Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction

• URL: http://arxiv.org/abs/2601.11667v1
• Date: Fri, 16 Jan 2026 02:01:40 GMT
• Title: Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction
• Abstract summary: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity limits practical deployment.<n> Linear attention mechanisms offer linear or near-linear scaling yet often incur performance degradation.<n>We introduce a greedy layer replacement strategy that iteratively substitutes full attention blocks with linear ones while monitoring validation performance on the target task.<n>This yields a task-specific hybrid model in a single efficient pass, without costly re-training or neural architecture search, and can be applied to any pretrained full-attention backbone for diverse downstream tasks.
• Score: 3.9660062354591754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or near-linear scaling yet often incur performance degradation. Hybrid models that integrate full and linear attention layers promise a balance between efficiency and expressiveness, but face two major challenges: training such hybrid models from scratch is computationally expensive, and manually designing the optimal placement of attention types is highly nontrivial. We address both issues by first transferring weights from the pretrained full-attention modules to its linear attention counterparts through blockwise local distillation, and second, introducing a greedy layer replacement strategy that iteratively substitutes full attention blocks with linear ones while monitoring validation performance on the target task. This yields a task-specific hybrid model in a single efficient pass, without costly re-training or neural architecture search, and can be applied to any pretrained full-attention backbone for diverse downstream tasks.

Related papers

• FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
  FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
  arXiv  Detail & Related papers  (2026-06-01T06:58:15Z)
• Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers [34.75985836977073]
  We propose a novel hybrid transformer that enables dynamic and fine-grained routing between full attention and sliding window attention.<n>SwiAttn routes dynamically the computation to either a full-attention branch for global information aggregation or a sliding-window branch for efficient local pattern matching.<n>Experiments are conducted on twenty-three benchmark datasets across both regular (4K) and long (32K) context lengths.
  arXiv  Detail & Related papers  (2026-03-27T13:04:29Z)
• MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling [80.48332380100915]
  MiniCPM-SALA is a hybrid model that integrates the high-fidelity long-context modeling of sparse attention with the global efficiency of linear attention.<n>On a single NVIDIA A6000D GPU, the model achieves up to 3.5x the inference speed of the full-attention model at the sequence length of 256K tokens.
  arXiv  Detail & Related papers  (2026-02-12T09:37:05Z)
• STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs [23.745366354566315]
  Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms.<n>We propose STILL, an intra-layer hybrid linearization framework for efficiently linearizing LLMs.
  arXiv  Detail & Related papers  (2026-02-02T14:49:18Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• STORE: Semantic Tokenization, Orthogonal Rotation and Efficient Attention for Scaling Up Ranking Models [11.965535230928372]
  Store is a unified and scalable token-based ranking framework built upon three core innovations.<n>Our framework consistently improves prediction accuracy(online CTR by 2.71%, AUC by 1.195%) and training effeciency (1.84 throughput)
  arXiv  Detail & Related papers  (2025-11-24T06:20:02Z)
• Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods [14.82822709954587]
  Post-training linearisation methods convert pre-trained Transformers to linear models efficiently.<n>We identify a critical flaw: existing hybrid methods inadvertently bypass the linear component.<n>We propose three solutions to ensure balanced component usage.
  arXiv  Detail & Related papers  (2025-10-07T13:11:13Z)
• CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up [64.38715211969516]
  We introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token.<n>Experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity.
  arXiv  Detail & Related papers  (2024-12-20T17:57:09Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences [60.489682735061415]
  We propose CHELA, which replaces state space models with short-long convolutions and implements linear attention in a divide-and-conquer manner. Our experiments on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-06-12T12:12:38Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer [34.790081960470964]
  We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) We make advanced modifications that include positional embedding, linear attention acceleration, gating mechanisms, tensor normalization, and inference acceleration and stabilization. We validate our model design through a series of ablations and train models with sizes of 385M, 1B, and 7B on our self-collected corpus.
  arXiv  Detail & Related papers  (2023-07-27T16:45:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.