ByteDance

Felis is an open-source, automated, and scalable toolkit designed for high-throughput Absolute Binding Free Energy (ABFE) calculations. Paired with By…

Most recent general-purpose AGI model designed for complex real-world task execution.

An open-source, trainable reproduction of AlphaFold 3 (AF3) for biomolecular structure prediction. Protenix is designed to predict the 3D structures o…

Next-generation AI video model with unified multimodal audio-video joint generation. Supports text, image, audio, and video inputs with multi-shot nar…

Policy gradient-based mask learning for massive-scale pre-training data selection.

1.5 trillion-token "distilled" subset of common crawl data optimized for pre-training.

A next-generation biomolecular folding model that scales up model capacity and performance beyond AlphaFold3. SeedFold introduces a width-scaling st…

Generalized agentic model with multimodal input (text + image). Industry-leading GUI agent, search, and code generation capabilities across desktop, w…

Unified spacetime autoregressive modeling framework for visual generation. Extends autoregressive approaches to jointly model spatial and temporal dim…

Foundation model for generating simulation-ready 3D assets from single images.

Introduces a multi-resolution systematically improvable quantum embedding scheme for large-scale surface chemistry calculations. This work enables h…

Robotic wrist design and learning framework for flexible, anthropomorphic motion.

Unified framework for text-to-image, image editing, and multi-image composition. Ranked first on both T2I and image-editing leaderboards.

Open-source framework for scaling any-modality foundation model training.

Industry-level video foundation model for unified text-to-video (T2V) and image-to-video (I2V) generation.

Open-source 36B-parameter LLM with 512K context window. Achieves strong performance across reasoning, agent, and general tasks despite being trained o…

A comprehensive survey co-authored by ByteDance Seed researchers providing a systematic taxonomy and roadmap for AI in the natural sciences. The pape…

A generative protein binder design suite featuring diffusion-based backbone generation (PXDesign-d) and hallucination-based methods (PXDesign-h). Va…

Research on scaling any-modality training recipes. Accepted at AAAI 2026.

Experimental diffusion-based language model capable of inference speeds exceeding 2,100 tokens/s.

Specialized model for automated theorem proving and formal mathematical reasoning (Lean 4).

Open-source multilingual translation series (7B parameters) rivaling GPT-4 in translation tasks. Includes Seed-X-Instruct, Seed-X-PPO, and Seed-X-RM.

ByteDance's video generation model. Ranked first on Artificial Analysis leaderboards for both text-to-video and image-to-video. Generates 5-second 108…

14B MoE unified multimodal model integrating vision-understanding and image-generation into a single framework.

Research on model merging techniques during pre-training of large language models, exploring how independently trained model branches can be merged to…

Vision-language foundation model with a 532M vision encoder and 20B-active MoE LLM. State-of-the-art on 38 of 60 public VLM benchmarks. Excels at GUI…

"SuperAgent" harness that orchestrates sub-agents and tools for long-horizon research and coding tasks.

Reasoning model advanced through reinforcement learning.

Reasoning-focused model that surpassed OpenAI's o1-preview on the AIME benchmark.

Native bilingual Chinese-English image generation model with integrated LLM text encoder and character-level text rendering.

Unified tokenizer for visual generation and understanding. Uses multi-codebook quantization to scale vocabulary size and bottleneck dimension, achievi…

Sparse MoE model (200B total, 20B active, 256 experts with 8 active per token) with a 256k context window. Part of ByteDance's flagship Doubao series.…

Open-source multimodal AI agent stack designed to control computers and browsers via vision.

Scaling bitwise autoregressive modeling for high-resolution image and spacetime (video) synthesis.

Unified multimodal generation framework that combines visual understanding and image generation within a single LLM without external pretrained visual…

Applying the Llama architecture to image generation.

State-of-the-art speech generation model family known for high-fidelity voice cloning and expressive prosody.

An Amber-compatible, data-driven force field for drug-like molecules. ByteFF is trained on millions of synthetic fragment geometries using an edge-aug…

Multimodal model specialized in localized visual grounding and reasoning.

High-quality dataset for instruction-based image editing.

NeurIPS 2024 Best Paper. Paradigm shift proving GPT-style autoregressive models could surpass diffusion (SDXL/Stable Diffusion) in image generation qu…

System for scaling LLM training to over 10,000 GPUs.

Lightning-fast distillation of SDXL allowing high-quality image generation in 1-4 steps.

Highly popular foundation model for monocular depth estimation.

Benchmark for comprehensive multi-shot video understanding.

Viral diffusion-based models for human image animation and high-dynamic video generation.

High-performance Transformer implementation optimized for variable-length sequences.

Legendary multi-object tracking algorithm that remains an industry standard.