Searcharxiv⌕ Search

arXiv subjects

Michael Bronstein

Publications and source records attributed to Michael Bronstein.

At least 19 recordsLinked to original sources
arXiv2026

Riemannian Metric Matching for Scalable Geometric Modeling of Distributions

High-dimensional datasets often concentrate near low-dimensional structures, but estimating their geometry from samples typically relies on graphs and kernels that scale poorly with dataset size and dimension. We propose Riemannian metric matching: a denoising probabilistic framework for learning the Riemannian geometry of data using neural networks. Specifically, we learn the carr\'e du champ operator, which, using diffusion geometry, gives us access to the Riemannian geometry toolkit for downstream machine learning and statistical tasks. Our key observation is that the carr\'e du champ operator can be formulated as a conditional expectation over random perturbations of the data, which can be exploited for sample-wise training and constant cost, amortized inference without explicit kernel construction. Empirically, metric matching rivals or improves the accuracy of $k$-NN-based diffusion geometry estimators, while enabling amortized inference that is up to $400\times$ faster, and supports graph-free geometric analysis on high-dimensional images where nearest neighbors break down.

cs.LG↗
arXiv2026

Graph Neural Networks Are Not Continuous Across Graph Resolutions

We show that contrary to conventional wisdom in the community, graph neural networks (GNNs) are not continuous with respect to all natural modes of graph convergence. As a result, GNNs may generate substantially different latent representations for graphs that are very similar. In particular they assign vastly different latent embeddings to graphs that represent the same underlying object at different resolution scales. We trace this failure of continuity back to a structural obstruction arising from commonly used information-propagation schemes. Building on this insight we then derive a principled modification to standard GNN architectures which equips models with continuity across scales. The proposed modification enables consistent integration of distinct resolutions and reliable generalization between them. We systematically validate our theoretical findings in a wide range of numerical experiments.

cs.LG↗
arXiv2026

MUX: Continuous Reasoning via Multiplexed Tokens

Language models solve complex problems by articulating intermediate reasoning steps in natural language. While effective, this process is computationally bottlenecked: each reasoning step conveys only a single subword, and many are spent expressing a thought instead of carrying out computation. We propose MUX, a simple method for high-bandwidth and compact reasoning based on distillation of discrete reasoning into continuous multiplexed tokens in a latent space. Here, each latent token is trained to represent a weighted linear superposition (multiplexing) of a span of discrete reasoning subwords, where this superposition is lossless by construction and the span can be fully recovered (demultiplexing). We prove that simple position-dependent weightings, such as suitable geometric decay, support lossless multiplexing, which in turn prevents shortcut behaviors caused by latent collapse. We further show that multiplexed reasoning can perform parallel exploration in problems that require search. Across 32 evaluation settings spanning four language models, MUX outperforms strong latent reasoning baselines. Ablation and probing analyses further show that the learned latent tokens encode faithful and interpretable reasoning. Our results suggest that lossless superposition as local learning targets constitutes a sufficient condition for achieving strong and efficient latent continuous reasoning.

cs.AI↗
arXiv2026

Training Transformers for KV Cache Compressibility

Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottleneck has motivated a range of context-compression methods, from token-level summarization to recent optimization-based KV compression methods. These post-hoc methods operate on the KV cache of a fixed pretrained model, so their effectiveness is fundamentally limited by how well the model's internal representations can be compressed. In this work, we formalize the notion of KV compressibility and show that it is a property of the learned representations, rather than of the context alone. We prove that almost any sequence-to-vector function admits both highly compressible and inherently non-compressible transformer implementations, highlighting the need to guide transformers toward compressible representations during training. Motivated by this, we propose KV-Compression Aware Training (KV-CAT), a continued pretraining procedure that incentivizes the emergence of compressible representations. We introduce a train-time KV sparsification policy that masks KV slots during training. This forces the model to use fewer KV slots and encourages it to learn representations amenable to post-hoc compression. Empirically, we show that KV-CAT improves the quality-budget tradeoff of downstream compression methods across retrieval, long-context question answering, and perplexity-based evaluation of compressed-prefix continuation.

cs.LG↗
arXiv2026

Can Graph Foundation Models Generalize Over Architecture?

Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse real-world benchmarks, these tasks share a crucial hidden limitation: they admit a narrow set of effective GNN architectures. In particular, current domain-agnostic GFMs rely on fixed architectural backbones, implicitly assuming that a single message-passing regime suffices across tasks. In this paper, we argue that architecture adaptivity is a necessary requirement for true GFMs. We show that existing approaches are non-robust to task-dependent architectural attributes and, as a case study, use range as a minimal and measurable axis along which this limitation becomes explicit. With theoretical analysis and controlled synthetic experiments, we demonstrate that fixed-backbone GFMs provably under-reach on tasks whose architectural requirements differ from those seen at training time. To address this issue, we introduce a framework that adapts effective GNN architecture at inference time by discovering and mixing task-specific linear graph operators, enabling zero-shot generalization across tasks with heterogeneous architectural requirements, without retraining. We validate our approach on arbitrary-range synthetic tasks and a suite of real-world benchmarks, demonstrating improved performance and robustness over existing domain-agnostic GFMs.

cs.LG↗
arXiv2026

MacroGuide: Topological Guidance for Macrocycle Generation

Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public datasets and the challenges of enforcing topological constraints in standard deep generative models. We introduce MacroGuide: Topological Guidance for Macrocycle Generation, a diffusion guidance mechanism that uses Persistent Homology to steer the sampling of pretrained molecular generative models toward the generation of macrocycles, in both unconditional and conditional (protein pocket) settings. At each denoising step, MacroGuide constructs a Vietoris-Rips complex from atomic positions and promotes ring formation by optimizing persistent homology features. Empirically, applying MacroGuide to pretrained diffusion models increases macrocycle generation rates from 1% to 99%, while matching or exceeding state-of-the-art performance on key quality metrics such as chemical validity, diversity, and PoseBusters checks.

cs.LG↗
arXiv2026

Categorical Flow Maps

We introduce Categorical Flow Maps, a flow-matching method for accelerated few-step generation of categorical data via self-distillation. Building on recent variational formulations of flow matching and the broader trend towards accelerated inference in diffusion and flow-based models, we define a flow map towards the simplex that transports probability mass toward a predicted endpoint, yielding a parametrisation that naturally constrains model predictions. Since our trajectories are continuous rather than discrete, Categorical Flow Maps can be trained with existing distillation techniques, as well as a new objective based on endpoint consistency. This continuous formulation also automatically unlocks test-time inference: we can directly reuse existing guidance and reweighting techniques in the categorical setting to steer sampling toward downstream objectives. Empirically, we achieve state-of-the-art few-step results on images, molecular graphs, and text, with strong performance even in single-step generation.

cs.LG↗
arXiv2025

OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction

Accurately predicting experimentally realizable 3D molecular crystal structures from their 2D chemical graphs is a long-standing open challenge in computational chemistry called crystal structure prediction (CSP). Efficiently solving this problem has implications ranging from pharmaceuticals to organic semiconductors, as crystal packing directly governs the physical and chemical properties of organic solids. In this paper, we introduce OXtal, a large-scale 100M parameter all-atom diffusion model that directly learns the conditional joint distribution over intramolecular conformations and periodic packing. To efficiently scale OXtal, we abandon explicit equivariant architectures imposing inductive bias arising from crystal symmetries in favor of data augmentation strategies. We further propose a novel crystallization-inspired lattice-free training scheme, Stoichiometric Stochastic Shell Sampling ($S^4$), that efficiently captures long-range interactions while sidestepping explicit lattice parametrization -- thus enabling more scalable architectural choices at all-atom resolution. By leveraging a large dataset of 600K experimentally validated crystal structures (including rigid and flexible molecules, co-crystals, and solvates), OXtal achieves orders-of-magnitude improvements over prior ab initio machine learning CSP methods, while remaining orders of magnitude cheaper than traditional quantum-chemical approaches. Specifically, OXtal recovers experimental structures with conformer $\text{RMSD}_1<0.5$ {\AA} and attains over 80\% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization.

cs.LG↗
arXiv2025

GraphBench: Next-generation graph learning benchmarking

Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, hindering reproducibility and broader progress. With the recent popularity of graph foundation models, these weaknesses have become apparent, as existing benchmarks are insufficient for thorough evaluation. To address these challenges, we introduce GraphBench, a comprehensive benchmark suite spanning diverse real-world domains and task settings, including node-level, edge-level, graph-level, and generative tasks. GraphBench provides standardized evaluation protocols, including consistent dataset splits and metrics for assessing out-of-distribution generalization across selected tasks, as well as a unified hyperparameter-tuning framework. We further evaluate GraphBench with recent message-passing neural networks and graph transformer models, establishing principled baselines for future research. See www.graphbench.io for further details.

cs.LG↗
arXiv2025

Curly Flow Matching for Learning Non-gradient Field Dynamics

Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about the underlying process in order to enable faithful learning of governing dynamics that mimic the actual system behavior. The de facto assumption in current approaches relies on the principle of least action that results in gradient field dynamics and leads to trajectories minimizing an energy functional between two probability measures. However, many real-world systems, such as cell cycles in single-cell RNA, are known to exhibit non-gradient, periodic behavior, which fundamentally cannot be captured by current state-of-the-art methods such as flow and bridge matching. In this paper, we introduce Curly Flow Matching (Curly-FM), a novel approach that is capable of learning non-gradient field dynamics by designing and solving a Schr\"odinger bridge problem with a non-zero drift reference process -- in stark contrast to typical zero-drift reference processes -- which is constructed using inferred velocities in addition to population snapshot data. We showcase Curly-FM by solving the trajectory inference problems for single cells, computational fluid dynamics, and ocean currents with approximate velocities. We demonstrate that Curly-FM can learn trajectories that better match both the reference process and population marginals. Curly-FM expands flow matching models beyond the modeling of populations and towards the modeling of known periodic behavior in physical systems. Our code repository is accessible at: https://github.com/kpetrovicc/curly-flow-matching.git

cs.LG↗
arXiv2025

LLMs can hide text in other text of the same length

A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something.

cs.AI↗
arXiv2025

Gradient Variance Reveals Failure Modes in Flow-Based Generative Models

Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective conceals fundamental failure modes: under deterministic training, low gradient variance drives memorization of arbitrary training pairings, even when interpolant lines between pairs intersect. To analyze this mechanism, we study Gaussian-to-Gaussian transport and use the loss gradient variance across stochastic and deterministic regimes to characterize which vector fields optimization favors in each setting. We then show that, in a setting where all interpolating lines intersect, applying Rectified Flow yields the same specific pairings at inference as during training. More generally, we prove that a memorizing vector field exists even when training interpolants intersect, and that optimizing the straight-path objective converges to this ill-defined field. At inference, deterministic integration reproduces the exact training pairings. We validate our findings empirically on the CelebA dataset, confirming that deterministic interpolants induce memorization, while the injection of small noise restores generalization.

cs.LG↗
arXiv2025

TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs

Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm

cs.LG↗
arXiv2025

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin

Attention sinks and compression valleys have attracted significant attention as two puzzling phenomena in large language models, but have been studied in isolation. In this work, we present a surprising connection between attention sinks and compression valleys, tracing both to the formation of massive activations in the residual stream. We prove theoretically that massive activations necessarily produce representational compression and establish bounds on the resulting entropy reduction. Through experiments across several models (410M-120B parameters), we confirm that when the beginning-of-sequence token develops extreme activation norms in the middle layers, both compression valleys and attention sinks emerge simultaneously. Targeted ablation studies validate our theoretical predictions. This unified view motivates us to propose the Mix-Compress-Refine theory of information flow, as an attempt to explain how LLMs organize their computation in depth by controlling attention and representational compression via massive activations. Specifically, we posit that Transformer-based LLMs process tokens in three distinct phases: (1) broad mixing in the early layers, (2) compressed computation with limited mixing in the middle layers, and (3) selective refinement in the late layers. Our framework helps explain why embedding tasks perform best at intermediate layers, whereas generation tasks benefit from full-depth processing, clarifying differences in task-dependent representations.

cs.LG↗
arXiv2025

Flock: A Knowledge Graph Foundation Model via Learning on Random Walks

We study the problem of zero-shot link prediction on knowledge graphs (KGs), which requires models to generalize to novel entities and novel relations. Knowledge graph foundation models (KGFMs) address this task by enforcing equivariance over both nodes and relations, which enables them to learn structural properties of nodes and relations that transfer to novel KGs with similar structure. However, the conventional notion of deterministic equivariance inherently limits the expressive power of KGFMs, as it prevents them from distinguishing relations that are structurally similar but semantically distinct. To overcome this limitation, we propose to leverage probabilistic node-relation equivariance, which preserves equivariance in distribution while using structured randomness to break symmetries at inference time. Building on this principle, we present Flock, a KGFM that iteratively samples random walks, encodes them into sequences, embeds them with a sequence model, and aggregates node and relation representations through learned pooling. Flock respects probabilistic node-relation equivariance and, crucially, is a universal approximator for isomorphism-invariant link-level functions over KGs. Empirically, Flock perfectly solves our new diagnostic dataset Petals on which current KGFMs fail, and achieves state-of-the-art performance on entity and relation prediction tasks across 54 KGs from diverse domains. Code is available at https://github.com/jw9730/flock.

cs.LG↗
arXiv2025

MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models

Molecular Dynamics (MD) is a powerful computational microscope for probing protein functions. However, the need for fine-grained integration and the long timescales of biomolecular events make MD computationally expensive. To address this, several generative models have been proposed to generate surrogate trajectories at lower cost. Yet, these models typically learn a fixed-lag transition density, causing the training signal to be dominated by frequent but uninformative transitions. We introduce a new class of generative models, MSM Emulators, which instead learn to sample transitions across discrete states defined by an underlying Markov State Model (MSM). We instantiate this class with Markov Space Flow Matching (MarS-FM), whose sampling offers more than two orders of magnitude speedup compared to implicit- or explicit-solvent MD simulations. We benchmark Mars-FM ability to reproduce MD statistics through structural observables such as RMSD, radius of gyration, and secondary structure content. Our evaluation spans protein domains (up to 500 residues) with significant chemical and structural diversity, including unfolding events, and enforces strict sequence dissimilarity between training and test sets to assess generalization. Across all metrics, MarS-FM outperforms existing methods, often by a substantial margin.

cs.LG↗
arXiv2025

Planner Aware Path Learning in Diffusion Language Models Training

Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through more flexible and parallel generation paths. This flexibility of sampling is unlocked by new engineered sampling strategies, or planners, that select more favorable generation paths by iteratively planning - versus uniformly at random - where to denoise along the sequence. However, by modifying the reverse paths via planning, planners create an irrevocable mismatch between the uniformly random denoising paths assumed during training and planning-based inference. In this paper, we systematically investigate the mismatch of discrete diffusion training and inference under planning and theoretically prove that the standard discrete diffusion training evidence lower bound (ELBO) does not accurately describe a denoiser that uses a non-uniform planner. To address this gap, we derive a new planned evidence lower bound (P-ELBO) that incorporates planner-based reverse dynamics directly into the training objective. Using the P-ELBO, we introduce Planner Aware Path Learning (PAPL), a novel training scheme that aligns training and inference under a planned denoiser. PAPL is implemented as a simple yet effective modification to the standard masked discrete diffusion loss, making it widely applicable and easy to adopt. Empirically, we show PAPL delivers consistent gains across domains, including a 40% relative improvement in protein sequences, improved text generation with up to a 4x relative MAUVE gain, and 23% relative improvement in code generation HumanEval pass@10. Code is available at github.com/pengzhangzhi/PAPL .

cs.LG↗
arXiv2025

Flow-Based Fragment Identification via Binding Site-Specific Latent Representations

Fragment-based drug design is a promising strategy leveraging the binding of small chemical moieties that can efficiently guide drug discovery. The initial step of fragment identification remains challenging, as fragments often bind weakly and non-specifically. We developed a protein-fragment encoder that relies on a contrastive learning approach to map both molecular fragments and protein surfaces in a shared latent space. The encoder captures interaction-relevant features and allows to perform virtual screening as well as generative design with our new method LatentFrag. In LatentFrag, fragment embeddings and positions are generated conditioned on the protein surface while being chemically realistic by construction. Our expressive fragment and protein representations allow location of protein-fragment interaction sites with high sensitivity and we observe state-of-the-art fragment recovery rates when sampling from the learned distribution of latent fragment embeddings. Our generative method outperforms common methods such as virtual screening at a fraction of its computational cost providing a valuable starting point for fragment hit discovery. We further show the practical utility of LatentFrag and extend the workflow to full ligand design tasks. Together, these approaches contribute to advancing fragment identification and provide valuable tools for fragment-based drug discovery.

q-bio.BM↗