activity
20242026
collaborators

10 papers

cs.CV2026

Test-time Sparsity for Extreme Fast Action Diffusion

Kangye Ji, Yuan Meng, Jianbo Zhou +3

Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promis…

cs.CR2026

Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models

Pengcheng Sun, Lan Zhang, Zhaopeng Zhang +2

Large language models (LLMs) are increasingly deployed in enterprise settings where they handle sensitive documents and user context, raising acute concerns over security and contr…

cs.LG2025

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration

Ye Li, Jiahe Feng, Yuan Meng +6

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity o…

cs.CV2025

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

Ye Li, Yuan Meng, Zewen Sun +7

Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities. However, their high computational cost and low execution frequency hi…

cs.CV2025

Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective

Jiacheng Jiang, Yuan Meng, Chen Tang +4

Current quantization-aware training (QAT) methods primarily focus on enhancing the performance of quantized models on in-distribution (I.D) data, while overlooking the potential pe…

cs.CV2025

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

Mingzi Wang, Yuan Meng, Chen Tang +9

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance an…