50 citations · 129 across the 35 of their papers we have counts for
36 papers
EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent
Junlong Li, Junxi Li, Yuxiang Yang +3
Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understanding and largely overlook compl…
StepAudio 2.5 Technical Report
Bin Lin, Bo Zhao, Boyong Wu +98
Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks.…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
STEP3-VL-10B Technical Report
Ailin Huang, Chengyuan Yao, Chunrui Han +90
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-…
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
Gemini Robotics Team, Abbas Abdolmaleki, Saminda Abeyruwan +169
General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the G…
Step-Audio 2 Technical Report
Boyong Wu, Chao Yan, Chen Hu +106
This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…
Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining
Yaru Niu, Yunzhe Zhang, Mingyang Yu +11
Quadrupedal robots have demonstrated impressive locomotion capabilities in complex environments, but equipping them with autonomous versatile manipulation skills in a scalable way…
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Ailin Huang, Bingxin Li, Bruce Wang +73
Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate na…
Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning
Nikhil Sobanbabu, Guanqi He, Tairan He +2
Sim-to-real discrepancies hinder learning-based policies from achieving high-precision tasks in the real world. While Domain Randomization (DR) is commonly used to bridge this gap,…
LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing
Changyi Lin, Yuxin Ray Song, Boda Huo +9
Quadrupedal robots have demonstrated remarkable agility and robustness in traversing complex terrains. However, they struggle with dynamic object interactions, where contact must b…
Gemini Robotics: Bringing AI into the Physical World
Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie +115
Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as…
QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment
Yuyou Zhang, Yihang Yao, Shiqi Liu +7
When operating at their full capacity, quadrupedal robots can produce loud footstep noise, which can be disruptive in human-centered environments like homes, offices, and hospitals…
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Ailin Huang, Boyong Wu, Bruce Wang +142
Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such…
Adaptive Hardness-driven Augmentation and Alignment Strategies for Multi-Source Domain Adaptations
Yang Yuxiang, Zeng Xinyi, Zeng Pinxian +4
Multi-source Domain Adaptation (MDA) aims to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Nevertheless, traditional methods primarily focu…
Judge Like a Real Doctor: Dual Teacher Sample Consistency Framework for Semi-supervised Medical Image Classification
Zhang Qixiang, Yang Yuxiang, Zu Chen +4
Semi-supervised learning (SSL) is a popular solution to alleviate the high annotation cost in medical image classification. As a main branch of SSL, consistency regularization enga…
Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing
Yuming Feng, Chuye Hong, Yaru Niu +6
Recently, quadrupedal locomotion has achieved significant success, but their manipulation capabilities, particularly in handling large objects, remain limited, restricting their us…
Agile Continuous Jumping in Discontinuous Terrains
Yuxiang Yang, Guanya Shi, Changyi Lin +8
We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuo…
BTMuda: A Bi-level Multi-source unsupervised domain adaptation framework for breast cancer diagnosis
Yuxiang Yang, Xinyi Zeng, Pinxian Zeng +4
Deep learning has revolutionized the early detection of breast cancer, resulting in a significant decrease in mortality rates. However, difficulties in obtaining annotations and hu…
Learning with Alignments: Tackling the Inter- and Intra-domain Shifts for Cross-multidomain Facial Expression Recognition
Yuxiang Yang, Lu Wen, Xinyi Zeng +4
Facial Expression Recognition (FER) holds significant importance in human-computer interactions. Existing cross-domain FER methods often transfer knowledge solely from a single lab…
Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptation
Yuxiang Yang, Lu Wen, Yuanyuan Xu +2
Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distrib…
LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators
Changyi Lin, Xingyu Liu, Yuxiang Yang +6
Quadrupedal robots have emerged as versatile agents capable of locomoting and manipulating in complex environments. Traditional designs typically rely on the robot's inherent body…
Active Neural Topological Mapping for Multi-Agent Exploration
Xinyi Yang, Yuxiang Yang, Chao Yu +5
This paper investigates the multi-agent cooperative exploration problem, which requires multiple agents to explore an unseen environment via sensory signals in a limited time. A po…
FP8-LM: Training FP8 Large Language Models
Houwen Peng, Kan Wu, Yixuan Wei +17
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs). Our key insight is that most variables, such as gradients and optimizer s…