Related papers: SoundMind: RL-Incentivized Logic Reasoning for Aud…

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…

Increasing interest in reasoning models has led math to become a prominent testing ground for algorithmic and methodological improvements. However, existing open math datasets either contain a small collection of high-quality, human-written…

Large audio-language models (LALMs), built upon powerful Large Language Models (LLMs), have exhibited remarkable audio comprehension and reasoning capabilities. However, the training of LALMs demands a large corpus of audio-language pairs,…

While Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes, their use for audio deepfake detection remains largely unexplored. In this work, we…

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by…

Recent advances such as OpenAI-o1 and DeepSeek R1 have demonstrated the potential of Reinforcement Learning (RL) to enhance reasoning abilities in Large Language Models (LLMs). While open-source replication efforts have primarily focused on…

Understanding the internal mechanisms of large audio-language models (LALMs) is crucial for interpreting their behavior and improving performance. This work presents the first in-depth analysis of how LALMs internally perceive and recognize…

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex…

Reasoning language models (RLMs), also known as Large Reasoning Models (LRMs), such as OpenAI's o1 and o3, DeepSeek-R1, and Alibaba's QwQ, have redefined AI's problem-solving capabilities by extending LLMs with advanced reasoning…

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language. However, their conventional usage through…

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities…

Large language models (LLMs) have shown exceptional versatility in natural language processing, prompting recent efforts to extend their multimodal capabilities to speech processing through the development of audio large language models…

Standard training for Multi-modal Large Language Models (MLLMs) involves concatenating non-textual information, like vision or audio, with a text prompt. This approach may not encourage deep integration of modalities, limiting the model's…

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Existing end-to-end speech large language models (LLMs) usually rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth. We focus on two fundamental problems between speech and text:…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…