Machine Learning
Learning Traffic Flow Dynamics with Stochastic Physics-Informed Neural Cellular Automata
Federica Bragone and Matthieu Barreau
Traffic flow modeling is essential for understanding and predicting the collective dynamics of vehicles on road networks. Cellular automata provide a simple, interpretable yet powerful framework for representing these dynamics via local interaction rules, while retaining the ability to reproduce complex macroscopic traffic phenomena. However, learning local transition rules from data while preserving physically meaningful constraints remains challenging, particularly for
stochastic models. In this work, we propose a physics-informed neural cellular automaton (PI-NCA) for data-driven traffic flow modeling. Building on the standard neural cellular automaton (NCA), we design a neural architecture that is physically consistent with the road
topology and guarantees conservation of the total number of vehicles, thereby constraining the learned transition rules to physically admissible dynamics. We further extend this framework to
stochastic dynamics by parameterizing probabilistic transition rules while preserving the same physics-informed constraints. We evaluate the proposed models on multiple traffic scenarios generated by the well-established Nagel-Schreckenberg and Kerner-Klenov-Wolf cellular automata. The results demonstrate that the PI-NCA successfully learns the dynamics of both traffic models and consistently outperforms a standard NCA, while the
stochastic extension captures probabilistic transition rules without compromising the imposed physical constraints.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
Haoru Li, Jinmei Liu, Zhiyong Wang et al. (+5 more)
Reinforcement learning (RL) fine-tuning improves
vision-
language-action (VLA) policies through closed-loop experience, yet generalization beyond the fine-tuning distribution remains limited. Our analysis reveals a selective reshaping of exploration: RL contracts behavior globally, yet diversifies successful trajectories, elicits success with fewer rollouts, and covers more of the latent task-valid solution space than supervised fine-tuning. Broader successful-mode coverage may provide alternative strategies under distribution shifts. Inspired by this, we introduce DRIVE (Diversity-driven RL fIne-tuning for VLA gEneralization), which turns successful-behavior diversity into an explicit RL objective. DRIVE groups rollouts under matched task conditions, compares their trajectories with temporal
alignment, and derives a success-conditioned intrinsic reward from relative behavioral diversity. This design encourages broader coverage of feasible solutions without rewarding diverse failures or superficial timing differences. Across LIBERO-Plus, ManiSkill3, and RoboTwin 2.0, DRIVE improves the average out-of-domain (OOD) performance over vanilla RL fine-tuning by 5.3 points on $\pi_0$ and 2.0 points on $\pi_{0.5}$. On a dual-arm AgileX PiPER-X platform, DRIVE further increases average OOD success from 64.1% to 73.3% (+9.2 points), demonstrating gains that persist under physical deployment.
Read the full abstract ▾
All authors Haoru Li, Jinmei Liu, Zhiyong Wang, Xiaoming Li, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang
Machine Learning
Expected Sample Complexity in Multi-Armed Bandits
Nadav Sukenik and Nadav Merlis
Sample complexity is a widely used metric in sequential decision-making problems, defined as the number of suboptimal decisions during the interaction between the
agent and an environment. We study the sample complexity of
stochastic multi-armed bandit problems and introduce the expected sample complexity performance measure, analyzing it in a novel framework called approximately correct in expectation (ACE). We show that ACE guarantees imply almost sure convergence to the optimal expected reward, in contrast to high-probability guarantees found in other frameworks, and also show how to convert ACE guarantees into explicit expected regret bounds. We further show that, in contrast to existing measures, deterministic
algorithms cannot obtain favorable ACE bounds, and analyze
stochastic algorithms in two settings: when the allowed suboptimality level $\epsilon$ is known to the
algorithm and when it is unknown. In the former, we devise an explore-then-$\epsilon$-greedy
algorithm, and in the latter, we analyze the expected sample complexity of Thompson sampling. Finally, we establish nearly matching lower bounds for both settings, showing that the
algorithms are tight in $\epsilon$ and proving a performance separation between the two regimes.
Read the full abstract ▾
Machine Learning
KGATE : a Knowledge Graph Embedding Training Environment
Benjamin Loire, Galadriel Brière, Célia Brahimi et al. (+2 more)
Knowledge graph
embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such as classification or link prediction. Most KGE models follow an autoencoder architecture, in which an encoder projects the knowledge graph into the latent space and a decoder reconstruct it. Combining both encoder and decoder components is increasingly needed, yet existing libraries rarely support complete autoencoders, are often unmaintained, rely on undocumented default hyperparameters, and produce results that cannot be compared across libraries. Here we present KGATE (Knowledge Graph Autoencoder Training Environment), a modular Python library built on PyTorch
Geometric and TorchKGE. KGATE lets users assemble initializers, encoders, decoders, losses, negative samplers, and evaluation metrics as building blocks, or plug in their own block. KGATE includes a preprocessing procedure that controls data leakage, a builtin training pipeline, and reproducibility by design.
Benchmarks against six existing KGE libraries show that KGATE training time is comparable with the fastest libraries while offering a broader set of features.
Read the full abstract ▾
All authors Benjamin Loire, Galadriel Brière, Célia Brahimi, Antoine Toffano, Anaïs Baudot
Machine Learning
Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking
Yossi Arjevani
Hessian spectra at trained models in deep learning exhibit a persistent pattern:
eigenvalues organize into distinct clusters, including a large bulk near zero and a few isolated outliers. This paper shows that a natural account of these spectral phenomena emerges when the original setting is understood as a departure from a nearby, otherwise hidden, highly symmetric reference. Modifications, including changes to the architecture, data distribution, or parameter metric, expose a nearby reference configuration whose Hessian exhibits rich invariances-ones not accounted for by weight
symmetries. There,
symmetry enables a precise description of the spectra, forcing high-dimensional kernels and
eigenvalues of large multiplicity. Returning to the original configuration breaks the Hessian
symmetry and thereby produces the observed hierarchy of clusters and outliers. The framework is developed in some generality, with a detailed analysis of three-layer ReLU networks and applications to convolutional, graph, and
transformer models, as well as to the NTK. The same mechanism is further shown to yield analogous spectral structures in layerwise Hessians and the Gauss-Newton
matrix.
Read the full abstract ▾
Machine Learning
NeuralZip: Reusable Setup for Fast Lossless Compression
Martín Bravo, Samuel Horváth, Gonzalo Navarro et al. (+1 more)
Lossless compression can reduce the storage and movement of model weights without changing their floating-point values, but repeated statistical analysis and code construction add computational overhead. We study whether the statistical structure of exponents can be prepared once and reused. For this, we introduce NeuralZip, which groups chunks with similar exponent distributions, shares Huffman codes, and selectively represents recurring exponent tuples using packed exponents, thereby achieving additional moderate compression ratios. A setup chooses these representations before subsequent encodings, while every encoding still processes the current tensor values. In floating-point model checkpoints, post-setup compression is 1.81-21.33$\times$ faster than the baselines and achieves exact bit-to-bit reconstruction. We show that this setup can be precomputed and transferred from another compatible architecture, preserving similar compression ratios and avoiding the need to amortize setup costs. Therefore, compression adaptation is transferable and reusable. Training checkpoints demonstrate continued reuse as the weights evolve. Finally, GPU experiments reduce active
memory usage by up to 27.5$\%$ while reproducing the logits exactly.
Read the full abstract ▾
All authors Martín Bravo, Samuel Horváth, Gonzalo Navarro, Andrés Abeliuk
Machine Learning
RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning
Yongqiang Yao, Jinru Tan, Kaihuan Liang et al. (+5 more)
Reinforcement learning is crucial for improving large
language models'
reasoning and generalization. It relies on massive rollouts whose lengths become increasingly long-tailed as context windows grow. In on-policy training, these long-tail rollouts can result in GPU bubbles, reducing system utilization and limiting RL scalability. Asynchronous or partial-rollout methods improve throughput by relaxing synchronization, but inevitably introduce stale off-policy samples (trajectories) that may hurt final accuracy. Existing approaches mainly mitigate this off-policy issue by reweighting off-policy samples during training, yet they can still leave a performance gap compared to fully on-policy training. In this work, rather than passively reweighting samples during training, we propose RollVerify, a lightweight RL framework built on partial rollout that actively verifies and repairs samples before they enter training. Specifically, it introduces an off-policy shift metric OPS, to quantify the off-policy deviation of partially generated trajectories. Guided by the OPS constraint, RollVerify performs both sequence-level and
token-level verification to identify and truncate invalid suffixes of trajectories. This yields high-quality samples that protect the models' accuracy while preserving the efficiency gains of partial rollout. Experiments on mathematical and tool-assisted mathematical
reasoning show that RollVerify achieves accuracy comparable to on-policy training while reducing training cost. Additional code-generation results provide preliminary evidence beyond mathematics.
Read the full abstract ▾
All authors Yongqiang Yao, Jinru Tan, Kaihuan Liang, Zixin Yin, Yazhe Niu, Ruihao Gong, Dahua Lin, Ningyi Xu
Machine Learning · Cross-listed from stat.AP
Learning joint probabilistic weather forecasts from station observations alone
Chaeyeon Yi and Yun Am Seo
Assessing compound weather risks requires forecasts representing dependence between variables. CLARA (Calibrated Advection-Routing
Attention) learns joint Gaussian predictive distributions of five surface variables from station observations alone, without numerical weather prediction or reanalysis; the approximately 28,000-parameter model supports CPU training and prediction. Across six multi-year folds on 96 stations, its lead-mean energy score is 4.9% lower than that of a learned comparator with matched temporal inputs (4.7% with a similar parameter count) and 11-65% lower than those of statistical baselines. Holding marginal variances fixed, removing learned correlations worsens joint negative log-likelihood by 1.0-2.8 nats per station. A covariance-scale
estimator, proved consistent under stated assumptions, improves short-lead calibration but over-corrects at long leads. Synthetic interventions show an
attention-bias coefficient alone does not measure forecast influence. Retrained in ten regions on six continents, CLARA outperforms persistence in all 60 multi-year region-lead comparisons and a similarly sized learned model in 57 of 60.
Read the full abstract ▾
Machine Learning
Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data
Arman Kostanian and Armen Beklaryan
Human learning is a dissipative dynamical process: mastery accumulates through practice, decays through forgetting, and propagates across interdependent concepts. We model it as a nonlinear dissipative system of ordinary differential equations whose parameters are mechanistically meaningful (a transfer-of-practice
matrix, per-concept forgetting rates, and a saturating practice-response gain), and we study when those parameters can actually be recovered from data. For two concepts, we prove a constructive structural identifiability
theorem for the associated inverse problem under explicit excitation conditions, together with monotonicity, robustness and L-stability results. We derive an implicit L-stable scheme and a batched solver numerically equivalent to the per-trajectory formulation yet two orders of magnitude faster. The empirical study is two-sided. Under the
theorem's excitation conditions, synthetic recovery is exact. On large observational
benchmarks it is not. An apparently strong recovery, with forgetting rates correlating with topic error rates at Spearman $\rho = 0.83$, is refuted by four controls: it survives destroying the temporal order of the data, is matched by a classical
Bayesian baseline, and is unaffected by removing real timestamps. A single shared forgetting rate attains the same accuracy, and replaying the real schedule with identical true rates reproduces most of the correlation. A positive control shows that the controls detect forgetting where it is observable. We trace the effect to the stationary structure of the model and show that it is consistent with the degeneration anticipated by the theory in the absence of designed excitation.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Sparsifying Stochasticity, Not Capacity: Partial Stochasticity via Deep Weight Factorization of Prior Scales
Marius P Linhard and Maurizio Filippone
Bayesian neural networks need not be fully
stochastic to be universal conditional density approximators, but it remains open which parameters should be
stochastic. We learn this split by applying deep weight factorization to the prior scales, which are the standard deviations of the parameter priors, while fitting the functional prior to a Gaussian process with a maximum mean discrepancy objective. A parameter whose prior scale falls below a cutoff becomes deterministic and is optimized during inference, so the regularizer sparsifies stochasticity rather than capacity. We give a certificate for universal conditional density approximation that is checkable in linear time, together with a minimal repair when it fails. We further show that the common hybrid scheme of sampling some parameters and optimizing the others is
stochastic approximation for a type-II maximum a posteriori objective, and that coupled step sizes can leave a tracking error that does not vanish as the step size shrinks. On a bimodal target, the learned split stays close to an unconstrained reference across all budgets and is insensitive to the cutoff, while random masks that distribute the same prior scales across layers are worse by up to two orders of magnitude. On UCI
benchmarks, our method performs on par with a fully
stochastic network while keeping about half of its parameters deterministic.
Read the full abstract ▾
Machine Learning
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
Samy Houache, Yann Traonmilin and Jean-François Aujol
Mixed-precision post-training quantization is a network compression method that assigns bits layer by layer, under a global
memory budget using a small calibration set. The main difficulties are to overcome the combinatorial nature of the allocation problem and to manage the sensitivity to small, potentially corrupted databases. Hence, an efficient allocation method should be fast to compute and preserve model quality when calibration data are corrupted. To design such a method, we derive a layerwise probabilistic analysis of the quantization error that separates propagated error from the local perturbation introduced at a given layer. We use this local term to build a separable score for a simple allocation
algorithm, that requires no external solver. The probabilistic nature of our approach brings robustness to corrupted data. On denoising tasks with DRUNet, with an average budget of 4 bits per weight, our method matches or improves state-of-the-art mixed-precision baselines under clean calibration, and is more robust to corrupted calibration, with PSNR gains of up to 7.5 dB under the tested corruptions. Experiments show bit-allocation speed-ups from 28x to 2,570x over the studied baselines. For quantized
diffusion models, our experiments show that a direct application of our framework also improves the state-of-the-art.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk et al. (+2 more)
Diffusion models generate realistic images but often fail on visual
reasoning tasks, such as filling in a Sudoku or drawing the path through a maze. When a discrete symbolic representation is available, recursive methods such as the Tiny Recursive Model (TRM) solve even hard instances of these puzzles. We ask how such
reasoning can be carried over to pixels, where no symbolic representation is available. We propose Painter-Thinker (PaTh): a small recursive network (the Thinker) reasons over a grid of learned
tokens that encode the noisy image and the conditioning, refines a latent state within every denoising step, and steers a frozen
diffusion model (the Painter) through ControlNet adapters. The Thinker is trained with the standard reconstruction loss alone, without symbolic targets, a solver, or a verifier. PaTh solves 92.5% of hard MNIST Sudoku puzzles (prior best 75%) and 71.2% of extreme ones (prior best 4.1%), with 10M parameters against 82M for a standard
diffusion model. It also improves on mazes, Queens, and CLEVR scenes with specified spatial relations, and its advantage grows with problem size. Diagnostic experiments show that PaTh recovers from injected mistakes that the
diffusion model cannot repair, especially when many
cells are wrong. Together, these results show that
reasoning mechanisms developed for symbolic data can be integrated into pixel-space
diffusion without symbolic supervision, opening a path toward generating data under increasingly complex constraints.
Read the full abstract ▾
All authors Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk, Jan-Willem van de Meent, Kamil Deja
Machine Learning · Cross-listed from physics.geo-ph
An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling
Stefan Carpentier, Jan Diederik van Wees, Eva de Boever et al. (+5 more)
Implicit modeling and Relative Geologic Time are geological modeling techniques that enable more efficient, faster, less biased and more reproducible modeling results. For optimal operation, these techniques require many well-constrained input data. In the framework of the Horizon Europe GO-Forward and MOOI WarmingUP GOO projects and to accelerate Implicit modeling, Machine Learning (ML) methods have been tested and implemented in a toolkit for the interpretation of (onshore) seismic data from the shallow to deep range (+- 300 - 3500 m). The goal is to rapidly characterise this depth domain by efficient interpretation of horizons and faults in seismic data. The first step is to improve the signal by applying AI techniques like self-supervised and semi-supervised contrastive learning CNN's for noise reduction and interpolation. Next, horizons and faults are interpreted with minimal use of human-generated training data by using (semi-) self-supervised methods. The resulting developed toolkit supports the application of the implemented
algorithms in an efficient workflow. As a first demonstration, the top of the Dutch Maassluis Formation has been interpreted in the Leeuwarden and Waalwijk 3D seismic cubes. Overall, this study demonstrates that AI-assisted interpretation workflows have reached a level of maturity that allows their integration into applied geological modeling and decision-making.
Read the full abstract ▾
All authors Stefan Carpentier, Jan Diederik van Wees, Eva de Boever, Jan Niederau, Camille Chapeland, Suzanne Atkins, Boris Boullenger, Jens Wollenweber
Machine Learning
MUNITE: Unified Multimodal Latent Inference for Any-to-Any Multimodal Generation
Kyeongmin Yeo and Minhyuk Sung
We introduce MUNITE, a latent-variable framework for flexible any-to-any
multimodal generation that treats encoding and latent generation as the same inference problem under different amounts of observed evidence. Given any subset of modalities, MUNITE models the conditional distribution over the latent representation associated with the complete observation. Full observation recovers deterministic encoding, no observation recovers the latent marginal, and intermediate subsets define conditional latent inference, all within a single conditional flow model. A shared latent sample captures variation that must remain consistent across generated targets, while modality-specific generative decoders model the remaining uncertainty independently. To learn these conditional distributions from incomplete training examples, we extend conditional flow matching through self-
distillation: predictions conditioned on richer available observations supervise the same model conditioned on smaller subsets at the same intermediate latent state. When the richer-evidence trajectory follows the exact conditional flow, this provides the same expected learning signal as full-target denoising. Across PolyMNIST-D-Q, FFHQ64, and image-text-audio, MUNITE achieves competitive or better generation quality and source-target
alignment, with higher joint-generation coherence. In particular, it attains the highest coherence in all one-to-many and unconditional image-text-audio comparisons, showing the effectiveness of unified latent inference across diverse
multimodal settings.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Global Average Precision for Representation Learning
Bill Psomas, Mohammad Mahdi, Michalis Thomas et al. (+3 more)
Standard information
retrieval metrics, such as mean Average Precision (mAP), assess performance one query at a time, based on how the similarities between a query and its positives compare against those with its negatives. The same holds for common representation learning losses, such as InfoNCE and per-query AP surrogates. None of them considers whether similarities are comparable across queries, which any system with a single decision threshold relies on. Global Average Precision (gAP) does, by ranking all query-candidate pairs in one list and computing a single AP. We introduce gSAP, a differentiable surrogate of gAP. It needs only a similarity
matrix and a binary
matrix marking the positive pairs, the same input as existing losses, so it is a drop-in replacement for them and agnostic to the encoder, the modality, and the source of supervision. Since it considers all possible pairwise comparisons in the batch jointly, it also remains trainable at low temperatures, a regime where per-query surrogates run out of gradient. Swapping it into established recipes improves supervised metric learning, cross-modal
alignment, and self-supervised pretraining, where, to our knowledge, it is the first ranking loss to replace the community standard InfoNCE in the latter two. Its similarities are more consistent across queries, which drives the gains under a universal threshold. gSAP retrieves up to four times as many positive pairs as the strongest AP surrogate at the same precision, and it degrades the least when queries with no positives in the database are added. Beyond thresholding, models trained with gSAP also learn better representations, with higher transfer, $k$NN and zero-shot classification accuracy.
Read the full abstract ▾
All authors Bill Psomas, Mohammad Mahdi, Michalis Thomas, Danda Pani Paudel, Giorgos Tolias, Giorgos Kordopatis-Zilos
Machine Learning · Cross-listed from cs.CV
DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic Monitoring
Jiapan Wang, Daan Hulskemper, Mathilde Letard et al. (+2 more)
4D point clouds acquired by permanent
laser scanning (PLS) enable accurate high-frequency monitoring of surface change in dynamic topographic environments. However, existing methods remain limited in organizing detected surface activities into meaningful process types. We propose DeepTopoClustering (DTC), an unsupervised framework for deriving a hierarchical process taxonomy from object-based surface activities, so-called 4D objects-by-change (4D-OBCs). We transform each 4D-OBC into a GeoMorphogram, a distributional sequence representing the temporal
evolution of topographic change within a spatially bounded surface activity. A convolutional autoencoder learns latent
embeddings from GeoMorphograms, which are jointly optimized using a hierarchical deep clustering objective to organize surface activities into a hierarchy. We evaluate the learned hierarchy using expert annotations on two 4D
datasets of sandy beach sites and their combination. DTC with GeoMorphograms achieves the highest agreement with expert judgment at the taxonomy level comprising eight major process types ($F_1=0.78$, match accuracy $=0.92$), outperforming dimensionality reduction and conventional flat clustering. The learned taxonomy separates major erosion- and deposition-dominated activities and distinguishes finer subtypes based on change magnitude, duration, compactness, and temporal
evolution. DTC thus provides a scalable and interpretable route from 4D change detection to a data-driven, expert-supported surface process taxonomy, advancing automated knowledge derivation for understanding surface dynamics in topographic monitoring.
Read the full abstract ▾
All authors Jiapan Wang, Daan Hulskemper, Mathilde Letard, Roderik Lindenbergh, Katharina Anders
Machine Learning · Cross-listed from cs.CL
Training Advisors for LLM Agents from Task Outcomes
Sergei Polezhaev, Barys Liskavets, Ori Press et al. (+1 more)
Large
language model
agents tackle multi-step tasks by interleaving
reasoning and tool calls with observations from the environment. Prior work has shown that natural-
language feedback can help these
agents revise their decisions during task execution. We introduce Caddie, a method for training critics to provide natural-
language analysis and advice as
agents work through a task. Unlike approaches that rely on step-level labels or reference critiques, Caddie learns from whether the
agent ultimately succeeds after receiving the critic's feedback. We optimize the critic through reinforcement learning while keeping the base model frozen. Trained on multi-hop question answering with a single base model, our Qwen3-4B critic improves success rates across four base models of different scales and architectures, including three not used during critic training. On the MuSiQue
benchmark, the trained critic improves Qwen3-4B's success rate by more than 25 percentage points, surpassing the performance of Kimi K3 without a critic. The same critic also yields gains on out-of-domain interactive
benchmarks, including $\tau^3$ and DeepDive, with no additional training. Our results show that
agents can decide when to seek help from a critic at inference time and that outcome-based critic training can produce guidance that transfers across base models and task domains.
Read the full abstract ▾
All authors Sergei Polezhaev, Barys Liskavets, Ori Press, Alexander Golubev
Machine Learning
Stream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study
Agung Nugraha, Hyerin Kwon, Heungjun Im et al. (+2 more)
Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large
dataset is slow and costly. This study addresses that problem for partial inverse design, where only some design variables are specified and the rest must be inferred to reach a target performance value. We propose CoNN-AL, a framework for data-efficient partial inverse design that adds stream-based active learning to the Cooperative Neural Network with Denoising Autoencoder (CoNN-DAE). The model estimates predictive uncertainty through Monte Carlo dropout and uses it to decide, in real time, which incoming candidate samples are worth labeling, so the limited labeling budget is spent on the most informative designs. We validate the framework on a real-world automotive glass run channel
dataset of more than 900,000 unique simulated designs. With only 20,000 actively selected labels, about 2.3% of the training pool, CoNN-AL reaches R-squared values of 0.967 to 0.982 across all missing-variable levels, approaching the upper-bound models trained on far more data. It reaches R-squared of at least 0.95 with 30 to 40% fewer labels than random sampling at the more difficult missing-variable levels and, at the most challenging level, is the only strategy in this study to reach R-squared of 0.98. Together with this work, we publicly release the
dataset to support future research on data-driven design.
Read the full abstract ▾
All authors Agung Nugraha, Hyerin Kwon, Heungjun Im, Gian Antariksa, Jihwan Lee
Machine Learning
For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance
Bjørn Leth Møller, Bulat Ibragimov and Christian Igel
The adoption of machine learning for socially relevant tasks requires effective explainable artificial intelligence (XAI) methods to better understand the behavior of machine learning models. Attribution methods are a popular XAI approach in which input-output relationships are characterized by heat maps that reflect the relative importance of input features for a particular prediction. The quality of such maps is often assessed by measuring faithfulness based on the area under insertion and deletion curves, which measures changes in the model output as features are added and removed. In this study, we derive an objective function from this notion of faithfulness and a way to approximate its gradient. We establish the connection between insertion curves and top-$k$ feature selection, which leads to a loss function measuring the quality of attributions. Randomization of the loss allows us to efficiently approximate its gradient. To show the effectiveness of the general approach, we combine the loss function with the neural explanation mask framework. The resulting method, termed Ra-NEM, can be used with any differentiable model without affecting the model's performance. Experiments demonstrate that Ra-NEM provides accurate attributions robustly and efficiently. Compared to other
algorithms, the attributions have not only higher faithfulness but also perform well in terms of other XAI metrics. The high inference speed of Ra-NEM makes the method suitable for online applications. The code is available online: https://github.com/baerminator/Ra_Nem
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani et al. (+4 more)
Text-to-image
diffusion models fail predictably on compositional
prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent architectures already augment CLIP with a T5 encoder precisely because CLIP's contrastive
embedding loses compositional structure, yet these failures persist. We argue the binding problem is therefore not one of missing information but of misaligned information: a text encoder preserves compositional structure, but in a representation space shaped by
language modelling rather than
vision, and the denoising objective does not directly reward aligning the two. We show this correspondence can be supplied as an explicit training signal, that the relevant cross-modal information is concentrated in a low-rank subspace of self-supervised visual features, and that supplying it can be folded into
diffusion training as a single auxiliary loss. Our method, ORCA (Orthogonal Residual Compositional
Alignment), aligns the latent of a
diffusion transformer with a low-rank target derived from a frozen visual encoder, through a predictor whose orthogonal basis is parameterised by a learned residual between T5 and CLIP
embeddings, which provides a
prompt-dependent signal for selecting the visual readout subspace. We prove that the cross-modal information recoverable at a given rank is bounded by the spectral mass of the visual encoder's covariance in the top components. Across three
diffusion-
transformer backbones (DiT-B/2, DiT-L/2, U-ViT-L), ORCA improves FID and GenEval over both vanilla and REPA baselines at zero inference-time cost; on DiT-L/2 it reaches FID 16.65 and GenEval 0.291 at 200K steps, exceeding the strongest 400K baseline at half the training cost, with the largest gains concentrated on attribute binding, spatial relations, and multi-object
prompts.
Read the full abstract ▾
All authors Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani, Mohammad Vali Sanian, Hesam Asadollahzadeh, Aryan Yazdan Parast, Mohammad Lotfollahi
Machine Learning
Fully Interpretable Minimal Transformers: From Geometry to Algorithm
Raneem Mahajne and Toviah Moldwin
We present a framework for building and interpreting minimal
transformer models. By constraining a
transformer's
embedding dimension and head size to 2, we enable full two-dimensional visualization of its internal representations.
Embeddings, query/key/value transforms,
attention outputs, residual streams, and decision boundaries can all be seen directly. Our central claim is that the learned geometry implies an
algorithm; the arrangement of points and boundaries in R^2 can be read as a step-by-step procedure. We train a
transformer on a simple task where it must produce the most recently observed even number whenever the '+' operator appears in a sequence of digits. Once trained, we visually walk through every step of the
transformer's computation. We show how the model embeds the
tokens and their respective positions in the sequence, transforms them via the Q, K, and V
matrices, uses the dot product between the Q and K representations to form the
attention matrix, and uses the
attention matrix to select values that move the representation of each input
token to the region of the domain of the output layer that will correctly predict the next
token. We introduce a suite of interpretability visualizations that make the algorithmic interpretation of this procedure explicit. Our framework offers a pedagogical and experimental testbed to explore how
transformers use informational geometry to implement next-
token prediction.
Read the full abstract ▾
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Origins of Universal Machine Learning Force-Field Errors in Multicomponent Materials
Hongwei Du, Dingyang Lv, Baole Wei et al. (+11 more)
Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed. We construct a
benchmark of 7,599 multicomponent configurations inspired by high-
entropy design, elemental substitution and anion mixing. Eleven pretrained models are evaluated against density functional theory for energies, forces and stresses, with assessment extended to elastic, vibrational and adsorption-related properties. Force errors are analysed through training-reference coverage, local
geometric heterogeneity, distance directionality and elemental response. Distances to training-reference environments reveal a qualitative association between coverage differences and increasing errors, while substantial variation remains at similar distances. Higher-error groups show greater local
geometric heterogeneity, although OMat24 provides broad coverage of these environments. Relative to training-reference pair medians, errors remain low near the median, rise steeply on the compression side and increase more weakly on the extension side. After matching element pairs and absolute distance deviations, compression-side force errors are 1.81-1.95 times extension-side errors. Model-predicted pairwise interaction curves show greater
curvature under compression. Fitting difficulty in independent elemental systems correlates with electronic band-energy responses to atomic displacements and Fermi-level shifts, and a similar pattern is observed in multicomponent systems. In parameter-matched comparisons, spherical-harmonic representations with maximum degrees of 2 and 4 lower test force errors for 38 and 40 of 43 elements, respectively, while differences in elemental difficulty remain. These findings inform force-field selection for experimental compositional design and identify targets for training-data sampling and model representations.
Read the full abstract ▾
All authors Hongwei Du, Dingyang Lv, Baole Wei, Yu Ren, Feng Yu, Xin He, Bonan Zhu, Jiahui Liu, Yongda Huang, Yongheng Li, Jianjun Liu, Siqi Shi, Hong Wang, Ziheng Lu
Machine Learning
Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches
Sunjoo Whang, Jungjun Oh, Minsung Kim et al. (+5 more)
Long inputs and extended generation increase the storage and access costs of the key-value (KV) cache. Low-bit quantization reduces storage and
memory traffic, while query-channel
pruning can further reduce key-cache reads. Rotation-based quantization redistributes the energy of key outliers across channels. To maintain computational invariance, the same orthogonal transform must be applied to queries, preserving query-key dot products. However, this rotation can disperse query energy, weakening the separation between a few large components to retain and many small ones to prune. We introduce Dual-QK, which uses paired non-orthogonal query and key transforms to address this conflict. Using calibrated query and key statistics, Dual-QK combines partial key whitening with a query-aligned basis to balance key scales for INT2 quantization and concentrate query energy for dynamic channel
pruning. Channel-0 protection and bucket-relative RoPE support low-bit accuracy over long contexts. Experiments on four models across five generative
benchmarks and long-context
retrieval tasks show improved accuracy over OSCAR on most tasks at 40% query-channel sparsity. At a 128K context, Dual-QK provides $6.8\times$ KV-cache compression and an estimated $8.3\times$ reduction in KV read volume relative to unpruned BF16. Under the evaluated configurations, our SGLang implementation achieves up to $3.75\times$ the decoding throughput of unpruned BF16.
Read the full abstract ▾
All authors Sunjoo Whang, Jungjun Oh, Minsung Kim, Dongho Seo, Jisu Shin, Gregory Kielian, Hoi-Jun Yoo, Sangjin Kim
Machine Learning
Homogenization in Multi-Agent Systems
Prakhar Ganesh, Kyra Wilson, Luca Zappella et al. (+4 more)
Multi-
agent systems (MAS) leverage interactions between
agents to perform complex tasks. Despite their success, we show that these interactions can also lead to homogenization, i.e.,
agents converging to similar behaviors. Homogenization in MAS can reduce
agent diversity and reinforce shared failures. In this paper, we operationalize homogenization using three metrics: conformity to the majority, polarization towards extremes, and growing inertia against changes over subsequent interactions. We evaluate homogenization in MAS for code generation, hiring, and scientific peer review. Across these tasks, we show that homogenization translates to concrete downstream risks: in code generation, it hides and amplifies correlated errors which can create systemic vulnerabilities; in hiring, it allows the influence of biased
agents to persist long after their removal; and in peer review, it creates uneven evaluation standards across research areas. Our results establish homogenization as a failure mode of MAS, demonstrating that MAS evaluations must move beyond aggregate performance to carefully analyze interaction dynamics. Finally, we show that simple approaches to increase diversity—leveraging sampling stochasticity and mixed-models MAS—fail to reduce homogenization risks, highlighting the need for strategies to effectively leverage
agent diversity.
Read the full abstract ▾
All authors Prakhar Ganesh, Kyra Wilson, Luca Zappella, Barry-John Theobald, Nicholas Apostoloff, Lucas Monteiro Paes, Nivedha Sivakumar
Machine Learning · Cross-listed from cs.SD
Backdooring Acoustic Foundation Models for Physically Realizable Triggers
Zebin Yun, Eyal Ronen and Mahmood Sharif
Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from
speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this gap by proposing the Foundation Acoustic model Backdoor (FAB) attack, demonstrating that state-of-the-art AFMs are susceptible to backdooring under practical settings. Despite making minimal assumptions about adversary capabilities (e.g., no access to pre-training data), we show that FAB preserves benign performance while inducing backdoors that survive fine-tuning and cause significant degradation across diverse downstream tasks when activated. Notably, FAB utilizes task-agnostic, physically realizable, inconspicuous, and sync-free triggers (e.g., a background siren). We evaluate FAB using two leading AFMs, nine downstream tasks, and four different triggers. We further demonstrate its effectiveness against established defenses and across both digital and physical domains. While extensive end-to-end fine-tuning can mitigate FAB, such a defense is resource-intensive and task-specific. Our work highlights critical risks to AFMs and calls for advanced defenses.
Read the full abstract ▾
Machine Learning
BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation
Yingxiang Yang, Weihang Xiao, Zhunxuan Wang et al. (+2 more)
Reinforcement learning is now central to eliciting
reasoning in large
language models, while in the popular
algorithm Group Relative Policy Optimization (GRPO) every
token in a rollout receives the same advantage. We ask how to make process supervision efficient: accelerating convergence and improving final quality without the cost of value networks. We propose Bag-of-
Tokens Group Relative Policy Optimization (BoT-GRPO), which extends GRPO to
token-level reward models through a length-invariant "bag of
tokens" aggregation: it collects all
token-level rewards across rollouts, weights each by the inverse of its source sequence length, and computes per-
token advantages relative to weighted group statistics. BoT-GRPO is critic-free, and is a drop-in replacement wherever GRPO is used when
token-level reward is available. On React front-end code generation, BoT-GRPO reaches $80\%$ compile rate up to $1.9\times$ faster than GRPO and converges faster than modern GRPO variants (GSPO, DAPO, PURE) while reaching higher final compile and VLM-judged win rates. On a second task, AIME mathematical
reasoning, BoT-GRPO delivers absolute Pass@$k$ gains up to $8.1\%$ over GRPO in half the steps. For both tasks we compare the
algorithm's performance on
reasoning vs. non-
reasoning base-model families (Qwen2.5-3B, SmolLM3-3B, Phi-4-mini-
reasoning). Our experiments also yield a practical recipe for the reward model itself: reward stability matters more than richness: clean, bounded, stable fine-grained signals consistently accelerate learning where noisier alternatives stall.
Read the full abstract ▾
All authors Yingxiang Yang, Weihang Xiao, Zhunxuan Wang, Joshua Flashner, Niresh Agarwal
Machine Learning · Cross-listed from cs.CV
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Adam Pardyl, Siddhartha Gairola, Sukrut Rao et al. (+4 more)
Concept-based
vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those models are often limited to fixed categories or depend on
language to define their concepts. We introduce DisParQ (Discrete Parts with Quantized attributes), a method that learns spatially grounded, discrete concept representations from a powerful frozen
vision-only self-supervised backbone. It requires no class labels and no
language supervision. Each image patch is assigned to exactly one concept from a learnable prototype dictionary, and only a sparse subset of concepts may activate per image. To capture how each concept varies across images (e.g., the type of a "wheel"), we learn continuous residuals alongside the concepts and then quantize them into discrete attributes. A spatial decoder reconstructs the backbone's representation from the concepts and attributes alone, so successful reconstruction means that the discrete representation preserves the backbone's information. We evaluate DisParQ across seven
datasets, from general recognition (ImageNet, PartImageNet, Places) to fine-grained
benchmarks (CUB, Cars, Dogs, Flowers). We show that DisParQ closely matches its frozen DINOv2 teacher on ImageNet linear probing (83.2% top-1), achieves higher concept consistency than
language-aligned models, remains competitive on fine-grained recognition, and enables cross-category part-based
retrieval.
Read the full abstract ▾
All authors Adam Pardyl, Siddhartha Gairola, Sukrut Rao, Adam Wróbel, Bartosz Zieliński, Bernt Schiele, Dawid Rymarczyk
Machine Learning
A Proof-of-Concept Study of Weakly Supervised Labeling of Fine-Grained EEG Components for Artifact Attenuation
Lu Wang-Nöth, Hai Huang, Philipp Heiler et al. (+3 more)
Electroencephalography (
EEG) is highly susceptible to electromyographic (EMG) artifacts, whose temporal heterogeneity and spatial-spectral overlap with neural activity can leave mixed sources after blind source separation. Existing artifact-removal methods are further limited by scarce reliable component-level ground truth: expert annotations are costly and subjective, while no established method provides realistic simulation-based ground truth for EMG contamination in multichannel scalp
EEG. To address these limitations, we propose a framework combining a frequency-aware high-dimensional representation with Multi-Instance Learning. The representation unfolds separated components into frequency-resolved intra-components, creating a space in which mixed neural and muscular activity becomes more separable, while the weakly supervised learning formulation enables artifact-likelihood scores for individual intra-components to be learned from epoch-level labels without finer-grained ground truth. The resulting intra-component classifier supports fine-grained EMG artifact detection and score-guided attenuation. Experiments on held-out subjects show that the framework learns informative intra-component scores and reduces artifact-related spectral deviations most clearly for jaw tension, with moderate effects for raising eyebrows and limited effects for frowning.
Read the full abstract ▾
All authors Lu Wang-Nöth, Hai Huang, Philipp Heiler, Shuqiong Wu, Liyun Zhang, Helmut Mayer
Machine Learning
AdaPS-LiNGAM: Adaptive Predecessor Selection for Linear Non-Gaussian Acyclic Models under Small-Sample Settings
Shun Yanashima, Kentaro Kanamori and Hirofumi Suzuki
Causal discovery becomes particularly challenging when the available sample size is small relative to the number of variables. This challenge also arises in the linear non-Gaussian acyclic model (LiNGAM), an identifiable framework for causal discovery from observational data. DirectLiNGAM estimates a causal order, which arranges variables so that causes precede their effects, by sequentially identifying an exogenous variable and removing its linear effect from the remaining variables. We establish a structural limitation of this procedure: when the number of variables exceeds the sample size, repeated residualization necessarily becomes degenerate before the full causal order can be determined. Our analysis further reveals that each residual can be reconstructed using only a graph-determined subset of variables already placed earlier in the causal order, termed the active boundary. This result motivates AdaPS-LiNGAM (Adaptive Predecessor Selection LiNGAM), which reconstructs each residual directly from the original observations using an adaptively chosen sparse subset of those earlier variables. The same subset-selection principle is also applied to the final
pruning step for edge estimation. Experiments on synthetic data demonstrate that AdaPS-LiNGAM provides accurate causal-structure recovery in sample-limited settings and degrades more gradually as the sample size decreases.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.PF
Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing
Arnold Olympio, Juan Manuel Servera Bondroit, Wael Abdelmalek et al. (+2 more)
Reproducible benchmarking of Large
Language Model (LLM) inference is challenging because repeated measurements can vary with execution and system state. We present the Sequential Isolation Methodology, a controlled benchmarking and regression-testing protocol designed to reduce between-run measurement variance while deliberately varying workload concurrency. We evaluate three representative open-source LLMs on an NVIDIA A100 80GB GPU using vLLM 0.9.1 across six context sizes and eight concurrency levels, with five repetitions per configuration. The final protocol reduces average coefficient of variation (CV) from 15.2% in the least controlled methodology stage to 2.2% under the final protocol; using CV computed across the five repetition-level median (P50) TTFT values per configuration, 113 of 144 configurations (78.5%) achieve CV below 3%. The measurements also show a marked latency transition between 200 and 500 concurrent users on the tested stack and descriptive differences in P99 latency across the three models. We additionally provide an explicit cost break-even model with sensitivity to API pricing. The protocol is intended to provide a stable reference for reproducible comparison and regression testing rather than to predict absolute behavior under uncontrolled production traffic. Infrastructure-as-Code and
benchmark scripts support replication of the experimental environment.
Read the full abstract ▾
All authors Arnold Olympio, Juan Manuel Servera Bondroit, Wael Abdelmalek, Guang Lu, João Carvalho