Publications (28)
Derived Stratifications and Arithmetic Intersection Theory for Varieties with Isolated Singularities
Jiaming Luo, Shirong Li
In this paper, We develop the stratified de Rham theory on singular spaces using modern tools including derived geometry and stratified structures. This work unifies and extends th…
Unsupervised Learning of Morphological Forests
Jiaming Luo, Karthik Narasimhan, Regina Barzilay
This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edgewis…
Lattice-induced spin dynamics in Dirac magnet CoTiO3
Andrey Baydin, Jiaming Luo, Zhiren He +8
Spin-lattice coupling is crucial for understanding the spin transport and dynamics for spintronics and magnonics applications. Recently, cobalt titanate (CoTiO3), an easy-plane ant…
On the Log Hodge Theory of Toroidal Varieties and a Partial Proof of the Absolute Hodge Conjecture
Jiaming Luo
In this paper, we establish an innovative framework in logarithmic Hodge theory for toroidal varieties, introducing weighted toroidal structures and developing a systematic obstruc…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior
Jiaming Luo, Frederik Hartmann, Enrico Santus +2
Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest know…
Layer-dependent exciton polarizability and the brightening of dark excitons in few-layer black phosphorus
Yuchen Lei, Junwei Ma, Jiaming Luo +11
The evolution of excitons from 2D to 3D is of great importance in photo-physics, yet the layer-dependent exciton polarizability has not been investigated in 2D semiconductors. Here…
Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
Lily H. Zhang, Hamid Dadkhahi, Mara Finkelstein +3
Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations. In this work, we explore the potential of util…
Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts
Eleftheria Briakou, Jiaming Luo, Colin Cherry +1
In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a…
How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP
Kushal Tatariya, Artur Kulmizev, Wessel Poelman +6
Wikipedia's perceived high quality and broad language coverage have established it as a fundamental resource in NLP. However, in recent years, such assumptions of high quality have…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
Chip-Scale Aligned Chiral Carbon Nanotubes Exhibiting Giant Second Harmonic Generation
Rui Xu, Jacques Doumani, Viktor Labuntsov +16
Chiral carbon nanotubes (CNTs) are direct-gap semiconductors with optical properties governed by one-dimensional excitons with enormous oscillator strengths. Each species of chiral…
TranslateGemma Technical Report
Mara Finkelstein, Isaac Caswell, Tobias Domhan +18
We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the t…
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
Kundan Krishna, Yao Zhao, Jie Ren +4
The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may…
Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
Jiaming Luo, Yuan Cao, Regina Barzilay
In this paper we propose a novel neural approach for automatic decipherment of lost languages. To compensate for the lack of strong supervision signal, our model design is informed…
A Diverse and Effective Retrieval-Based Debt Collection System with Expert Knowledge
Jiaming Luo, Weiyi Luo, Guoqing Sun +5
Designing effective debt collection systems is crucial for improving operational efficiency and reducing costs in the financial industry. However, the challenges of maintaining scr…
To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation
Jiaming Luo, Colin Cherry, George Foster
We conduct a large-scale fine-grained comparative analysis of machine translations (MT) against human translations (HT) through the lens of morphosyntactic divergence. Across three…
Derived Stratified-Microlocal Framework and Moduli Space Resolution for the Cheeger-Goresky-Macpherson Conjecture
Jiaming Luo
In this paper, We define the stratified metric -category and the middle perversity moduli stack . We construct a un…
The optical properties of few-layer InSe
Chaoyu Song, Shenyang Huang, Chong Wang +2
Few-layer InSe draws tremendous research interests owing to the superior electronic and optical properties. It exhibits high carrier mobility up to more than 1000 cm2/Vs at room te…
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation
Muhammed Yusuf Kocyigit, Eleftheria Briakou, Daniel Deutsch +3
Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we prese…
A superior two-dimensional nanoporous graphene membrane for hydrogen separation
Liliang Tian, Humin Duan, Jiaming Luo +2
Hydrogen is one of the prime candidates for clean energy source with high energy density. However, current industrial methods of hydrogen production are difficult to provide hydrog…
From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity
Tianxi Wan, Jiaming Luo, Siyuan Chen +4
Psychiatric comorbidity is clinically significant yet challenging due to the complexity of multiple co-occurring disorders. To address this, we develop a novel approach integrating…
Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation
Bryan Li, Jiaming Luo, Eleftheria Briakou +1
While large language models (LLMs) have been increasingly adopted for machine translation (MT), their performance for specialist domains such as medicine and law remains an open ch…
SMOL: Professionally translated parallel data for 115 under-represented languages
Isaac Caswell, Elizabeth Nielsen, Jiaming Luo +23
We open-source SMOL (Set of Maximal Overall Leverage), a suite of training data to unlock machine translation for low-resource languages. SMOL has been translated into 124 (and gro…
Stratified Interpretation for De Rham Cohomology and Non-Witt Spaces
Jiaming Luo, Shirong Li
In this paper, we mainly build up the theory of sheaf-correspondence filtered spaces and stratified de Rham complexes for studying singular spaces. We prove the finiteness of a str…
Prompting PaLM for Translation: Assessing Strategies and Performance
David Vilar, Markus Freitag, Colin Cherry +3
Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an i…
Large effective magnetic fields from chiral phonons in rare-earth halides
Jiaming Luo, Tong Lin, Junjie Zhang +5
Time-reversal symmetry (TRS) is pivotal for materials optical, magnetic, topological, and transport properties. Chiral phonons, characterized by atoms rotating unidirectionally aro…
Out-of-Distribution Detection and Selective Generation for Conditional Language Models
Jie Ren, Jiaming Luo, Yao Zhao +4
Machine learning algorithms typically assume independent and identically distributed samples in training and at test time. Much work has shown that high-performing ML classifiers c…