#memory efficiency
11 papers · 1 filter
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +1
The paper introduces a training‑free pipeline that separates 3D geometry reconstruction from semantic labeling to create compact, object‑level semantic maps from a single monocular…
Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA
Zhongkuan Mao, Xianjie Liu, Tianyu Meng +9
The paper proposes a training‑free, single‑pass method that routes intermediate‑layer visual evidence to improve high‑resolution visual question answering without extra image proce…
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
Stephen Gould, Anton van den Hengel
The paper introduces a KV cache eviction method for large language models that removes entries predicted well by future tokens using a counter‑causal attention pass, improving memo…
Memory Efficient Tabular Foundation Models
Shuting Luo, Monika Mikhail Kanaan, Cameron Gordon +2
The paper studies how to reduce the memory footprint of tabular foundation models like TabPFN using compression techniques, achieving up to 7.6× memory savings with little performa…
BATS: Resource-Efficient Volumetric Segmentation with Boundary-Aware Mixed-Resolution Tokens
David Hagerman, Roman Naeem, Fredrik Kahl
BATS is a 3D medical image segmentation model that adaptively uses fine-resolution tokens near predicted class boundaries, reducing memory usage and speeding up inference compared…
FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
Minguk Kang, Suha Kwak
FlashDecoder is a pure‑Transformer video decoder that converts latent representations to pixel frames in real time, using a rolling key‑value cache to keep computation and memory c…