Article
Security incident disclosure — July 2026
system
• • 813
Li-Wei Chen
txya900619
AI & ML interests
TTS, ASR, SE
Recent Activity
updated a Space 5 days ago
ILRDF/formosan-translation updated a model 5 days ago
ILRDF/nllb-600m-formosan-all-finetune-v3 published a model 5 days ago
ILRDF/nllb-600m-formosan-all-finetune-v3Organizations
upvoted an article 4 months ago
upvoted an article 8 months ago
Article
Mixture of Experts (MoEs) in Transformers
- +5
ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap
• • 182 upvoted 7
papers about 1 year ago
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 200
EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
Paper • 2509.09174 • Published • 61
VibeVoice Technical Report
Paper • 2508.19205 • Published • 181
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
Paper • 2508.14444 • Published • 50
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Paper • 2508.11598 • Published • 18
DINOv3
Paper • 2508.10104 • Published • 321
Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
Paper • 2508.02193 • Published • 138
upvoted 11
papers over 1 year ago
ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents
Paper • 2507.22827 • Published • 101
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 66
Group Sequence Policy Optimization
Paper • 2507.18071 • Published • 321
Step-Audio 2 Technical Report
Paper • 2507.16632 • Published • 76
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
Paper • 2507.14129 • Published • 13
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 262
Test-Time Scaling with Reflective Generative Model
Paper • 2507.01951 • Published • 108
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 159
SingLoRA: Low Rank Adaptation Using a Single Matrix
Paper • 2507.05566 • Published • 116
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
Paper • 2506.20639 • Published • 32
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
Paper • 2506.20920 • Published • 81