5 citations · 10 across the 18 of their papers we have counts for
19 papers
Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts
Qingfei Zhao, Huan Song, Shuyu Tian +2
On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories. However, scaling OPD to long-horizon reasoning exposes…
Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise
Cheng Yuan, Zhenyu Jia, Jiawei Shao +1
Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic. However, both traditional standa…
Ruyi2.5 Technical Report
Huan Song, Shuyu Tian, Qingfei Zhao +5
We present Ruyi2.5, a multimodal familial model built on the AI Flow framework. Extending Ruyi2's "Train Once, Deploy Many" paradigm to the multimodal domain, Ruyi2.5 constructs a…
Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
Zhuoxu Huang, Mengxi Jia, Hao Sun +2
Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLM…
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +5
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft…
Privacy-Aware Camera 2.0 Technical Report
Huan Song, Shuyu Tian, Ting Long +5
With the increasing deployment of intelligent sensing technologies in highly sensitive environments such as restrooms and locker rooms, visual surveillance systems face a profound…
Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
Zheyuan Gu, Qingsong Zhao, Yusong Wang +6
Current Vision-Language Models (VLMs) for deepfake detection excel at identifying spatial artifacts but overlook a critical dimension: temporal inconsistencies in video forgeries.…
A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration
Huan Song, Shuyu Tian, Junyi Hao +4
As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillanc…
The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models
Dakuan Lu, Jiaqi Zhang, Cheng Yuan +2
Recent advances in large language models (LLMs) have been largely driven by scaling laws for individual models, which predict performance improvements as model parameters and data…
Theoretical Foundations of Scaling Law in Familial Models
Huan Song, Qingfei Zhao, Ting Long +4
Neural scaling laws have become foundational for optimizing large language model (LLM) training, yet they typically assume a single dense model output. This limitation effectively…
Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives
Kai Jiang, Siqi Huang, Xiangyu Chen +4
Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively p…
Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression
Cheng Yuan, Jiawei Shao, Xuelong Li
Recent years have witnessed the rapid advancements of large language models (LLMs) and their expanding applications, leading to soaring demands for computational resources. The wid…
ScRPO: From Errors to Insights
Lianrui Li, Dakuan Lu, Jiawei Shao +1
We introduce Self-correction Relative Policy Optimization (ScRPO), a novel reinforcement learning framework designed to empower large language models with advanced mathematical rea…
CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
Zhiyuan Ning, Jiawei Shao, Ruge Xu +4
Speculative decoding has become a widely adopted as an effective technique for lossless inference acceleration when deploying large language models (LLMs). While on-the-fly self-sp…
Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding
Ruanjun Li, Ziheng Liu, Yuanming Shi +3
Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost because each output token is generated auto-regressively through all model la…
SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models
Yufei Xue, Yushi Huang, Jiawei Shao +4
Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-language models (VLMs) for multimodal und…
AI Flow: Perspectives, Scenarios, and Approaches
Hongjun An, Wenhan Hu, Sida Huang +11
Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and c…
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference
Cheng Yuan, Zhening Liu, Jiashu Lv +4
With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with li…
AI Flow at the Network Edge
Jiawei Shao, Xuelong Li
Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and…