Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model

Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach employs interleaved token-output of text and audio to enhance semantic coherence and combines Direct Preference Optimization (DPO) with model merge to improve performance. Evaluations on the StepEval-Audio-360 benchmark demonstrate that Step-Audio-AQAA excels especially in speech control, outperforming the state-of-art LALMs in key areas. This work contributes a promising solution for end-to-end LALMs and highlights the critical role of token-based vocoder in enhancing overall performance for AQAA tasks.

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than simple scripts. Building such repositories from scratch remains a major challenge. Fortunately, GitHub hosts a vast, evolving collection of open-source repositories, which developers frequently reuse as modular components for complex tasks. Yet, existing frameworks like OpenHands and SWE-Agent still struggle to effectively leverage these valuable resources. Relying solely on README files provides insufficient guidance, and deeper exploration reveals two core obstacles: overwhelming information and tangled dependencies of repositories, both constrained by the limited context windows of current LLMs. To tackle these issues, we propose RepoMaster, an autonomous agent framework designed to explore and reuse GitHub repositories for solving complex tasks. For efficient understanding, RepoMaster constructs function-call graphs, module-dependency graphs, and hierarchical code trees to identify essential components, providing only identified core elements to the LLMs rather than the entire repository. During autonomous execution, it progressively explores related components using our exploration tools and prunes information to optimize context usage. Evaluated on the adjusted MLE-bench, RepoMaster achieves a 110% relative boost in valid submissions over the strongest baseline OpenHands. On our newly released GitTaskBench, RepoMaster lifts the task-pass rate from 24.1% to 62.9% while reducing token usage by 95%. Our code and demonstration materials are publicly available at https://github.com/wanghuacan/RepoMaster.

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning

Recent advances in reasoning language models have witnessed a paradigm shift from short to long CoT pattern. Given the substantial computational cost of rollouts in long CoT models, maximizing the utility of fixed training datasets becomes crucial. Our analysis reveals that negative responses contain valuable components such as self-reflection and error-correction steps, yet primary existing methods either completely discard negative samples (RFT) or apply equal penalization across all tokens (RL), failing to leverage these potential learning signals. In light of this, we propose Behavior Constrained Policy Gradient with Negative Sample Augmentation (BCPG-NSA), a fine-grained offline RL framework that encompasses three stages: 1) sample segmentation, 2) consensus-based step correctness assessment combining LLM and PRM judgers, and 3) policy optimization with NSA designed to effectively mine positive steps within negative samples. Experimental results show that BCPG-NSA outperforms baselines on several challenging math/coding reasoning benchmarks using the same training dataset, achieving improved sample efficiency and demonstrating robustness and scalability when extended to multiple iterations.

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs

We propose DialogueReason, a reasoning paradigm that uncovers the lost roles in monologue-style reasoning models, aiming to boost diversity and coherency of the reasoning process. Recent advances in RL-based large reasoning models have led to impressive long CoT capabilities and high performance on math and science benchmarks. However, these reasoning models rely mainly on monologue-style reasoning, which often limits reasoning diversity and coherency, frequently recycling fixed strategies or exhibiting unnecessary shifts in attention. Our work consists of an analysis of monologue reasoning patterns and the development of a dialogue-based reasoning approach. We first introduce the Compound-QA task, which concatenates multiple problems into a single prompt to assess both diversity and coherency of reasoning. Our analysis shows that Compound-QA exposes weaknesses in monologue reasoning, evidenced by both quantitative metrics and qualitative reasoning traces. Building on the analysis, we propose a dialogue-based reasoning, named DialogueReason, structured around agents, environment, and interactions. Using PPO with rule-based rewards, we train open-source LLMs (Qwen-QWQ and Qwen-Base) to adopt dialogue reasoning. We evaluate trained models on MATH, AIME, and GPQA datasets, showing that the dialogue reasoning model outperforms monologue models under more complex compound questions. Additionally, we discuss how dialogue-based reasoning helps enhance interpretability, facilitate more intuitive human interaction, and inspire advances in multi-agent system design.

Point Cloud-based Grasping for Soft Hand Exoskeleton

Grasping is a fundamental skill for interacting with and manipulating objects in the environment. However, this ability can be challenging for individuals with hand impairments. Soft hand exoskeletons designed to assist grasping can enhance or restore essential hand functions, yet controlling these soft exoskeletons to support users effectively remains difficult due to the complexity of understanding the environment. This study presents a vision-based predictive control framework that leverages contextual awareness from depth perception to predict the grasping target and determine the next control state for activation. Unlike data-driven approaches that require extensive labelled datasets and struggle with generalizability, our method is grounded in geometric modelling, enabling robust adaptation across diverse grasping scenarios. The Grasping Ability Score (GAS) was used to evaluate performance, with our system achieving a state-of-the-art GAS of 91% across 15 objects and healthy participants, demonstrating its effectiveness across different object types. The proposed approach maintained reconstruction success for unseen objects, underscoring its enhanced generalizability compared to learning-based models.

MultiClear: Multimodal Soft Exoskeleton Glove for Transparent Object Grasping Assistance

Grasping is a fundamental skill for interacting with the environment. However, this ability can be difficult for some (e.g. due to disability). Wearable robotic solutions can enhance or restore hand function, and recent advances have leveraged computer vision to improve grasping capabilities. However, grasping transparent objects remains challenging due to their poor visual contrast and ambiguous depth cues. Furthermore, while multimodal control strategies incorporating tactile and auditory feedback have been explored to grasp transparent objects, the integration of vision with these modalities remains underdeveloped. This paper introduces MultiClear, a multimodal framework designed to enhance grasping assistance in a wearable soft exoskeleton glove for transparent objects by fusing RGB data, depth data, and auditory signals. The exoskeleton glove integrates a tendon-driven actuator with an RGB-D camera and a built-in microphone. To achieve precise and adaptive control, a hierarchical control architecture is proposed. For the proposed hierarchical control architecture, a high-level control layer provides contextual awareness, a mid-level control layer processes multimodal sensory inputs, and a low-level control executes PID motor control for fine-tuned grasping adjustments. The challenge of transparent object segmentation was managed by introducing a vision foundation model for zero-shot segmentation. The proposed system achieves a Grasping Ability Score of 70.37%, demonstrating its effectiveness in transparent object manipulation.

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio.

NatureLM: Deciphering the Language of Nature for Scientific Discovery

Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, and RNA. However, these models are typically trained in isolation, lacking the ability to integrate across different scientific domains. Recognizing that entities within these domains can all be represented as sequences, which together form the "language of nature", we introduce Nature Language Model (briefly, NatureLM), a sequence-based science foundation model designed for scientific discovery. Pre-trained with data from multiple scientific domains, NatureLM offers a unified, versatile model that enables various applications including: (i) generating and optimizing small molecules, proteins, RNA, and materials using text instructions; (ii) cross-domain generation/design, such as protein-to-molecule and protein-to-RNA generation; and (iii) achieving state-of-the-art performance in tasks like SMILES-to-IUPAC translation and retrosynthesis on USPTO-50k. NatureLM offers a promising generalist approach for various scientific tasks, including drug discovery (hit generation/optimization, ADMET optimization, synthesis), novel material design, and the development of therapeutic proteins or nucleotides. We have developed NatureLM models in different sizes (1 billion, 8 billion, and 46.7 billion parameters) and observed a clear improvement in performance as the model size increases.

Distributed Learning for UAV Swarms

Unmanned Aerial Vehicle (UAV) swarms are increasingly deployed in dynamic, data-rich environments for applications such as environmental monitoring and surveillance. These scenarios demand efficient data processing while maintaining privacy and security, making Federated Learning (FL) a promising solution. FL allows UAVs to collaboratively train global models without sharing raw data, but challenges arise due to the non-Independent and Identically Distributed (non-IID) nature of the data collected by UAVs. In this study, we show an integration of the state-of-the-art FL methods to UAV Swarm application and invetigate the performance of multiple aggregation methods (namely FedAvg, FedProx, FedOpt, and MOON) with a particular focus on tackling non-IID on a variety of datasets, specifically MNIST for baseline performance, CIFAR10 for natural object classification, EuroSAT for environment monitoring, and CelebA for surveillance. These algorithms were selected to cover improved techniques on both client-side updates and global aggregation. Results show that while all algorithms perform comparably on IID data, their performance deteriorates significantly under non-IID conditions. FedProx demonstrated the most stable overall performance, emphasising the importance of regularising local updates in non-IID environments to mitigate drastic deviations in local models.

Gradient is All You Need: Gradient-Based Attention Fusion for Infrared Small Target Detection

Infrared small target detection (IRSTD) is widely used in civilian and military applications. However, IRSTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Gradient Network (GaNet), which aims to extract and preserve edge and gradient information of small targets. GaNet employs the Gradient Transformer (GradFormer) module, simulating central difference convolutions (CDC) to extract and integrate gradient features with deeper features. Furthermore, we propose a global feature extraction model (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the background information. We compare the network with state-of-the-art (SOTA) approaches, and the results demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/Gradient-Transformer.