervals, including PR, QRS duration, and QT/QTc, is central to cardiac diagnosis, yet the published ECG delineation lite

safetyarxiv-cs-lg

Tutorials

Automated web insight extraction with Amazon Bedrock AgentCore

Extracting insights from dozens of websites by hand quickly becomes overwhelming. This post shows how to build an automated web insight extraction solution with Amazon Bedrock AgentCore Browser, Amazo

tutorialsaws-ml-blog

Automatic Annotation of Ancient Greek Vowel Length

arXiv:2608.01935v1 Announce Type: new Abstract: Prior work in Ancient Greek NLP relies on corpora that do not disambiguate the phonemic vowel length of alpha, iota, and ypsilon, together known as the

Automatic LV Localization and Short-Axis Plane Estimation from Arbitrary CMR Slice

model-releasesarxiv-cs-cv

arXiv:2608.00145v1 Announce Type: cross Abstract: Accurate estimation of left ventricular (LV) orientation is essential for cardiac magnetic resonance (CMR) imaging and downstream analysis. Existing m

Averaging Bias: Human Faithfulness Annotations are not Locally Faithful

arXiv:2608.00205v1 Announce Type: new Abstract: Evaluation of faithfulness of text summarization treats a model generated summary as faithful only if every of its sentences is supported by the source

safetyarxiv-cs-cl

AWS launches Kiro Crew, an autonomous agentic orchestrator for 24/7 code development

model-releasessiliconangle

Amazon Web Services Inc. today launched Kiro Crew, an autonomous workspace that keeps artificial intelligence coding agents running all day and all night. The company said it developed Crew to allow d

b10247

ggml: use dynamic allocation for split graph inputs (#22789) ggml: use dynamic allocation for split graph inputs Replace fixed-size GGML_SCHED_MAX_SPLIT_INPUTS arrays with dynamically allocated buffer

b10248

vocab : validate default special token ids (#26506) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra

b10249

server: add get_info tool (#26522) server: add get_info tool fix --rpc in docs server: harden get_info probe result handling Report the OS as unknown when the probe process fails to spawn or times out

b10250

tests: add model resolution test on synthetic repo listings (#26172) tests: add model resolution test on synthetic repo listings Include download.cpp and arg.cpp inside a namespace with hf_cache monke

b10251

model : support MTP in GLM-4.7-Flash (#24868) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework

b10252

vendor : update BoringSSL to 0.20260803.0 (#26523) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram

b10253

vendor : update cpp-httplib to 0.52.0 (#26485) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor

b10254

chat : add new template for DeepSeek V4 Flash 0731 (#26398) common/chat: update DeepSeek V4 templates Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of th

b10255

Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches Extends the oneDNN SDPA path (PR #25222) to handle non-F16 KV cach

b10256

sycl: parallelize the non-contiguous concat kernel (#25852) sycl: parallelize the non-contiguous concat kernel Launch geometry only: the non-contiguous concat kernel launched a single-lane work-group

b10258

llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520) This matches how it is done for logit_bias and mirostat samplers, see #25262 (comment) Website: https://llama.app macOS/iOS: ma

b10259

model : allow reshape of tensors during load (#26531) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF

b10261

vocab : validate plamo2 byte tokens (#26511) validate plamo2 byte tokens --typo Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED

b10262

vulkan backend ops: implemented GATED_LINEAR_ATTN (#25601) vulkan : add GATED_LINEAR_ATTN op docs : update Vulkan ops vulkan : remove unused GLA spec constant Updated ops.md ops.md update Website: htt

b10265

sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar

b10267

speculative : refactor enabled configs common_speculative_init (#26510) This commit contains a suggestion to reduce some code duplication in common_speculative_init when adding the enabled speculative

b10268

ci: fix pre-built binaries no longer working on macOS 15 and below (#26375) ci: fix pre-built binaries no longer working on macOS 15 and below ci: add macOS deployment target to disabled KleidiAI buil