ByteDance Seed

Team

company

https://opensource.bytedance.com

AI & ML interests

None defined yet.

Recent Activity

taesiri submitted a paper about 11 hours ago

LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics

taesiri submitted a paper 3 days ago

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

zandaoguang updated a dataset 6 days ago

ByteDance-Seed/Multi-SWE-bench-flash

View all activity

Papers

LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics

SpatialTree: How Spatial Abilities Branch Out in MLLMs

View all Papers

ByteDance-Seed 's Papers 55

Submitted by

taesiri

LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics

ByteDance-Seed

Submitted by

taesiri

SpatialTree: How Spatial Abilities Branch Out in MLLMs

ByteDance-Seed

Submitted by

taesiri

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

ByteDance-Seed

3

Submitted by

Yuwei Guo

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

ByteDance-Seed

Submitted by

[email protected]

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

ByteDance-Seed

2

Submitted by

taesiri

UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving

ByteDance-Seed

Submitted by

taesiri

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

ByteDance-Seed

Submitted by

Shwai He

Understanding and Harnessing Sparsity in Unified Multimodal Models

ByteDance-Seed

Submitted by

Xiao Ma

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation

ByteDance-Seed

Submitted by

Yifan Du

Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization

ByteDance-Seed

Submitted by

Peter Lin

Adversarial Flow Models

ByteDance-Seed

Submitted by

taesiri

Virtual Width Networks

ByteDance-Seed

Submitted by

taesiri

DiscoX: Benchmarking Discourse-Level Translation task in Expert Domains

ByteDance-Seed

Submitted by

Adina Yakefu

Depth Anything 3: Recovering the Visual Space from Any Views

ByteDance-Seed

Submitted by

taesiri

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

ByteDance-Seed

Submitted by

taesiri

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

ByteDance-Seed

Submitted by

taesiri

Visual Spatial Tuning

ByteDance-Seed

Submitted by

taesiri

Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots

ByteDance-Seed

Submitted by

taesiri

MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

ByteDance-Seed

Submitted by

Yiyang Zhou

When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought

ByteDance-Seed

Submitted by

taesiri

Scaling Latent Reasoning via Looped Language Models

ByteDance-Seed

8

Submitted by

Mengzhao Chen

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

ByteDance-Seed

Submitted by

Wu Bohong

Parallel Loop Transformer for Efficient Test-Time Computation Scaling

ByteDance-Seed

Submitted by

Zhongcong Xu

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

ByteDance-Seed

Submitted by

Jiawei Zhang

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

ByteDance-Seed

Submitted by

sijin

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

ByteDance-Seed

1

Submitted by

XinLi

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

ByteDance-Seed

Submitted by

taesiri

Generative Universal Verifier as Multimodal Meta-Reasoner

ByteDance-Seed

Submitted by

taesiri

Trace Anything: Representing Any Video in 4D via Trajectory Fields

ByteDance-Seed

Submitted by

Weiwei Sun

Scaling Long-Horizon LLM Agent via Context-Folding

ByteDance-Seed

Submitted by

yichen he

Memory Retrieval and Consolidation in Large Language Models through Function Tokens

ByteDance-Seed

Submitted by

Weihao Yu

Artificial Hippocampus Networks for Efficient Long-Context Modeling

ByteDance-Seed

Submitted by

yongxinzhu

Heptapod: Language Modeling on Visual Signals

ByteDance-Seed

Submitted by

cuijiaxing

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

ByteDance-Seed

Submitted by

Ziniu Li

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

ByteDance-Seed

Submitted by

taesiri

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

ByteDance-Seed

Submitted by

Zehui Chen

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

ByteDance-Seed

Submitted by

Minghuan Liu

Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

ByteDance-Seed

Submitted by

Wei Li

Robix: A Unified Model for Robot Interaction, Reasoning and Planning

ByteDance-Seed

6

Submitted by

Ge Zhang

TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

ByteDance-Seed

Submitted by

taesiri

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

ByteDance-Seed

Submitted by

jiashuo liu

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

ByteDance-Seed

5

Submitted by

yichen he

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

ByteDance-Seed

Submitted by

sijin

GR-3 Technical Report

ByteDance-Seed

2

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

ByteDance-Seed

VINCIE: Unlocking In-context Image Editing from Video

ByteDance-Seed

Submitted by

JIANYI WANG

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

ByteDance-Seed

Seed-Coder: Let the Code Model Curate Data for Itself

ByteDance-Seed

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

ByteDance-Seed

Submitted by

Daoguang Zan

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

ByteDance-Seed

Submitted by

Ju He

FlowTok: Flowing Seamlessly Across Text and Image Tokens

ByteDance-Seed

Submitted by

Yuanxin Liu

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?

ByteDance-Seed

Submitted by

haoxintong

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

ByteDance-Seed

2

Submitted by

JIANYI WANG

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

ByteDance-Seed

Submitted by

Hanshi

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

ByteDance-Seed