activity
20242026
collaborators

10 papers

cs.CV2026

Dynamic Execution Commitment of Vision-Language-Action Models

Feng Chen, Xianghui Wang, Yuxuan Chen +4

Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level actions in a single forward pas…

cs.CV2026

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

Junkang Zhou, Yefei He, Feng Chen +2

Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies on strictly next-token predic…

cs.LG2026

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

Songtao Wei, Yi Li, Zhikai Li +7

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajec…

cs.LG2026

ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking

Lequan Lin, Dai Shi, Andi Han +7

Supervised learning relies on high-quality labeled data, but obtaining such data through human annotation is both expensive and time-consuming. Recent work explores using large lan…

cs.LG2026

Sparsity Forcing: Reinforcing Token Sparsity of MLLMs

Feng Chen, Yefei He, Lequan Lin +4

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods mere…

cs.CV2025

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs

Feng Chen, Yefei He, Shaoxuan He +9

Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge t…