Siyu Chen

papers

478

total citations

papers (12)

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

ICML 2024arXiv

citations

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

ECCV 2022arXiv

citations

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

NEURIPS 2021arXiv

citations

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention

ICML 2025arXiv

citations

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

ICLR 2025

citations

Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation

ICCV 2025arXiv

citations

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

NEURIPS 2025arXiv

citations

Siyu Chen

papers (12)

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

PyPose: A Library for Robot Learning With Physics-Based Optimization

Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding

MambaIC: State Space Models for High-Performance Learned Image Compression

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

papers (12)

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

PyPose: A Library for Robot Learning With Physics-Based Optimization

Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding

MambaIC: State Space Models for High-Performance Learned Image Compression

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds