Tag

Seedance

Generates 1080p videos from text or images, with native multi-shot storytelling that keeps subjects, style, and atmosphere consistent across cuts. Ranked first on Artificial Analysis T2V and I2V leaderboards, ahead of Veo 3 and Kling 2.0.

AIBrix

Cloud-native control plane that scales vLLM on Kubernetes, adding the routing, autoscaling, and fault tolerance single-instance serving lacks. Brings high-density LoRA management, an LLM gateway, distributed KV cache reuse, and SLO-aware GPU serving.

verl: Volcano Engine Reinforcement Learning for LLMs

Open-source HybridFlow implementation for RL post-training of LLMs. Decouples control flow from compute so PPO, GRPO, GSPO and DAPO share one dataflow; pairs FSDP/Megatron with vLLM/SGLang rollout and reports 1.5-20x throughput over prior RLHF stacks.

Protenix

High-accuracy biomolecular structure prediction suite: open-source models (protenix-v2/v1), a benchmark/evaluation toolkit, and a web server for inference. Targets protein/antibody–antigen and ligand-aware predictions with inference-time sampling and constraint support.

UI-TARS Desktop

Drives your computer from natural language: a vision-language model reads raw screenshots and works the mouse and keyboard like a person, controlling any GUI app without APIs or accessibility hooks. Local or remote operator modes on Windows and macOS.

UI-TARS

Reads GUI screenshots and directly outputs desktop, mobile, and browser actions — clicking, typing, navigating — as one end-to-end vision-language model rather than a modular pipeline. Scores 84.8% on WebVoyager and 42.5% on OSWorld.

DeerFlow

Orchestrates a lead agent, isolated parallel sub-agents, long-term memory, and sandboxes for long-horizon tasks — minutes to hours of deep research, coding, and content creation. LangChain/LangGraph-based with extensible skills; v2 is a full rewrite.

Dolphin

Converts document images—scans, photos, born-digital PDFs—into structured text in two stages: first map layout and reading order, then parse each element (text, tables, formulas, figures) in parallel, each guided by its own task prompt.

MineContext

Continuously screenshots your screen, feeds the captures to a vision-language model, then pushes back daily summaries, weekly recaps, and todos on its own. Local-first desktop app: data stays on your machine; runs on OpenAI-format or local LLMs.

OpenViking

Models an AI agent's context as a file system, unifying memory, resources, and skills instead of flat vector RAG. Uses L0/L1/L2 tiered loading to cut tokens, directory-recursive plus semantic retrieval, and visualized retrieval traces for debugging.

Seedance 2.0 Skill OS

Converts scene intent into production-ready Seedance 2.0 prompts, reference-role mappings, and IP-safe rewrites for multimodal (text/image/audio/video) video generation. Ships as a modular agent-skill OS with multilingual examples, troubleshooting tools, and pro filmmaker handoff artifacts.

CUDA-Agent-Ops-6K

Provides 6,000 runnable, operator-level PyTorch tasks for training and evaluating CUDA kernel generation models; each sample includes executable code, operator descriptors, and provenance tags, with execution-driven filtering to ensure reproducibility and contamination control.