A framework for building rich, real-time user interfaces without writing complex JavaScript.

A hybrid Mamba model for audio-visual navigation using Mamba State Encoders.

Framework for self-aware policy execution in Vision-Language-Action (VLA) models for robots.

A peer-community benchmark for measuring LLM structural intelligence and factual accuracy.

Geometry-Aware Low-Rank Adaptation for RLVR to preserve pre-trained structures and improve efficiency.

A looped visual reasoner for visual abstract reasoning tasks using grounded trace supervision.

Benchmark for project-level multi-screen mobile app generation.

Self-Evolving Skill-Augmented Agent framework for tool-augmented search self-play.

An open-source CRM built to integrate AI agents for automated customer relationship management.

An intent-governed authorization layer for restricting AI agent tool access.

A self-evolving agent harness that extracts episodic memory and state graphs to improve LLM agent reliability.

Self-hosted radio station server with an AI DJ.

Time-Frequency Consistency Learning framework for robust speech deepfake detection.

Reliability-Guided Evidence Fusion framework for robust UAV-satellite cross-view geo-localization.

Parameter-efficient framework for EEG-to-text decoding using contrastive learning.

A 0.9B-parameter vision-language-action model for robotic action sequences.

Knowledge-enhanced memory evolution for remote sensing agents to improve tool execution.

A mechanism to prevent memory contamination in LLM agents via self-consistency admission control.

A serving-native framework for deploying mechanistic interpretability apps in production inference environments.

Open-source Cloudflare deployed agent native task management and wiki.