All entries

I wonder how this could be used to study creative thinking and the generation of new ideas. If I understand correctly, the J-space is some s…

model-releasescristobal-valenzuela--x

I wonder how this could be used to study creative thinking and the generation of new ideas. If I understand correctly, the J-space is some sort of internal workspace where the model holds concepts to

Industry

I write about this in my book The Last Economy 'tis the Great Fragmentation https://ii.inc/the-last-economy/chapter-16#future-two-the-great-…

DGX agent

Emad Mostaque references a chapter from his book 'The Last Economy' discussing 'the Great Fragmentation,' likely exploring economic decentralization, the breakdown of traditional economic structures,

industryemad-mostaque--x

7 Jul 2026

Agents

I wrote an article on the core Agent architecture for Row-Bot. How it uses a @LangChain LangGraph agent at its core for the main agent, back…

I wrote an article on the core Agent architecture for Row-Bot. How it uses a @LangChain LangGraph agent at its core for the main agent, background workflows and child agents. Each is a full LangGraph

agentsharrison-chase--x

IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition

arXiv:2510.24936v3 Announce Type: replace Abstract: Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and

applicationsarxiv-cs-cv

IBM debuts compact z17 mainframes and LinuxONE servers for on-premises enterprise AI

IBM Corp. today announced a massive expansion of its on-premises enterprise infrastructure lineup, with new single-frame and rack-mount versions of its iconic z17 mainframes and more compact LinuxONE

applicationssiliconangle

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

arXiv:2607.04675v1 Announce Type: new Abstract: This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Gra

ICR-RL: Deep Reinforcement Learning via In-Context Regression

model-releasesarxiv-cs-ai

arXiv:2509.11259v2 Announce Type: replace-cross Abstract: Recent advancements in machine learning have largely been driven by foundation models (FMs) trained on large, diverse datasets, enabling them

IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning

arXiv:2607.03614v1 Announce Type: new Abstract: Spatial question answering is the dominant paradigm for evaluating spatial intelligence in Vision-Language Models (VLMs), but it leaves a complementary

Identifiability of Relational Queries in Multi-View Pretraining

arXiv:2607.04735v1 Announce Type: cross Abstract: When data sources are integrated through a shared interface, a downstream query may or may not be determined by what the interface exposes: two global

applicationsarxiv-cs-lg

Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

arXiv:2606.12471v2 Announce Type: replace-cross Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability,

safetyarxiv-cs-cl

If you care about AI, and want a nuanced view, you should watch this. I promise it will be worth your time.

model-releasesgary-marcus--x

If you care about AI, and want a nuanced view, you should watch this. I promise it will be worth your time. An excellent video from the @WorldSciFest featuring @GaryMarcus , in which he discusses—amon

iFLYTEK-Embodied-Omni Technical Report

arXiv:2607.02542v1 Announce Type: new Abstract: General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actio

imo this is the most impt part of anthropic's J-space paper today. it's a two-parter: 1) ant proved that they can do 'brain surgery' interve…

imo this is the most impt part of anthropic's J-space paper today. it's a two-parter: 1) ant proved that they can do 'brain surgery' interventions into reasoning to change topics midstream* 2) THE MOD

model-releasesswyx--x

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

arXiv:2607.04146v1 Announce Type: cross Abstract: This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics

applicationsarxiv-cs-ai

Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse

arXiv:2607.03613v1 Announce Type: new Abstract: We study the implicit bias of noisy stochastic gradient descent in training wide two-layer ReLU networks for multivariate regression. In a mean-field re

safetyarxiv-cs-lg

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

arXiv:2409.08469v4 Announce Type: replace-cross Abstract: We provide finite-particle convergence rates for the Stein Variational Gradient Descent (SVGD) algorithm in the Kernelized Stein Discrepancy (

Improved generalization bounds for binary linear classification via isoperimetry

arXiv:2505.16713v3 Announce Type: replace-cross Abstract: We examine the concentration of uniform generalization errors around their expectation in binary linear classification problems via an isoperi

Improving LLMs via Validator-to-Generator Alignment

arXiv:2607.02668v1 Announce Type: new Abstract: Large language models are inconsistent: varying prompts or including unrelated information can lead to unexpected changes in model outputs. The generato

safetyarxiv-cs-cl

ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incomplete Recordings for Cardiac Assessment

arXiv:2607.05009v1 Announce Type: cross Abstract: Complete digital 12-lead electrocardiograms (ECGs) are essential for AI-enabled cardiovascular assessment, yet many clinical ECG records, particularly

applicationsarxiv-cs-ai

in game mechanics, these are called a variable rewards (also, yay)

model-releasesyohei-nakajima--x

Variable rewards are game mechanics that provide unpredictable or randomized incentives to players, designed to encourage repeated engagement through the uncertainty of outcomes. This concept is commo

In-span learning: adapting reduced-order models using their own predictions

arXiv:2607.02937v1 Announce Type: new Abstract: Reduced-order models compress high-dimensional dynamics into low-dimensional representations that can be evaluated rapidly, but they lose accuracy when

Agents

Incentivizing Vision Language Models to Search for Long Video Question Answering

arXiv:2607.02959v1 Announce Type: new Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-t

agentsarxiv-cs-cv

Inclusive KL Gradient Flows: Otto-Wasserstein, Fisher-Rao-Gaussian, and Local-Estimator Dynamics

arXiv:2411.00214v2 Announce Type: replace-cross Abstract: Otto's Wasserstein gradient flow of the inclusive (forward) Kullback--Leibler (KL) divergence offers a principled framework for analyzing stat

Incredible WSJ reporting on how European leaders deal with Trump -European leaders workshopped tweets to send Trump, debating which words to…

Incredible WSJ reporting on how European leaders deal with Trump -European leaders workshopped tweets to send Trump, debating which words to capitalize. They had to sound extra stupid to win over his

researchyann-lecun--x

Tutorials

Incremental Learning of Sparse Attention Patterns in Transformers

arXiv:2602.19143v2 Announce Type: replace Abstract: This paper studies simple transformers trained on a high-order Markov chain, where the model must incorporate information from multiple past positio

tutorialsarxiv-cs-lg

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

arXiv:2607.02964v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does. Dominant circuit-fin

Tutorials

Induction Heads Interpolate N-Grams

arXiv:2607.02800v1 Announce Type: new Abstract: Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they i

tutorialsarxiv-cs-lg

Industrial3D: A Water-Treatment TLS Point Cloud Dataset and Cross-Paradigm Benchmark for MEP Scene Understanding

arXiv:2603.28660v2 Announce Type: replace Abstract: Automated semantic understanding of dense terrestrial laser scanning (TLS) point clouds is a prerequisite for Scan-to-BIM, digital twin maintenance,

IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation

arXiv:2511.17384v2 Announce Type: replace-cross Abstract: While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reas

Inelastic Constitutive Kolmogorov-Arnold Networks: A generalized framework for automated discovery of interpretable inelastic material models

arXiv:2602.17750v2 Announce Type: replace-cross Abstract: A key problem of solid mechanics is the identification of the constitutive law of a material, that is, the relation between strain history and

InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics

arXiv:2607.05389v1 Announce Type: new Abstract: Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assump

Information-Geometric Superposed Vowel Evaluation: Part 1. Moraic Syllabary (Japanese)

arXiv:2607.04154v1 Announce Type: cross Abstract: This paper explains the principles and provides examples of a new method for distinguishing between FAKE human speech synthesized by generative AI and

InfraNet: Quality-Aware RGB Guidance for Efficient Infrared Object Detection

arXiv:2607.03795v1 Announce Type: new Abstract: Robust object detection under adverse visual conditions remains a long-standing challenge for multi-modal perception systems. Existing fusion-based meth

Local Ai

Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies

arXiv:2607.02560v1 Announce Type: new Abstract: Pedestrian-level wind prediction is essential for urban design and wind-comfort assessment, but high-fidelity simulations such as LES remain computation

local-aiarxiv-cs-cv

Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study

model-releasesarxiv-cs-ai

arXiv:2607.04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor 'oracle' code, or an entangled perceptual vector -- shape

InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360{eg} Image

arXiv:2607.03990v1 Announce Type: new Abstract: Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation

researcharxiv-cs-cv

Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas

arXiv:2607.04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in so

safetyarxiv-cs-ai

Integrated Forward-Inverse Network for Lensless Image Reconstruction

arXiv:2607.04608v1 Announce Type: new Abstract: Lensless imaging enables compact and versatile computational cameras by replacing bulky optics with thin coded elements. However, reconstruction from th

researcharxiv-cs-cv

Integrated Graph Search and Model Predictive Control for Smooth and Efficient Path Planning in Autonomous Vehicles

arXiv:2607.04259v1 Announce Type: new Abstract: Path planning is a fundamental component of autonomous vehicles, where achieving safe, comfortable, and dynamically feasible paths while ensuring comput

safetyarxiv-cs-ro

Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data

model-releasesarxiv-cs-lg

arXiv:2607.04647v1 Announce Type: cross Abstract: Scalable Bayesian inference for generalized linear mixed models (GLMMs) provides uncertainty-aware analysis of correlated longitudinal data, but exist

Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System

arXiv:2607.03125v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) offers powerful control for industrial cyber-physical systems (ICPSs), but its 'black-box' exploration risks violating

safetyarxiv-cs-lg

Interaction Dynamics for Dexterous Manipulation

arXiv:2606.14606v2 Announce Type: replace Abstract: Dexterous manipulation is fundamentally a problem of interaction dynamics: the hand must track precise finger trajectories, regulate the contact for

safetyarxiv-cs-ro

Interaction Techniques that Encourage Longer Prompts Can Improve Psychological Ownership when Writing with AI

arXiv:2507.03670v2 Announce Type: replace-cross Abstract: Writing longer prompts for an AI assistant to generate a story increases psychological ownership, a user's feeling that the writing belongs to

Tutorials

Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds

arXiv:2506.21887v2 Announce Type: replace Abstract: High-stakes decision-making involves navigating multiple competing objectives with expensive evaluations. For instance, in brachytherapy, clinicians

tutorialsarxiv-cs-ai

Local Ai

Internal Pluralism and the Limits of Pairwise Comparisons

arXiv:2607.02672v1 Announce Type: new Abstract: Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.g., in participatory design or alignment. However,

local-aiarxiv-cs-ai

InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

arXiv:2607.04988v1 Announce Type: new Abstract: Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through

safetyarxiv-cs-ro

Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

model-releasesarxiv-cs-ai

arXiv:2607.05393v1 Announce Type: cross Abstract: Time-domain surveys generate many transient candidates, making Real-Bogus classification a critical step in automated discovery pipelines. Reliable la

Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features

arXiv:2607.02553v1 Announce Type: new Abstract: Introduction: Objective neuroimaging biomarkers may improve Parkinson's disease motor assessment by capturing brain variation not directly observable fr

researcharxiv-cs-cv