ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Yunji Chen

Yunji Chen

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, 12:57 AM AMS

23

papers

294

total citations

papers (23)

Distilling Object Detectors with Feature Richness

NEURIPS 2021arXiv

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

NEURIPS 2022arXiv

Context Shift Reduction for Offline Meta-Reinforcement Learning

NEURIPS 2023arXiv

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

NEURIPS 2021arXiv

Learning Domain-Aware Detection Head with Prompt Tuning

NEURIPS 2023arXiv

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

NEURIPS 2025arXiv

ANPL: Towards Natural Programming with Interactive Decomposition

NEURIPS 2023arXiv

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

NEURIPS 2023arXiv

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

NEURIPS 2023arXiv

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

NEURIPS 2023arXiv

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Object-Category Aware Reinforcement Learning

NEURIPS 2022arXiv

Emergent Communication for Numerical Concepts Generalization

Prompt-based Visual Alignment for Zero-shot Policy Transfer

AutoOS: Make Your OS More Powerful by Exploiting Large Language Models

QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models

OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning

Emergent Communication for Rules Reasoning

NEURIPS 2023arXiv

Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning

Fixed-Point Back-Propagation Training

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

NEURIPS 2025arXiv