Rui Xin

Zijie J. Wang, Chudi Zhong, Rui Xin et al. · gatech

Given thousands of equally accurate machine learning (ML) models, how can users choose among them? A recent ML technique enables domain experts and data scientists to generate a complete Rashomon set for sparse decision trees--a huge set of almost-optimal interpretable ML models. To help ML practitioners identify models with desirable properties from this Rashomon set, we develop TimberTrek, the first interactive visualization system that summarizes thousands of sparse decision trees at scale. Two usage scenarios highlight how TimberTrek can empower users to easily explore, compare, and curate models that align with their domain knowledge and values. Our open-source tool runs directly in users' computational notebooks and web browsers, lowering the barrier to creating more responsible ML models. TimberTrek is available at the following public demo link: https://poloclub.github.io/timbertrek.

Rui Xin, Chudi Zhong, Zhi Chen et al.

In any given machine learning problem, there may be many models that could explain the data almost equally well. However, most learning algorithms return only one of these models, leaving practitioners with no practical way to explore alternative models that might have desirable properties beyond what could be expressed within a loss function. The Rashomon set is the set of these all almost-optimal models. Rashomon sets can be extremely complicated, particularly for highly nonlinear function classes that allow complex interaction terms, such as decision trees. We provide the first technique for completely enumerating the Rashomon set for sparse decision trees; in fact, our work provides the first complete enumeration of any Rashomon set for a non-trivial problem with a highly nonlinear discrete function class. This allows the user an unprecedented level of control over model choice among all models that are approximately equally good. We represent the Rashomon set in a specialized data structure that supports efficient querying and sampling. We show three applications of the Rashomon set: 1) it can be used to study variable importance for the set of almost-optimal trees (as opposed to a single tree), 2) the Rashomon set for accuracy enables enumeration of the Rashomon sets for balanced accuracy and F1-score, and 3) the Rashomon set for a full dataset can be used to produce Rashomon sets constructed with only subsets of the data set. Thus, we are able to examine Rashomon sets across problems with a new lens, enabling users to choose models rather than be at the mercy of an algorithm that produces only a single model.

Rui Zhang, Rui Xin, Margo Seltzer et al.

Regression trees are one of the oldest forms of AI models, and their predictions can be made without a calculator, which makes them broadly useful, particularly for high-stakes applications. Within the large literature on regression trees, there has been little effort towards full provable optimization, mainly due to the computational hardness of the problem. This work proposes a dynamic-programming-with-bounds approach to the construction of provably-optimal sparse regression trees. We leverage a novel lower bound based on an optimal solution to the k-Means clustering algorithm in 1-dimension over the set of labels. We are often able to find optimal sparse trees in seconds, even for challenging datasets that involve large numbers of samples and highly-correlated features.

Yusheng Liu, Rui Xin, Tao Yang et al.

Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure.The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset consisting of all sparse labels and partial dense labels, and improve the ability of automatic IAN segmentation. In this work, in order to avoid the negative impact brought by sparse labeling, we transform the mixed supervised problem into a semi-supervised problem. Inspired by self-training via pseudo labeling, we propose a selective re-training framework based on IAN connectivity. Our method is quantitatively evaluated on the ToothFairy verification cases, achieving the dice similarity coefficient (DSC) of 0.7956, and 95\% hausdorff distance (HD95) of 4.4905, and wining the champion in the competition. Code is available at https://github.com/GaryNico517/SSL-IAN-Retraining.

Nihang Fu, Lai Wei, Yuqi Song et al.

Pre-trained transformer language models on large unlabeled corpus have produced state-of-the-art results in natural language processing, organic molecule design, and protein sequence generation. However, no such models have been applied to learn the composition patterns of inorganic materials. Here we train a series of seven modern transformer language models (GPT, GPT-2, GPT-Neo, GPT-J, BLMM, BART, and RoBERTa) using the expanded formulas from material deposited in the ICSD, OQMD, and Materials Projects databases. Six different datasets with/out non-charge-neutral or balanced electronegativity samples are used to benchmark the performances and uncover the generation biases of modern transformer models for the generative design of materials compositions. Our extensive experiments showed that the causal language models based materials transformers can generate chemically valid materials compositions with as high as 97.54\% to be charge neutral and 91.40\% to be electronegativity balanced, which has more than 6 times higher enrichment compared to a baseline pseudo-random sampling algorithm. These models also demonstrate high novelty and their potential in new materials discovery has been proved by their capability to recover the leave-out materials. We also find that the properties of the generated samples can be tailored by training the models with selected training sets such as high-bandgap materials. Our experiments also showed that different models each have their own preference in terms of the properties of the generated samples and their running time complexity varies a lot. We have applied our materials transformer models to discover a set of new materials as validated using DFT calculations.

Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar et al. · allen-ai, cmu

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are ultimately trained and evaluated. For instance, scaling is usually studied in the compute-optimal training regime (i.e., "Chinchilla optimal" regime). In contrast, models are often over-trained to reduce inference costs. Moreover, scaling laws mostly predict loss on next-token prediction, but models are usually compared on downstream task performance. To address both shortcomings, we create a testbed of 104 models with 0.011B to 6.9B parameters trained with various numbers of tokens on three data distributions. First, we fit scaling laws that extrapolate in both the amount of over-training and the number of model parameters. This enables us to predict the validation loss of a 1.4B parameter, 900B token run (i.e., 32$\times$ over-trained) and a 6.9B parameter, 138B token run (i.e., a compute-optimal run)$\unicode{x2014}$each from experiments that take 300$\times$ less compute. Second, we relate the perplexity of a language model to its downstream task performance by proposing a power law. We use this law to predict top-1 error averaged over downstream tasks for the two aforementioned models, using experiments that take 20$\times$ less compute. Our experiments are available at https://github.com/mlfoundations/scaling.

Team Olmo, Allyson Ettinger, Amanda Bertsch et al. · uw

We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date.

Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan et al.

Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. This challenge is becoming increasingly urgent as modern AI agents--such as OpenClaw and Gemini Agent--are granted persistent access to highly sensitive personal information. To tackle this longstanding bottleneck and the rising risks, we present Privasis (i.e., privacy oasis), the first million-scale fully synthetic dataset entirely built from scratch--an expansive reservoir of texts with rich and diverse private information--designed to broaden and accelerate research in areas where processing sensitive social data is inevitable. Compared to existing datasets, Privasis, comprising 1.4 million records, offers orders-of-magnitude larger scale with quality, and far greater diversity across various document types, including medical history, legal documents, financial records, calendars, and text messages with a total of 55.1 million annotated attributes such as ethnicity, date of birth, workplace, etc. We leverage Privasis to construct a parallel corpus for text sanitization with our pipeline that decomposes texts and applies targeted sanitization. Our compact sanitization models (<=4B) trained on this dataset outperform state-of-the-art large language models, such as GPT-5 and Qwen-3 235B. We plan to release data, models, and code to accelerate future research on privacy-sensitive domains and agents.

Matthew Becker, Yifei Chen, Nicholas Cochran et al.

We report on Just-in-Time catching test generation at Meta, designed to prevent bugs in large scale backend systems of hundreds of millions of line of code. Unlike traditional hardening tests, which pass at generation time, catching tests are meant to fail, surfacing bugs before code lands. The primary challenge is to reduce development drag from false positive test failures. Analyzing 22,126 generated tests, we show code-change-aware methods improve candidate catch generation 4x over hardening tests and 20x over coincidentally failing tests. To address false positives, we use rule-based and LLM-based assessors. These assessors reduce human review load by 70%. Inferential statistical analysis showed that human-accepted code changes are assessed to have significantly more false positives, while human-rejected changes have significantly more true positives. We reported 41 candidate catches to engineers; 8 were confirmed to be true positives, 4 of which would have led to serious failures had they remained uncaught. Overall, our results show that Just-in-Time catching is scalable, industrially applicable, and that it prevents serious failures from reaching production.

Rulin Shao, Shuyue Stella Li, Rui Xin et al.

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For example, RLVR improves MATH-500 performance for Qwen2.5-Math-7B in absolute points by 21.4% (random reward), 13.8% (format reward), 24.1% (incorrect label), 26.0% (1-shot RL), and 27.1% (majority voting) -- nearly matching the 29.1% gained with ground truth rewards. However, the spurious rewards that work for Qwen often fail to yield gains with other model families like Llama3 or OLMo2. In particular, we find code reasoning -- thinking in code without actual code execution -- to be a distinctive Qwen2.5-Math behavior that becomes significantly more frequent after RLVR, from 65% to over 90%, even with spurious rewards. Overall, we hypothesize that, given the lack of useful reward signal, RLVR must somehow be surfacing useful reasoning representations learned during pretraining, although the exact mechanism remains a topic for future work. We suggest that future RLVR research should possibly be validated on diverse models rather than a single de facto choice, as we show that it is easy to get significant performance gains on Qwen models even with completely spurious reward signals.

Shuyue Stella Li, Rui Xin, Teng Xiao et al.

Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or scalar reward models) to produce reward signals. Each imposes a ceiling. Human judgment cannot supervise capabilities beyond its own, proprietary APIs create dependencies, and verifiable rewards cover only domains with ground-truth answers. Self-improvement from a model's own evaluative capacity is a reward source that scales with the model itself, yet remains largely untapped by current methods. We introduce EVOLM, a post-training method that structures this capacity into explicit discriminative rubrics and uses them as training signal. EVOLM trains two capabilities within a single language model in alternation: (1) a rubric generator producing instance-specific evaluation criteria optimized for discriminative utility, which maximizes a small frozen judge's ability to distinguish preferred from dispreferred responses; and (2) a policy trained using those rubric-conditioned scores as reward. All preference signals are constructed from the policy's own outputs via temporal contrast with earlier checkpoints, requiring no human annotation or external supervision. EVOLM trains a Qwen3-8B model to generate rubrics that outperform GPT-4.1 on RewardBench-2 by 25.7%. The co-trained policy achieves 69.3% average on the OLMo3-Adapt suite, outperforming policies trained with GPT-4.1 prompted rubrics by 3.9% and with the state-of-the-art 8B reward model SkyWork-RM by 16%. Overall, EVOLM demonstrates that structuring a model's evaluative capacity into co-evolving discriminative rubrics enables self-improvement without external supervision.

Rui Xin, Niloofar Mireshghallah, Shuyue Stella Li et al.

Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only assessed by measuring the leakage of explicit identifiers but ignoring nuanced textual markers that can lead to re-identification. We challenge the above illusion of privacy by proposing a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release. Our approach shows that seemingly innocuous auxiliary information -- such as routine social activities -- can be used to infer sensitive attributes like age or substance use history from sanitized data. For instance, we demonstrate that Azure's commercial PII removal tool fails to protect 74\% of information in the MedQA dataset. Although differential privacy mitigates these risks to some extent, it significantly reduces the utility of the sanitized text for downstream tasks. Our findings indicate that current sanitization techniques offer a \textit{false sense of privacy}, highlighting the need for more robust methods that protect against semantic-level information leakage.

Rui Zhang, Rui Xin, Margo Seltzer et al.

Interpretability is crucial for doctors, hospitals, pharmaceutical companies and biotechnology corporations to analyze and make decisions for high stakes problems that involve human health. Tree-based methods have been widely adopted for survival analysis due to their appealing interpretablility and their ability to capture complex relationships. However, most existing methods to produce survival trees rely on heuristic (or greedy) algorithms, which risk producing sub-optimal models. We present a dynamic-programming-with-bounds approach that finds provably-optimal sparse survival tree models, frequently in only a few seconds.

Jian Yang, Jiahui Wu, Li Fang et al.

Transforming road network data into vector representations using deep learning has proven effective for road network analysis. However, urban road networks' heterogeneous and hierarchical nature poses challenges for accurate representation learning. Graph neural networks, which aggregate features from neighboring nodes, often struggle due to their homogeneity assumption and focus on a single structural scale. To address these issues, this paper presents MSRFormer, a novel road network representation learning framework that integrates multi-scale spatial interactions by addressing their flow heterogeneity and long-distance dependencies. It uses spatial flow convolution to extract small-scale features from large trajectory datasets, and identifies scale-dependent spatial interaction regions to capture the spatial structure of road networks and flow heterogeneity. By employing a graph transformer, MSRFormer effectively captures complex spatial dependencies across multiple scales. The spatial interaction features are fused using residual connections, which are fed to a contrastive learning algorithm to derive the final road network representation. Validation on two real-world datasets demonstrates that MSRFormer outperforms baseline methods in two road network analysis tasks. The performance gains of MSRFormer suggest the traffic-related task benefits more from incorporating trajectory data, also resulting in greater improvements in complex road network structures with up to 16% improvements compared to the most competitive baseline method. This research provides a practical framework for developing task-agnostic road network representation models and highlights distinct association patterns of the interplay between scale effects and flow heterogeneity of spatial interactions.

Benjamin Newman, Abhilasha Ravichander, Jaehun Jung et al. · cmu, uw

Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination, but concerns remain; obtaining factual gold data can be expensive and training on correct but unfamiliar data may potentially lead to even more downstream hallucination. What data should practitioners finetune on to mitigate hallucinations in language models? In this work, we study the relationship between the factuality of finetuning data and the prevalence of hallucinations in long-form generation tasks. Counterintuitively, we find that finetuning on factual gold data is not as helpful as finetuning on model-generated data that models believe to be factual. Next, we evaluate filtering strategies applied on both factual gold data and model-generated data, and find that finetuning on model-generated data that is filtered by models' own internal judgments often leads to better overall factuality compared to other configurations: training on gold data filtered by models' judgments, training on gold data alone, or training on model-generated data that is supported by gold data. These factuality improvements transfer across three domains we study, suggesting that a models' own beliefs can provide a powerful signal for factuality.

Jeffrey Li, Alex Fang, Georgios Smyrnis et al.

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations. Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing at model scales ranging from 412M to 7B parameters. As a baseline for DCLM, we conduct extensive experiments and find that model-based filtering is key to assembling a high-quality training set. The resulting dataset, DCLM-Baseline enables training a 7B parameter language model from scratch to 64% 5-shot accuracy on MMLU with 2.6T training tokens. Compared to MAP-Neo, the previous state-of-the-art in open-data language models, DCLM-Baseline represents a 6.6 percentage point improvement on MMLU while being trained with 40% less compute. Our baseline model is also comparable to Mistral-7B-v0.3 and Llama 3 8B on MMLU (63% & 66%), and performs similarly on an average of 53 natural language understanding tasks while being trained with 6.6x less compute than Llama 3 8B. Our results highlight the importance of dataset design for training language models and offer a starting point for further research on data curation.

Alex Oesterling, Angikar Ghosal, Haoyang Yu et al.

We present our entry into the 2021 3C Shared Task Citation Context Classification based on Purpose competition. The goal of the competition is to classify a citation in a scientific article based on its purpose. This task is important because it could potentially lead to more comprehensive ways of summarizing the purpose and uses of scientific articles, but it is also difficult, mainly due to the limited amount of available training data in which the purposes of each citation have been hand-labeled, along with the subjectivity of these labels. Our entry in the competition is a multi-task model that combines multiple modules designed to handle the problem from different perspectives, including hand-generated linguistic features, TF-IDF features, and an LSTM-with-attention model. We also provide an ablation study and feature analysis whose insights could lead to future work.

Rui Xin, Edirisuriya M. D. Siriwardane, Yuqi Song et al.

Active learning has been increasingly applied to screening functional materials from existing materials databases with desired properties. However, the number of known materials deposited in the popular materials databases such as ICSD and Materials Project is extremely limited and consists of just a tiny portion of the vast chemical design space. Herein we present an active generative inverse design method that combines active learning with a deep variational autoencoder neural network and a generative adversarial deep neural network model to discover new materials with a target property in the whole chemical design space. The application of this method has allowed us to discover new thermodynamically stable materials with high band gap (SrYF$_5$) and semiconductors with specified band gap ranges (SrClF$_3$, CaClF$_5$, YCl$_3$, SrC$_2$F$_3$, AlSCl, As$_2$O$_3$), all of which are verified by the first principle DFT calculations. Our experiments show that while active learning itself may sample chemically infeasible candidates, these samples help to train effective screening models for filtering out materials with desired properties from the hypothetical materials created by the generative model. The experiments show the effectiveness of our active generative inverse design approach.

Leonardo Mariani, Cristina Monni, Mauro Pezzé et al.

By leveraging large clusters of commodity hardware, the Cloud offers great opportunities to optimize the operative costs of software systems, but impacts significantly on the reliability of software applications. The lack of control of applications over Cloud execution environments largely limits the applicability of state-of-the-art approaches that address reliability issues by relying on heavyweight training with injected faults. In this paper, we propose \emph(LOUD}, a lightweight fault localization approach that relies on positive training only, and can thus operate within the constraints of Cloud systems. \emph{LOUD} relies on machine learning and graph theory. It trains machine learning models with correct executions only, and compensates the inaccuracy that derives from training with positive samples, by elaborating the outcome of machine learning techniques with graph theory algorithms. The experimental results reported in this paper confirm that \emph{LOUD} can localize faults with high precision, by relying only on a lightweight positive training.