Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history and numerous applications notwithstanding, inference of phylogenetic trees from sequence data remains challenging: the high complexity of tree space poses a significant obstacle for the current combinatorial and probabilistic techniques. In this paper, we adopt the framework of generative flow networks (GFlowNets) to tackle two core problems in phylogenetics: parsimony-based and Bayesian phylogenetic inference. Because GFlowNets are well-suited for sampling complex combinatorial structures, they are a natural choice for exploring and sampling from the multimodal posterior distribution over tree topologies and evolutionary distances. We demonstrate that our amortized posterior sampler, PhyloGFN, produces diverse and high-quality evolutionary hypotheses on real benchmark datasets. PhyloGFN is competitive with prior works in marginal likelihood estimation and achieves a closer fit to the target distribution than state-of-the-art variational inference methods. Our code is available at https://github.com/zmy1116/phylogfn.
Mingyang Zhou, Zichao Yan, Elliot Layne et al.· 0 citations
It is discovered that the energy benefits of quantum computing economies are contingent on large-scale computation, and quantum computing may represent a more sustainable pathway for the computing industry.
Junyu Liu, Hansheng Jiang, Zuo‐Jun Max Shen· 2 citations
A new point process model for discrete-event data over networks is presented, built upon Hawkes' classic influence-kernel formulation to capture the effects of historical events on the occurrence of future events.
Zheng Dong, Matthew P. Repasky, Xiuyuan Cheng et al.· 5 citations
Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Estimating both from target rollouts across four domains, four open-weight targets, and a frontier API target yields three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash rejection and $85$--$92\%$ of DSpark's oracle-conditioned rejection. These findings separate the value of short-range conditioning from proposal quality.
Xinwei Qiang, Xiang Fang, Changli Chen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The hybrid classical-quantum architecture QuantumBoostNet is proposed, which combines a classical backbone with two heads: one classical and one quantum, a parametrized 10-qubit quantum circuit, which outperforms the implemented baselines under matched training conditions.
Mihai Udrescu-Milosav, S. Jura, M. Udrescu et al.· 0 citations
A new algorithm DMFL-SQ is proposed, a decentralized multi-task learning algorithm that couples personalized model training over a communication graph with an agnostic mixture fairness objective, while reducing communication through sparsification, quantization, and event-triggered synchronization.
Krishnendu S. Tharakan, Carlo Fischione· 0 citations
CON decomposition is introduced, which quantifies how much of a layer's variance each concept explains given all other concepts and the outcome, and how much none of them explains, yielding layer-comparable, calibrated scores that suppress false positives.
R. Rane, Marco Simnacher, Manuel Pfeuffer et al.· 0 citations
This paper argues that the current main approaches in multi-objective RL (SER and ESR), and successor features, are insufficient, and motivates that this can indeed be the case by an example, leading to a new perspective, and a significant and non-trivial gap in the literature.
L. P. J. Mertens, L. N. Alegre, Florent Delgrange et al.· 0 citations
WDANet, a frequency-aware forecasting framework that integrates stationary wavelet decomposition, a Feature-wise Linear Modulation strategy, and a dual-branch encoder-decoder architecture, enabling separate modeling of trend and fluctuation components is proposed, highlighting its potential for offshore wind power operation, disaster warning, and risk mitigation.
Xue-Fei Wang, Tingting Liu, Heng Zhang et al.· 0 citations
We consider the problem of learning a mixture of $k$ Plackett-Luce models given multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has many applications in AI alignment and preference optimization. Prior work has studied mixtures of Bradley-Terry models from pairwise comparisons. However, uncovering mixture models is theoretically unidentifiable when $k$ exceeds $m/2$, where $m$ is the length of a ranking. We propose an efficient implementation to address this limitation, which involves first augmenting the rankings to a larger size by generating new responses from a base language model, followed by a gradient-based estimation to reduce inference cost in the input embedding space. Based on this procedure, we then design an expectation-maximization algorithm with these two steps to fit a mixture of Plackett-Luce models, called MoPLEx. Extensive experiments are conducted to verify this approach. First, we show that the gradient-based approximation estimates true probabilities with less than 5% error on models with up to 34 billion parameters. Second, we show that MoPLEx improves clustering and ranking accuracy by an average of 43.7% and 15.2% over baselines using single ranking and mixtures of Bradley-Terry models, on preference optimization datasets. These results demonstrate the effectiveness of MoPLEx for tackling multi-way rankings from heterogeneous preferences through measuring alignment between gradients.
Dongyue Li, Ziniu Zhang, Lu Wang et al.· 0 citations
DeMMO is proposed, an interpretable framework for longitudinal, multi-disease, and multi-outcome learning that infers signed relations directly from learned longitudinal DMO-outcome mappings, thereby enabling selective information sharing across cohorts without requiring paired participants.
Menghui Zhou, Zhipeng Yuan, V. Lanfranchi et al.· 0 citations
A novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs and a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strategy based on the Fisher information sensitivity metric.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
