LASER introduces curvature-weighted SVD from second-order loss approximation and loss-aware rank allocation to compress VLMs, reporting over 2.3x decoding speedup under low-precision settings.
TheLLM surgeon
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
citing papers explorer
-
LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models
LASER introduces curvature-weighted SVD from second-order loss approximation and loss-aware rank allocation to compress VLMs, reporting over 2.3x decoding speedup under low-precision settings.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.