PixelRAG is an open-source, native visual RAG framework developed by Berkeley's SkyLab/BAIR. Instead of the traditional approach of extracting web pages into plain text for retrieval, the framework uses the browser to render web pages and PDFs into screenshot tiles, fine-tuning them using LoRA...
Grok Bot is an AI Agent system launched by SpaceXAI. It can log into a user's account and operate websites and tools like a real person, performing tasks for the user 24/7 in the cloud. The system supports multiple bots working in parallel, recording...
dots.tts is a 2 billion-parameter fully continuous autoregressive speech synthesis foundation model jointly open-sourced by the Xiaohongshu dots team and the Shanghai Jiao Tong University X-LANCE Lab. The model directly generates 48kHz audio block by block in a continuous latent space...
DeepSeek Harness is an AI agent runtime framework launched by DeepSeek, with the core concept of 'Model + Harness = Agent'. The framework utilizes engineering modules such as context management, tool call orchestration, and execution sandboxing...
Nemotron 3.5 Lightning is an open-source MoE model with 30 parameters from NVIDIA, optimized for multi-agent systems. Compared to similar models, it offers 4x faster output speed and 30% faster agent task completion...
HOMIE is an open-source digital human video generation framework from the Hong Kong University of Science and Technology. It is based on the Wan2.1-T2V-14B backbone network and integrates the Qwen3-VL multimodal large model. The framework can uniformly handle four elements: digital human, product, logo, and text...
PAST-Bench is a benchmark test developed by Mengdi Wang's team at Princeton University to examine the recursive self-improvement capabilities of personal AI agents. PAST-Bench compares task performance under conditions with and without memory to determine...
Shotcut is an open-source video editing software based on FFmpeg. It is completely free, watermark-free, and has no duration limit. The software supports hundreds of audio and video formats for direct editing without importing, and offers multi-track timelines, keyframe animation, and rich features...
Palmier Pro is a native macOS video editor built from scratch in Swift for the AI era. It's open-source and its basic functions are free. The product embeds generative AI directly into the timeline, supporting Seedance, Kling, and more...
GPT-5.6-Cyber is an AI model developed by OpenAI specifically for cybersecurity. It is built on GPT-5.6 Sol and enhanced for specialized tasks such as vulnerability exploitation and privilege escalation. The model is only available to Daybreak Red level audit customers and...
Muse Glimmer is an open-source language model from Meta with 30 billion parameters, deeply optimized for 24/7 local agent workflows. The model utilizes 4-bit quantization technology, allowing it to run on a single GPU with 24GB of VRAM or...
SmartSub is an open-source, one-stop desktop tool for audio and video subtitling. It integrates the entire workflow into a single application, providing offline speech-to-text conversion based on local models such as Whisper, FunASR, and Qwen3-ASR, and supports 2...
Wan-Animate-2 is a new generation of character animation model open-sourced by the Wanxiang team. As a major architectural upgrade to Wan-Animate, it abandons the dependence on explicit pose skeletons and auxiliary pose extraction networks, replacing them with an end-to-end dual-branch architecture...
Grok Imagine Image 2.0 is a new generation image generation and editing model released by SpaceXAI, available in "Quality Mode" on the grok web platform and iOS and Android apps. It's more than just "re-picking an image"...
SALMONN-2 is a general-purpose audio language model jointly open-sourced by Tsinghua University, Shanghai Artificial Intelligence Laboratory, and the University of Cambridge. It is built upon ByteDance's SPEAR unified self-supervised audio encoder and multi-layer feature fusion adapter, and...
Wan3.0 is the latest video generation model launched by the Alibaba Cloud Wanxiang team. The model has been comprehensively upgraded in dimensions such as generation duration, versatile creation, all-around reference, and realism. It can generate 30-second videos in a single run and supports doc, xls, and other formats for the first time.
Hunyuan3D-Buffalo 1.0 is a unified 3D multimodal framework launched by Tencent Hunyuan. It integrates 3D question answering, spatial positioning, text-based 3D, instruction editing, and component generation into a single process through the shared Hunyuan3D-VLM backbone.
InstructAV2AV is an audio and video co-editing model jointly developed by the Beijing Academy of Artificial Intelligence and Peking University. Users only need a single natural language command to simultaneously edit video footage and corresponding content during the end-to-end generation process...
JoyAI-Video-Edit is a real-time streaming video editing model developed and open-sourced by JD.com. Based on a 16B-parameter autoregressive diffusion architecture, it achieves an inference speed of 30FPS at 720P resolution and supports stable streaming editing of any duration.
SeedRealtime is a native full-duplex audio and video model launched by ByteDance's Seed team. Based on a unified architecture, it natively integrates audio, video, and text to achieve real-time multimodal interaction, allowing users to watch, listen, and speak simultaneously.
MAGI-2-preview is Sand.ai's open-source MoE multimodal video generation model, boasting a total of 114 bytes of parameters and only 6 bytes of activation. The model continues the single-stream architecture, integrating text, video, and audio into a single T...
Shieldstral is an open-source, multimodal content security classification model with 3B parameters, developed by Mistral AI and built upon Ministral-3B. The model redefines traditional fixed-category content moderation as a binary question-answering task...
MemHarness is an LLM agent memory reconstruction framework developed by the Shanghai AI Lab in collaboration with universities such as Zhejiang University, Fudan University, and Shanghai Jiao Tong University. Existing memory enhancement agents often directly inject retrieved historical experiences into the context, but if old experiences...
Hy ASR 3.0 preview is a next-generation speech recognition model launched by Tencent Hunyuan. Based on the Hy3 large language model, it integrates high-precision speech recognition with deep semantic understanding. The model supports Mandarin, English, Cantonese, and 10 major dialect regions...