ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xinyi Wang

Xinyi Wang

2

Affiliations

Affiliations

Carnegie Mellon UniversityUC Santa Barbara

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 14, 2026, 7:27 PM AMS

13

papers

348

total citations

papers (13)

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

NEURIPS 2023arXiv

Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

The Good, The Bad, and Why: Unveiling Emotions in Generative AI

MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

Counterfactual Maximum Likelihood Estimation for Training Deep Networks

NEURIPS 2021arXiv

Logits DeConfusion with CLIP for Few-Shot Learning

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

Position: AI/ML Influencers Have a Place in the Academic Process

GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts

AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models

NEURIPS 2025arXiv

Iterative Search Attribution for Deep Neural Networks