Publications

Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang
Catherine Arnett
Abdelrahman Sadallah
Ana Chkhaidze
Cristina España-Bonet
Cynthia Amol
Ivan Spada
Julia Alekseenko
Leshem Choshen
Maximos Skandalis
David Stap
Duygu Ataman
Hila Gonen
Jiayi Wang
HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields
Yumin Zheng
Qingtian Zhu
Ziyan Zhu
Kailu Song
Yinqiang Zheng
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
Bowei He
Yankai Chen
Xiaokun Zhang
Changjiang Han
Chong Li
Xue Liu
Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs
Kiarash Shamsi
Tran Gia Bao Ngo
Baris Coskunuzer
Michael M. Bronstein
Cuneyt Gurcan Akcora
Real-world evolving networks are naturally modeled as temporal graphs (TGs), where capturing temporal dynamics is essential for predicting f… (see more)uture graph properties that support downstream decision-making. Existing temporal graph methods have been developed primarily for single-task prediction, and little is known about their generalization across tasks or transfer to unseen networks. This leaves the challenge of multi-task graph property prediction in TGs largely open. We address this challenge by introducing Hydra, a novel architecture that integrates local connectivity features from temporal GNNs with a spectral learning module that captures global connectivity patterns. This design enables joint learning of local and global information under a multi-task objective. In multi-task classification, Hydra achieves an 8.9% relative gain in AUC over the strongest competitor. In multi-task regression, Hydra achieves competitive results in all three tasks, while obtaining the best results in two tasks with a 8.2% relative gain in MAE compared to the strongest baseline. Moreover, Hydra delivers these gains with a 22× reduction in training time compared to temporal transfer models. These results provide the first systematic evidence that multi-task transferable learning on temporal graphs is effective. By delivering consistent top-ranked performance, Hydra highlights multi-task training on temporal graphs as a promising direction toward adaptable foundation models for temporal graphs.
Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual Flow
Inverting the Bellman Equation: From $Q$-Values to World Models
Alistair Letcher
Mattie Fellows
Alexander D. Goldie
Jonathan Richens
Jakob N. Foerster
Oliver Richardson
A latent control model for realistic rodent motion
Charles Y. Zhang
Yuanjia Yang
Bence P. Ölveczky
Talmo D. Pereira
Blake A. Richards
Modeling the Vividness of Imagined Natural Scenes Reveals a Model-Common Image-Level Component in Vision Models
Catherine Landry
Jasper JF van den Bosch
Frédéric Gosselin
Path-independent Flow Matching for Multi-parameter Generative Dynamics
Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formu… (see more)lation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce Path-independent Flow Matching (PiFM), a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples.
Pixels over Symbols: Sensory Realism Improves Behavioral Alignment in Models of Cognition
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
Yashi Zhang
Hongyu Guo
Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expre… (see more)ssion responses for unobserved conditions. A promising recent direction leverages large language models (LLMs) as"virtual cell"simulators-using stepwise, knowledge-grounded mechanistic reasoning to infer differential expression-pointing toward an interpretable, knowledge-driven paradigm that transcends purely data-driven approaches. However, we find that plausibility is not prediction: despite producing biologically plausible explanations, these methods fail to capture perturbation-specific effects: systematically overestimating differential expression, often underperforming a simple gene-frequency baseline in aggregate evaluations, and collapsing to chance-level performance at the per-gene level. This reveals a reliance on intrinsic gene response tendencies rather than true perturbation reasoning. We trace this failure to how evidence is presented: existing methods evaluate perturbation-gene pairs in isolation, without exposing how related perturbations differ in their effects on the same gene. To address this limitation, we introduce CORE (Contrastive Organization of Relational Evidence), which reframes prediction as a comparison task by organizing evidence into positive and negative outcomes from related perturbations. Using a biomedical knowledge graph for evidence retrieval, CORE improves calibration and substantially boosts perturbation-specific prediction in both LLM-based and non-LLM settings: for example, on drug-perturbation data, CORE-Reasoning improves Qwen3.5-9B aggregate metrics by up to 28.6%, while on generic perturbation data, CORE-Voting raises macro-per-gene AUROC from chance to 0.703 in average across four cell lines. This highlights contrastive evidence organization as essential to reliable LLM-based perturbation reasoning
Probabilistic Recursive Reasoning