Contrastive Learning for Many-to-many Multilingual Neural Machine Translation
Paper
•
2105.09501
•
Published
ByteDance Papers
ByteDance papers collection
-
-
Cross-modal Contrastive Learning for Speech Translation
Paper • 2205.02444 • Published -
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
Paper • 2210.03052 • Published -
Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
Paper • 2212.10240 • Published • 1 -
DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises
Paper • 2302.10025 • Published -
Efficient Neural Music Generation
Paper • 2305.15719 • Published • 2 -
PolyVoice: Language Models for Speech to Speech Translation
Paper • 2306.02982 • Published • 4 -
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining
Paper • 2308.05734 • Published • 37 -
MagicEdit: High-Fidelity and Temporally Coherent Video Editing
Paper • 2308.14749 • Published • 1 -
SALMONN: Towards Generic Hearing Abilities for Large Language Models
Paper • 2310.13289 • Published • 17 -
Make Pixels Dance: High-Dynamic Video Generation
Paper • 2311.10982 • Published • 69 -
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Paper • 2311.16498 • Published • 1 -
PixelLM: Pixel Reasoning with Large Multimodal Model
Paper • 2312.02228 • Published -
Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens
Paper • 2312.08870 • Published • 1 -
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
Paper • 2312.10300 • Published • 1 -
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper • 2401.10891 • Published • 62 -
Magic-Me: Identity-Specific Video Customized Diffusion
Paper • 2402.09368 • Published • 30 -
SDXL-Lightning: Progressive Adversarial Diffusion Distillation
Paper • 2402.13929 • Published • 28 -
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Paper • 2402.15627 • Published • 39 -
You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs
Paper • 2403.12931 • Published • 1 -
Magic-Boost: Boost 3D Generation with Mutli-View Conditioned Diffusion
Paper • 2404.06429 • Published • 7 -
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
Paper • 2404.09990 • Published • 13 -
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Paper • 2404.13686 • Published • 29 -
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Paper • 2404.16994 • Published • 37 -
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Paper • 2405.01434 • Published • 57 -
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Paper • 2405.07510 • Published • 2 -
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Paper • 2405.14156 • Published -
ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
Paper • 2405.17532 • Published • 1 -
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
Paper • 2405.18424 • Published • 9 -
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Paper • 2405.17871 • Published • 1 -
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Paper • 2406.02430 • Published • 37 -
Towards Semantic Equivalence of Tokenization in Multimodal LLM
Paper • 2406.05127 • Published -
An Image is Worth 32 Tokens for Reconstruction and Generation
Paper • 2406.07550 • Published • 60 -
Autoregressive Pretraining with Mamba in Vision
Paper • 2406.07537 • Published -
Depth Anything V2
Paper • 2406.09414 • Published • 103 -
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Paper • 2406.13340 • Published -
Let the Code LLM Edit Itself When You Edit the Code
Paper • 2407.03157 • Published -
Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
Paper • 2407.04675 • Published -
IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model
Paper • 2407.07577 • Published -
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Paper • 2407.07895 • Published • 43 -
ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development
Paper • 2407.20143 • Published -
An X-ray Significantly Variable, Luminous, Type 2 Quasar at z = 2.99 with a Massive Host Galaxy
Paper • 2409.01960 • Published • 1 -
Seed-Music: A Unified Framework for High Quality and Controlled Music Generation
Paper • 2409.09214 • Published • 55 -
HybridFlow: A Flexible and Efficient RLHF Framework
Paper • 2409.19256 • Published -
Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
Paper • 2409.16167 • Published -
MaskBit: Embedding-free Image Generation via Bit Tokens
Paper • 2409.16211 • Published • 17 -
Hyper-Connections
Paper • 2409.19606 • Published • 23 -
Video Instruction Tuning With Synthetic Data
Paper • 2410.02713 • Published • 39 -
Loong: Generating Minute-level Long Videos with Autoregressive Language Models
Paper • 2410.02757 • Published • 38 -
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 27 -
KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks
Paper • 2410.06526 • Published • 1 -
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Paper • 2410.08067 • Published • 2 -
Why Does the Effective Context Length of LLMs Fall Short?
Paper • 2410.18745 • Published • 18 -
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
Paper • 2410.20424 • Published • 41 -
How Far is Video Generation from World Model: A Physical Law Perspective
Paper • 2411.02385 • Published • 36 -
Classification Done Right for Vision-Language Pre-Training
Paper • 2411.03313 • Published -
Multi-Reward as Condition for Instruction-based Image Editing
Paper • 2411.04713 • Published • 1 -
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
Paper • 2411.03884 • Published • 29 -
SeedEdit: Align Image Re-Generation to Image Editing
Paper • 2411.06686 • Published • 1 -
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
Paper • 2411.08446 • Published -
Understanding Chain-of-Thought in LLMs through Information Theory
Paper • 2411.11984 • Published • 3 -
Ultra-Sparse Memory Network
Paper • 2411.12364 • Published • 24 -
DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs
Paper • 2411.13611 • Published -
FullStack Bench: Evaluating LLMs as Full Stack Coder
Paper • 2412.00535 • Published -
The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
Paper • 2412.07298 • Published -
Diffusion Adversarial Post-Training for One-Step Video Generation
Paper • 2501.08316 • Published • 34 -
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Paper • 2501.09781 • Published • 29 -
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
Paper • 2501.12326 • Published • 59 -
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving
Paper • 2502.03438 • Published • 2 -
MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion
Paper • 2502.04235 • Published • 22 -
MagicArticulate: Make Your 3D Models Articulation-Ready
Paper • 2502.12135 • Published • 8 -
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
Paper • 2502.19811 • Published -
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Paper • 2502.14739 • Published • 103 -
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
Paper • 2502.20766 • Published -
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Paper • 2503.07703 • Published • 36 -
Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning
Paper • 2503.07906 • Published • 4 -
FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis
Paper • 2503.13265 • Published • 15 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 128 -
Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?
Paper • 2504.00509 • Published • 21 -
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
Paper • 2504.02605 • Published • 47 -
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
Paper • 2504.13914 • Published -
Seedream 3.0 Technical Report
Paper • 2504.11346 • Published • 60 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 60 -
Seed1.5-VL Technical Report
Paper • 2505.07062 • Published • 137 -
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Paper • 2505.07293 • Published • 25 -
DanceGRPO: Unleashing GRPO on Visual Generation
Paper • 2505.07818 • Published • 28 -
MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
Paper • 2505.11432 • Published • 1 -
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
Paper • 2505.11896 • Published • 50 -
Model Merging in Pre-training of Large Language Models
Paper • 2505.12082 • Published • 31 -
Emerging Properties in Unified Multimodal Pretraining
Paper • 2505.14683 • Published • 97 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 34