Research moves fast. resmon does, too.

resmon is a free desktop app. It asks arXiv, PubMed, OpenAlex, CrossRef, and 22 more on a schedule or when you ask, keeps every paper it finds on your computer, and records what each source did on every run. This is its morning view, drawn from a real collection.

Download resmon Install guide Version 1.0.0 for macOS, Windows, and Linux. Free, under the MIT license.

073090180 days since collected
new since today
a watch’s papers
more papers nearby

The plate: all 1,808 papers on the map, placed by how much wording they share, worked out on the computer that holds them. Drawn from the engine's own map and Today, exported unedited from a collection built on November 3, 2026: three watches' papers from arXiv, and three searches' from the sources they asked. The papers and the day's runs are real. For the watches' earlier papers, the day each was collected, and so how bright it is drawn, is set from its publication date.

New since today 18

Diffusion models

15 new

Ran today at 11:36 AM in 1 s · 45 found · 1 of 1 sources answered

4

Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks

Yusong Zhao, Edgar Y. Walker, Hao Wang, et al. arXiv F5

From the abstract Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain.
5

Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theory: Analytical Foundations and Numerical Scaling Tests

Gert Aarts, Diaa E. Habibi, Andreas Ipp, et al. arXiv F4

From the abstract Gauge-equivariant diffusion models can be used to generate ensembles of field configurations in non-abelian lattice gauge theories. Previously, we demonstrated the feasibility of modeling these theories by combining L-CNN-based diffusion models with the Metropolis-adjusted annealed Langevin algorithm (MAALA).
6

Fracture-Bench: A Controlled Benchmark Suite for Machine Learning Surrogates in Phase-Field Fracture Mechanics

Meenu Krishnan U., Maryam Hakimzadeh, Indrashish Saha, et al. arXiv E6

From the abstract Machine-learning surrogates are increasingly proposed to replace phase-field fracture simulations in many-query tasks such as uncertainty quantification, inverse analysis and design. Little controlled evidence shows which architectures are reliable, for which fracture problems and how far beyond their training data.
7

Online Class Posteriors for Interpretable and Controllable Discrete Diffusion

Felix Koulischer, Gianni Van De Velde, François Remy, et al. arXiv E3

From the abstract Discrete diffusion models remain far less understood than their continuous counterparts, despite recent breakthroughs across modalities, most notably in text.
8

When Optimization Meets Human Intent: Human-Centered Diffusion Model Optimization

Renye Yan, Jikang Cheng arXiv G5

From the abstract Diffusion models are evolving from general tools into personalized systems that adapt to user needs through fine-tuning and guidance. However, diffusion optimization mainly targets measurable objectives such as aesthetics, rarely examining whether they align with human intent.
9

Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion

Fei Peng, Junqiang Wu, Haoxian Tan, et al. arXiv G3

From the abstract Numerous distillation methods have been developed to accelerate diffusion models. Recent research indicates that hybrid strategies---blending different paradigms---yield superior results compared to single-method approaches.
10

Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score

Jerome Garnier-Brun, Giulio Biroli, Marc Mézard, et al. arXiv F4

From the abstract While state of the art for image and video generation, the fundamental reasons for the effectiveness of generative diffusion remain unclear.
11

Balancing Representations by Identifying and Generating Under-represented Data

Filipe Laitenberger, Hirokatsu Kataoka, Yuki Asano, et al. arXiv F5

From the abstract Self-supervised learning inherits the coverage of its source data. When an unlabeled corpus is long-tailed, the representation becomes dense around frequent modes and thin where coverage is weak. Objectives for long-tailed SSL reweight the images already in the corpus and add no new ones.
12

Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion

Zhengyang Yu, Akio Hayakawa, Masato Ishii, et al. arXiv H5

From the abstract Autoregressive video diffusion models (AR-VDMs) enable real-time, long-horizon video generation but degrade rapidly once the inference horizon outruns the training horizon, due to compounding exposure bias.
13

Train the Sampler You Run: Few-Step Masked Diffusion Language Models via Mixture-Likelihood Fine-Tuning

Amin Najafgholizadeh arXiv E3

From the abstract When a masked diffusion language model is sampled in a few parallel steps in a random order, the model actually run is a mixture over reveal plans, while cross-entropy training fits token conditionals rather than this mixture.
14

Latent Diffusion-GAN: Adversarial Learning in the Autoencoded Latent Space

U-Chae Jun, Jaeeun Ko, Jiwoo Kang arXiv G4

From the abstract Diffusion models are powerful generative frameworks for producing high-quality images by denoising latent variables from random noise.
15

W2A: Distilling World Priors into Action Models for Real-Time Robotic Control

Xiaopeng Zhang, Yongjin Mu, Yueyang Weng, et al. arXiv H5

From the abstract World Action Models (WAMs) have recently shown great promise in robotic control, benefiting from the future imagination capability of large-scale pretrained video models.
16

Probing Local Conditional Fit for Diffusion Model Membership Inference

ByungHee Cha, Naoki Murata, Yuhta Takida, et al. arXiv F3

From the abstract Membership inference determines whether a candidate example was used to train a text-to-image diffusion model and is an important tool for auditing training-data use.
17

Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm

Amindu Kumarasinghe, Vinh Bui, Reza Ghanbarzadeh arXiv F5

From the abstract Skin cancer classifiers need large sets of annotated images, which are scarce, especially for rare lesion types. AI-generated images can fill the gap, but a generator produces images of widely varying quality, so selecting which images to retain is important.
18

GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel

Gia-Huy Dinh, Thinh-Phuc Nguyen, Thanh-Hai Nguyen, et al. arXiv G5

From the abstract In virtual environments, choosing appropriate outfits requires contextual harmony with surrounding scenes, yet bridging the visual gap between 3D ambient views and catalog garment assets remains challenging.

Graph neural networks

3 new

Ran today at 11:36 AM in 1 s · 15 found · 1 of 1 sources answered

1

Certifying Graph Neural Networks Against Label and Structure Poisoning

Lukas Gosch, Xichuan Chen, Yan Scholten, et al. arXiv E4

From the abstract Robust machine learning for graph-structured data has made significant progress against test-time attacks, yet certified robustness to poisoning - where adversaries manipulate the training data - remains largely underexplored.
2

Resilient Cell-Free MIMO ISAC Under Uncertainties: An Impairment-Aware Graph Neural Network Framework

Oways Alsoloh, Robert-Jeron Reifert, Aymen Khaleel, et al. arXiv C6

From the abstract Beamforming designs for integrated sensing and communication (ISAC) in cell-free multiple-input multiple-output (MIMO) systems face the challenge to stay reliable under uncertainties from both channel state information (CSI) as well as clutter.
3

Control Foundation Models across Changing Block Diagrams: Generalizing Time-Series Prediction to Dynamic Graphs

Yuji Okamoto, Kenta Hoshino, Masaki Inoue arXiv E6

From the abstract In the prediction and control of physical systems, combining records from different experiments and operations is expected to supply information that no single experiment provides on its own.

Nothing new from

Protein structure

Ran today at 11:36 AM in 0 s · 1 found · 1 of 2 sources answered

CORE: no API key configured Why

CORE. Selected, but the API key it requires was not configured, so this source returned nothing. It did not contribute to the search.

The sources

26 sources

Every source resmon asks, with what the app tells you before a search: whether it needs your key, the rate resmon holds itself to, how it combines your terms, and the finest window of dates it can answer. Open a source for the rest.

The facts come from the catalog in resmon’s source code. What each source’s terms let resmon keep, and why some sources are not here, is in Sources and their terms.

What every source did

A quiet morning and a broken search must never look the same. resmon records what every source did on every run, and says why a source returned nothing: it answered and had nothing, it could not be asked, or it never answered. This is the Source wall of the collection above, starting with its verdict, word for word.

“CORE, DBLP, and Semantic Scholar have not answered any run resmon has a record of.”

CrossRef, DOAJ, EuropePMC, HAL, OpenAlex, PLOS, PubMed, and Zenodo answered when last asked and are no longer in the most recent run's saved selection.

What each of 12 sources did on each of 6 runs, recorded November 3, 2026. Choose a mark to read it.
Source	Tue, Nov 3						When last asked
Source	Run 52 11:35 AM	Run 53 11:35 AM	Run 54 11:35 AM	Run 55 11:36 AM	Run 56 11:36 AM	Run 57 11:36 AM	When last asked
arXiv							answered11:36 AM EST
CORE							no API key configured11:36 AM EST
CrossRef							answered11:35 AM EST
DBLP							could not answer this window11:35 AM EST
DOAJ							answered11:35 AM EST
EuropePMC							answered11:35 AM EST
HAL							answered11:35 AM EST
OpenAlex							answered11:35 AM EST
PLOS							answered11:35 AM EST
PubMed							answered11:35 AM EST
Semantic Scholar							did not answer11:35 AM EST
Zenodo							answered11:35 AM EST

Semantic Scholar · Deep Sweep, “protein structure” · 11:35 AM EST

did not answer

Semantic Scholar could not be queried: HTTP 429 after 4 attempts. This is not a zero — the source did not answer.

Papers
In this run’s selection: Yes

52 Deep Sweep, “protein language models”, 4 sources 11:35 AM EST · 240 returned · 234 new
53 Deep Dive, “equivariant graph neural networks”, 1 source 11:35 AM EST · 80 returned · 80 new
54 Deep Sweep, “protein structure”, 10 sources 11:35 AM EST · 147 returned · 147 new
55 Watch, Graph neural networks, 1 source 11:36 AM EST · 15 returned · 3 new
56 Watch, Protein structure, 2 sources 11:36 AM EST · 1 returned · 0 new
57 Watch, Diffusion models, 1 source 11:36 AM EST · 45 returned · 15 new

answered The source replied and returned records.
answered, zero The source replied and genuinely had nothing. A quiet field, not a fault.
answered in part The source answered every page; resmon stopped at its own time budget or the run's cap.
could not be asked No key, retired, no author query, or a window the source cannot answer.
failed The source was asked and the exchange broke.
outcome not recorded resmon did not observe an outcome. This is not a success and not a failure.
not asked on this run This run's saved selection did not name this source. Nothing was asked of it.

The Source wall of the same collection on November 3, 2026, exported unedited: three searches and each watch's run of the day, every one asked of the public sources for real.

The tour

2 min 13 s

0:00 Today What is new since you last looked, on a map of your whole collection.
0:22 A Deep Dive One source, asked in depth, and its papers on a map of their own.
0:38 A Deep Sweep Several sources at once, and how each one answered.
1:01 Watches A search that runs on a schedule, and the calendar of what is due.
1:25 Library Your own PDFs, read in focus mode.
1:41 Health What every source did on recent runs, and what needs attention.
1:58 Getting around The command palette, the shortcuts, and a swipe back.

Recorded on November 3, 2026, in a copy of the collection drawn above. The searches in it asked the public sources for real; the clicks are scripted, at a person’s pace.

What it does

Today: What is new since you last looked, on a map of everything you have collected. Papers sit by the wording they share, brighter the newer they are. The new ones are ringed and numbered, and each number is one entry in the list beside the map.
Watches: A search resmon runs on a schedule, keeping every paper it finds. A watch can follow words, a person’s new papers, or retractions and corrections on a person’s papers. The Calendar shows when each is due, and says so when nothing will run it.
Search: Ask the sources, or search what you already hold. A Deep Dive asks one source in depth and a Deep Sweep asks several at once. Before you ask, resmon lists each source’s limits: how it combines your terms, how finely it dates a paper, and whether it needs a key.
Library: A reading queue, your own files, and the passages you keep. Keep PDF, TXT, and MD files as unchanging copies in a folder you choose, read them in the app, and pin exact passages in Evidence projects. The Library is not yet available on Windows.
Ask: An assistant that reads your watches, runs, and papers. Through Claude Code or Codex under your own sign-in, or your own provider key. It uses the same tools an outside program can, and nothing is billed through resmon.
Health: Whether the watching itself is intact. The Source wall marks what every source did on each recent run. The Watchdog says what resmon can tell is wrong with its watching, and a check finds retractions and newer versions of papers you hold.
Outside the window: A command line, an MCP server, and a local HTTP API. The resmon command ships inside the app and installs from its menu. Tools that speak the Model Context Protocol can run watches and searches and read the collection.
Delivery and backup: Reports where you read them. Every run writes a report. A watch can email it, post it to a signed webhook, or put it in a folder or a feed on your own disk. Back up the database to a folder you keep.

Settings › Tutorials walks through each screen in the app, and the guide goes further.

On your computer

No account: There is nothing to sign up for, and no resmon server to sign in to.
Your collection: A database and a folder of reports on your own disk, with your watches, runs, and reading.
Your keys: Kept in your operating system’s keychain, never in the database, and sent only to the service they belong to.
No telemetry: resmon sends no usage data. A search sends its terms only to the sources it asks; summaries, delivery, and backup send only what you switch on, to where you point them.

Get it

Version 1.0.0 · MIT license

Platform	File	Tested
macOS, Apple Silicon	DMG	Used daily.
macOS, Intel	DMG	Built and opened by the release check on every release; not used daily.
Windows (x64)	Installer (.exe)	Built and opened by the release check; not used daily. The Library is not yet available.
Linux (x64)	AppImage	Built and opened by the release check; not used daily.

Download resmon

The macOS builds are not signed, so the first launch needs one extra step. Windows and Linux builds update themselves. The install guide covers both, and running from the source.