AdaCodec introduces a predictive visual code that cuts visual token use in video MLLMs by sending full frames only on high predictive cost and otherwise encoding inter-frame changes as P-tokens, yielding better benchmark scores at lower budgets.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A distributed arithmetic algorithm for CMVM operations on FPGAs reduces area by up to one third and latency for quantized neural networks, integrated into hls4ml.
A neural network predicts optimal frame rate and resolution pairs for bandwidth-constrained streaming of rendered content to boost perceptual quality.
citing papers explorer
-
da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
A distributed arithmetic algorithm for CMVM operations on FPGAs reduces area by up to one third and latency for quantized neural networks, integrated into hls4ml.