Related papers: Step-Audio-R1 Technical Report

Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues…

Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While a few recent studies have begun to explore AudioLLM-based…

We present Gazal-R1, a 32-billion-parameter language model that achieves state-of-the-art performance in medical reasoning while providing transparent, step-by-step explanations for clinical decision-making. Built upon Qwen3 32B, our model…

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning…

Traditional evaluations of reasoning capabilities of language models are dominated by adult-centric benchmarks that presuppose broad world knowledge, complex instruction following, and mature pragmatic competence. These assumptions are…

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the…

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…

Automating penetration testing is crucial for enhancing cybersecurity, yet current Large Language Models (LLMs) face significant limitations in this domain, including poor error handling, inefficient reasoning, and an inability to perform…

The human capability to reason about one domain by using knowledge of other domains has been researched for more than 50 years, but models that are formally sound and predict cognitive process are sparse. We propose a formally sound method…

Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an ``Audio-Visual Confusion'' scene by modifying…

Audio language models process audio inputs using textual prompts for tasks like speech recognition and audio captioning. Although built on multilingual pre-trained components, most are trained primarily on English, limiting their usability…

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG systems based on…

Recent advances in reasoning-enhanced Large Language Models such as OpenAI-o1/3 and DeepSeek-R1 have significantly improved performance on complex tasks. However, the quality and transparency of their internal reasoning processes remain…

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal,…

Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning…

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover can achieve…

Despite strong performance on existing benchmarks, it remains unclear whether large language models can reason over genuinely novel scientific information. Most evaluations score end-to-end RAG pipelines, where reasoning is confounded with…

This study presents the first examination of the ability of Large Language Models (LLMs) to follow reasoning strategies that are used to guide Automated Theorem Provers (ATPs). We evaluate the performance of GPT4, GPT3.5 Turbo and Google's…

Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question…

In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL training has become a central technique for implementing…