MANTA -- Model Adapter Native generations that's Affordable
The presiding model generation algorithms rely on simple, inflexible adapter selection to provide personalized results. We propose the model-adapter composition problem as a generalized problem to past work factoring in practical hardware and affordability constraints, and introduce MANTA as a new approach to the problem. Experiments on COCO 2014 validation show MANTA to be superior in image task diversity and quality at the cost of a modest drop in alignment. Our system achieves a $94\%$ win rate in task diversity and a $80\%$ task quality win rate versus the best known system, and demonstrates strong potential for direct use in synthetic data generation and the creative art domains.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitymodelSynthetic Data GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling
Static subword tokenization algorithms have been an essential component of recent works on language modeling. However, their static nature results in important flaws that degrade the models' downstream performance and ro…
Language ModelingLanguage ModellingHarbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for a…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically trea…
Mathematical ReasoningManta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their applic…
Action RecognitionContrastive LearningFew-Shot action recognitionFew Shot Action Recognition+1Exploring Adapter Design Tradeoffs for Low Resource Music Generation
Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, therefore, significant hardware resources. Pa…
Music Generationparameter-efficient fine-tuningRhythm