10 papers
Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models
Hongyu Zhang, Cheng Yan, Xiang Xia +1
Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full expert pool. Training-free expe…
DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models
Yongkang Zhou, Xiang Xia, Cheng Yan +2
Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial re…
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models
Xiang Xia, Cheng Yan, Yiming Zhang +3
Mixture-of-experts (MoE) models increase parameter capacity by activating only a small subset of experts for each token. This conditional-computation paradigm has enabled autoregre…
UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention
Cheng Yan, Guangyang Ye, Wuyang Zhang +5
While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and…
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
Xiang Xia, Wuyang Zhang, Jiazheng Liu +2
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation due to their potential for parallel decoding and global refinement of…
FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation
Yao Li, Peiyuan Tang, Wuyang Zhang +7
Force/torque feedback can substantially improve Vision-Language-Action (VLA) models on contact-rich manipulation, but most existing approaches fuse all modalities at a single opera…