Deng Lab @ SJTU

SJTU-Deng-Lab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

zhijie3 

authored 7 papers about 19 hours ago

Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation

Paper • 2304.02841 • Published Apr 6, 2023

Online Speculative Decoding

Paper • 2310.07177 • Published Oct 11, 2023 • 2

LOVECon: Text-driven Training-Free Long Video Editing with ControlNet

Paper • 2310.09711 • Published Oct 15, 2023 • 1

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Paper • 2310.11142 • Published Oct 17, 2023

Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks

Paper • 2306.13103 • Published Jun 16, 2023 • 2

CLLMs: Consistency Large Language Models

Paper • 2403.00835 • Published Feb 28, 2024 • 4

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation

Paper • 2403.01505 • Published Mar 3, 2024 • 1

zhijie3 

authored 7 papers about 20 hours ago

Optimizing Speculative Decoding for Serving Large Language Models Using Goodput

Paper • 2406.14066 • Published Jun 20, 2024 • 2

On Calibrating Diffusion Probabilistic Models

Paper • 2302.10688 • Published Feb 21, 2023 • 1

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models

Paper • 2406.13233 • Published Jun 19, 2024 • 1

FaceScore: Benchmarking and Enhancing Face Quality in Human Generation

Paper • 2406.17100 • Published Jun 24, 2024 • 1

Aligning CodeLLMs with Direct Preference Optimization

Paper • 2410.18585 • Published Oct 24, 2024

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

Paper • 2412.00127 • Published Nov 28, 2024 • 1

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward

Paper • 2406.07327 • Published Jun 11, 2024

zhijie3 

authored a paper about 22 hours ago

Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile

Paper • 2502.06155 • Published 2 days ago • 7

UnhurriedDawn 

authored a paper about 22 hours ago

Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation

Paper • 2502.05415 • Published 4 days ago • 14

zhijie3 

authored a paper about 22 hours ago

Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation

Paper • 2502.05415 • Published 4 days ago • 14

karrykkk 

authored 3 papers about 2 months ago

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Paper • 2310.11142 • Published Oct 17, 2023

CLLMs: Consistency Large Language Models

Paper • 2403.00835 • Published Feb 28, 2024 • 4

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

Paper • 2412.00127 • Published Nov 28, 2024 • 1