1 citations · 1 across the 9 of their papers we have counts for
9 papers
Crab: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
Dongnuan Cai, Henghui Du, Chang Zhou +5
Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models w…
Video Detective: Seek Critical Clues Recurrently to Answer Question from Long Videos
Henghui Du, Chunjie Zhang, Xi Chen +2
Long Video Question-Answering (LVQA) presents a significant challenge for Multi-modal Large Language Models (MLLMs) due to immense context and overloaded information, which could a…
Step-DeepResearch Technical Report
Chen Hu, Haikuo Du, Heng Wang +64
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands f…
BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona Reasoning
Siyuan Zheng, Pai Liu, Xi Chen +2
Human-like virtual characters are crucial for games, storytelling, and virtual reality, yet current methods rely heavily on annotated data or handcrafted persona prompts, making it…
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…
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…
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…
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
Yue Fan, Xiaojian Ma, Rongpeng Su +4
This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored…
Slicing Vision Transformer for Flexible Inference
Yitian Zhang, Huseyin Coskun, Xu Ma +6
Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe…