会员服务
Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking
Arxiv
1+阅读 · 4月3日
Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
Arxiv
1+阅读 · 4月3日
Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research
Arxiv
0+阅读 · 4月3日
RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety
Arxiv
0+阅读 · 4月3日
Solving the Paint Shop Problem with Flexible Management of Multi-Lane Buffers Using Reinforcement Learning and Action Masking
Arxiv
0+阅读 · 4月3日
SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation
SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation
Arxiv
0+阅读 · 4月3日
SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model
Arxiv
0+阅读 · 4月3日
SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model
Arxiv
0+阅读 · 4月2日
Visually Image Encryption and Compression Using a CNN-Based Auto Encoder
Arxiv
0+阅读 · 4月1日
MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors
MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors
Arxiv
0+阅读 · 4月2日
A Diffusion-Based Framework for Occluded Object Movement
A Diffusion-Based Framework for Occluded Object Movement
Arxiv
0+阅读 · 4月2日
Target-Aware Video Diffusion Models
Arxiv
0+阅读 · 4月2日
How to safely discard features based on aggregate SHAP values
Arxiv
0+阅读 · 3月29日
MGD-SAM2: Multi-view Guided Detail-enhanced Segment Anything Model 2 for High-Resolution Class-agnostic Segmentation
Arxiv
0+阅读 · 3月31日
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Arxiv
0+阅读 · 3月31日
参考链接
微信扫码咨询专知VIP会员
Top