Related papers: Breaking Negative Cycles: A Reflection-To-Action S…

A longstanding challenge in robot learning for manipulation tasks has been the ability to generalize to varying initial conditions, diverse objects, and changing objectives. Learning based approaches have shown promise in producing robust…

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring…

Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation. We present a predictive theory that resolves this gap by showing that recoverability follows a…

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Conversational Recommender Systems (CRS) provide personalized services through multi-turn interactions, yet most existing methods overlook users' heterogeneous decision-making styles and knowledge levels, which constrains both accuracy and…

Reminiscence therapy is mental health care based on the recollection of memories. However, the effectiveness of this method varies amongst individuals. To solve this problem, it is necessary to provide more personalized support; therefore,…

People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich…

The strategy of pre-training a large model on a diverse dataset, then fine-tuning for a particular application has yielded impressive results in computer vision, natural language processing, and robotic control. This strategy has vast…

This study addresses the matter of reflexive control of the emotional states by means of Reflexive Game Theory (RGT). It is shown how to build a bridge between RGT and emotions. For this purpose the Pleasure-Arousal-Dominance (PAD) model is…

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Large language models are often described as capable of reflective reasoning, yet recursive self-evaluation without external feedback frequently yields reformulation rather than progress. We test this prediction in a cross-provider study of…

Background. The objective of the present study was to apply the nonlinear response function model of subjective well-being (RFSWB model) to evaluate the outcome of rhythmic movement therapy (RMT) for increasing subjective well-being and to…

While emotional text-to-speech (TTS) has made significant progress, most existing research remains limited to utterance-level emotional expression and fails to support word-level control. Achieving word-level expressive control poses…

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…

Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…

Transition states (TSs) govern the rates and outcomes of chemical reactions, making their accurate prediction a central challenge in computational chemistry. Although recent machine-learning models achieve near chemical accuracy in the…

As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts…

Student simulation supports educators to improve teaching by interacting with virtual students. However, most existing approaches ignore the modulation effects of course materials because of two challenges: the lack of datasets with…

We consider the predict-then-optimize paradigm for decision-making in which a practitioner (1) trains a supervised learning model on historical data of decisions, contexts, and rewards, and then (2) uses the resulting model to make future…