Xin Zhang
5 papers · Latest:
Comparative analysis of missing data imputation methods for CSST survey: Impact on photometric redshift estimation performance
Evaluates imputation methods to improve photometric redshift accuracy amid missing data in CSST surveys.
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
This paper introduces a method to 'unsilence' visual latents in MLLMs by optimizing latent reasoning at inference time, improving their contribution to predictions.
Robust parameter inference for Taiji via time-frequency contrastive learning and normalizing flows
This paper introduces a glitch-robust deep learning framework for Taiji gravitational-wave parameter inference using time-frequency contrastive learning and normalizing flows.
Unifying topological, geometric, and complex classifications of black hole thermodynamics
This paper unifies three distinct classification schemes for black hole thermodynamics using the critical point structure of temperature curves.
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
PASK develops an intent-aware proactive AI agent with long-term memory, using a novel paradigm and a real-world benchmark for complex user needs.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.