Picture for Zijun Yao

Zijun Yao

Sparse Auto-Encoder Interprets Linguistic Features in Large Language Models

Add code
Feb 27, 2025
Viaarxiv icon

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

Add code
Feb 26, 2025
Viaarxiv icon

Iterative Feature Space Optimization through Incremental Adaptive Evaluation

Add code
Jan 24, 2025
Viaarxiv icon

Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Add code
Jan 20, 2025
Figure 1 for Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Figure 2 for Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Figure 3 for Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Figure 4 for Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Viaarxiv icon

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation

Add code
Dec 24, 2024
Viaarxiv icon

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning

Add code
Nov 25, 2024
Figure 1 for AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Figure 2 for AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Figure 3 for AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Figure 4 for AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Viaarxiv icon

Pre-training Distillation for Large Language Models: A Design Space Exploration

Add code
Oct 21, 2024
Figure 1 for Pre-training Distillation for Large Language Models: A Design Space Exploration
Figure 2 for Pre-training Distillation for Large Language Models: A Design Space Exploration
Figure 3 for Pre-training Distillation for Large Language Models: A Design Space Exploration
Figure 4 for Pre-training Distillation for Large Language Models: A Design Space Exploration
Viaarxiv icon

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

Add code
Oct 21, 2024
Figure 1 for RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Figure 2 for RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Figure 3 for RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Figure 4 for RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Viaarxiv icon

Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks

Add code
Oct 03, 2024
Viaarxiv icon

Meta-Learning on Augmented Gene Expression Profiles for Enhanced Lung Cancer Detection

Add code
Aug 19, 2024
Viaarxiv icon