nanjinguniv (Nanjing University)

wangfuyun

authored a paper 3 days ago

Unleashing Vecset Diffusion Model for Fast Shape Generation

Paper • 2503.16302 • Published 3 days ago • 37

wangfuyun

authored a paper 3 months ago

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

Paper • 2501.02690 • Published Jan 5 • 17

JesseZhang

authored a paper 3 months ago

StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors

Paper • 2412.11586 • Published Dec 16, 2024 • 11

hehesang

authored a paper 3 months ago

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Paper • 2412.09604 • Published Dec 12, 2024 • 35

wangfuyun

authored 4 papers 5 months ago

Stable Consistency Tuning: Understanding and Improving Consistency Models

Paper • 2410.18958 • Published Oct 24, 2024 • 10

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

Paper • 2406.18583 • Published Jun 5, 2024

Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis

Paper • 2410.07155 • Published Oct 9, 2024 • 11

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

Paper • 2410.07303 • Published Oct 9, 2024 • 18

wangfuyun

authored a paper 6 months ago

OSV: One Step is Enough for High-Quality Image to Video Generation

Paper • 2409.11367 • Published Sep 17, 2024 • 14

Swtheking

authored 2 papers 6 months ago

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation

Paper • 2409.06957 • Published Sep 11, 2024 • 6

LongRecipe: Recipe for Efficient Long Context Generalization in Large Languge Models

Paper • 2409.00509 • Published Aug 31, 2024 • 41

walkingshadow

authored a paper 7 months ago

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Paper • 2409.02095 • Published Sep 3, 2024 • 36

ParadiseYu

authored 3 papers 9 months ago

Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation

Paper • 2403.20289 • Published Mar 29, 2024 • 1

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Paper • 2402.08679 • Published Feb 13, 2024 • 1

Flow of Reasoning: Efficient Training of LLM Policy with Divergent Thinking

Paper • 2406.05673 • Published Jun 9, 2024 • 3

wangfuyun

authored a paper 10 months ago

Phased Consistency Model

Paper • 2405.18407 • Published May 28, 2024 • 48

starreeze

authored a paper 10 months ago

AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability

Paper • 2405.14129 • Published May 23, 2024 • 14

wangfuyun

posted an update 11 months ago

Post

8155

Live recordings of [AnimateLCM]( wangfuyun/AnimateLCM).

3 replies

·

walkingshadow

authored a paper 11 months ago

SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Paper • 2404.14396 • Published Apr 22, 2024 • 19

wangfuyun

authored a paper about 1 year ago

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

Paper • 2403.13745 • Published Mar 20, 2024 • 11

Nanjing University

AI & ML interests

nanjinguniv's activity

Unleashing Vecset Diffusion Model for Fast Shape Generation

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Stable Consistency Tuning: Understanding and Improving Consistency Models

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

OSV: One Step is Enough for High-Quality Image to Video Generation

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation

LongRecipe: Recipe for Efficient Long Context Generalization in Large Languge Models

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Flow of Reasoning: Efficient Training of LLM Policy with Divergent Thinking

Phased Consistency Model

AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability

SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

AI & ML interests

Team members 223

nanjinguniv's activity