English
Related papers

Related papers: Countering Language Drift with Seeded Iterated Lea…

200 papers

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

Computation and Language · Computer Science 2021-04-14 Di Wu , Yiren Chen , Liang Ding , Dacheng Tao

Modern sensing systems generate large volumes of unlabeled multivariate time-series data. This abundance of unlabeled data makes self-supervised learning (SSL) a natural approach for learning transferable representations. However, most…

Artificial Intelligence · Computer Science 2026-03-13 Yuliang Chen , Arvind Pillai , Yu Yvonne Wu , Tess Z. Griffin , Lisa Marsch , Michael V. Heinz , Nicholas C. Jacobson , Andrew Campbell

Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. The recent introduction of benchmarks (Padmakumar et al., 2022) raises the question of how best to train and…

Machine Learning · Computer Science 2022-10-13 So Yeon Min , Hao Zhu , Ruslan Salakhutdinov , Yonatan Bisk

Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open…

Computation and Language · Computer Science 2026-04-29 George Morgulis , John Hewitt

One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations --…

Machine Learning · Computer Science 2024-08-13 Philipp Wu , Kourosh Hakhamaneshi , Yuqing Du , Igor Mordatch , Aravind Rajeswaran , Pieter Abbeel

We propose gated language experts and curriculum training to enhance multilingual transformer transducer models without requiring language identification (LID) input from users during inference. Our method incorporates a gating mechanism…

Computation and Language · Computer Science 2023-07-11 Eric Sun , Jinyu Li , Yuxuan Hu , Yimeng Zhu , Long Zhou , Jian Xue , Peidong Wang , Linquan Liu , Shujie Liu , Edward Lin , Yifan Gong

Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g.,…

Computation and Language · Computer Science 2022-06-07 Zhengxuan Wu , Atticus Geiger , Josh Rozner , Elisa Kreiss , Hanson Lu , Thomas Icard , Christopher Potts , Noah D. Goodman

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

Computation and Language · Computer Science 2020-12-24 Shaolei Zhang , Yang Feng , Liangyou Li

We introduce a new approach for speech pre-training named SPIRAL which works by learning denoising representation of perturbed data in a teacher-student framework. Specifically, given a speech utterance, we first feed the utterance to a…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-08 Wenyong Huang , Zhenhe Zhang , Yu Ting Yeung , Xin Jiang , Qun Liu

We are increasingly surrounded by artificially intelligent technology that takes decisions and executes actions on our behalf. This creates a pressing need for general means to communicate with, instruct and guide artificial agents, with…

We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…

Machine Learning · Computer Science 2025-07-22 Alex Cloud , Minh Le , James Chua , Jan Betley , Anna Sztyber-Betley , Jacob Hilton , Samuel Marks , Owain Evans

Learning motor skills for sports or performance driving is often done with professional instruction from expert human teachers, whose availability is limited. Our goal is to enable automated teaching via a learned model that interacts with…

Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and…

Machine Learning · Computer Science 2026-05-21 Sanghyeon Lee , Sangjun Bae , Yisak Park , Seungyul Han

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Qinhao Zhou , Yuwen Tan , Boqing Gong , Xiang Xiang

Class-Incremental Learning (CIL) requires a model to continually learn new classes without forgetting old ones. A common and efficient solution freezes a pre-trained model and employs lightweight adapters, whose parameters are often forced…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Ruiqi Liu , Boyu Diao , Zijia An , Runjie Shao , Zhulin An , Fei Wang , Yongjun Xu

When communicating, people behave consistently across conversational roles: People understand the words they say and are able to produce the words they hear. To date, artificial agents developed for language tasks have lacked such symmetry,…

Computation and Language · Computer Science 2020-10-13 Charles Lovering , Ellie Pavlick

Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require extensive offline training using large datasets and tremendous…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Umberto Cappellazzo , Enrico Fini , Muqiao Yang , Daniele Falavigna , Alessio Brutti , Bhiksha Raj

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only provided at the end…

Computation and Language · Computer Science 2021-11-03 Hongru Wang , Huimin Wang , Zezhong Wang , Kam-Fai Wong

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu