OTF-CBM

★ 70

Optimal Transport Flow Concept Bottleneck Model for interpretable vision-language alignment.

A benchmark dataset for red-teaming multimodal agentic RAG systems.

Multi-level feature fusion diffusion model for skin lesion segmentation.

WatchAct

★ 70

Benchmark for behavior-grounded robot manipulation.

EVOM

★ 70

An agentic meta-evolution framework for discovering high-performance actor-critic architectures in RL.

Targeted backdoor framework for poisoning diffusion models.

Survey of vision-language perception paradigm evolution in MLLMs.

NEST-V1

★ 70

A multimodal framework for emotion-conditioned Nepali Sign Language avatar generation.

Index for measuring AI adoption and labor task capability using O*NET and MCP servers.

Publicly available lithography dataset for physics-informed world model research.

Simple, self-hostable restaurant table reservation management system.

Kalpana

★ 70

An Android launcher with local notification processing and reply suggestions.

Incus

★ 70

VS Code running on a remote server, accessible via a browser.

Applying CSS styling to ESP32 graphics libraries

Un0

★ 70

An image-generation system tool designed to significantly reduce AI power consumption.

Tw-fade

★ 70

Pure CSS scroll-driven edge masking for web interfaces.

Slint

★ 70

A declarative UI toolkit for building fluid, lightweight, and embedded-friendly GUIs.

tropius

★ 70

Detects AI tropes and patterns in prose to identify machine-generated text.

Automated system for producing Rivet routines from journal publications using LLMs.