Python

Page 1 of 1

A novel framework overcoming high-resolution bottlenecks with mask-free shifted-window attention and lightweight autoencoders for live-stream applications.

SwiftVR: Real-Time Generative Video Restoration on Consumer GPUs

SwiftVR is a streaming one-step generative video restoration framework for live-stream applications. It addresses consumer GPU bottlenecks with mask-free shifted-window self-attention and a lightweight autoencoder, achieving real-time 1080p streaming on consumer-grade GPUs and 4K on H100.

A practical guide to mnemo, a Rust-based sidecar service providing structured, persistent memory for LLMs without cloud dependencies.

mnemo: Local-First Knowledge Graph for Persistent LLM Memory

mnemo is a local-first memory layer for LLMs, offering persistent, structured context via a sidecar service. It extracts entities and relationships into a knowledge graph from raw text, and retrieves ranked context for LLM prompts, supporting fully local setups with Ollama or integration with OpenAI.

Achieving state-of-the-art performance with AudioVAE, full-history conditioning, and reward-free self-corrective post-training for robust, expressive, and efficient speech synthesis.

dots.tts: 2B-Parameter Continuous Autoregressive TTS Foundation Model

Introducing dots.tts, a 2B-parameter continuous autoregressive text-to-speech foundation model. It leverages AudioVAE, full-history conditioning, and self-corrective post-training for unparalleled performance on multilingual benchmarks, offering strong generation stability, voice cloning, and emotional expressiveness with efficient MeanFlow distillation.

Transform a cheap desk toy into an intuitive, glanceable indicator for AI agent activity, freeing your focus from the monitor.

Your AI Assistant Doesn't Need a Screen: Build a Physical Status Lamp

Learn how to build CursorLight, a physical status lamp for Cursor Agent using an ESP32-C3 and a rewired traffic light toy. Get real-time, glanceable feedback on AI's thinking, busy, success, or error states without watching your screen. Includes hardware, software, and wiring guides.

Learn to use MLLM-Jailbreak-Bench, a reproducible and model-agnostic framework for measuring harmful output in multimodal large language models.

How to Evaluate Multimodal LLM Safety with MLLM-Jailbreak-Bench

Discover MLLM-Jailbreak-Bench, an evaluation framework for assessing multimodal LLM safety across five attack categories. Understand how to measure Attack Success Rate, refusal quality, and calibration error to identify real safety gaps and avoid false positives. Get started with installation and quick-start instructions.

Explore the Diffusion Transformer with Flow Matching that powers high-fidelity 48 kHz audio generation from natural language.

How MOSS-SoundEffect v2.0 Revolutionizes Text-to-Audio Synthesis

Discover MOSS-SoundEffect v2.0, a cutting-edge text-to-audio model using a 1.3B-parameter Diffusion Transformer and Flow Matching for superior sound generation. Learn about its capabilities, multilingual support, and optimal settings for creating diverse audio content.

Models are no longer bounded by single-call context windows; SkyRL's infrastructure enables execution-driven meta-reasoning via stateful child agents.

The Recursion Ceiling is a Myth: NovaSky Unleashes Recursive Language Models

Discover how NovaSky's SkyRL framework shatters the limitations of large language models. By spawning recursive child agents within persistent Python sandboxes, models can now reason in multi-turn, multi-agent trees, redefining what "thinking" means for AI.

Full fine-tune family based on Alibaba's Z-Image S3-DiT, with variants for quality, speed, and low VRAM.

Z-Anime: Full Anime Fine-Tune on Z-Image Base

Z-Anime is a full fine-tune of the Z-Image Base architecture, not a LoRA merge. It provides anime-style generation with natural language prompting, high diversity, and multiple variants including Base, Distill-8-Step, Distill-4-Step, GGUF, and AIO. Supports 8GB VRAM and includes VAE and text encoder.

From zero-day exploits to autonomous malware, state-sponsored and criminal actors increasingly use AI for vulnerability discovery, evasion, and operations.

GTIG AI Threat Tracker: Adversaries Weaponize AI for Cyber Attacks

Google Threat Intelligence Group's latest report reveals how adversaries exploit AI for vulnerability discovery, obfuscation, autonomous malware (PROMPTSPY), information operations, and supply chain attacks. Includes first identification of an AI-developed zero-day exploit.