影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
62.07/100
前 4.3%
全站排名 #2,753
发表论文17 篇
平均评分
年均产出5.7 篇/年
Xiao Zhang
研究方向
large language models · trustworthy machine learning · recommender system · information retrieval · online learning · model selection · causal learning
15
Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
ICLR 2026Poster
三作31
StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
ICLR 2026Poster
24
CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment
ICLR 2026Rejected
26
Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models
ICLR 2026Poster
17
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
ICLR 2026Rejected
11
Generalization Analysis for Controllable Learning
ICML 2025Poster
二作21
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
ICLR 2025Spotlight
20
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
ICLR 2025Poster
33
Length-Induced Embedding Collapse in Transformer-based Models
ICLR 2025Rejected
16
On the Power of Federated Learning for Online Sparse Linear Regression with Decentralized Data
ICLR 2025Rejected
二作21
Matrix Sketching in Bandits: Current Pitfalls and New Framework
ICLR 2025Rejected
三作9
Dimension-Free Adaptive Subgradient Methods with Frequent Directions
ICML 2025Poster
34
Generating Model Parameters for Controlling: Parameter Diffusion for Controllable Multi-Task Recommendation
ICLR 2025Rejected
三作