Xiang Li
8 papers · Latest:
UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
UniRank unifies autoregressive and non-autoregressive reranking using confidence-ordered denoising, improving performance and user engagement.
Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
Q-MMR is a novel off-policy evaluation framework using recursive reweighting and moment matching, offering dimension-free finite-sample guarantees.
From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
GloRank introduces a generative reranking framework for recommender systems that uses global item identifiers instead of local indices, improving item understanding and performance.
NeuroClaw Technical Report
NeuroClaw is a multi-agent AI system designed to make neuroimaging research more executable and reproducible by handling diverse data and complex pipelines.
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot enhances robot manipulation's view robustness by combining geometric models with video diffusion for closed-loop control.
PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
PokeVLA is a lightweight Vision-Language-Action model that improves robot manipulation by integrating comprehensive world knowledge and spatial awareness.
SWE-chat: Coding Agent Interactions From Real Users in the Wild
SWE-chat dataset reveals real-world coding agent usage, showing inefficiencies, security risks, and user interaction patterns in developer workflows.
From Clerks to Agentic-AI: How will Technology Change Labor Market in Finance?
This paper tracks how technological waves (computerization, passive investing, AI) have impacted labor productivity in financial asset management.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.