Related papers: AQA-TTRL: Self-Adaptation in Audio Question Answer…
This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to…
The Audio Question Answering (AQA) task includes audio event classification, audio captioning, and open-ended reasoning. Recently, AQA has garnered attention due to the advent of Large Audio Language Models (LALMs). Current literature…
While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…
Large audio language models (ALMs) extend LLMs with auditory understanding. A common approach freezes the LLM and trains only an adapter on self-generated targets. However, this fails for reasoning LLMs (RLMs) whose built-in…
Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio…
Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…
Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse…
Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely…
Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority…
In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…
One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However,…
Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…
Large Language Models (LLMs) have achieved excellent performances in various tasks. However, fine-tuning an LLM requires extensive supervision. Human, on the other hand, may improve their reasoning abilities by self-thinking without…
Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration…
Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a…
Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…
Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…
Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be…
Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…
Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. The significance of possessing high-quality, diverse, and…