A single 15B supernet checkpoint supports runtime switching between attention mixer placements for multiple decode speed presets while retaining 77-96% quality relative to the teacher model.
Training verifiers to solve math word problems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
Systematic testing of prompt engineering for LLM equational reasoning finds a performance ceiling of 60-79% accuracy that extensive engineering cannot exceed, driven by undecidability and model capacity limits.
citing papers explorer
-
Super Apriel: One Checkpoint, Many Speeds
A single 15B supernet checkpoint supports runtime switching between attention mixer placements for multiple decode speed presets while retaining 77-96% quality relative to the teacher model.
-
RouterBench: A Benchmark for Multi-LLM Routing System
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
-
LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
-
Less Is More: Cognitive Load and the Single-Prompt Ceiling in LLM Mathematical Reasoning
Systematic testing of prompt engineering for LLM equational reasoning finds a performance ceiling of 60-79% accuracy that extensive engineering cannot exceed, driven by undecidability and model capacity limits.
- FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models