All entries

MoCA: Implicit Social Context Analysis

model-releasesarxiv-cs-cl

arXiv:2608.05825v1 Announce Type: new Abstract: Human social communication, such as affection and intent, is often conveyed in highly implicit ways, where underlying meanings are expressed through ind

Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

arXiv:2608.05409v1 Announce Type: new Abstract: Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep est

safetyarxiv-cs-cl

7 Aug 2026

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra)

model-releasessimon-willison

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5, where I had Claude Fable 5 build a full working game

MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation

arXiv:2608.05450v1 Announce Type: new Abstract: Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substanti

MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification

model-releasesarxiv-cs-lg

arXiv:2608.05196v1 Announce Type: new Abstract: Multiple sclerosis (MS) is diagnosed through clinical assessment, magnetic resonance imaging, laboratory evidence when appropriate, and exclusion of bet

Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application

arXiv:2608.05346v1 Announce Type: cross Abstract: Time-sensitive networking (TSN) is increasingly integrated into mobile edge computing (MEC) to support applications with stringent latency requirement

safetyarxiv-cs-ai

Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks

arXiv:2608.05340v1 Announce Type: cross Abstract: Time-Sensitive Networking (TSN) and Mobile Edge Computing (MEC) hold strong potential for enabling ultra-reliable low-latency communication for time-s

agentsarxiv-cs-ai

Multi-Representation Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition

model-releasesarxiv-cs-cv

arXiv:2506.14243v4 Announce Type: replace Abstract: LiDAR-based place recognition is critical for long-term autonomous driving without GPS. Existing handcrafted feature methods face dual limitations.

Multi-Year Geospatial Reasoning using Interannually-Consistent Historical Predictions as a Free Input Modality

arXiv:2608.05979v1 Announce Type: new Abstract: Machine learning, and deep networks in particular, are increasingly used to derive higher-level Earth observation (EO) products such as annual land-cove

Multivariate Time Series Forecasting needs Cross Variable Loss

arXiv:2608.05742v1 Announce Type: cross Abstract: Multivariate time series forecasting presents unique challenges because future variables often co-evolve under shared system dynamics. While existing

Muon on the Stiefel Manifold Admits an Exact Closed-Form Update

arXiv:2608.06218v1 Announce Type: cross Abstract: We study Muon, a recently proposed matrix-aware optimization method, in the context of the Stiefel manifold. This manifold consists of matrices with o

My issue with Artificial Analysis's 'intelligence index'

model-releasesr-localllama

I swear AA is not the bipartisan they so claim. An open source mode (Qwen 3.8 max) was number 1 on the agentic index, then they just so happen to launch 'v4.1.1' of their index in which they just adju

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

arXiv:2603.19229v2 Announce Type: replace-cross Abstract: There are two major categories of embodied navigation: Vision-Language Navigation (VLN), where agents navigate by following natural language i

Near-sensor Computing for Rapid Visuotactile Perception

arXiv:2608.05725v1 Announce Type: new Abstract: Visuotactile sensors reconstruct dense contact geometry from measured surface gradients, but host-based processing increases power consumption and intro

researcharxiv-cs-ro

Negotiating Risk Boundaries in AI for Policing Through Mixed-Stakeholder Deliberation

arXiv:2608.05418v1 Announce Type: new Abstract: AI tools are being increasingly adopted in policing in the UK and worldwide. Racial bias is a known and well-documented risk, yet representatives of aff

safetyarxiv-cs-ai

NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering

model-releasesarxiv-cs-cl

arXiv:2608.06292v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. H

Neuro-Symbolic Closed-Loop Control of Laser Powder Bed Fusion with an In-Loop Ontology

model-releasesarxiv-cs-lg

arXiv:2608.05773v1 Announce Type: new Abstract: A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates

NeuroAdaptTrainer: A Fiji/ImageJ Plugin for YOLO-Based Neuron Segmentation, InteractiveCorrection and Transfer Learning

arXiv:2608.05226v1 Announce Type: new Abstract: Neuron counting and segmentation in microscopy images of neuronal cultures is a routine and time-consuming task in neuroscience research, traditionally

Applications

nnMIL: A generalizable multiple instance learning framework for computational pathology

arXiv:2511.14907v2 Announce Type: replace Abstract: Computational pathology holds substantial promise for improving diagnosis and guiding treatment decisions. Recent pathology foundation models enable

applicationsarxiv-cs-cv

Nonvisual Classification of Ground-Condition by Artificial Proprioception in an Amoeba-Inspired Autonomous Walking Robot

arXiv:2608.05684v1 Announce Type: cross Abstract: Nonvisual classification of ground condition based on a multimodal sensing approach was investigated for an amoeba-inspired autonomous walking robot.

agentsarxiv-cs-ai

Now we have a timeline of the OpenAI accidental attack against Hugging Face

OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about 'the Hugging Face Incident' (previously on this blog). The video was published yesterday. It's short and information

agentssimon-willison

Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control

arXiv:2608.05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning

safetyarxiv-cs-lg

Local Ai

Ollama Customer Support Non-existent

Hi there! I've messaged the Ollama support team 4 times with no response in 3 weeks. This is getting ridiculous. Does anyone have any recommendations as to how I should seek support? I don't want to i

local-air-ollama

Applications

omega-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation

arXiv:2608.06375v1 Announce Type: new Abstract: Humanoid household tasks often require concurrent loco-manipulation, where the robot must move, adjust posture, maintain balance, and manipulate objects

applicationsarxiv-cs-ro

OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction

model-releasesarxiv-cs-cv

arXiv:2608.05539v1 Announce Type: new Abstract: Recent vision-language models (VLMs) can generate executable CAD programs from images, but existing methods mainly target coarse, general-purpose 3D obj

On-Policy Delta Distillation for Multilingual Math Reasoning

arXiv:2608.05802v1 Announce Type: new Abstract: On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingu

safetyarxiv-cs-cl

On-Policy Self-Distillation without Any Supervision

arXiv:2608.06296v1 Announce Type: new Abstract: On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still re

safetyarxiv-cs-lg

On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities

arXiv:2608.06182v1 Announce Type: cross Abstract: We study stochastic extragradient (SEG) methods for solving monotone variational inequality problems (VIPs) over a feasible set. Although extragradien

On the Anisotropy of Score-Based Generative Models

arXiv:2510.22899v2 Announce Type: replace Abstract: We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce t

Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration

arXiv:2608.05741v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and convincing text at scale, creating growing risks for misinformation dissemination, educational mi

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

arXiv:2512.14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its secur

One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization

arXiv:2608.05240v1 Announce Type: cross Abstract: One-bit post-training quantization represents each weight using only its sign, requiring all deployment contexts to share the same binary weight matri

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

arXiv:2608.05707v1 Announce Type: new Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Sinc

Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning

arXiv:2604.01170v2 Announce Type: replace-cross Abstract: While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute

OpenAI puts the brakes on a new model because it’s supposedly too powerful

model-releasesthe-verge-ai

OpenAI says it is pausing 'internal activities' around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows i

OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents

arXiv:2608.05990v1 Announce Type: new Abstract: Autonomous agents choose actions using scores that may not reflect experimental success. We developed OPERA, an operator-residual framework for optical

agentsarxiv-cs-ai

Operating Multi-Node Full Fine-Tuning on NVIDIA B300: A Field Report on Telemetry-Based Triage, Negative Results, and Operational Hardening

model-releasesarxiv-cs-lg

arXiv:2608.05944v1 Announce Type: cross Abstract: We report operational experience full-fine-tuning a 32.76B-parameter dense model (Qwen3-32B) on 16 x NVIDIA B300 (two nodes, FSDP / ZeRO-3) -- among t

Optimal or Greedy Decision Trees? Revisiting their Objectives, Tuning, and Performance

arXiv:2409.12788v3 Announce Type: replace Abstract: Recently there has been a surge of interest in optimal decision tree (ODT) methods that globally optimize accuracy directly, in contrast to traditio

Optimal Rates for Learning with Monotone Adversaries

arXiv:2608.06337v1 Announce Type: cross Abstract: A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correc

OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality

arXiv:2608.05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipelin

Ordered Diffusion for 3D Human Registration

arXiv:2608.05804v1 Announce Type: new Abstract: 3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an in

safetyarxiv-cs-cv

OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations

arXiv:2608.06264v1 Announce Type: new Abstract: The development of deep learning over the past decade has revolutionized medical imaging segmentation, allowing the extraction of precise descriptors fr

Otter: A Time-Aware, History-Conditioned Human Chess AI

arXiv:2608.05206v1 Announce Type: new Abstract: Otter is a 15.3M-parameter human chess AI that predicts human move selection by modeling play as a time-aware, sequential process rather than treating e

Outstanding cost-to-performance from DeepSeek GPT-5.6 Luna (Max) performance for a 1/4th of the cost on ARC-AGI

model-releasesfrancois-chollet--x

Outstanding cost-to-performance from DeepSeek GPT-5.6 Luna (Max) performance for a 1/4th of the cost on ARC-AGI DeepSeek V4 Flash from @deepseek_ai on ARC-AGI (Verified): - ARC-AGI-2: 61.4%, 0.04/task

Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement

arXiv:2608.05843v1 Announce Type: new Abstract: Restoring high-fidelity remote sensing imagery from extreme low-light degradation is indispensable for reliable Earth observation and downstream machine

safetyarxiv-cs-cv

PaCoNet: Deep Data Extraction for Parallel Coordinates

arXiv:2608.06030v1 Announce Type: new Abstract: Extracting data from visualizations has long challenged computer vision, with current research focused on bar, line, and pie charts, among other low-dim

Hardware

PaDoc: Layout-Grounded Parallel Decoding for Document Parsing

arXiv:2608.06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formula

hardwarearxiv-cs-ai

Local Ai

parakeet.wgsl – Fast, accurate ASR in the browser, via raw WebGPU & SIMD WASM

High-performance inference of NVIDIA's Parakeet TDT 0.6B V2 English transcription model, in the browser. Check out the live demo: https://parakeet.narcotic.sh/ A fully custom, dependancy-free implemen

local-air-localllama