Related papers: Calibration-Reasoning Framework for Descriptive Sp…

Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve…

The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where…

Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing. Traditional intrusive speech quality assessment requires the clean reference of the degraded…

Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) approach that jointly…

As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score~(MOS) usually requires multiple annotators to score the same speech. Such an annotation approach requires a lot of manpower and is also time-consuming.…

Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, particularly when users provide ambiguous initial…

Deep noise suppressors (DNS) have become an attractive solution to remove background noise, reverberation, and distortions from speech and are widely used in telephony/voice applications. They are also occasionally prone to introducing…

Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these…

Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning…

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advancements, existing models often fail to achieve a reliable…

Most of the traditional Applicant Tracking Systems (ATS) depend on strict matching using keywords, where candidates that are highly qualified are many times disqualified because of minor semantic differences. In this article, the two-stage…

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to…

We introduce Self-correction Relative Policy Optimization (ScRPO), a novel reinforcement learning framework designed to empower large language models with advanced mathematical reasoning capabilities through iterative self-reflection and…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…