FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient hybrid architectures.
Let’s verify step by step
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost. However, their original formulation suffers from poor scaling and underperforms compute-matched transformers. Recent linear models such as RWKV and Mamba have attempted to address these shortcomings by proposing novel time-mixing and gating architectures, but pre-training large language models requires significant data and compute investments. Thus, the search for subquadratic architectures is limited by the availability of compute and quality pre-training datasets. As a cost-effective alternative to pre-training linear transformers, we propose Scalable UPtraining for Recurrent Attention (SUPRA). We present a method to uptrain existing large pre-trained transformers into Recurrent Neural Networks (RNNs) with a modest compute budget. This allows us to leverage the strong pre-training data and performance of existing transformer LLMs, while requiring 5% of the training cost. We find that our linearization technique leads to competitive performance on standard benchmarks, but we identify persistent in-context learning and long-context modeling shortfalls for even the largest linear models. Our code and models can be found at https://github.com/TRI-ML/linear_open_lm.
representative citing papers
Delta-rule linear attention faithfully approximates softmax attention through key-dependent rank-1 projections, enabling efficient post-hoc linearization of LLMs up to 32B parameters.
A new conversion method (KEPT) transforms Orion-14B into Llama-format models while preserving benchmark performance using ~123M tokens of distillation.
A two-stage distillation recipe converts a Pythia-1B Transformer into a Mamba model that preserves performance with perplexity 14.11 versus the teacher's 13.86.
SpikingBrain-7B and SpikingBrain-76B achieve Transformer-comparable performance after continual pre-training on 150B tokens, with over 100x TTFT speedup on 4M-token sequences and 69.15% sparsity from event-driven spiking.
Lizard linearizes Transformer LLMs via subquadratic attention and adaptive learnable modules, recovering near-original performance while outperforming prior linearization methods on MMLU and associative recall.
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.
LightTransfer identifies lazy layers in LLMs like LLaMA and replaces their attention with streaming attention to form hybrid models, delivering up to 2.17x throughput with under 1.5% drop on LongBench and strong results on reasoning benchmarks.
SpikingBrain2.0 is a 5B hybrid spiking-Transformer that recovers most base model performance while delivering 10x TTFT speedup at 4M context and supporting over 10M tokens on limited GPUs via dual sparse attention and dual quantization paths.
citing papers explorer
-
Morphing into Hybrid Attention Models
FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient hybrid architectures.
-
The Key to Going Linear: Analysis-Driven Transformer Linearization
Delta-rule linear attention faithfully approximates softmax attention through key-dependent rank-1 projections, enabling efficient post-hoc linearization of LLMs up to 32B parameters.
-
Llamion Technical Report
A new conversion method (KEPT) transforms Orion-14B into Llama-format models while preserving benchmark performance using ~123M tokens of distillation.
-
Attention to Mamba: A Recipe for Cross-Architecture Distillation
A two-stage distillation recipe converts a Pythia-1B Transformer into a Mamba model that preserves performance with perplexity 14.11 versus the teacher's 13.86.
-
SpikingBrain: Spiking Brain-inspired Large Models
SpikingBrain-7B and SpikingBrain-76B achieve Transformer-comparable performance after continual pre-training on 150B tokens, with over 100x TTFT speedup on 4M-token sequences and 69.15% sparsity from event-driven spiking.
-
Lizard: An Efficient Linearization Framework for Large Language Models
Lizard linearizes Transformer LLMs via subquadratic attention and adaptive learnable modules, recovering near-original performance while outperforming prior linearization methods on MMLU and associative recall.
-
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.
-
LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
LightTransfer identifies lazy layers in LLMs like LLaMA and replaces their attention with streaming attention to form hybrid models, delivering up to 2.17x throughput with under 1.5% drop on LongBench and strong results on reasoning benchmarks.
-
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference
SpikingBrain2.0 is a 5B hybrid spiking-Transformer that recovers most base model performance while delivering 10x TTFT speedup at 4M context and supporting over 10M tokens on limited GPUs via dual sparse attention and dual quantization paths.