Yunji Chen

22

Papers

10

Total Citations

Papers (22)

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

Prompt-based Visual Alignment for Zero-shot Policy Transfer

Fixed-Point Back-Propagation Training

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

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

Emergent Communication for Numerical Concepts Generalization

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

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

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Emergent Communication for Rules Reasoning

ANPL: Towards Natural Programming with Interactive Decomposition

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

Context Shift Reduction for Offline Meta-Reinforcement Learning

Distilling Object Detectors with Feature Richness

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

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

Object-Category Aware Reinforcement Learning

Learning Domain-Aware Detection Head with Prompt Tuning

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression