Author

Xi Xiao

University of Alabama at Birmingham

h-index 10 View on Semantic Scholar

We have 7 of 38 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

PTQ4SAM3: Semantics-Preserving Post-Training Quantization for Segment Anything Model 3

Segment Anything Model 3 (SAM 3) can segment objects from text prompts and track them across video, but its memory and computation costs make deployment difficult. Post-training quantization (PTQ) reduces these costs by using fewer bits. However, a quantized model can select the wrong object or lose track of its target...

Xi Xiao, Yun-Bei Zhang, Lin Zhao et al. · 0 citations

Preprint Oct 2026

MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning

Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but risky for medical images, where answers may depend on localized boundary and texture evidence. We study training free pre-decoding pruning an...

Meng-Chen Fan, Qi-Zhen Lan, Xi Xiao et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Posterior Flow Matching

Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state. This paper introduces Posterior Flow Matching (PFM), a general generative modeling framework that learns conditional velocity means and componentwise var...

Chen-Rui Ma, Xi Xiao, Lin Zhao et al. · 0 citations

#machine learning Preprint Sep 2026

Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence

ReaLVR is proposed, which brings visual-evidence supervision to the model's own free-running latent trajectories, and is the first to scale visual reasoning in latent space, showing that the framework continues to deliver robust improvements at frontier model scales up to 235B.

Xi Xiao, Tian-Chen Zhao, Youngeun Kim et al. · 0 citations

#machine learning Preprint Sep 2026

FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents

ForGE is proposed, a unified framework for adapting frozen models through per-query routing over a joint action space that spans both support form and thinking depth and improves accuracy at 42-45% lower token cost on both main hosts.

Xi Xiao, Yun-Bei Zhang, Chen Liu et al. · 0 citations

Jul 2026

Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation

Inspired by the Information Bottleneck principle, Prompted Information Bottlenecks (PIB) is introduced, a framework that regularizes layer-wise compression-sufficiency trade-offs and promotes a more coherent cross-layer information path.

Yuqi Li, Xi Xiao, Yun-Bei Zhang et al. · arXiv.org · 10 citations

Preprint Aug 2026

Dynamic Hub-and-Spoke Memory for Streaming Video Understanding

Dynamic Hub-and-Spoke Memory is proposed, a training-free framework that represents distant history as structured textual memory while preserving the recent frames as visual tokens for fine-grained perception in streaming video understanding.

Xin-Ru Jiang, Lin Zhao, Xi Xiao et al. · 4 citations