English
Related papers

Related papers: Birdie: Advancing State Space Models with Reward-D…

200 papers

Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded…

Machine Learning · Computer Science 2020-03-02 Lisa Lee , Benjamin Eysenbach , Emilio Parisotto , Eric Xing , Sergey Levine , Ruslan Salakhutdinov

In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this…

Machine Learning · Computer Science 2025-08-29 Souradeep Nanda , Anay Majee , Rishabh Iyer

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models…

Machine Learning · Computer Science 2026-01-06 Hongze Sun , Wuque Cai , Duo Chen , Quan Tang , Shifeng Mao , Jiayi He , Zhenxing Wang , Yan Cui , Dezhong Yao , Daqing Guo

Achieving reliable multidimensional Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is both challenging and crucial for optimizing downstream tasks that depend on instantaneous CSI. This work extends traditional…

Systems and Control · Electrical Eng. & Systems 2024-09-24 Lei Chu , Daoud Burghal , Rui Wang , Michael Neuman , Andreas F. Molisch

We present BRIEE (Block-structured Representation learning with Interleaved Explore Exploit), an algorithm for efficient reinforcement learning in Markov Decision Processes with block-structured dynamics (i.e., Block MDPs), where rich…

Machine Learning · Computer Science 2022-10-12 Xuezhou Zhang , Yuda Song , Masatoshi Uehara , Mengdi Wang , Alekh Agarwal , Wen Sun

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine Learning · Computer Science 2025-10-02 Anushka Tiwari , Sayantan Pal , Rohini K. Srihari , Kaiyi Ji

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs,…

Machine Learning · Computer Science 2022-08-08 Albert Gu , Karan Goel , Christopher Ré

Regression problems that have closed-form solutions are well understood and can be easily implemented when the dataset is small enough to be all loaded into the RAM. Challenges arise when data is too big to be stored in RAM to compute the…

Machine Learning · Computer Science 2019-10-08 Xiang Liu , Ziyang Tang , Huyunting Huang , Tonglin Zhang , Baijian Yang

Token-free language models learn directly from raw bytes and remove the inductive bias of subword tokenization. Operating on bytes, however, results in significantly longer sequences. In this setting, standard autoregressive Transformers…

Computation and Language · Computer Science 2024-08-13 Junxiong Wang , Tushaar Gangavarapu , Jing Nathan Yan , Alexander M. Rush

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity,…

Machine Learning · Computer Science 2025-03-11 Chengqi Zheng , Haiyan Yin , Jianda Chen , Terence Ng , Yew-Soon Ong , Ivor Tsang

Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, without access to original training data. Unfortunately, its application to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Seongsoo Heo , Dong-Wan Choi

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

Computation and Language · Computer Science 2022-04-27 Haozhe Ji , Rongsheng Zhang , Zhenyu Yang , Zhipeng Hu , Minlie Huang

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Computation and Language · Computer Science 2025-12-09 Sebastian Sztwiertnia , Felix Friedrich , Kristian Kersting , Patrick Schramowski , Björn Deiseroth

With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of sequences with respect to the sequence length during training…

Machine Learning · Computer Science 2026-05-19 Florent De Geeter , Gaspard Lambrechts , Damien Ernst , Guillaume Drion

Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced…

Computation and Language · Computer Science 2025-08-06 Jiahao Zhao

Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model…

Computation and Language · Computer Science 2026-05-28 Sangyun Lee , Sean McLeish , Tom Goldstein , Giulia Fanti

State space models (SSMs) often sacrifice capacity, search space, or stability to offset the memory and compute costs of large state dimensions. We introduce a structured post-training pruning method for SSMs -- AIRE-Prune (Asymptotic…

Machine Learning · Computer Science 2026-02-03 Apurba Prasad Padhy , Fernando Camacho , Saibal Mukhopadhyay

Despite pre-training's progress in many important NLP tasks, it remains to explore effective pre-training strategies for dense retrieval. In this paper, we propose RetroMAE, a new retrieval oriented pre-training paradigm based on Masked…

Computation and Language · Computer Science 2022-10-18 Shitao Xiao , Zheng Liu , Yingxia Shao , Zhao Cao

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-01 Zhifeng Ma , Hao Zhang , Jie Liu