Sliding Window Attention Training for Efficient Large Language Models
Reviewed by Pithpith:YGOEO3DGopen to challenge →
read the original abstract
Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck for processing long documents. As a result, many efforts like sparse attention and state space models have been proposed to improve the efficiency of LLMs over long sequences. Though effective, these approaches compromise the performance or introduce structural complexity. This calls for a simple yet efficient model that preserves the fundamental Transformer architecture. To this end, we introduce SWAT, which enables efficient long-context handling via Sliding Window Attention Training. This paper first attributes the inefficiency of Transformers to the attention sink phenomenon resulting from the high variance of softmax operation. Then, we replace softmax with the sigmoid function and utilize a balanced ALiBi and Rotary Position Embedding for efficient information compression and retention. Experiments demonstrate that SWAT achieves SOTA performance compared with state-of-the-art linear recurrent architectures on eight benchmarks. Code is available at https://github.com/Fzkuji/swat-attention.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
Chorus accelerates video DiT serving up to 45% via inter-request caching reuse in a three-stage denoising strategy with token-guided attention amplification.
-
IAFormer: Interaction-Aware Transformer network for collider data analysis
IAFormer uses boost-invariant pairwise quantities and differential attention to create a sparse Transformer that achieves state-of-the-art classification on top-quark and quark-gluon jet datasets while using over an o...
-
Training-Inference Consistent Segmented Execution for Long-Context LLMs
A training-inference consistent segmented execution framework for long-context LLMs matches full-context performance with substantially lower peak memory at very long lengths.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
-
HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
HARD-KV bridges dynamic head-adaptive KV cache compression with static inference engine constraints via Cascade Cache and Logits Calibration, reporting up to 2x throughput gains on long-context math benchmarks.
-
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
EngGPT2MoE-16B-A3B matches or exceeds other Italian open-source LLMs on most international benchmarks while remaining competitive on ITALIC, though it trails some top international models.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
ISA prunes low-saliency context tokens and routes queries by sharpness to either full or 0-th order Taylor sparse attention, enabling LIVEditor to cut attention latency ~60% while beating prior video editing methods o...
-
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
Nirvana adds a task-aware memory trigger and updater to specialized generalist models, achieving strong general benchmark results, lowest perplexity in biomedicine/finance/law, and improved MRI reconstruction fidelity.
-
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
EngGPT2MoE-16B-A3B matches or beats other Italian models on most international benchmarks but trails top international models such as GPT-5 nano and Qwen3-8B.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.