Aryo Pradipta Gema

Computer Science · Physical Sciences

9h-index348citations51works3.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(15), Natural Language Processing Techniques(8), Computational Drug Discovery Methods(5), Semantic Web and Ontologies(5), Biomedical Text Mining and Ontologies(5)

Publications51 total

Same Answer, Different Representations: Hidden instability in VLMs
arXiv (Cornell University)·2026Open Access
Same Answer, Different Representations: Hidden instability in VLMs
ArXiv.org·2026Open Access
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
arXiv (Cornell University)·2025Open Access
Learning Binding Affinities via Fine-Tuning of Protein and Ligand Language Models
Journal of Chemical Information and Modeling·2025· 3 citedOpen Access
PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
arXiv (Cornell University)·2025Open Access
Inverse Scaling in Test-Time Compute
arXiv (Cornell University)·2025Open Access
GRADA: Graph-based Reranking against Adversarial Documents Attack
arXiv (Cornell University)·2025Open Access
Noiser: Bounded Input Perturbations for Attributing Large Language Models
arXiv (Cornell University)·2025Open Access
An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
arXiv (Cornell University)·2025Open Access
Self-Training Large Language Models for Tool-Use Without Demonstrations
arXiv (Cornell University)·2025Open Access
Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
arXiv (Cornell University)·2025· 1 citedOpen Access
Fostering effective hybrid human-LLM reasoning and decision making
Frontiers in Artificial Intelligence·2025· 8 citedOpen Access
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning
2025Open Access
GRADA: Graph-based Reranking against Adversarial Documents Attack
2025· 1 citedOpen Access
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
2025Open Access
Are We Done with MMLU?
2025· 4 citedOpen Access
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
2025· 1 citedOpen Access
Self-Training Large Language Models for Tool-Use Without Demonstrations
2025Open Access
Natural language processing for detecting adverse drug events: A systematic review protocol
NIHR Open Research·2024· 1 citedOpen Access
Learning Binding Affinities via Fine-tuning of Protein and Ligand Language Models
2024· 6 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Pasquale Minervini(23), Beatrice Alex(14), Xuanli He(11), Derwin Suhartono(9), Giwon Hong(8), Luke Daines(6), Suhendro Winton(6), Theodorus David(6), Xiaotang Du(6), Mohamad Ivan Fanany(5), Aniati Murni Arymurthy(5), Alessio Devoto(5), Rohit Saxena(4), Emile van Krieken(4), Javier A. Alfaro(3), Ajitha Rajan(3), Yu Zhao(3), Mohammad Reza Ghasemi Madani(3), Imane Guellil(3), Jinge Wu(3)