English
Related papers

Related papers: Tree Cross Attention

200 papers

Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, and scaling laws seem to be the most successful strategy:…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Corentin Dancette , Matthieu Cord

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

Computation and Language · Computer Science 2026-05-15 Manish Nagaraj , Sakshi Choudhary , Utkarsh Saxena , Deepak Ravikumar , Kaushik Roy

Transformer-based Large Language Models (LLMs) have exhibited remarkable success in extensive tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute…

Computation and Language · Computer Science 2025-08-05 Yaofo Chen , Zeng You , Shuhai Zhang , Haokun Li , Yirui Li , Yaowei Wang , Mingkui Tan

Spatiotemporal forecasting on transportation networks is a complex task that requires understanding how traffic nodes interact within a dynamic, evolving system dictated by traffic flow dynamics and social behavioral patterns. The…

Machine Learning · Computer Science 2025-12-01 Christopher Cheong , Gary Davis , Seongjin Choi

We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed point after several inference steps. The convergence time…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Haozhe Liu , Wentian Zhang , Jinheng Xie , Francesco Faccio , Mengmeng Xu , Tao Xiang , Mike Zheng Shou , Juan-Manuel Perez-Rua , Jürgen Schmidhuber

Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…

Machine Learning · Computer Science 2025-06-10 Linjing You , Jiabao Lu , Xiayuan Huang

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

Information Retrieval · Computer Science 2025-07-22 Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

In video-based emotion recognition, audio and visual modalities are often expected to have a complementary relationship, which is widely explored using cross-attention. However, they may also exhibit weak complementary relationships,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 R. Gnana Praveen , Jahangir Alam

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

Knowledge Graphs~(KGs) often suffer from unreliable knowledge, which restricts their utility. Triple Classification~(TC) aims to determine the validity of triples from KGs. Recently, text-based methods learn entity and relation…

Computation and Language · Computer Science 2026-01-21 Xu Xiaodan , Hu Xiaolin

A method is presented for reducing the cost of representative token selection in transformer attention layers by exploiting the coherence of the representative set across depth. Activation Decorrelation Attention (ADA) selects $r \ll T$…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and…

Computation and Language · Computer Science 2026-03-13 Yushi Bai , Qian Dong , Ting Jiang , Xin Lv , Zhengxiao Du , Aohan Zeng , Jie Tang , Juanzi Li

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Samyak Jha , Junho Kim

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Machine Learning · Computer Science 2026-05-08 Ahmed Abdelmuniem Abdalla Mohammed

We introduce inference trees (ITs), a new class of inference methods that build on ideas from Monte Carlo tree search to perform adaptive sampling in a manner that balances exploration with exploitation, ensures consistency, and alleviates…

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challenging for cross-domain adaptation scenarios. To address the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jinhong Deng , Xiaoyue Zhang , Wen Li , Lixin Duan