The paper introduces OASIS, a method designed to stabilize dual‑normalized attention‑residual architectures by employing explicit null routing and token‑to‑depth null coupling. OASIS mitigates attention sinks and activation outliers, improving low‑bit quantization performance across several language‑model backbones. Empirical results show significant reductions in attention norms and perplexity, with notable gains on long‑context benchmarks.
By Haozheng Luo, Haoran Dai, Jingyuan Huang, Shaoyang Zhang, Xi Chen, Eric Hanchen Jiang, Yijiang Li, Chenghao Qiu, Chenwei Xu, Zhenyu Pan, Haotian Zhang, Binghui Wang, Yan Chen
Attention-Aware Routing (AAR) augments the router in Mixture-of-Experts language models with temporal and spectral features derived from a sliding window of attention weights, thereby separating contextual information from the token’s hidden state. By keeping the base transformer frozen and training only routing parameters, AAR achieves a +3.37‑point improvement on GSM8K over a routing‑only baseline and demonstrates that routing changes propagate through the residual stream to reshape attention without directly updating the attention mechanism. The method also reduces long diverging generations, shows depth‑sensitivity affecting retrieval versus reasoning, and offers a controlled probe of routing‑relevant information across layers.
By Despoina Kosmopoulou, Anastasios Tsetsilas, Efthymios Georgiou, Giannis Karamanolakis, Swastik Roy, Alexandros Potamianos
arXiv:2606. 06564v1 Announce Type: cross Abstract: Residual connections are central to training deep Transformers, but standard PreNorm residual streams aggregate sublayer updates with fixed unit weights.
By Kehan Wang
arXiv:2609.22884v1 Announce Type: new
Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling...
By Xinwei Long, Weigao Sun, Weibo Gao, Pengkun Jiao, Biqing Qi, Feida Zhu, Yiran Zhong, Steven Hoi, Bowen Zhou
arXiv:2607. 06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation.
By Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesus Olivera
arXiv:2509. 07963v2 Announce Type: replace Abstract: The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair.
By Yilun Kuang, Noah Amsel, Sanae Lotfi, Shikai Qiu, Andres Potapczynski, Andrew Gordon Wilson
The paper introduces Weight-Redundancy Pruning (WRP), a forward‑free depth‑pruning technique for large language models that estimates inter‑layer redundancy using only checkpoint weights. WRP compares attention outputs and MLP down‑projection weights across layers, combining pairwise similarities with relative projection‑scale information to guide layer grouping and block selection. Experiments show that WRP consistently outperforms existing forward‑free magnitude pruning methods and approaches the performance of activation‑based pruning across various pruning settings, model families, and downstream tasks.
By Vincent-Daniel Yun, Woosang Lim
arXiv:2602.04852v3 Announce Type: replace
Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate tha...
By Philipp Nazari, T. Konstantin Rusch
SHIFT-LLM is a training‑free post‑pruning correction framework that inserts a Linear Residual Adapter (LRA) at each depth‑pruned site in large language models. Each LRA preserves the original residual identity while adding a lightweight affine correction calibrated via closed‑form least‑squares regression on a small held‑out set, thereby approximating the hidden state that would have been produced by the removed block. Experiments across multiple model families and benchmarks show that SHIFT‑LLM consistently recovers accuracy lost to depth pruning, achieving gains up to +15.7 points on Llama‑3.1‑8B‑Instruct with only a few hundred calibration samples and no gradient computation.
By Ali Bahri, Hang Li, Hongliang Li, Zhitang Chen
arXiv:2606. 06564v2 Announce Type: replace-cross Abstract: Block-level residual routing makes learned residual aggregation practical by routing over block summaries, but each summary compresses an ordered sequence of attention and MLP updates into one cumulative vector.
By Kehan Wang
arXiv:2603. 24787v2 Announce Type: replace Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models.
By Yaopei Zeng, Congchao Wang, Blake JianHang Chen, Lu Lin
arXiv:2607. 24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck.
By Vimal William, Ravi Tandon, Jyotikrishna Dass