Lu Chen

papers

332

total citations

papers (12)

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

AAAI 2024arXiv

132

citations

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models

CVPR 2025arXiv

citations

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

NEURIPS 2025arXiv

citations

Evolving Subnetwork Training for Large Language Models

ICML 2024arXiv

citations

Arrow: Accelerator for Time Series Causal Discovery with Time Weaving

ICML 2025

citations

Less-forgetting Multi-lingual Fine-tuning

NEURIPS 2022

citations

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

NEURIPS 2021

citations

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations

AAAI 2025arXiv

citations

Lu Chen

papers (12)

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Reducing Tool Hallucination via Reliability Alignment

EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

Evolving Subnetwork Training for Large Language Models

Arrow: Accelerator for Time Series Causal Discovery with Time Weaving

Less-forgetting Multi-lingual Fine-tuning

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations

papers (12)

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Reducing Tool Hallucination via Reliability Alignment

EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

Evolving Subnetwork Training for Large Language Models

Arrow: Accelerator for Time Series Causal Discovery with Time Weaving

Less-forgetting Multi-lingual Fine-tuning

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations