Related papers: Transfer Reward Learning for Policy Gradient-Based…

Recognizing emotions in conversations is a challenging task due to the presence of contextual dependencies governed by self- and inter-personal influences. Recent approaches have focused on modeling these dependencies primarily via…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising way to train an agent…

Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a…

In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning. Reward inference is the key…

Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…

We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting…

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not…

Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at…

Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that…

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

Decision trees are ubiquitous in machine learning for their ease of use and interpretability. Yet, these models are not typically employed in reinforcement learning as they cannot be updated online via stochastic gradient descent. We…

Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA. In this paper, we propose a new method to edit the scene graph according to the user…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…