SOTAVerified

Feature Compression

Compress data for machine interpretability to perform downstream tasks, rather than for human perception.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 96 papers

TitleStatusHype
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law—0
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal UnderstandingCode2
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models—0
Generative Map Priors for Collaborative BEV Semantic Segmentation—0
Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding—0
Structurally Consistent MRI Colorization using Cross-modal Fusion Learning—0
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference—0
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image SynthesisCode3
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach—0
Distilling Channels for Efficient Deep Tracking—0
Show:102550
← PrevPage 2 of 10Next →

No leaderboard results yet.