Tencent just released Hunyuan Hy4, upgraded with vision and computer-use capabilities to run complex workflows across apps like Blender and CAD. It tackles knowledge work like financial modeling and 3D scientific reconstruction, with open weights coming in days.
Tencent just introduced Hy4, its new flagship model rivaling top open models on benchmarks with built-in vision and computer use. The model is already accessible on Tencent Cloud and OpenRouter, with open weights dropping soon alongside ecosystem partnerships with vLLM and SGLang.
Tencent Hunyuan just open-sourced Hy-SimulMT, a bidirectional Chinese-English simultaneous translation model with roughly 3-second streaming latency. Beyond delivering real-time speech and text, it clones the speaker's vocal tone into the target language. The repository includes full inference and training tools, designed to keep multilingual meetings moving without awkward pauses.
Tencent's WeChat Vision Team just open-sourced WeVisOne-VL, an all-in-one vision model in 2B and 4B sizes that unifies detection, counting, OCR, and matting. It ditches heavy external segmentation models like SAM in favor of a tiny 9.6M-parameter decoder, generating hair-level alpha mattes while reliably rejecting absent targets. Weights and code are out under Apache 2.0.
Tencent just open-sourced Hy-Nomas, an interactive world generation model that turns natural language and camera trajectories into 720p virtual environments. By generating short chunks with persistent memory, it keeps scenes consistent for over a minute, and a 9GB distilled version runs locally on a single consumer GPU under Apache 2.0. Why it matters: It brings real-time interactive video down from datacenter clusters to individual creators and robotics researchers.
Tencent just open-sourced Hy-Memory 2.0, a unified memory system that lets different AI tools like Cursor and Codex share the exact same context. Paired with a 30B model and the MemHub app, it tracks chat history, task workflows, and code diffs across platforms. Why it matters: switching between coding agents no longer means starting from scratch.
Researchers from Tencent and HKU just open-sourced Multix, a world model capable of simulating multiple players interacting in the same environment. It generates individual camera views while syncing player states, cutting computation by 86% with hierarchical communication. Trained on just 4 players, it scales up to 10 without extra training.
Researchers from Fudan University, Tencent Hunyuan, and Zhejiang University just open-sourced Prism, a framework designed for native 2K joint video-audio generation. Instead of wasting compute across every pixel, Prism uses dynamic sparse attention to focus on sound-producing and rapidly changing visual regions, speeding up training by 2.5x while keeping audio and video tightly synchronized. Preview weights and inference scripts are already available on Hugging Face.
Tencent researchers just introduced WorldCrafter, an interactive video world model with an implicit 3D-aware memory that remembers scene structure when the camera turns away and revisits. It turns text prompts or single images into minute-scale explorable environments, with distillation enabling real-time streaming. Basically, AI video worlds no longer forget what was behind you.
Tencent just open-sourced AuK, a 1.5B foundation model that lets you generate and edit speech using simple text prompts. Beyond zero-shot voice cloning, it can seamlessly insert or delete words from existing audio, tweak emotional tone, and remove background noise. It brings text-editor simplicity to voice workflows and runs on consumer GPUs.
Tencent just open-sourced Hy4 preview, a 770B-parameter MoE model (49B active) with a 1M context window tailored for real-world coding, finance, and scientific tasks. Crucially, the model helped train itself through a recursive self-improvement loop for data strategy and kernel optimization. It is already rolling out across Tencent products like Yuanbao and CodeBuddy.
Tencent just introduced WorldClaw, an agentic system that turns a single text prompt into an explorable, editable 3D open world. It maps large-scale terrain, populates regions with textured meshes, and deploys render agents to tweak contacts and object poses—all while keeping every single asset reusable.
Tencent just open-sourced Octop, a self-hosted platform that runs a multi-agent environment from a single local process. It connects directly with chat apps like WeChat, Feishu, and Discord, letting specialized agents collaborate on complex workflows while keeping all conversation history, knowledge bases, and memory strictly on your own machine.
Tencent just introduced Hunyuan3D-Buffalo 1.0, a unified multimodal framework handling 3D generation, visual reasoning, natural language editing, and part decomposition in one pipeline. Powered by a shared VLM backbone and DiT modules, it lets creators edit or break down 3D meshes using plain text prompts without chaining multiple standalone tools.
Tencent just open-sourced Hy3, a 295B-parameter Mixture-of-Experts model that activates 21B parameters per token. Tuned for agentic workflows and coding, it boasts a 256K context window and cuts hallucination rates down to 5.4% in internal evaluations. It offers developers a cost-effective, Apache 2.0-licensed alternative to massive proprietary frontier models.
Tencent researchers just introduced SCoPE, a camera control method for video diffusion models that treats camera rays as a second positional coordinate. By adding less than 0.1% parameters to pretrained models, it achieves precise trajectory control and locks revisited scenes in place without geometric drift.
Tencent just open-sourced Hy-MT2, a multilingual translation model supporting 33 languages in 1.8B, 7B, and 30B MoE sizes. Using AngelSlim 1.25-bit quantization, the 1.8B version shrinks down to just 440MB for smooth on-device use. It prioritizes controllable output like preserving JSON structure and enforcing terminology consistency, making edge-based localization surprisingly practical.
Tencent just open-sourced HYMT2, a family of multilingual translation models spanning from 1.8B to 30B parameters. Unlike standard translation tools, HYMT2 is fine-tuned to follow strict structural prompts, keeping code placeholders and JSON keys intact. Thanks to ultra-low bit quantization, the 1.8B version can run directly on everyday smartphones.
Tencent's Hunyuan team just open-sourced HY-World 2.0, moving beyond video-only world models to produce actual, editable 3D assets. It transforms text, images, or video clips into meshes and 3D Gaussian Splats ready for Unity, Unreal Engine, and Isaac Sim with physics-aware navigation.
Tencent just open-sourced Covo-Audio-Chat, a 7B end-to-end audio language model. It processes continuous audio directly in a unified architecture to enable native, low-latency full-duplex conversations that can listen, speak, and handle interruptions on the fly. Weights and code are now available on Hugging Face and GitHub.
