All entries

Optimistic Rates for Multiclass PAC Learning

arXiv:2608.10869v1 Announce Type: new Abstract: Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarante

Agents

Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization

arXiv:2608.10694v1 Announce Type: cross Abstract: Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answerin

agentsarxiv-cs-ai

12 Aug 2026

Optimized Sequential Testing for Binary Ensemble Classifiers

model-releasesarxiv-cs-lg

arXiv:2606.15237v1 Announce Type: cross Abstract: Ensemble classifiers are predictive models that combine the results of simpler base models, often by majority vote. A classic example is random forest

Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

model-releasesarxiv-cs-lg

arXiv:2602.13136v2 Announce Type: replace Abstract: Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches r

Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences

arXiv:2608.10908v1 Announce Type: cross Abstract: As generative multimedia evolves from static image synthesis to complex, interleaved visual narratives, a foundational bottleneck has emerged: the jud

researcharxiv-cs-cl

P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing

arXiv:2608.10131v1 Announce Type: new Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are diffic

local-aiarxiv-cs-cv

Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignment

arXiv:2608.10619v1 Announce Type: new Abstract: Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local prop

safetyarxiv-cs-lg

Tutorials

Part 2: Amazon Bedrock cost attribution with Amazon Athena and CUDOS

Learn how to visualize and analyze Amazon Bedrock cost attribution using Amazon Athena and CUDOS dashboards. This post shows how to set up CUR 2.0 with IAM principal data, query Bedrock spend by princ

tutorialsaws-ml-blog

Partially Observable Learning for Multi-Platform Dispatch Optimization

arXiv:2608.10897v1 Announce Type: new Abstract: Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic

safetyarxiv-cs-lg

Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control

model-releasesarxiv-cs-lg

arXiv:2608.10777v1 Announce Type: new Abstract: Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained re

Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure

arXiv:2606.17441v2 Announce Type: replace-cross Abstract: Simulating realistic patient interactions is a key requirement to testing clinical applications of LLMs at scale without time-consuming and ex

researcharxiv-cs-ai

Agents

Pay with confidence: How Solv Labs built verifiable, auditable agent payments on Amazon Bedrock AgentCore payments

Solv Labs built a governed agent-payments workflow on Amazon Bedrock AgentCore payments, where every transaction is authorized, attested in an AWS Nitro Enclave, priced for risk, and anchored to a pub

agentsaws-ml-blog

PBD-AG: Persistent Baseline-Delta Active Graphs with Uncertainty-Aware Inspection for Long-Horizon Service Robots

arXiv:2608.10449v1 Announce Type: new Abstract: Long-horizon service robots require persistent world models that can be built autonomously in unseen environments and revised as task-relevant objects c

local-aiarxiv-cs-ro

PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders

model-releasesarxiv-cs-cv

arXiv:2608.10985v1 Announce Type: new Abstract: Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infrin

PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing

arXiv:2608.10109v1 Announce Type: new Abstract: Social media has become a major venue for multilingual communication, where users frequently mix multiple languages within a single utterance. Although

researcharxiv-cs-cl

Persistent Recursive Worlds Enable Autonomous Software Evolution

arXiv:2608.10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve conti

Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation

arXiv:2608.10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assess

Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems

arXiv:2608.10941v1 Announce Type: new Abstract: Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operationa

Physics-Informed Machine Learning in Prognostics and Health Management: A Systematic Literature Review

arXiv:2608.10047v1 Announce Type: cross Abstract: In modern industry, keeping complex systems reliable, safe, and efficient hinges on Prognostics and Health Management (PHM). Machine Learning (ML) has

pi-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image Enhancement

arXiv:2608.10589v1 Announce Type: cross Abstract: This paper presents pi-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap

Policy Convergence and Divergence Across National and Within Regional AI Strategies: A Policy Design Element Analysis

arXiv:2608.11006v1 Announce Type: cross Abstract: Governments worldwide have responded to the rapid expansion of AI by publishing national and regional AI strategies. Comparing national and regional A

Applications

PolyLayout: Hierarchical VLM-Guided Layout Generation Beyond Rectangular Rooms

arXiv:2608.10838v1 Announce Type: new Abstract: Generating physically plausible 3D room layouts is essential for home furnishing retail, enabling customers to visualize products in their own homes and

applicationsarxiv-cs-cv

PolypVision: A Three-Stage Hierarchical Deep Learning Framework for Classification and Segmentation of Colorectal Polyps

arXiv:2608.10649v1 Announce Type: new Abstract: Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, predominantly arising from precancerous polyps. Accurat

researcharxiv-cs-cv

Position Encoding in Transformers: From Absolute and Relative Methods to Rotary Position Embeddings and Long-Context Scaling

arXiv:2608.10021v1 Announce Type: new Abstract: Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitati

safetyarxiv-cs-cl

Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection

arXiv:2608.10406v1 Announce Type: cross Abstract: Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.

Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents

arXiv:2608.10198v1 Announce Type: new Abstract: Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reaso

researcharxiv-cs-ai

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference

model-releasesarxiv-cs-cl

arXiv:2608.10288v1 Announce Type: cross Abstract: The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bili

Pre- to Post-Contrast Synthesis of Breast DCE-MRI using Latent Bridge Matching

arXiv:2608.10000v1 Announce Type: cross Abstract: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is central to breast cancer imaging, but gadolinium administration increases scan burde

researcharxiv-cs-cv

Applications

Precise Top-Layer Fabric Segmentation for Fabric Destacking with Edge- and Shape-Aware Deep Networks

arXiv:2608.10648v1 Announce Type: new Abstract: Fabric destacking requires precise segmentation of the topmost fabric layer, a task complicated by subtle fabric boundaries and high visual similarity b

applicationsarxiv-cs-cv

Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning

arXiv:2608.10483v1 Announce Type: new Abstract: Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because avai

Pretrained Optimization Model for Zero-Shot Black Box Optimization

arXiv:2405.03728v3 Announce Type: replace-cross Abstract: Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or

PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models

model-releasesarxiv-cs-cv

arXiv:2608.11149v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in storing and recalling rich person-related knowledge, raising incre

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions

arXiv:2608.10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formula

safetyarxiv-cs-lg

Procedural Fairness Failures in RLHF from Preference Averaging

arXiv:2608.10126v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. Wh

Projected climate memory and inherited warm-tail risk in accelerated European summer warming

arXiv:2608.09966v1 Announce Type: cross Abstract: European summer warming reflects interactions among background change, persistent ocean--land--circulation states, and same-season variability. We dev

ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes

arXiv:2608.10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-

Protecting Creative Writing Copyright against AI Imitation via Implicit Watermarking

arXiv:2504.00035v4 Announce Type: replace-cross Abstract: Large language models (LLMs) enable powerful knowledge injection through approaches such as in-context learning and fine-tuning, but they also

researcharxiv-cs-ai

Agents

Protection Levels for Vision-Based Pose Estimation

arXiv:2608.10023v1 Announce Type: cross Abstract: Vision-based navigation complements Global Navigation Satellite Systems, but certification demands integrity guarantees that account for faulty measur

agentsarxiv-cs-cv

Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers

arXiv:2608.10989v1 Announce Type: cross Abstract: Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with differe

Putting sign language AI into users’ hands

model-releasesgoogle-deepmind

Google DeepMind’s new sign‑language‑to‑text (SL2T) model powers real‑time sign-to-text dictation in Gboard and Live Transcribe on Pixel 11, currently supporting American Sign Language to English. The

Applications

Quantifying the noise sensitivity of the Wasserstein metric for images

arXiv:2510.01015v3 Announce Type: cross Abstract: Wasserstein metrics are increasingly adopted as similarity scores for images. We consider the sensitivity of Wasserstein metrics with respect to pixel

applicationsarxiv-cs-lg

Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent Memory

arXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-acce

local-aiarxiv-cs-ai

Quantum Incremental Learning with Mixed State Prototypes

arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c

Quoting Florian Herrengt

model-releasessimon-willison

But then users start to report a weird bug. It's the 4th time your team has been trying to fix it. I mean... asking AI to fix it. Unfortunately, it seems like not even Fable can figure it out. You go

Qwen 3.8 2.4T is out , no 27b today RIP.

model-releasesr-localllama

i was hoping they would release both today but the big one just dropped now , and it says its been listed since 5 hours ago on huggingface. I guess the real date for 27b is https://modelscope.cn/model

Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, l…

model-releasesfireworks-ai--x

Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, large context windows, and is ideal for coding and agentic pe

Qwen3.8-2.4T-A95B is now live on Together AI. The Qwen Team’s latest flagship model is built for coding and long-horizon agent workflows, wi…

model-releasestogether-ai--x

The Qwen Team has released its flagship model, Qwen3.8‑2.4T‑A95B, on the Together AI platform (togethercompute) as of August 12 2026. This 2.4‑trillion‑parameter model is engineered for coding tasks a

R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video

arXiv:2608.11017v1 Announce Type: cross Abstract: Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it la

local-aiarxiv-cs-ai