Related papers: Thinking While Listening: Simple Test Time Scaling…
Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-time budget hurts overall performance, but not all problems are…
Recent Large Audio-Language Models (LALMs) have shown strong performance on various audio understanding tasks such as speech translation and Audio Q\&A. However, they exhibit significant limitations on challenging audio reasoning tasks in…
Large Language Models (LLMs) excel at reasoning, traditionally requiring high-quality large-scale data and extensive training. Recent works reveal a very appealing Less-Is-More phenomenon where very small, carefully curated high-quality…
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek R1) have led to a popular belief that extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance. This raises a natural…
Thinking aloud is an effective meta-cognitive strategy human reasoners apply to solve difficult problems. We suggest to improve the reasoning ability of pre-trained neural language models in a similar way, namely by expanding a task's…
Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many…
The ability of artificial intelligence (AI) systems to perceive and comprehend audio signals is crucial for many applications. Although significant progress has been made in this area since the development of AudioSet, most existing models…
Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. While current researches continue to explore the benefits…
Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been to…
Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reasoning quality and responsiveness are tightly coupled: delaying reasoning until the speech…
Recent advancements in multimodal reasoning have largely overlooked the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks. We meticulously curated a large-scale and diverse…
Recent advancements in the field of large language models, particularly through the Chain of Thought (CoT) approach, have demonstrated significant improvements in solving complex problems. However, existing models either tend to sacrifice…
Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…
The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model's potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive…
Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards.…
Even without directly hearing sounds, humans can effortlessly reason about auditory properties, such as pitch, loudness, or sound-source associations, drawing on auditory commonsense. In contrast, language models often lack this capability,…
Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time…
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling to arbitrary depth at test-time. This…
The use of large language models in digital forensics has been widely explored. Beyond identifying potential applications, research has also focused on optimizing model performance for forensic tasks through fine-tuning. However, limited…
This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an…