All entries

Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing

arXiv:2607.01690v1 Announce Type: new Abstract: Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

DGX agent

arXiv:2607.01789v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing param

model-releasesarxiv-cs-ai

3 Jul 2026

ESC: Emotional Self-Correction for Reliable Vision-Language Models

arXiv:2607.02089v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Ex

Estimating Individualized Treatment Effects in Acute Ischemic Stroke with Causal Transformation Models (TRAM-DAG): A Multi-Centre Observational Study with External RCT Validation

arXiv:2606.12623v3 Announce Type: replace-cross Abstract: Personalized medicine in acute ischemic stroke requires moving beyond average treatment effects (ATE) to individualized treatment effect (ITE)

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

arXiv:2607.01852v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside the

Evidence-State Rewards for Long-Context Reasoning

arXiv:2607.02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods us

Evolutionary Feature Engineering for Structured Data

arXiv:2607.01548v1 Announce Type: cross Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering

Tutorials

Evolutionary Wave Function Collapse

arXiv:2607.02082v1 Announce Type: cross Abstract: Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to gene

tutorialsarxiv-cs-ai

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

arXiv:2607.02440v1 Announce Type: new Abstract: Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a

eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

arXiv:2607.01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture t

Exactly. I've been disseminating a similar message for years. The concentration of power in AI and the desire for control is by far the bigg…

Exactly. I've been disseminating a similar message for years. The concentration of power in AI and the desire for control is by far the biggest danger of AI. It could lead to a few private companies a

researchyann-lecun--x

Excited to share our paper, “Learning Multi-Agent Coordination via Sheaf-ADMM” to be presented at #ICML2026 Blog: https://pub.sakana.ai/shea…

model-releasesdavid-ha--x

Excited to share our paper, “Learning Multi-Agent Coordination via Sheaf-ADMM” to be presented at #ICML2026 Blog: https://pub.sakana.ai/sheaf-admm/ Most AI models process information as one giant, mon

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

arXiv:2607.01799v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcom

ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

arXiv:2607.01242v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used by end users, yet existing personalization methods relying on static profiles or text-only signals

Exploring Large Language Models for Access Control Policy Synthesis and Summarization

arXiv:2510.20692v2 Announce Type: replace-cross Abstract: Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow admi

Applications

Extreme Adaptive Transformer for Time Series Forecasting

arXiv:2607.02437v1 Announce Type: new Abstract: Time series forecasting remains challenging when the underlying data contain rare but critical extreme events. This issue is particularly important in h

applicationsarxiv-cs-lg

Applications

Fable: 'Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation…

applicationsethan-mollick--x

Fable: 'Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation and images using access to the APIs you have (elevenlabs, h

Fable's judgement

model-releasessimon-willison

One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use

Agents

FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning

arXiv:2607.01440v1 Announce Type: new Abstract: Faithful reasoning is essential in medicine, where clinical decisions require transparent justification grounded in reliable evidence. Current medical L

agentsarxiv-cs-cl

Fast and Accurate Anomaly Detection in Time Series

arXiv:2607.02046v1 Announce Type: new Abstract: Anomaly detection is a critical and evolving field in Machine Learning, with applications targeting different domains such as cybersecurity, finance, he

safetyarxiv-cs-lg

Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks

arXiv:2607.01266v1 Announce Type: cross Abstract: We study binary classification problems whose decision sets are given by definable sets in o-minimal expansions of the real field. Motivated by cell d

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

arXiv:2607.02396v1 Announce Type: new Abstract: Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behav

Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes

arXiv:2607.01297v1 Announce Type: cross Abstract: Most existing audio classification methods suppose that each query (testing) sample belongs to a class of support (training) samples, and misrecognize

Industry

Filing: GoDaddy challenges a New Delhi court ruling requiring domain sellers to stop offering privacy by default, saying it could expose website owners globally (Reuters)

Reuters: Filing: GoDaddy challenges a New Delhi court ruling requiring domain sellers to stop offering privacy by default, saying it could expose website owners globally — The world's biggest internet

industrytechmeme

Finite-Lag Operator Geometry of Recurrent Representations

arXiv:2607.01746v1 Announce Type: new Abstract: Recurrent representations are trajectories, but representation geometry is often measured from static snapshots. We develop finite-lag operator geometry

Industry

First builds of Model Y Long Wheelbase at Giga Texas

Tesla has begun initial production of the Model Y Long Wheelbase variant at its Gigafactory Texas facility. The Long Wheelbase version offers extended interior space and cargo capacity compared to the

industryelon-musk--x

Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery

arXiv:2607.01280v1 Announce Type: new Abstract: Programming-by-example systems infer programs from a small set of input-output examples. Robust PBE work usually models wrong examples as samples from a

Fourier Neural Operators for Rayleigh-Benard Convection

arXiv:2607.02088v1 Announce Type: new Abstract: We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Benard convection by predicting time increments instead of fu

Fourier Preconditioning for Neural Feature Learning

arXiv:2607.02199v1 Announce Type: cross Abstract: Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence str

Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations

arXiv:2607.01694v1 Announce Type: new Abstract: Solving partial differential equations (PDEs) with high-frequency solutions remains a central challenge in physics-informed machine learning due to spec

From Approximation to Emergence: A Theory of Deep Learning

arXiv:2607.01311v1 Announce Type: new Abstract: Deep learning has outgrown any single mathematical explanation. From Approximation to Emergence develops a unified, proof-oriented account of modern dee

safetyarxiv-cs-lg

From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Physics

arXiv:2603.13191v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have transformed AI agents into proficient executors of computational materials science, performing a hundr

From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection

arXiv:2512.10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiv

From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages

model-releasesarxiv-cs-cl

arXiv:2607.01502v1 Announce Type: new Abstract: Recent advances in automatic speech recognition (ASR) have explored different sequence models, including Conformer-based models and newer state space mo

Full Bayesian Reinforcement Learning via LF-IBIS

arXiv:2607.01741v1 Announce Type: cross Abstract: Reinforcement Learning (RL) is a sequential decision-making framework in which an agent learns optimal policies through interaction with an environmen

Fully Unsupervised Detection of Physical Contacts on Subsea Cables via State-of-Polarization Monitoring

arXiv:2607.01484v1 Announce Type: cross Abstract: We present a fully unsupervised Fast-Slow DSVDD detector for continuous State-of-Polarization monitoring on a deployed subsea cable. Trained without e

Tutorials

G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models

arXiv:2607.02491v1 Announce Type: new Abstract: In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a

tutorialsarxiv-cs-ai

Game Physics Just Got 170 Times Faster

researchtwo-minute-papers

This video from Two Minute Papers discusses groundbreaking research by NVIDIA that achieves a 100x speedup in physics-based character animations using AI-powered super-resolution applied to physics si

Applications

Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking

arXiv:2607.01824v1 Announce Type: new Abstract: Crowdsourced fact-checking systems have been adopted by major social media companies such as X, Meta, TikTok and Google with the aim of combating mislea

applicationsarxiv-cs-lg

Local Ai

GAP-GDRNet: Geometry-Aware Monocular Visual Pose Sensing on a Single-Target Synthetic Spacecraft Dataset

arXiv:2607.02360v1 Announce Type: cross Abstract: Monocular relative pose sensing is a central perception problem in non-cooperative rendezvous and on-orbit servicing. In spacecraft images, however, w

local-aiarxiv-cs-ai

Gemini Omni Flash can manipulate objects and environments in existing videos using simple text prompts. Sometimes it takes a bit of iteratio…

Gemini Omni Flash can manipulate objects and environments in existing videos using simple text prompts. Sometimes it takes a bit of iteration and specific prompting, but it opens up a lot of creative

model-releasescomfyui--x

Gender Differences in Research Topic and Method Selection in Library and Information Science: Perspectives from Three Top Journals

arXiv:2607.01828v1 Announce Type: cross Abstract: Research in the social sciences has shown that there are gender differences in the selection of research methods, with women often opting for qualitat

researcharxiv-cs-cl

Generalization in offline RL: The structure is more important than the amount of pessimism

arXiv:2607.02288v1 Announce Type: cross Abstract: While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering c

Generative AI and Federated Learning for Intrusion Detection Systems: A Survey

arXiv:2607.01305v1 Announce Type: cross Abstract: Intrusion Detection Systems (IDSs) are essential for monitoring network traffic and identifying malicious activities in modern cyber-physical, Interne

Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

arXiv:2607.01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without dow

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

arXiv:2607.01571v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps. While much a

Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity

arXiv:2511.02496v2 Announce Type: replace Abstract: We study latent geometry as an explicit component of representation quality in data-scarce learning. For an encoder (phi), we define (Q_{eta,gamma}(

Geometry-Aware R-Structured Kolmogorov-Arnold Networks

arXiv:2607.01449v1 Announce Type: new Abstract: We propose a novel hybrid neural architecture, the Geometry-aware R-Structured Kolmogorov-Arnold Network (GRS-KAN), which integrates V.L.Rvachev's R-fun