Related papers: Countering Language Drift with Seeded Iterated Lea…
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…
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…
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…
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…
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…
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 --…
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…
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.,…
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…
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…
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)…
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…
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…
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…
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,…
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…
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…
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…