All entries

This post captures excitement about an upcoming presentation by Swyx at an AI Engineer conference, noting the unexpectedly large attendance at the event's world fair component. The message was posted

toolsswyx--x

Research

3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems

DGX agent

arXiv:2603.02149v2 Announce Type: replace Abstract: Volume denoising is a foundational problem in computational imaging, as many 3D imaging inverse problems face high levels of measurement noise. Insp

researcharxiv-cs-cv

30 Jun 2026

3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

model-releasesarxiv-cs-cv

arXiv:2606.30514v1 Announce Type: new Abstract: Human image animation, which aims to generate a video of a reference subject following a provided action sequence, has received increasing research inte

5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control

arXiv:2606.28737v1 Announce Type: cross Abstract: We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. Multi

A Bayesian latent Gaussian process framework for aerodynamic uncertainty quantification

model-releasesarxiv-cs-lg

arXiv:2606.28871v1 Announce Type: cross Abstract: Predicting the aerodynamic performance (e.g. lift, drag, and moment coefficients) of an aircraft is challenging -- computational models are biased and

Tutorials

A binarized-domains arc-consistency algorithm for TCSPs: its computational analysis and its use as a filtering procedure in solution search algorithms

arXiv:2002.11508v3 Announce Type: replace Abstract: TCSPs (Temporal Constraint Satisfaction Problems) [Dechter et al. 1991] get rid of unary constraints by binarizing them after having added an 'origi

tutorialsarxiv-cs-ai

Tools

A candid hallway track interview with the man himself - @swyx Mini Podcast if you will, he's told me about a huge milestone tomorrow, things…

A candid hallway track interview with the man himself - @swyx Mini Podcast if you will, he's told me about a huge milestone tomorrow, things that have surprised him about @aiDotEngineer and ... a few

toolsswyx--x

Safety

A causal modeling perspective on decision theory

arXiv:2606.29911v1 Announce Type: new Abstract: Decision theory provides a formal framework for how agents should make choices under uncertainty, drawing on ideas from philosophy, probability, and cau

safetyarxiv-cs-ai

A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP

arXiv:2606.30342v1 Announce Type: new Abstract: Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely

A Cognition-Emotion-Personality Framework for Modeling Human-Like Awareness and Behavior in Emergency Evacuations

arXiv:2606.29212v1 Announce Type: new Abstract: Agent-based evacuation simulations are widely used to study crowd behavior during emergencies, but many models rely on assumptions such as perfect event

agentsarxiv-cs-ai

a common pattern for (a part of) memory that we see: Wiki Memory Examples: - DeepWiki (@cognition) - AutoWiki (@FactoryAI) - LLM Wiki (@karp…

This post describes a common architectural pattern for integrating memory components into AI systems, illustrated through examples like DeepWiki and AutoWiki that automatically generate and maintain k

agentsharrison-chase--x

A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories

arXiv:2606.29068v1 Announce Type: cross Abstract: Text encoders are known for their utility in natural language processing, as they are able to efficiently compress inputs into dense vectors while pre

A Conditional GAN for Tabular Data Generation with Probabilistic Sampling of Latent Subspaces

arXiv:2508.00472v2 Announce Type: replace Abstract: The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, t

A conversation is all it takes to launch powerful ComfyUI workflows. This showcase demonstrates how Comfy MCP can generate, refine, and iter…

A conversation is all it takes to launch powerful ComfyUI workflows. This showcase demonstrates how Comfy MCP can generate, refine, and iterate on creative assets using natural language. To try this w

agentscomfyui--x

A Deep Multiscale Neural Network for Accurate Neurological Disorder Detection from MRI Scans and Real-Time Web Deployment

arXiv:2606.29106v1 Announce Type: cross Abstract: Neurological disorders involve diverse pathologies of the brain and nervous system, making early and accurate detection essential. While many deep CNN

A Deterministic Sampling Method via Maximum Mean Discrepancy Flow with Adaptive Kernel

arXiv:2111.10722v4 Announce Type: replace-cross Abstract: We propose a novel deterministic sampling method, EVI-MMD, to approximate a target distribution rho^* by minimizing the kernel discrepancy, al

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

model-releasesarxiv-cs-cl

arXiv:2606.29719v1 Announce Type: cross Abstract: Measurements of proprietary LLM evaluators can become invalid within weeks -- we document one case and provide the diagnostic framework to detect it.

Tutorials

A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems

arXiv:2606.30230v1 Announce Type: cross Abstract: Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution dur

tutorialsarxiv-cs-lg

A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition

arXiv:2606.30159v1 Announce Type: new Abstract: Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in

A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training

arXiv:2606.28526v1 Announce Type: new Abstract: The clinical and communication skills of medical students are commonly assessed through Objective Structured Clinical Examinations (OSCEs), which consis

researcharxiv-cs-cl

Applications

A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks

arXiv:2606.28531v1 Announce Type: cross Abstract: Automatically generated videos from scientific papers are increasingly used for education and research dissemination. However, existing evaluation met

applicationsarxiv-cs-cl

Safety

A Gravitational Interpretation of Fine-Tuning Reversion

arXiv:2606.28525v1 Announce Type: cross Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearne

safetyarxiv-cs-ai

A great read from @LangChain Best framing I've seen for agent architecture. Every non-model piece like the filesystem, sandbox, compaction, …

A great read from @LangChain Best framing I've seen for agent architecture. Every non-model piece like the filesystem, sandbox, compaction, Ralph loops exists to patch a specific model limitation. htt

agentsharrison-chase--x

Local Ai

A Hybrid Framework For Crypto-Ransomware Detection In Enterprise Shared Storage

arXiv:2606.30586v1 Announce Type: cross Abstract: Most corporate workplace environments enforce policies and technical controls that limit the storage of sensitive data on client endpoints. Consequent

local-aiarxiv-cs-lg

Safety

A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment

arXiv:2606.29273v1 Announce Type: cross Abstract: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song. As a result, lyric

safetyarxiv-cs-ai

A Kernel Fisher Discriminant Analysis-Based Tree Ensemble Classifier: KFDA Forest

arXiv:2606.29053v1 Announce Type: new Abstract: In general, an ensemble classifier is more accurate than a single classifier. In this study, we propose an ensemble classifier called the kernel Fisher

Applications

A Knowledge Theory of Capital:The Value of Natural and Artificial Intelligence, Volume 1

arXiv:2606.18288v2 Announce Type: replace-cross Abstract: This volume develops a knowledge theory of capital for economies in which productive capacity increasingly resides in software, data, models,

applicationsarxiv-cs-ai

A Linear Matching Bandit Approach to Online Multi-Human Multi-Robot Teaming

arXiv:2606.29221v1 Announce Type: new Abstract: We address the problem of online multi-human multi-robot teaming through the lens of a linear matching bandit framework, where a learner assigns robots

A living map of everything your Hermes agent has learned; every memory & skill Press play to watch it unfold, @NousResearch Copy yours into …

This post from Nous Research demonstrates a visualization tool or system that maps the accumulated knowledge, memories, and skills learned by a Hermes AI agent during its training or operation. The in

agentsnous-research--x

A Machine-Verified Proof of a Quantum-Optimization Conjecture

arXiv:2606.29687v1 Announce Type: cross Abstract: We report a machine-verified resolution of a problem open for over a decade in quantum optimization: the Farhi, Goldstone and Gutmann (FGG) conjecture

A Mathematical Optimization Approach for Expert-Informed Bayesian Best Subset Selection

arXiv:2606.29516v1 Announce Type: new Abstract: A central challenge in statistical modeling is identifying the subset of features that belong in the true regression model. The classical best subset se

A Mechanistic Study of Transformers Training Dynamics

arXiv:2410.24050v3 Announce Type: replace Abstract: Large-scale pretraining of transformers has been central to the success of foundation models. However, the scale of those models limits our understa

A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP

arXiv:2508.02923v3 Announce Type: replace Abstract: Maximum A Posteriori (MAP) estimation is a cornerstone framework for blind inverse problems, where an image and a forward operator are jointly estim

A multi-architecture study of specificity refinement and false-positive mechanism analysis in prostate MRI

model-releasesarxiv-cs-cv

arXiv:2606.29977v1 Announce Type: cross Abstract: Objectives: To characterize residual false positives in prostate MRI detection, and to evaluate a lightweight post-hoc refinement head for case-level

A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories

arXiv:2606.30209v1 Announce Type: cross Abstract: We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels

A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure Diagnosis

arXiv:2606.29193v1 Announce Type: cross Abstract: LLM-based agents are reshaping microservice operations into AgentOps, where benchmarks are key to evaluating failure diagnosis over multimodal observa

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

arXiv:2606.30572v1 Announce Type: cross Abstract: Malware classification remains a challenging problem due to its inherent heterogeneity, the presence of packed binaries, and the diverse distribution

A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI

arXiv:2606.28684v1 Announce Type: cross Abstract: Causally linking disease-related factors to image-derived biomarkers provides a powerful pathway to understanding disease mechanisms. Despite growing

A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization

arXiv:2606.29112v1 Announce Type: new Abstract: Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks

Local Ai

A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility

arXiv:2606.28751v1 Announce Type: new Abstract: We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world

local-aiarxiv-cs-lg

A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

model-releasesarxiv-cs-cv

arXiv:2606.28757v1 Announce Type: new Abstract: Generative world models hold immense promise as scalable simulators for autonomous systems, particularly for synthesizing rare but safety-critical multi

A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises

arXiv:2606.30309v1 Announce Type: new Abstract: Rehabilitation exercises are essential in restoring lost physical functions of patients suffering from various diseases (e.g., Parkinson's, back pain).

A Posteriori Error Analysis for Decoupled Neural Approximations of Fully Coupled FBSDEs with Control Mismatch

arXiv:2606.29474v1 Announce Type: cross Abstract: This paper develops an a posteriori error analysis framework for decoupled neural approximations of fully coupled forward--backward stochastic differe

A Probabilistic Approach to Trajectory-Based Optimal Experimental Design

model-releasesarxiv-cs-lg

arXiv:2601.11473v2 Announce Type: replace-cross Abstract: We present a novel probabilistic approach for optimal experimental path design. In this approach a discrete path optimization problem is defin

A Query-Driven Communication-Efficient Digital Twins Design for Autonomous Driving

arXiv:2606.28384v1 Announce Type: cross Abstract: Digital twins (DTs) have become a potential technology to perform risk-free simulation of physical entities for deterministic and high-reliability ser

agentsarxiv-cs-ai

A Self-Supervised Learning Framework for Video Encoding Complexity Clustering

arXiv:2606.29166v1 Announce Type: cross Abstract: Adaptive video streaming is a widely used technique for delivering video content over the internet. One of the key challenges is determining the optim

A Stochastic--Geometric Theory of Scaling Laws in Grokking

arXiv:2606.30388v1 Announce Type: cross Abstract: Delayed generalization (ie~grokking) refers to the phenomenon in which a neural network fits its training data early in training but only begins to ge

Local Ai

A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterpr…

A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared

local-aiclem-delangue--x