Xinyi Wang

11

Papers

108

Total Citations

Papers (11)

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

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

Logits DeConfusion with CLIP for Few-Shot Learning

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

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

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

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

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

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

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

Iterative Search Attribution for Deep Neural Networks