Related papers: When Missing Becomes Structure: Intent-Preserving …
In this work, we address optimization problems where the objective function is a nonlinear function of an expected value, i.e., compositional stochastic {strongly convex programs}. We consider the case where the decision variable is not…
Conformal prediction provides a pivotal and flexible technique for uncertainty quantification by constructing prediction sets with a predefined coverage rate. Many online conformal prediction methods have been developed to address data…
We present FinRL-X, a modular and deployment-consistent trading architecture that unifies data processing, strategy construction, backtesting, and broker execution under a weight-centric interface. While existing open-source platforms are…
Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented chatbots, help users achieve a predefined goal (e.g. book a movie ticket) within a closed domain. A first step is to understand the user's goal by using natural…
Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…
LLMs serve as the backbone in SpeechLLMs, yet their behavior on spontaneous conversational input remains poorly understood. Conversational speech contains pervasive disfluencies -- interjections, edits, and parentheticals -- that are rare…
In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through…
Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…
Spoken language understanding (SLU) typically includes two subtasks: intent detection and slot filling. Currently, it has achieved great success in high-resource languages, but it still remains challenging in low-resource languages due to…
Offline-to-online deployment of reinforcement-learning (RL) agents must bridge two gaps: (1) the sim-to-real gap, where real systems add latency and other imperfections not present in simulation, and (2) the interaction gap, where policies…
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose…
Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities, yet they often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.…
In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the reasoning capability, especially in mathematics tasks.…
Algorithmic trading requires short-term tactical decisions consistent with long-term financial objectives. Reinforcement Learning (RL) has been applied to such problems, but adoption is limited by myopic behaviour and opaque policies. Large…
Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools during long-form reasoning, such as search engines and code interpreters, to solve tasks beyond the capabilities of internal…
In this work, we address the challenging problem of long-horizon goal-reaching policy learning from non-expert, action-free observation data. Unlike fully labeled expert data, our data is more accessible and avoids the costly process of…
Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completion rates in extended conversations. To address this…
Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions.…
Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning…