English
Related papers

Related papers: Unified token representations for sequential decis…

200 papers

Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult. Since model-based UTC methods may not accurately describe the complex nature of traffic dynamics in all situations,…

Artificial Intelligence · Computer Science 2018-08-27 Yilun Lin , Xingyuan Dai , Li Li , Fei-Yue Wang

One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Hao Wu , Xudong Wang , Jialiang Zhang , Junlong Tong , Xinghao Chen , Junyan Lin , Yunpu Ma , Xiaoyu Shen

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions.…

Machine Learning · Computer Science 2021-02-09 Siyi Hu , Fengda Zhu , Xiaojun Chang , Xiaodan Liang

Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and…

Artificial Intelligence · Computer Science 2025-12-29 Zitian Gao , Lynx Chen , Yihao Xiao , He Xing , Ran Tao , Haoming Luo , Joey Zhou , Bryan Dai

Unified multimodal transformers, which handle both generation and understanding tasks within a shared parameter space, have received increasing attention in recent research. Although various unified transformers have been proposed, training…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Weijia Mao , Zhenheng Yang , Mike Zheng Shou

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Hyojeong Lee , Joo-Young Kim

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling…

As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Fan Ma , Mike Zheng Shou , Linchao Zhu , Haoqi Fan , Yilei Xu , Yi Yang , Zhicheng Yan

Decision Transformer (DT), a trajectory modelling method, has shown competitive performance compared to traditional offline reinforcement learning (RL) approaches on various classic control tasks. However, it struggles to learn optimal…

Machine Learning · Computer Science 2025-09-18 Xingshuai Huang , Di Wu , Benoit Boulet

Improving user retention with reinforcement learning~(RL) has attracted increasing attention due to its significant importance in boosting user engagement. However, training the RL policy from scratch without hurting users' experience is…

Information Retrieval · Computer Science 2023-03-14 Kesen Zhao , Lixin Zou , Xiangyu Zhao , Maolin Wang , Dawei yin

Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Yixun Liang , Hao He , Ying-cong Chen

The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired…

Machine Learning · Computer Science 2025-10-15 Xiaohang Tang , Zhuowen Cheng , Satyabrat Kumar

We study learned memory tokens as a computational scratchpad for a single-block Universal Transformer with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. Memory tokens are empirically necessary: no…

Machine Learning · Computer Science 2026-05-05 Grigory Sapunov

This study examines transformer-based models and their effectiveness in named entity recognition tasks. The study investigates data representation strategies, including single, merged, and context, which respectively use one sentence,…

Computation and Language · Computer Science 2024-06-26 Michał Marcińczuk

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…

Machine Learning · Computer Science 2022-06-08 Vince Jankovics , Michael Garcia Ortiz , Eduardo Alonso

Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across…

Machine Learning · Computer Science 2025-04-04 Tung M. Luu , Donghoon Lee , Chang D. Yoo

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

Multi-source user representation learning plays a critical role in enabling personalized services on web platforms (e.g., Alipay). While prior works have adopted late-fusion strategies to combine heterogeneous data sources, they suffer from…

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Computation and Language · Computer Science 2025-05-27 Zhihong Pan , Kai Zhang , Yuze Zhao , Yupeng Han

Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex problems can be solved more efficiently through…

Computation and Language · Computer Science 2025-05-27 Ruihan Gong , Yue Liu , Wenjie Qu , Mingzhe Du , Yufei He , Yingwei Ma , Yulin Chen , Xiang Liu , Yi Wen , Xinfeng Li , Ruidong Wang , Xinzhong Zhu , Bryan Hooi , Jiaheng Zhang