conftrace_

flop reduction

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (2) efficient computing (2) model compression (2) early termination (1) dynamic token compression (1) semantic density (1) dynamic compression (1) cpu inference (1) integer linear program (1) token compression (1)

Papers

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025 Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors EMNLP 2025 FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning AISTATS 2024 LookupFFN: Making Transformers Compute-lite for CPU inference ICML 2023 Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs ICML 2022