DENG Lab @ SJTU

university

https://SJTU-DENG-Lab.github.io/

AI & ML interests

None defined yet.

Recent Activity

karrykkk submitted a paper about 2 months ago

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

karrykkk updated a model about 2 months ago

SJTU-DENG-Lab/Think-Then-Generate-T2I

karrykkk published a model about 2 months ago

SJTU-DENG-Lab/Think-Then-Generate-T2I

View all activity

Papers

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

View all Papers

submitted a paper to Daily Papers about 2 months ago

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

Paper • 2601.10332 • Published Jan 15 • 28

updated a model about 2 months ago

SJTU-DENG-Lab/Think-Then-Generate-T2I

Text-to-Image • Updated Jan 15 • 16 • 2

published a model about 2 months ago

SJTU-DENG-Lab/Think-Then-Generate-T2I

Text-to-Image • Updated Jan 15 • 16 • 2

updated 3 models 2 months ago

SJTU-DENG-Lab/D2F_DiffuCoder_Instruct_7B_Lora

Text Generation • Updated Dec 31, 2025

SJTU-DENG-Lab/D2F_Dream_Instruct_7B_Lora

Text Generation • Updated Dec 31, 2025

SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora

Text Generation • Updated Dec 31, 2025 • 4

updated a collection 2 months ago

D2F-LoRA

4 items • Updated Dec 31, 2025

published 2 models 2 months ago

SJTU-DENG-Lab/D2F_DiffuCoder_Instruct_7B_Lora

Text Generation • Updated Dec 31, 2025

SJTU-DENG-Lab/D2F_Dream_Instruct_7B_Lora

Text Generation • Updated Dec 31, 2025

submitted a paper to Daily Papers 2 months ago

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

Paper • 2512.16229 • Published Dec 18, 2025 • 16

Yysrc

authored a paper 3 months ago

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

Paper • 2511.16175 • Published Nov 20, 2025 • 12

updated a model 7 months ago

SJTU-DENG-Lab/D2F_LLaDA_Instruct_8B_Lora

Text Generation • Updated Aug 14, 2025 • 5

published 2 models 7 months ago

SJTU-DENG-Lab/D2F_LLaDA_Instruct_8B_Lora

Text Generation • Updated Aug 14, 2025 • 5

SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora

Text Generation • Updated Dec 31, 2025 • 4

authored a paper 9 months ago

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks

Paper • 2506.00411 • Published May 31, 2025 • 31

authored a paper 9 months ago

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks

Paper • 2506.00411 • Published May 31, 2025 • 31

Yysrc

authored a paper 9 months ago

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks

Paper • 2506.00411 • Published May 31, 2025 • 31