EGM enables 8B VLMs to reach 91.4 IoU on RefCOCO at 737 ms latency, outperforming a 235B model at 4320 ms, by substituting volume of mid-quality tokens for model scale.
In: Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles (2023)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LLM4MEM achieves an average 5.1% F1 improvement on six multi-table entity matching datasets by combining prompt-based attribute coordination, transitive embedding matching, and density-aware pruning.
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
citing papers explorer
-
EGM: Efficient Visual Grounding Language Models
EGM enables 8B VLMs to reach 91.4 IoU on RefCOCO at 737 ms latency, outperforming a 235B model at 4320 ms, by substituting volume of mid-quality tokens for model scale.
-
Unlocking the Power of Large Language Models for Multi-table Entity Matching
LLM4MEM achieves an average 5.1% F1 improvement on six multi-table entity matching datasets by combining prompt-based attribute coordination, transitive embedding matching, and density-aware pruning.
-
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.