Machine Learning
Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng et al. (+5 more)
Time series
forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, sequences of observations generally provide only a partial view of the dynamics of the underlying system, with future observations being shaped by latent dynamics. Recent latent-space
forecasting methods thus achieve improved performance by predicting future observations from latent-space representations of historical observations rather than directly
forecasting future observations in the observation space. Next, while future observations are also shaped by external factors, how to incorporate external, often
multimodal, information into
forecasting, so that it can shape latent-state formation and
evolution directly, remains underexplored. We propose WorldTS, a world-modeling based
forecasting framework that integrates
multimodal covariates directly into the
forecasting to further improve
forecasting performance. Specifically, WorldTS employs a two-stage training strategy. First, it learns
forecasting-relevant latent state dynamics conditioned on
multimodal covariates, yielding encoded future states. Next, the learned state dynamics are frozen, and an observation decoder is trained to map the predicted future states back to future observations. Extensive experiments on 21 real-world
datasets offer insight into WorldTS and its effectiveness.
Read the full abstract ▾
All authors Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng, Wangmeng Shen, Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen
Machine Learning
I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?
Yuhang Liu, Zhuo Huang and Javen Qinfeng Shi
Recent empirical and theoretical advances suggest that joint-
embedding predictive architectures (JEPAs) may learn meaningful representations for action-conditioned prediction of future outcomes, thus becoming one of the foundational structures for world models. However, accurate prediction does not, in general, necessarily imply recovery of underlying causal states that give rise to the observed dynamics. This work investigates when and how JEPAs can recover the underlying causal states from observations. We first introduce a latent variable model, in which high-dimensional observations are generated from latent causal states whose dynamics are governed by action-conditioned transition mechanisms. Based on this formulation, we develop a general information-theoretic objective that combines conditional likelihood maximization for learning transition dynamics with
entropy maximization for preserving latent state information. We then establish identifiability conditions under which representations learned by this general objective recover the underlying latent causal states up to component-wise invertible transformations and permutation. One key condition for such identifiability is sufficient action-induced variation in the transition mechanisms. Guided by this finding, we instantiate the general objective with an action-modulated Gaussian additive-noise model, yielding action-modulated JEPA (A-JEPA). Experiments on synthetic environments verify the theoretical findings under the identifiability conditions and robustness to moderate violations, while visual
benchmarks demonstrate improved state recovery and transfer to unseen transition mechanisms.
Read the full abstract ▾
Machine Learning
Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection
Jianan Liu and Chunguang Li
Multi-dimensional time series, inherently tensorial, are common in practice. Despite great progress in time series anomaly detection, most existing methods are confined to uni-/multi-variate time series. When handling multi-dimensional time series using these methods, reshaping operations are required, which inevitably break the intrinsic correlations and thus lead to performance degradation. In uni-/multi-variate time series anomaly detection, AutoEncoders (AEs) are widely adopted and generally categorized into reconstruction-based and prediction-based AEs. The reconstruction-based AE utilizes the current observation for reconstruction, while the prediction-based AE utilizes the historical information to predict the current observation. Thus, the two AEs utilize different information. To bridge the gap between reconstruction-based and prediction-based AEs, so as to fully leverage the available information and thus further enhance performance, we propose a predictive prior and incorporate it into the reconstruction-based AE. It may not be very difficult to conceive this idea, but designing the predictive prior so that it can work for tensor anomaly detection is non-trivial. Specifically, to avoid breaking the intrinsic correlations within the multi-dimensional time series, we use the tensor AE as the backbone. To incorporate the predictive prior into the reconstruction-based AE, we propose a
Bayesian fusion approach and our analysis reveals that this approach can enhance the modeling capability of the model for normal data. To mitigate the over-generalization problem of AE, we incorporate physical laws, i.e. tensor low-rank decomposition rules, into the neural networks in the predictive prior, leading to the Physics-informed Predictive Prior Tensor AE (PPPTAE) framework. Experimental results on real-world
datasets demonstrate the effectiveness of the proposed method.
Read the full abstract ▾
Machine Learning
Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift
Alejandro Rodriguez Dominguez, Muhammad Shahzad and Xia Hong
Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We study selection over such a family, with candidates and teacher fixed and target labels absent or scarce. Two findings organize the label-free case. Minimum teacher distortion behaves almost as a constant rule, selecting the same eight-bit, per-channel, unclipped configuration in every run, which does not minimize empirical target cross-
entropy. Established
estimators divide sharply: in the overconfident-collapse regime of the CNN families, confidence-based
estimators order the family close to backwards, and the diagnostics that identify it need the labels the setting denies, while output-distribution
estimators match the teacher-relative anchor and on one architecture beat it. Distortion is nonetheless stable, so a supervised term can move selection away from it. Combining the two, we give exact quadratic identities for a canonical quadratic analogue of the family. We also show that under symmetric corruption the label-dependent part of a criterion linear in the label indicator is multiplied by one common factor whenever its coefficient sums are candidate-invariant, a class holding teacher contrasts and accuracy but not cross-
entropy. These characterize the score's components without bounding selection regret. Across one hundred and thirty-four candidate families, one per independently trained convolutional or
Vision Transformer teacher, anchoring reduces mean regret at the smallest label budget in every setting, an advantage that fades beyond twenty-five labels.
Read the full abstract ▾
Machine Learning
CRNDiff: Count-Native Diffusion Framework via Chemical Reaction Networks
Yuxuan Qiu, Praful Gagrani and Tetsuya J Kobayashi
Scientific measurements such as single-
cell RNA (scRNA) sequencing often take the form of nonnegative integer counts, whereas continuous-state
diffusion models approximate this discrete structure using continuous coordinates. Building on
stochastic chemical reaction networks (CRNs), a class of count-native Markov jump processes, we introduce CRNDiff, a structured framework that combines count-space
diffusion with inference-time conditioning on rare subpopulations. An independent birth–death instantiation yields a closed-form transition kernel for forward noising. This kernel enables reverse sampling via forward-filtering backward-sampling (FFBS) and supports data-driven selection of the terminal noising time, eliminating the need for a validation sweep. This tractability also lets us introduce tilted Feynman–Kac (FK) steering, a method for sampling target subpopulations from a frozen generator without retraining. By tilting posterior marginals before FK particle correction, steering mitigates importance-weight concentration when the target population is rare. Using scRNA-seq data from the human heart
cell atlas, we test the ability of CRNDiff to generate
cell-type-specific distributions. Across the three evaluated target populations, CRNDiff achieves the highest conditional fidelity among the evaluated generative models, with larger mean purity margins for rarer target populations. Generated
cells preserve marker-level differential-expression structure. Replacing real training
cells for the target classes with generated
cells yields downstream classification performance approaching that of the real-data reference.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NI
Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One Year
Mahmoud Abbasi
Knowledge
distillation is the standard way to compress encrypted-traffic classifiers for the edge, and almost all such work judges students by accuracy alone. We ask what else a student inherits: unknown-traffic detection, calibration, shortcut reliance, and whether any survives a year of drift. Resemblance proves little on its own, since soft targets also regularise. We therefore distil one 101k-parameter student from two teachers of equal accuracy but different construction, a five-member ensemble and a single wider model, so that following one rather than the other is attributable to it. The design was pre-registered before any test result was seen. We tested ten hypotheses on CESNET-TLS-Year22, a year of real TLS traffic, across 18 test windows over 35 weeks. Two are supported: a student's per-flow unknown-scores shift toward its own teacher, but only at a conventional temperature, not the accuracy-optimal one; and a shortcut-reliant teacher passes its over-confidence to a student that never sees the feature. The drift prediction is reversed under both scores, the gap narrowing rather than widening and the student overtaking under the energy score in two of three replicates, as is the prediction that such a teacher harms its student's detection, which improves slightly. Shortcut reliance is set by model size, not
distillation. Under the logit-based scores nothing else transfers:
distillation beats neither a temperature-scaled direct student nor label smoothing. Exploratory analysis shows this turns on the scoring rule: with a feature-space detector the teacher detects unknown traffic 0.073 AUROC better than the direct student, where the energy score sees 0.000, and the conventional-temperature student inherits most of it. Label smoothing, with no teacher, recovers more.
Distillation transfers the teacher's habits; what looks like an inherited ability is available without one.
Read the full abstract ▾
Machine Learning
Frame the adversary: a structure-aware attack methodology
Vicky Kouni, Stelios Perrakis, Francis Bach et al. (+2 more)
Frequency-based
adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial perturbations, frequency-based attacks expose deeper vulnerabilities, making them especially valuable for robust evaluation of safety-critical and security-sensitive applications. Yet, existing approaches are typically not derived as solutions to an optimization problem that explicitly captures transform-domain structure. In this paper, we propose a methodology for crafting principled frequency-based
adversarial attacks, via a dedicated optimization framework. A cornerstone of our method hinges on the introduction of a perturbation constraint set, tied to highly structured non-orthogonal transforms, well-known for their flexible, non-predefined frequency handling. We prove that the attacks emerge as weighted $\ell_2$-projections onto this set, yielding a general and controlled attack generation mechanism. By this, we provide a clear
geometric attack characterization, ensuring
alignment between the optimization objective and the perturbation constraint. We assess our framework on standardized
datasets, for pretrained and adversarially robust models. Results highlight that our attacks, being solutions to an optimization problem, over a structured perturbation set, are highly effective, even across different, unseen architectures. Our methodology could serve as a theoretical baseline for designing and analyzing transformed-based attacks, targeting fundamental model vulnerabilities, instead of mere architecture-specific artifacts typically studied in the robustness literature.
Read the full abstract ▾
All authors Vicky Kouni, Stelios Perrakis, Francis Bach, Pascal Frossard, Yann Chevaleyre
Machine Learning · Cross-listed from cs.CL
LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
Irene Tallini, Lorenzo Basile, Valentino Maiorca et al. (+2 more)
Activation steering is a powerful training-free paradigm for controlling large
language models at inference time. However, standard approaches estimate a per-layer steering direction from contrastive data and apply it on the layer's entire representation space, which may couple the intervention to off-target properties present in the contrastive data and degrade unrelated capabilities. To mitigate this issue, we introduce LocUS (Localized Unembedding Steering), a method which grounds activation steering to the model's own output vocabulary subspace. By identifying a property-specific linear subspace within the unembedding
matrix, LocUS enforces a
geometric constraint that restricts the steering transformation to a specific subspace and at the same time localizes its application to a sparse subset of
attention heads. Extensive evaluations across three model families on toxicity mitigation, sentiment redirection and sycophancy suppression show that LocUS matches or outperforms state-of-the-art baselines while intervening on under 6% of parameters and better preserving general capability.
Read the full abstract ▾
All authors Irene Tallini, Lorenzo Basile, Valentino Maiorca, Francesco Locatello, Alberto Cazzaniga
Machine Learning
From Shortcut Learning to Discrete Neural Insertion Sort
Konstantinos Mylonas and Thrasyvoulos Spyropoulos
Neural algorithmic
reasoning aims to train neural networks to follow known
algorithms and generalize beyond the input sizes seen during training. However, correct final outputs and intermediate supervision do not necessarily show that a model follows the intended execution. We study this problem using insertion sort. Our analysis of the CLRS30 baseline NAR shows that the hint objective is weakly optimized and that hint accuracy remains low. Moreover, many intermediate representations can already be decoded into sorted sequences before the reference insertion-sort execution terminates, suggesting that the model learns a shortcut to the final output. Motivated by these findings, we introduce Discrete Neural Insertion Sort. Our model represents the sequence as a chain, separates scalar exchanges from control-state transitions, and projects node representations back to discrete states after every processor step. When trained only on sequences of length 16, the model achieves $100\%$ sorted-sequence accuracy on sequences of length 64 and 128. However, an ablation shows that discretization and graph structure alone are insufficient: without additional supervision of the global inner-loop state, the model fails even at the training length. Our results show that discrete execution can support strong length generalization, while also highlighting the problem-specific inductive bias required to learn a faithful algorithmic execution.
Read the full abstract ▾
Machine Learning
Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
Saksham Kiroriwal, Julius Pfrommer and Jürgen Beyerer
We study
Bayesian optimization (BO) through the lens of information geometry. Pulling back the Fisher information metric through the surrogate posterior map yields a local sensitivity tensor on the input space, which leads to an upper bound on the gradient of reparameterizable acquisition functions. This view explains vanishing-gradient behavior in high-dimensional BO and provides a common interpretation of heuristics such as RAASP and dimension-scaled lengthscales. Building on this analysis, we propose FITR, a trust-region-based BO method that replaces lengthscale-based scaling by local pullback-Fisher weights. FITR is not restricted to GP kernels with explicit lengthscales. On GP
benchmarks with an SE kernel, experiments show competitive performance using FITR. The proposed method also easily generalizes to non-isotropic surrogates, although the gains are more task-dependent in that setting.
Read the full abstract ▾
Machine Learning · Cross-listed from cond-mat.dis-nn
A Flatness-Generalization Relation in the Teacher-Student Tree-Committee Machine
Brandon Livio Annesi, Davide Straziota and Enrico Maria Malatesta
The flatness of the loss landscape at a minimizer is a widely used heuristic for
reasoning about neural-network generalization, yet evidence for this relation is mostly empirical and controversial. We study this relation in a teacher-student tree committee machine, where both the ERM
estimator and the Hessian spectrum are analytically tractable in the proportional high-dimensional limit. First, we use a zero-temperature Gibbs formulation to obtain predictions for the observables of the typical minimizers of the empirical loss. Secondly, we use Edwards-Jones formalism to derive the limiting Hessian resolvent around these typical minimizers. All predictions agree with finite-size gradient-descent simulations. Finally, we study three measures of flatness, namely the left and right edges and the spectral mean, and check if a decrease in generalization error as the
dataset size is increased corresponds to an increase in flatness. We find that the answer strongly depends on the learning task and on the ratio of the number of parameters to the number of data points. In regression, the spectral mean and right edge correlate with the generalization error, while the left edge does so only in the overparametrized regime. In classification this correlation reliably holds only in the highly overparametrized phase, while for underparametrized networks it can even reverse.
Read the full abstract ▾
Machine Learning
The Residual Stream's Effective Depth
Barak Gahtan, Ido Galil and Alex M. Bronstein
We introduce effective depth ($\Deff$), a scalar diagnostic that treats the layer-wise residual stream of a
transformer as a discrete-time process, measures how representation similarity decays with layer distance, and aggregates that profile into one number. Across sixteen decoder-only
language models, $\Deff$ separates a structural consequence of residual accumulation from an empirical one: even maximally diverse orthogonal updates have the closed-form reference $F_L = 2L/(L+1)<2$, yet fifteen of sixteen default measurements lie below $F_L$ (Qwen3.5: 32–44%, OLMo-2: 40–41%, Pythia: 23–28%). Matched references show that the gap is not caused by the persistent initial state or update-size imbalance, but is largely a calibrated signature of correlated residual updates rather than evidence that depth is unused. Symmetric position-0,
token-normalisation, and top-PC controls show the regime is not reducible to BOS or top-PC artefacts: the lone above-reference default outlier joins the same regime, and all sixteen models are sub-reference after
token-normalisation or top-1-PC removal. Intermediate checkpoints show that the regime is established early in OLMo-2 and stable through 5T
tokens, while Pythia-1.4B follows a distinct decreasing trajectory. A controlled residual-carry intervention supports the mechanism, and $\Deff$ is best read as a global accumulated-state diagnostic, not as a capability score or
pruning method.
Read the full abstract ▾
Machine Learning
Block Sparse Attention with Log-Linear Complexity
Bohao Tang, Zhen Qin, Yuqi Pan et al. (+2 more)
Scaling
language models to long contexts is limited by the quadratic cost of self-
attention. Block sparse
attention offers an efficient alternative, but selecting the retained blocks remains a bottleneck. Conventional block selection requires scoring all query-block pairs and therefore remains quadratic in sequence length. To address this issue, we propose PISA, a block-sparse
attention mechanism that employs a pyramid Top-$K$ selection strategy. The main idea is to gradually narrow down the candidates across different levels, making it more efficient to find the most relevant keys. Specifically, we construct a coarse-to-fine hierarchy of keys and perform selection from the coarsest level. At each level, LogSumExp scoring is applied to a bounded candidate set to select candidates for the next finer level, continuing until the finest level is reached. Through pooling, we construct $O(\log N)$ levels of keys, yielding an overall complexity of $O(N\log N)$, where $N$ denotes the sequence length. We develop hardware-aware Triton kernels for both training and inference, fusing hierarchical routing and LogSumExp scoring without materializing the query-key score
matrix. We further evaluate our method on
language modeling tasks. Compared with the baseline, our method achieves comparable performance on
benchmarks such as commonsense
reasoning while delivering better results on
retrieval tasks.
Read the full abstract ▾
All authors Bohao Tang, Zhen Qin, Yuqi Pan, Zheng Li, Pengfei Liu
Machine Learning
SAGE: A sampling-aware global evaluation benchmark for species distribution modeling
Emilia Arens, Nina van Tiel, Robin Zbinden et al. (+8 more)
Knowing where species occur is fundamental for biodiversity research and conservation. Species distribution models (SDMs) link species observations to environmental conditions to estimate their spatial distribution. However, accuracy varies with the underlying data and models, making it essential to know for which species models can be trusted. Deep-learning-based SDMs ("DeepSDMs") now jointly model thousands of species, drawing on hundreds of millions of community-science records. At this scale, averaging performance hides substantial species-level variability, particularly for rare species, often of greatest conservation concern. Records are also strongly biased, making occurrence counts misleading. Accounting for these factors is essential for a reliable and informative evaluation of multi-species SDMs. Here, we introduce a Sampling-Aware Global Evaluation (SAGE)
benchmark, combining GBIF records for training with sPlotOpen vegetation plots for presence-absence evaluation across 5771 plant species. We propose an evaluation framework that groups species based on two properties, sampling effort and relative prevalence, which describe how densely a species' range is sampled and how frequently the species is recorded. Evaluating single-species SDMs and multi-species DeepSDMs, we find that Random Forests and DeepSDMs perform best overall, but neither dominates: DeepSDMs outperform single-species SDMs for infrequently recorded species while offering no consistent advantage for well-sampled ones. Crucially, this advantage emerges only when established bias-correction practices, such as spatial thinning and reweighting, are carried over to the deep-learning setting. SAGE helps identify the species and data conditions for which a given approach is beneficial, thereby supporting the development of more transparent and ecologically credible SDMs. Data and code: https://earens.github.io/sage/
Read the full abstract ▾
All authors Emilia Arens, Nina van Tiel, Robin Zbinden, Damien Robert, Lukas Drees, Chiara Vanalli, Benjamin Kellenberger, Niklaus E. Zimmermann, Loïc Pellissier, Devis Tuia, Jan Dirk Wegner
Machine Learning · Cross-listed from eess.IV
Quantum Diffusion Models for Medical Image Analysis
Francesco Aldo Venturelli, Stefano Martina, Marco Parigi et al. (+3 more)
Quantum Machine Learning is a novel field of research aimed at devising machine learning approaches exploiting principles of
quantum mechanics, such as superposition,
entanglement and interference. In this context, we present a scalable hybrid
Quantum Diffusion Model, and evaluate its use for medical image analysis. Specifically, our method is based on a Discrete-Time
Quantum Walk
algorithm, executed on a real
quantum device, to model the forward dynamics of the
diffusion model. For the backward step of the
diffusion model, we devise and evaluate a classical learning model, which is used to reversely denoise the data. In contrast with other existing attempts at applying
quantum machine learning for image analysis tasks, severely limited by the size of existing
quantum devices, our method allows to process real-world large size medical data. In particular, we present results on grayscale and RGB images, as well as 3D volumes of moderate sizes. We
benchmark our results by reproducing an alternative classical counterpart model, based on
diffusion models on discrete state spaces. By doing so, we compare the generation capabilities of both models in terms of three distinct state-of-the-art metrics in the field of image generation, showing the competitive, promising results of our approach.
Read the full abstract ▾
All authors Francesco Aldo Venturelli, Stefano Martina, Marco Parigi, Filippo Caruso, Alba Cervera-Lierta, Miguel A. González Ballester
Machine Learning
Distributed Learning as a Service: The Developer's Perspective
Tianyue Chu, Filippo Vannella, Dimitra Tsigkari et al. (+5 more)
Application developers of distributed learning services face challenges that a typical
federated learning loop does not address. Specifically, the model updates can still leak private data, devices might not be able to participate in the training due to limited resources, a single aggregator might not be able to scale, and the transmissions of model weights induce a considerable bandwidth cost. This paper demonstrates DLaaS (Distributed Learning as a Service) from the developer's vantage point. Using a single admin dashboard, the developer initiates a distributed/
federated learning job and is able to activate Differential
Privacy (DP), Split Learning (SL), Hierarchical Aggregation (HA), and Knowledge
Distillation (KD) as declarative options, with no change to the clients' code. We demonstrate the complete service lifecycle on an industrial smart-home Wake-up Word (WuW) task, using the "Ok Aura"
dataset. Once the developer initiates a distributed learning job by toggling DP, SL, HA, and KD in the admin dashboard, the system dispatches the job to a set of Android clients and Dockerized helper aggregators. In the demonstration, these mechanisms run live across configurations. Then, the clients train the model locally and return their updates. The trained model is served to a consumer-side Android application that performs on-device WuW detection on a live microphone stream. In particular, the conference attendees will be invited to speak the trigger phrase and monitor in real time the per-class confidence and inference latency. Finally, we release the source code and short
video walkthroughs of these configurations.
Read the full abstract ▾
All authors Tianyue Chu, Filippo Vannella, Dimitra Tsigkari, Paula Delgado-Santos, Fernando López, Pablo Gomez Guerrero, Sotirios Spantideas, David Solans Noguero
Machine Learning · Cross-listed from cs.DC
DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving
Junyi Shen, Noppanat Wadlom, Zhengyuan Su et al. (+1 more)
Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin until the model or the user resolves the branch. We call this serialization the branch-resolution barrier. Caching alone does not hide it: the key that identifies a reusable result is not known until then. In this paper, we propose DynBranch, which makes an unresolved branch addressable before it resolves. Its stable coordinate lets candidate subgraphs run during resolution and completed subgraph results be reused across later requests. A two-level controller admits this work when its expected benefit exceeds the load price. DynBranch sits at the model-API boundary and requires no changes to
agent harnesses or model execution engines. Across four agentic workloads with Qwen3-32B on 4x H200 GPUs, DynBranch reduces mean latency by up to 32% over each workload's strongest prior system and by 46-66% against a no-reuse floor, while preserving workflow results. The benefit persists across backbone families and on a commodity Qwen3-8B/RTX 4090 deployment.
Read the full abstract ▾
All authors Junyi Shen, Noppanat Wadlom, Zhengyuan Su, Yao Lu
Machine Learning · Cross-listed from cs.IR
KuaFu: Compressing Long User Behavior into Understanding at Billion Scale
Jiahao Hui, Lin Zhu, Ben Tan et al. (+7 more)
Learning user preferences from long behavioral sequences is fundamental to large-scale advertising, recommender systems, and conversational
agents. In industrial systems, preference modeling is typically task-wise, with different downstream tasks independently processing the same user history to capture different aspects of preference. This repeated processing creates substantial redundancy at billion-user scale, especially as preferences evolve and representations require frequent updates. We present KuaFu, a unified user preference modeling system that replaces repeated user-level sequence encoding with reusable item-level compressed representations. Each behavioral item is encoded once and shared across users and downstream tasks, while a user's history is built chronologically and extended with new item representations as they arrive, letting KuaFu capture evolving preferences without re-encoding the entire history. To reduce inference and storage overhead, KuaFu introduces a two-axis projector:
token-axis compression shortens behavior sequences by up to 15x and reduces each item from 150 KB to 10 KB, while width-axis compression reduces the cached representation to 0.5 KB. We further develop a four-stage training pipeline consisting of reconstruction pre-training, preference-understanding post-training, joint compression-generation training, and
hallucination-aware reinforcement learning, progressively improving representation fidelity and downstream utility. Across six MRQA and five RecBench
benchmarks, KuaFu consistently outperforms existing compression methods at comparable ratios, with gains of up to 17.7 EM and 1.90 AUC points respectively. KuaFu has been deployed and evaluated on the Tencent advertising and recommendation platform for ten months. Over this period, it improves per-GPU throughput by up to 350%, saves 190 GPUs, and increases overall GMV by 1.37%.
Read the full abstract ▾
All authors Jiahao Hui, Lin Zhu, Ben Tan, Yishen Hu, Jingdong Shu, Zetai Jiang, Xining Ran, Yeshou Cai, Gong Chen, Haijie Gu
Machine Learning
Aurora-X: Built for Extreme Time Series Forecasting
Xingjian Wu, Chenjuan Guo, Xiangfei Qiu et al. (+6 more)
Time series foundation models (TSFMs) enable cross-domain
forecasting, but their development as general-purpose forecasters remains constrained by underexplored training potential and limited architectural versatility. To address these challenges, we introduce Aurora-X, a billion-scale TSFM with a progressive curriculum and a unified architecture. We first use channel-independent pretraining to learn temporal patterns, then introduce cross-variable dependencies, varied context and horizon lengths, and future
covariates if available during midtraining. Variable-resolution post-training further enables an adjustable temporal span per
token at inference. With fixed model weights, this supports longer histories under a fixed
token budget or fewer
tokens for the same history, enabling test-time scaling. With a versatile architecture, Aurora-X supports cross-variable modeling,
covariate conditioning, and parallel decoding of future patches for probabilistic
forecasting. These are supported by a novel pattern-guided mixture-of-experts that expands model capacity through sparse activation and uses shallow patch similarities to constrain deep-layer routing, guiding expert specialization across heterogeneous time series. Furthermore, we propose an implicit
quantile network head that predicts arbitrary
quantiles to characterize predictive distributions, enhancing probabilistic
forecasting flexibility. Comprehensive experiments on GIFT-Eval, TIME, FEV-Bench, TFB, and DAG-Bench demonstrate state-of-the-art
forecasting performance against pretrained TSFMs and task-specific supervised models.
Read the full abstract ▾
All authors Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
Machine Learning
Robust Graph Clustering Network for Multiple Missing Data
Keyuan Qiu, Renda Han, Zhen Tang et al. (+6 more)
Clustering on graphs where both node attributes and structural links are partially missing remains a challenging task. Existing methods typically rely on imputation-then-clustering on single-view missingness incomplete graphs, which are vulnerable to cross-view error propagation and cluster-boundary blurring under simultaneous attribute and structure missingness. To address these limitations, we propose a Robust Graph Clustering Network for Multiple Missing Data (RGCN), which is designed to handle simultaneous node attribute and graph structure incompleteness. RGCN introduces three key innovations: First, we design a view-decoupled dual-branch imputation to mitigate interference and enable mutual enhancement in recovering missing data. Second, we employ a multi-hyperspherical mixture prior to enhance intra-cluster compactness and inter-cluster separability on a directional latent
manifold. Third, a boundary-aware contrastive enhancement objective mitigates the blurring of clusters caused by imputation bias. Extensive experiments on real-world
datasets demonstrate that RGCN consistently outperforms state-of-the-art baselines under various missing patterns.
Read the full abstract ▾
All authors Keyuan Qiu, Renda Han, Zhen Tang, Qiang He, Xingwei Wang, Wenxin Zhang, Guangzhen Yao, Junxin Chen, Qingjian Ni
Machine Learning
Metacognitive Selective Ensemble for Mobile Systems
Sungmin Lee, Kichang Lee, Joonhee Lee et al. (+3 more)
Deep ensembles improve robustness in mobile sensing, but repeatedly executing many models over continuous sensor streams is costly. Selecting only a few members reduces this cost, yet adaptive selection often requires additional model execution to obtain reliable evidence about inactive candidates. We present MetaSE, an active ensemble framework that exploits short-term persistence in per-model reliability. MetaSE maintains a small active set across windows, uses post-execution evidence to reject unreliable members, and invokes lightweight routing only when replacement is needed. This stateful design accesses the diversity of a larger pool without repeated full-pool evaluation. Across four HAR
datasets and four model architectures, MetaSE consistently improves over a fixed three-model ensemble and achieves accuracy comparable to substantially more expensive adaptive and full-ensemble inference. On a Raspberry Pi 4B, MetaSE is 2.7x faster and uses 69% less
memory than full ten-model inference.
Read the full abstract ▾
All authors Sungmin Lee, Kichang Lee, Joonhee Lee, JaeYeon Park, Songkuk Kim, JeongGil Ko
Machine Learning · Cross-listed from cs.RO
Precision at Speed: Sample-Efficient Online Model-Based Reinforcement Learning for Hydraulic Excavator Control
Claudio Canales, Fang Nan, Marco Hutter et al. (+1 more)
Precise, high-speed control remains challenging for
robots with complex actuation dynamics. Learning directly on hardware is further constrained by the cost of real-world interaction. We present an online model-based reinforcement learning framework that learns a probabilistic dynamics ensemble model from scratch for sampling-based model predictive control. A precision-gated contouring objective conditions the progress reward on path accuracy, prioritizing precision over speed. In a data-driven excavator simulator, the framework achieves higher sample efficiency than the evaluated model-based reinforcement learning baselines. We validate the framework by learning directly on an 11.5-ton Menzi Muck M445 hydraulic excavator, without demonstrations or simulation pretraining. After 20 minutes of interaction, the controller reaches tracking accuracy comparable to prior learned controllers trained on 100-150 minutes of data. After 40 minutes, it sustains sub-centimeter mean path error at high operating speeds.
Read the full abstract ▾
All authors Claudio Canales, Fang Nan, Marco Hutter, Javier Ruiz-del-Solar
Machine Learning · Cross-listed from cs.SD
Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search
Ben Hayes, Haokun Tian and Stefan Lattner
Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often difficult to optimize, while direct search requires rendering every candidate. We introduce Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data. At inference, candidate parameters are scored directly in this learned space, yielding a renderer-free objective whose audio geometry is shaped by parameter correspondences rather than generic audio similarity. We evaluate Synth-JEPA on Surge XT using held-out synthesizer sounds and out-of-domain NSynth and FSD50K targets, against inverse models, direct search, and learned proxy objectives. Synth-JEPA outperforms all baselines in-domain and remains competitive out-of-domain. Its matching quality continues to improve with additional test-time search, allowing compute to be traded for match quality. In pairwise listening tests, listeners preferred Synth-JEPA in 85% of trials overall. Together, these results show that an audio representation with a parameter-induced geometry allows synthesizer sound matching to be approached as an effective renderer-free search problem.
Read the full abstract ▾
Machine Learning
Robust Successor Features
Erik Nikulski, Yamen Habib, Vicenç Gomez et al. (+3 more)
Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the
agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based
benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel.
Read the full abstract ▾
All authors Erik Nikulski, Yamen Habib, Vicenç Gomez, Anders Jonsson, Rubén Moreno-Bote, Javier Segovia-Aguas
Machine Learning · Cross-listed from cs.CR
Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
Kai Yao
Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. This becomes a robustness problem once a source image can be edited before the verifier sees it. We study the problem as source–target verification under
adversarial distribution shift. Our first result gives the exact best-case limit for any image-only verifier: the largest robust target-acceptance gap equals the minimum total-variation distance between the target distribution and the set of attacked source distributions. This quantity depends on the source, target, and edit class, not on the verifier architecture. Our second result explains why deployed public verifiers can fail before this statistical limit is reached. If the verifier can be emulated on the attack region to error $\varepsilon$, then a surrogate black-box attack reaches target acceptance within $2\varepsilon$ plus optimization error of the white-box optimum; score-revealing logistic and softmax heads over public features are identifiable, and approximate score access gives stable recovery bounds. A finite-state experiment checks the minimax identity where both sides are computable. On same-
prompt real/
diffusion benchmarks, the evaluated public CLIP verifiers fail under targeted pixel attacks, while a ResNet-18 victim exhibits partial fake-to-real transfer. Binary feedback with abstention reduces measured attack success, but positive empirical gap upper bounds do not establish robustness. These results motivate separate evaluation of the source–target statistical ceiling and the information released by a deployed verifier.
Read the full abstract ▾
Machine Learning
The Linear Representation Hypothesis for Vision-Language-Action Models
Minseok Jeong, Hyewon Choi, Hiroyasu Tsukamoto et al. (+1 more)
The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on semantic information through the internal representations of large
language models (LLMs). A growing body of work has begun extending this perspective to
vision-
language-action (VLA) models, but the dynamical nature of
embodied interaction introduces an additional challenge. Unlike semantic attributes commonly studied in LLMs, such as gender or
language, a physical quantity of interest (QoI) in a VLA evolves jointly with the system dynamics: the representation influences the actions selected by the policy, which alter the physical state and, in turn, the next representation. In this paper, we develop a theoretical, signature-based formulation of the LRH for VLA that unifies representations and policies. On the representation side, we establish the existence of representations from which the future
evolution of a QoI under a candidate action trajectory can be recovered via linear probing. On the policy side, we introduce a signature generalized linear model for
stochastic action chunks. This structure yields a monotonic change in the expected future QoI along linear paths in natural parameter space, enabling linear steering. We first validate this structure in a controlled oracle setting, then examine whether the same probing and steering mechanisms emerge in a pretrained VLA.
Read the full abstract ▾
All authors Minseok Jeong, Hyewon Choi, Hiroyasu Tsukamoto, SooJean Han
Machine Learning
Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Models
Shan Zhao, Ilija Trajkovic, Julia Kaltenborn et al. (+4 more)
Machine learning (ML) emulators provide a fast and cost-effective method to simulate
climate change scenarios after being trained on Earth System Models projections. However, the black-box nature of those data-driven approaches limit the usability and trustworthiness of their outputs and in particular their use as causal attribution tools. Here, we develop a hierarchical causal representation learning framework applied to sea surface temperature fields from a state-of-the-art global
climate model. As a key advance over previous work, our framework explicitly models both atmospheric dynamical interactions arising from internal
climate variability and forced responses due to changes in atmospheric greenhouse gas and aerosol concentrations. When trained on future
climate change scenarios, our method accurately predicts the long-term global mean and regional temperature
evolution and shows physically realistic responses to perturbations in greenhouse gas and aerosol concentrations when evaluated on unseen scenarios. Our results underline the potential of causal representation learning frameworks for advancing
climate model emulation.
Read the full abstract ▾
All authors Shan Zhao, Ilija Trajkovic, Julia Kaltenborn, Yaniv Gurwicz, Peer Nowack, David Rolnick, Julien Boussard
Machine Learning
Does Uniform Discrete Diffusion Need Time?
Chunsan Hong, Chieh-Hsin Lai, Satoshi Hayakawa et al. (+3 more)
Uniform discrete
diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this paper, we first show that the population-optimal UDM predictor generally depends on time: time controls how much the model should trust the observed context. We then show that this dependence can become negligible in finite-data settings relevant to
language. When a corrupted training sequence remains much closer to its original clean sequence than to competing training sequences, the empirical-optimal predictor is nearly insensitive to time over most of the
diffusion trajectory, where the guarantee weakens toward the high-noise endpoint. Empirically, trained
language UDMs exhibit limited time sensitivity over most of the trajectory, while time-agnostic predictors remain competitive with, and often outperform, time-conditioned models across
datasets and training objectives. These results challenge the use of explicit time conditioning in UDMs: although the population optimum depends on time, explicitly conditioning on it may often be unnecessary in practice.
Read the full abstract ▾
All authors Chunsan Hong, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Jong Chul Ye, Yuki Mitsufuji
Machine Learning · Cross-listed from eess.AS
A Comprehensive Study of Content Representations for Speech Synthesis
Diego Torres, Axel Roebel and Nicolas Obin
Speech content representations are central to voice conversion,
speech-to-
speech translation, and
multimodal language models, yet they are rarely compared under a common generative framework that directly measures what each representation contains. We address this by training a generative model conditioned solely on each representation and evaluating the generated audio along the content, speaker identity, and prosody axes. Across SSL features, supervised
tokens, posteriorgrams, and neural audio codecs, we find two distinct regimes: representations that nearly reconstruct the original audio, and representations that effectively disentangle speaker identity. These results show that disentanglement depends not on supervision alone, but on the interaction between the training objective and the representation's information capacity: supervised representations only disentangle speaker identity when their capacity is sufficiently constrained.
Read the full abstract ▾
Machine Learning
LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers
Natsuki Yoshino, Ren Uchida, Kazuki Matsumoto et al. (+1 more)
Lipschitz continuity is a fundamental principle in the design of certifiably robust deep neural networks (DNNs), wherein adjusting the Lipschitz constant, which quantifies network robustness, is of central theoretical importance. A standard approach to enforcing Lipschitz continuity requires each layer of a DNN to be Lipschitz continuous, thereby guaranteeing overall Lipschitz continuity. However, this layer-wise approach typically imposes overly conservative restrictions by producing a loose estimate of the overall Lipschitz constant, which limits the expressive capacity of the DNN and degrades empirical performance at a prescribed level of robustness. To overcome this loose estimation, the recently proposed LipKernel transfers information across layers to yield a much tighter overall Lipschitz bound than conventional layer-wise construction. In this paper, we extend this concept to cascaded state-space models (SSMs) to construct Lipschitz-continuous DNNs capable of modeling longer-term dependencies. The proposed architecture, named LipSSM, is theoretically justified and empirically evaluated.
Read the full abstract ▾
All authors Natsuki Yoshino, Ren Uchida, Kazuki Matsumoto, Kohei Yatabe