ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Zi Yu Zhou

Zi Yu Zhou

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 4:51 AM AMS

21

papers

371

total citations

papers (21)

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

NEURIPS 2025arXiv

On the Role of Attention Heads in Large Language Model Safety

OpenCUA: Open Foundations for Computer-Use Agents

NEURIPS 2025arXiv

Can LLMs Understand Time Series Anomalies?

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

PanTS: The Pancreatic Tumor Segmentation Dataset

NEURIPS 2025arXiv

Emergent Response Planning in LLMs

Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

Generating Physical Dynamics under Priors

CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search

Distributionally Robust Policy Learning under Concept Drifts

LIFEBENCH: Evaluating Length Instruction Following in Large Language Models

NEURIPS 2025arXiv

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

Precise Asymptotics and Refined Regret of Variance-Aware UCB

NEURIPS 2025arXiv

SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation

VLMs can Aggregate Scattered Training Patches

NEURIPS 2025arXiv