5 citations · 8 across the 10 of their papers we have counts for
10 papers
Recursive Multi-Agent Systems
Jiaru Zou, Rui Pan, Ruizhong Qiu +8
Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend…
Investigating Tool-Memory Conflicts in Tool-Augmented LLMs
Jiali Cheng, Rui Pan, Hadi Amiri
Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of know…
AstroMLab 5: Structured Summaries and Concept Extraction for 400,000 Astrophysics Papers
Yuan-Sen Ting, Alberto Accomazzi, Tirthankar Ghosal +4
We present a dataset of 408,590 astrophysics papers from arXiv (astro-ph), spanning 1992 through July 2025. Each paper has been processed through a multi-stage pipeline to produce:…
Subjective Perspectives within Learned Representations Predict High-Impact Innovation
Likun Cao, Rui Pan, James Evans
Existing studies of innovation emphasize the power of social structures to shape innovation capacity. Emerging machine learning approaches, however, enable us to model innovators'…
AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model
Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal +7
General-purpose large language models (LLMs), despite their broad capabilities, often struggle with specialized domain knowledge. This gap hinders their deployment as reliable rese…
AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model
Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal +6
AstroSage-Llama-3.1-8B is a domain-specialized natural-language AI assistant tailored for research in astronomy, astrophysics, cosmology, and astronomical instrumentation. Trained…
AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
Rui Pan, Tuan Dung Nguyen, Hardik Arora +3
Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy…
AstroMLab 1: Who Wins Astronomy Jeopardy!?
Yuan-Sen Ting, Tuan Dung Nguyen, Tirthankar Ghosal +8
We present a comprehensive evaluation of proprietary and open-weights large language models using the first astronomy-specific benchmarking dataset. This dataset comprises 4,425 mu…
AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
Ernest Perkowski, Rui Pan, Tuan Dung Nguyen +11
We explore the potential of enhancing LLM performance in astronomy-focused question-answering through targeted, continual pre-training. By employing a compact 7B-parameter LLaMA-2…
Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?
Yichi Zhang, Jiayi Pan, Yuchen Zhou +2
Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perceptio…