Machine Learning
Limits of spectral learning under noise
Sabin Roman, Ljupco Todorovski, Saso Dzeroski et al. (+2 more)
Learning functional relationships from noisy data is a central problem in scientific inference. Spectral methods approximate unknown functions by expanding them in a basis and estimating the corresponding coefficients from data, but the stability of these coefficients under noise remains poorly understood. Here we study supervised regression with additive label noise using sparse spectral representations across multiple bases and dimensions. We show that noise induces a predictable drift in the learned coefficient vector whose magnitude depends on the effective number of active spectral modes. After whitening the empirical feature geometry, we derive a closed-form expression for the overlap between noisy and noiseless coefficient vectors, revealing a universal degradation curve governed by a single intrinsic noise scale. Numerical experiments across
Fourier, Legendre, Bessel, and Haar bases confirm the theoretical prediction. The results demonstrate that spectral learning exhibits a fundamental noise threshold beyond which coefficient estimates become unstable, placing intrinsic limits on recovering functional structure from noisy data.
Read the full abstract ▾
All authors Sabin Roman, Ljupco Todorovski, Saso Dzeroski, Marta Sales-Pardo, Roger Guimera
Machine Learning
A green solvent screening tool for emerging materials via uncertainty aware, transformer enhanced transfer learning
Ioannis Kouroudis, Simon Ternes, Zhaosu Gu et al. (+5 more)
Accurate prediction of solubility remains a central challenge across materials science and sustainable chemistry. In particular due to emerging technologies like organic and hybrid photovoltaics, batteries, and catalysis, solvent usage is expected to increase significantly within the coming years. Therefore, substituting solvents with greener alternatives is vital. This is where machine learning can have substantial impact. However, the limited data on critical parameters of solubility significantly constraints machine learning efficacy. In this work, we transfer a pre-trained foundational model on QM9 targets to our application with minimal data requirements. Additionally, the pipeline integrates uncertainty quantification, allowing the user to gauge the confidence of the predictions. As baseline, we succeed in predicting the Hansen solubility parameters and Dielectric Constant for which extensive databases exist. Importantly, we achieve high model performance on additional targets, such as Gutmann Donor and Acceptor numbers, where the available data is extremely limited. Overall, we augment data on solubility descriptors by orders of magnitude with high quality predictions. For effective dissemination, we deploy easy-to-use, easily integrateable with high throughput labs, customizable tool for ranking and screening possible solvent substitutes. Finally, we rediscovered known green solvent alternatives and proposed new candidates proving its relevance for finding eco-friendly solvents.
Read the full abstract ▾
All authors Ioannis Kouroudis, Simon Ternes, Zhaosu Gu, Gohar Ali Siddiqui, Marina Ustinova, Angelo Lembo, Alessio Gagliardi, Aldo Di Carlo
Machine Learning
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
Zhixiong Zhao, Zukang Xu, Zhixuan Chen et al. (+3 more)
Large
language models (LLMs) exhibit exceptional general
language processing capabilities, but their
memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression and 4-bit activation quantization while maintaining high accuracy. TWLA comprises three components: (1) Euclidean-to-
Manifold Asymmetric Ternary Quantizer (E2M-ATQ) minimizes layer-output error under weight ternarization via a two-stage optimization from Euclidean initialization to
manifold relocation; (2) Kronecker Orthogonal Tri-Modal Shaping (KOTMS) applies a Kronecker-structured orthogonal rotation to reshape weights into ternary-friendly tri-modal distributions, while the shared rotation statistically suppresses activation outliers; and (3) Inter-Layer Aware Activation Mixed Precision (ILA-AMP) explicitly introduces adjacent-layer second-order interaction costs in bit allocation and jointly optimizes for the layer-wise disparity of activation quantization gains induced by the shared orthogonal transform, preventing cascades triggered by a few weak layers. Extensive experiments demonstrate that TWLA maintains high accuracy under W1.58A4, while delivering significant inference acceleration. The code is available at https://github.com/Kishon-zzx/TWLA.
Read the full abstract ▾
All authors Zhixiong Zhao, Zukang Xu, Zhixuan Chen, Xing Hu, Zhe Jiang, Dawei Yang
Machine Learning · Cross-listed from cond-mat.dis-nn
A solvable model for unsupervised federated learning
Giovanni Catania, Aurélien Decelle, Gianluca Manzan et al. (+2 more)
We introduce a theoretical framework for analyzing
federated learning in a generative setting through a teacher-multiple interacting students scenario, in which each student receives a distinct realization of the data, either through a different noise corruption or by accessing a different subset, possibly of varying size. Using theoretical tools in
equilibrium disordered system, we analytically show that interactions among students systematically enhance learning performance: highly noisy students require fewer samples to recover the underlying pattern, while low-noise students achieve a larger overlap with the ground-truth signal. We derive the optimal
Bayesian conditions for teacher recovery as functions of the sample complexity, noise level, and interaction strength, and validate these predictions through numerical simulations. The resulting dynamics can be mapped onto
equilibrium sampling in a Restricted Boltzmann Machine with a structured hidden layer, providing a principled theoretical understanding of how interactions improve distributed generative modeling.
Read the full abstract ▾
All authors Giovanni Catania, Aurélien Decelle, Gianluca Manzan, Beatriz Seoane, Daniele Tantari
Machine Learning
CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
Bo Liu, Di Dai, Jingwei Liu et al. (+5 more)
Granger Causal Discovery (GCD) is fundamental for analyzing temporal dependencies in complex systems. However, existing neural GCD methods predominantly rely on a "one-size-fits-all" paradigm, struggling to capture distribution shifts and dynamic regime changes inherent in real-world time series. This often leads to entangled representations and spurious causal graphs. In this paper, we propose CausalMoE, a billion-scale
multimodal Granger causal foundation model that explicitly models patch-level heterogeneity. CausalMoE introduces a Pattern-Routed Mixture of Heterogeneous Experts, which dynamically identifies latent temporal patterns and routes patches to specialized domain experts, effectively decoupling regime-specific mechanisms from shared dynamics. To ensure interpretable graph recovery, we design a Causality-Aware Self-
Attention mechanism operating across variables, yielding sparse Granger causal graphs via proximal optimization. Furthermore, CausalMoE is the first to integrate LLMs and VLMs to align numerical signals with textual and visual priors, regularizing causal estimation in complex scenarios. Extensive experiments demonstrate that CausalMoE establishes a new state-of-the-art on fully supervised
benchmarks, while effectively generalizing to few-shot settings where traditional methods fail.
Read the full abstract ▾
All authors Bo Liu, Di Dai, Jingwei Liu, Jiarui Jin, Xiaocheng Fang, Guangkun Nie, Hongyan Li, Shenda Hong
Machine Learning · Cross-listed from cs.CV
Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition
Ziyi Chang, Kanglei Zhou, Xiaohui Liang et al. (+1 more)
Adversarial attacks on skeletal human action recognition have received significant
attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently perceptible with recent advancements in S-HAR systems. We discover that this degradation stems from the gap between empirical and true risks during the optimization process of previous
adversarial attacks. To address this issue, we propose an attack where
adversarial motions are obtained without compromising their motion quality. To minimize the risk gap and preserve motion quality, we propose a distribution-based
adversarial attack method without introducing noise-like perturbations. To faithfully evaluate the motion quality, we propose a new metric that aligns with human perception on real-world naturalness. Experiments have been conducted on the state-of-the-art S-HAR methods across two
datasets, demonstrating the superiority of our method in both the attack success rate and the post-attack motion quality through qualitative and quantitative analyses. The success of our quality-preserving attack application and distribution-based method raises serious concerns about the robustness of action recognizers, highlighting the need for further enhancements in this domain.
Read the full abstract ▾
All authors Ziyi Chang, Kanglei Zhou, Xiaohui Liang, Hubert P. H. Shum
Machine Learning · Cross-listed from q-bio.NC
Deep Sleep Classification via EEG Signal Criticality: A Passive BCI Approach for Sleep-Improvement Neurofeedback
Stanisław Narębski, Tomasz Komendziński and Tomasz M. Rutkowski
Automated sleep staging is a fundamental application of passive
Brain-Computer Interfaces (pBCI), decoding spontaneous neural states to enable closed-loop interventions independent of user intent. This study evaluates criticality features derived from Detrended Fluctuation Analysis (DFA) for the specific identification of deep sleep (N3). We analyzed $347,232$
EEG epochs from $290$ older women using UMAP
manifold learning to visualize state transitions. Subsequently, six classifiers were benchmarked via 10-fold cross-validation, using balanced accuracy to determine the optimal "state-sensing" engine for neurofeedback.Naive Bayes achieved the highest mean balanced accuracy ($87.17\% \pm 0.24\%$), significantly outperforming a fully connected deep neural network (FNN: $81.58\%$) and Random Forest ($80.97\%$). Linear models (LDA: $57.21\%$; SVM: $51.01\%$) performed poorly, indicating that DFA-derived criticality features reside on a distinct, non-linear
manifold. Probabilistic decoding of
EEG criticality provides a high-accuracy sensing mechanism for pBCIs. This robust classification pipeline supports the development of state-dependent neurofeedback, such as targeted auditory stimulation, to enhance cognitive recovery.
Read the full abstract ▾
Machine Learning
scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing
Ping Xu, Pengjiang Li, Tian Du et al. (+6 more)
Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying
cell populations and resolving tissue heterogeneity. However, existing methods focus on mining numerical statistical patterns, suffering from semantic agnosticism by neglecting the intrinsic biological functions encoded by genes. While Large
Language Models (LLMs) offer promising semantic capabilities, their direct adaptation to
cell clustering is hindered by the structural mismatch between generative pre-training objectives and discriminative downstream tasks. To bridge this gap, we propose scLLM-DSC, a novel LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering framework. Diverging from data-driven paradigms, scLLM-DSC establishes a semantically-grounded representation by synergizing two views: a Knowledge-Driven Semantic View derived from NCBI gene priors and contextualized
Cell2Sentence
embeddings, and a Structure-Aware Topological View extracted via a graph-guided encoder. Crucially, we introduce a cross-modal contrastive
alignment mechanism to enforce consistency between biological semantics and transcriptomic features within a unified latent space. Extensive
benchmarks demonstrate that scLLM-DSC significantly outperforms eleven state-of-the-art baselines in clustering accuracy.
Read the full abstract ▾
All authors Ping Xu, Pengjiang Li, Tian Du, Zaitian Wang, Jiawei Gu, Zhiyuan Ning, Ziyue Qiao, Pengfei Wang, Yuanchun Zhou
Machine Learning
Reliability of Probabilistic Emulation of Physical Systems
Sam F. Greenbury, Radka Jersakova, Paolo Conti et al. (+5 more)
Two dominant approaches have emerged for generating probabilistic forecasts of physical systems: generative models, such as
diffusion or flow matching; and ensembles of deterministic models with stochasticity injected, trained using the continuous ranked probability score (CRPS) loss. While both approaches have demonstrated strong predictive accuracy, the reliability of their uncertainties has not been systematically assessed. We address this gap by developing a framework to evaluate both approaches across diverse 2D spatiotemporal physical systems, under matched model size and computational budget. We assess the reliability of probabilistic emulation by inspecting the empirical coverage of predictive intervals, while also considering accuracy and computational efficiency metrics. CRPS-trained ensembles typically achieve more reliable uncertainties on both single-step prediction and autoregressive rollouts, demonstrating better coverage than the standard alternative of training generative models in a latent space. Moreover, the CRPS approach offers significantly faster inference. When generative models are trained in ambient rather than a compressed latent space, which is often infeasible for high-dimensional problems, they exhibit comparable coverage to CRPS-trained ensembles, though with substantially larger inference latency. In contrast, when CRPS-trained ensembles are trained in latent space they do not show a marked degradation in coverage with respect to ambient space. Both generative models and CRPS-trained ensembles demonstrate good predictive accuracy. To facilitate future research and application, we release AutoCast, a modular framework implementing both generative models and CRPS-trained ensembles, alongside AutoSim, a flexible
dataset generation package for rapid prototyping.
Read the full abstract ▾
All authors Sam F. Greenbury, Radka Jersakova, Paolo Conti, Marjan Famili, Christopher Iliffe Sprague, Edwin Brown, Farhan Feroz, Jason D. McEwen
Machine Learning
DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation
Soyoung Yoo, Leekyo Jeong, Jinsu Ra et al. (+4 more)
Data-driven engineering design is constrained by the lack of large-scale 3D
datasets that pair geometry with physics-based performance labels. In particular, existing 3D data augmentation techniques have limitations in preserving subtle and diverse
geometric variations, and it remains difficult to automate the subsequent simulation-labeling process, where boundary conditions vary depending on the generated geometry. We present DeepJEB++, a foundation-model-driven data-augmentation framework that expands a small seed set of jet engine brackets into a large, simulation-labeled 3D
dataset under constrained resources. Our key idea is to augment in the data-rich 2D latent space, then transfer to 3D. In Stage 1, we fine-tune a pretrained 2D latent
diffusion model on multi-view renders and synthesize novel views by latent interpolation, retaining manufacturable designs through a
vision-
language-model (VLM) quality filter. In Stage 2, the validated images are lifted to 3D meshes by a domain-adapted generative foundation model. In Stage 3, an automated pipeline recognizes the load and bolt interfaces on each mesh and assigns finite-element labels – mass, stress, and displacement – without manual intervention. We assess augmentation quality along three intrinsic axes: manufacturability, label fidelity against the SimJEB ground truth, and distributional consistency. Starting from fewer than 400 seed designs, DeepJEB++ yields 15,360 simulation-labeled 3D brackets – a 40x expansion – using a single GPU per stage. The
dataset will be made publicly available to support reproducible engineering-AI research.
Read the full abstract ▾
All authors Soyoung Yoo, Leekyo Jeong, Jinsu Ra, Dongeon Lee, Sunwoong Yang, Hyogu Jeong, Namwoo Kang
Machine Learning
Exposure Bias as Epistemic Underidentification in Recursive Forecasting
Riku Green, Zahraa S. Abdallah and Telmo M Silva Filho
Recursive multi-step
forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is incomplete by proving that, under partial observability or state truncation, recursive rollout is also an epistemic underidentification problem. Even with deterministic latent dynamics, one-step Bayes supervision identifies behavior only on observed contexts and need not identify the deployed recursive predictor once rollout queries self-generated induced states whose correct local targets are not determined by numeric state alone. We formalize this with induced states $Z$ and provenance variables $P$, and derive a decomposition of induced-state error into teacher-forcing/rollout mismatch, representation–class approximation, and provenance information gaps. Empirically, we show that rollout enters a distinct induced-state regime, that fixed induced states define a distinct local corrective task, and that closed-loop gains arise not only from local adaptation but also from changing the induced states visited during rollout. Using a simple binary provenance encoding, provenance-aware correction can further improve performance, though gains are conditional rather than uniform. These results recast exposure bias as
reasoning under self-induced epistemic uncertainty.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Diffusion Transformer World-Action Model for AV Scene Prediction
Ruslan Sharifullin, Benjamin Jiang and Kai Xi Chew
Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to $256 \times 256$ frames up to 8 seconds ahead, evaluated on 150 held-out nuScenes scenes. We first
benchmark where to predict: across six frozen encoders spanning four representation families, V-JEPA2 with temporal context reduces steering RMSE by 40% over the best single-frame encoder. We then train a latent
Diffusion Transformer (DiT) and, through a controlled diagnosis, identify the four ingredients it needs: spatial
tokens, the $x_0$ objective, residual anchoring, and sampling matched to target uncertainty. In a Stable-
Diffusion-VAE encode-predict-decode pipeline we expose the central tension: distortion metrics (cosine similarity, SSIM) favor the blurry mean, masking that the
diffusion model is far closer to the real frame distribution. Inception-based FID and KID reveal a clean perception-distortion frontier:
diffusion attains KID 0.078 versus 0.375 for regression ($4.8\times$ better), and a deployable train-derived calibration makes this practical without test-time ground truth. The model is genuinely action-controllable (steering drives scene displacement, Spearman $\rho = 0.81$, vs $-0.18$ for regression). We trace limited single-pass motion to a shared-present anchor and engineer a compact 1.7M-parameter "jump" model that recovers full ground-truth motion magnitude ($1.02\times$ GT), where single-pass models capture less than half.
Read the full abstract ▾
Machine Learning
EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models
Vedant Pandya
JEPA-family world models use a static predictor whose weights do not adapt when test-time dynamics diverge from training. We compare two mechanisms for incorporating accumulated experience into a JEPA predictor under distribution shift: operand-side injection, where a compressed experience representation is added as a residual to the predictor's hidden state (EI-JEPA), and operator-side modulation, where the same representation generates low-rank weight deltas via LoRA applied to the predictor's weights (EPM-JEPA). On a pre-registered comparison (Moving MNIST,
gravity shift), EPM-JEPA (D_shift^{n=50} = 0.7848 +/- 0.0078, three seeds) differs from EI-JEPA (0.8238) by delta = 4.74% - Outcome C: a null result - by our stated criterion, a valid outcome. As a secondary, non-pre-registered observation, EPM-JEPA improves 1.90% over a no-
memory baseline (0.8000), consistently across seeds, while EI-JEPA underperforms the baseline, indicating the benefit is specific to weight-level modulation. Our primary contribution is a mechanism analysis: the D_shift^{n=50} trajectory reflects three independent dynamical processes - buffer cycling, EMA target drift, and an intrinsic LoRA settling transient of +0.021 - rather than convergence to
equilibrium. These findings motivate PEM-JEPA, a physics-grounded successor addressing this dynamical-peak limitation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
Jianwei Fei, Yunshu Dai, Zhihua Xia et al. (+4 more)
Model fingerprinting,
embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rights (IPR) of generative text-to-image (T2I) models and prevent unauthorized redistribution. In this work, we reveal a previously unexplored systematic vulnerability in existing generative model fingerprinting methods: they lack robustness against collusion attacks, where multiple attackers combine their models to remove or obscure the fingerprints. To address this issue, we take the first step towards a robust fingerprinting method for T2I models with anti-collusion capabilities. The proposed method encodes strings of bits, namely fingerprints, into the coefficients of a personalized normalization module (PNM) incorporated into T2I models, so that fingerprints can be reliably recovered from any generated image. To defend against collusion attacks and prevent unauthorized model redistribution, we introduce an anti-collusion mechanism based on lossless function-invariant parameter transformations. This mechanism significantly degrades the image generation quality of colluded models, making them effectively unusable. Moreover, our method allows developers to efficiently create multiple copies of fingerprinted T2I models by reparameterizing the PNM without the need for retraining. We also introduce a worst-case optimization strategy to improve robustness against model-level attacks. Our experiments demonstrate that the proposed method achieves high fidelity and robustness across multiple T2I image generation and editing tasks, with fingerprint extraction accuracy exceeding 99.5%. Compared with existing methods, our method demonstrates, for the first time, a notable proactive robustness to collusion attacks by significantly increasing the FID of colluded models.
Read the full abstract ▾
All authors Jianwei Fei, Yunshu Dai, Zhihua Xia, Xiaochun Cao, Jiantao Zhou, Alessandro Piva, Benedetta Tondi
Machine Learning
Predicting Cognitive Load from Speech and Interaction Dynamics in Dyadic Conversations
Tahiya Chowdhury
Estimating cognitive load from
speech has largely been studied in controlled laboratory settings, with limited understanding of its reliability in natural collaborative conversations. We investigate whether
speech and interaction dynamics predict perceived cognitive load during dyadic conversations. We analyze audio from 53 dyads performing nine collaborative tasks and extract static acoustic, dynamic, and interaction features to train a two-head Gated Recurrent Unit encoder to predict cognitive load scores. Results show conversational interaction provides useful signals for predicting cognitive load related to time pressure, mental work, effort, and task performance. Temporal demand is associated with turn-taking dynamics such as overlap and speaker switch, while mental demand is linked to imbalanced participation between speakers. These findings highlight the importance of task structure and conversational interaction for modeling cognitive load in natural collaborative settings.
Read the full abstract ▾
Machine Learning
Learned Structure Shows Up Earlier in the Task's Own Basis: A Controlled Look at a Synchronisation Precursor in Grokking
Achyuthan Sivasankar
Analyses of grokking usually read hidden activations in one basis, most often the
Fourier basis modulo $p$. We ask how much the answer to "has the network organised yet?" depends on that choice. The measure FSD$_{\rm gen}$ averages each unit's activation over inputs with the same answer and counts how many units share the same strongest irreducible representation. For modular multiplication we read one answer-averaged profile in three orders: discrete-logarithm order, in which the characters of the multiplicative group become
Fourier modes; natural order; and random orders. Across 60 networks at $p\in\{59,97,113\}$, the discrete-log reading reached a fixed threshold before both other readings in 60 of 60 networks (59 of 60 when it had to hold 500 steps). Because untrained networks already score higher in discrete-log order, we also required an equal rise above each reading's untrained level; the discrete-log reading was still first in at least 16 of 20 networks at every
prime. At $p=59$ and $p=97$ this happened during the memorisation plateau in 35 of 39 networks; at $p=113$ in 12 of 20. Memorisation preceded grokking in all 179 runs that grokked, by more than any synchronisation signal on average, so a lead over grokking is not by itself evidence of a detected
circuit. Synchronisation time is only weakly related to grokking time (pooled $\rho=0.18$). On six finite groups, read with the same measure in every basis, the irreducible-representation reading came before random element orders on all six; with equal-rise thresholds this held in every case on four groups, in 7 of 10 on $\mathbb{Z}_5\times\mathbb{Z}_5$ and in none on $D_{16}$, where about half the profile power lies in one-dimensional representations the measure leaves out. We also correct a conjugate-pair artefact that roughly halves the measure on abelian groups. This version withdraws the causal and predictive claims of v1.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
OpenMedQ: Broad Open Pretraining for Medical Vision-Language Models
Ibrahim Gulluk, Max Van Puyvelde and Olivier Gevaert
We present OpenMedQ, a medical
vision-
language model pretrained on the broadest fully-open medical mix to date: 14
datasets totaling ~3.35M pretraining samples spanning pathology, radiology, microscopy, and text-only clinical QA. OpenMedQ reaches state-of-the-art BLEU-1 on PathVQA (75.9), beating Med-PaLM M variants up to 562B parameters (~80x larger), and matches the best reported VQA-MED BLEU-1 (64.5). Its
vision encoder, transferred to 8 unseen medical classification
benchmarks under an identical downstream recipe, obtains the highest average macro-F1 (0.757) among BiomedCLIP (0.745), PMC-CLIP (0.745), PubMedCLIP (0.746), and a from-scratch baseline (0.616). We release our code and an interactive demo is publicly available as a reproducible baseline for the community.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
Xiang Li, Yixuan Zhou, Jingran Xie et al. (+2 more)
Neural
speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for
speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Modifying the quantizer or increasing model capacity are common fixes, but they complicate downstream
language modeling. Our core idea is to align the decoder's internal feature
manifolds when processing both the quantized
tokens and their original continuous
embeddings, using a lightweight feature-mapping loss. This requires minimal training overhead and no inference-time changes. Applied to XCodec2, self-guidance improves all reconstruction metrics, achieving state-of-the-art low-bitrate performance. Notably, it enables a 4x codebook reduction without fidelity loss, which downstream TTS experiments show significantly improves LLM-based synthesis by simplifying the
token modeling space. Multiple statistical observations and visualizations corroborate the enhanced internal
manifold alignment in the decoder. Extensive experiments confirm its generality across various inductive biases. Self-guidance thus establishes an efficient, broadly applicable method for high-fidelity neural audio coding.
Read the full abstract ▾
All authors Xiang Li, Yixuan Zhou, Jingran Xie, Zhiyong Wu, Hui Wang
Machine Learning
Is Spurious Correlation Removal Always Learnable?
Yibo Zhou, Bo Li, Hai-Miao Hu et al. (+3 more)
Invariant learning can fail even when the invariant structure is statistically identifiable. We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive motivated by average-case sparse-recovery reductions, there exist samplable multi-environment instances with a one-dimensional predictive invariant subspace ($k=1$) that are learnable with
polynomial samples by exhaustive search, while any
polynomial-time constant-accuracy recovery
algorithm would contradict the primitive. We further quantify environment diversity by a separation parameter $\gamma$, which controls identifiability and the
curvature of invariance objectives. Under sufficient diversity and local Gaussian regularity, the minimax risk is $\mathbb{E}[\dist(\hat{V},V_{\mathrm{inv}})^2]=\Theta(k(d-k)/(n|\mathcal{E}|))$, and under label-induced shifts a phase transition occurs at $n^*\propto k(d-k)/(|\mathcal{E}|\gamma^2)$ with refined estimation error scaling proportional to $1/\gamma^2$. Synthetic and real
datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.
Read the full abstract ▾
All authors Yibo Zhou, Bo Li, Hai-Miao Hu, Hanzi Wang, Xiaokang Zhang, Ruifan Zhang
Machine Learning · Cross-listed from cs.CV
Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Qiru Li, Ao Zhou, Zhiwei Jiang et al. (+4 more)
Multi-label recognition with frozen
Vision-
Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce
Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned
Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label
benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.
Read the full abstract ▾
All authors Qiru Li, Ao Zhou, Zhiwei Jiang, Zifeng Cheng, Cong Wang, Yafeng Yin, Qing Gu
Machine Learning
Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems
Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi et al. (+2 more)
AI
alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects. We argue that order is not control. Control requires a receiver-gated response law: a denominator-indexed operator mapping material state, action/drive, bath, and receiver state to response displacement, sinks, effort, and basin projection. We identify it across biological, LLM, adapter, and
stochastic-operator panels. The laws are local: an intervention can be admitted, saturated, sign-changing, leaky, or overdriven depending on medium, bath, receiver state, action port, and comparator. Control is assigned when finite effort moves a target or outcome-readout class under the same denominator while damage, null/evasive, invalid format, overdrive, and unnecessary effort stay bounded. Mouse ALM, C. elegans, and zebrafish panels provide physical response-operator evidence while excluding coordinate identity and controller conclusions. LLM panels show generated-output response laws: across four material conditions, response vectors are predictable at 72.8-73.7% component-sign accuracy, rising to 84.3-84.8% on nonzero components; held-out observers predict system-effect and target/oracle families at 93.6% and 91.7% accuracy. Constitution-conditioned adapters reshape susceptibility as prepared media, and
stochastic-operator panels separate measured opportunity from deployable action policies. This gives a driven-dissipative response-system account at the mesoscopic control level: drives act through prepared media, baths, and receivers, producing admitted movement, impedance, sinks, or overdrive. The evidence supports local admitted control and measurable
stochastic response operators, while leaving deployable pre-generation control, hidden/logit causal sufficiency, biological-to-LLM coordinate identity, and literal thermodynamic quantities outside scope.
Read the full abstract ▾
All authors Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi, Jeffrey Molendijk, Tim Elson
Machine Learning
LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold
Franz Louis Cesista, Katherine Crowson, Cédric Simal et al. (+1 more)
Low-Rank Adaptation (LoRA) significantly reduces compute and
memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines. We derive LoRA-
Muon by applying the
Muon optimizer's spectral steepest-descent rule to the low-rank setting. Along with our split weight-decay rule, our main claim is that LoRA-
Muon is a good low-rank proxy for full-rank
Muon and Shampoo-family optimizers. Its optimal learning rates transfer across rank, width, depth, and factor-rescaling. In our compute-matched TinyShakespeare study, a rank-$2$ proxy recovers the dense best tested learning rate, and a rank-$32$ LoRA-
Muon run attains lower mean validation loss than the dense baseline in the seed-averaged sweep. We further show that the Spectron optimizer depends on arbitrary factor scaling, so it would likely be a poor fit when finetuning starts from badly imbalanced factors, and that LoRA-RITE's simplified QR-coordinate core implements the same spectral update. LoRA-
Muon computes that update without QR-decomposition and avoids storing second moments, making it more accelerator-friendly and
memory-efficient.
Read the full abstract ▾
All authors Franz Louis Cesista, Katherine Crowson, Cédric Simal, Stella Biderman
Machine Learning
Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function
Atharva Gupta, Dhruv Kumar, Murari Mandal et al. (+1 more)
We present the first causal mechanistic analysis of a tabular foundation model, investigating how TabPFN 2.5's feature wise
attention heads distribute computation across layers. Using activation patching, ablation, and
attention entropy across two synthetic regression
datasets, we find clear temporal specialisation: one head's causal necessity dominates that of the others by 2 to 5 times at peak layer, with its dominant layer shifting across tasks of different complexity, while the remaining heads exhibit symmetric late layer profiles.
Attention entropy and patching provide convergent evidence for the computationally active layers of the dominant head. We additionally investigate inference time steerability via contrastive activation steering, which fails to transfer across samples. We attribute this result to TabPFN's in context learning mechanism, which encodes task structure through context dependent
attention rather than the stable parametric directions that make steering tractable in
language models.
Read the full abstract ▾
All authors Atharva Gupta, Dhruv Kumar, Murari Mandal, Saurabh Deshpande
Machine Learning · Cross-listed from cs.AI
MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback
Zehong Wang, Yijun Ma, Connor R. Schmidt et al. (+7 more)
Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error. We automate this expert pipeline-design process with an LLM
agent. Unlike existing MD
agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the
agent's behavior is reshaped online by verbal reward. Specifically, we build MDForge, an LLM
agent whose in-context update rule densifies the sparse reward via a multi-
agent debate among physics experts. On three SAMPL host-guest binding free-energy
benchmarks, MDForge automatically designs MD pipelines competitive with human experts. Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder. Our data and code are available at https://github.com/Zehong-Wang/MDForge.
Read the full abstract ▾
All authors Zehong Wang, Yijun Ma, Connor R. Schmidt, Tianyi Ma, Weixiang Sun, Ziming Li, Xiaoguang Guo, Chuxu Zhang, Matthew J. Webber, Yanfang Ye
Machine Learning
Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
Dongyue Wu, Zilin Guo, Xiaoyu Li et al. (+4 more)
The rapid growth of modern training
datasets has significantly increased computational cost, motivating
dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost. Existing
pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations. While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different
pruning ratios or data distribution. In this work, we present a unified graph-based DP framework. By modeling the
dataset as a weighted graph, where node weights encode intrinsic value and edge weights encode extrinsic value, DP can be cast as a Maximum Weight Clique Problem (MWCP). Although MWCP is NP-hard, its structure admits a principled greedy solution based on sample-wise marginal gains. Under a few mild conditions, we further prove that this unified objective enjoys a formal approximation guarantee, which applies to a broad family of importance metrics and provides practical design guidelines. Extensive experiments show that our method outperforms existing DP methods while substantially reducing training cost, reducing training time by over 40% without sacrificing accuracy on ImageNet-1k with ResNet-50.
Read the full abstract ▾
All authors Dongyue Wu, Zilin Guo, Xiaoyu Li, Jiajia Liu, Jingdong Chen, Nong Sang, Changxin Gao
Machine Learning · Cross-listed from cs.AI
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
Jiahao Yang, Shuhai Zhang, Hailong Kang et al. (+3 more)
Large
language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content, posing significant risks to their safe use. Detecting such
hallucinations is particularly challenging under the zero-source constraint, where no model internals or external references are available, and detection must rely solely on the textual query-answer pair. In this paper, we propose Human-like Criteria Probing for
Hallucination Detection (HCPD), a paradigm that emulates the multi-faceted
reasoning of human evaluators. Its core is a Human-like Criteria Probing (HCP) mechanism, in which a LLM
agent adaptively decomposes its judgment into a weighted set of interpretable criteria and aggregates criterion-specific scores into a final truthfulness measure. To achieve this adaptive capability, we introduce a reward-based
alignment scheme using only weak supervision from semantic consistency. At inference, we employ a multi-sampling aggregation strategy to ensure robust decisions while preserving full interpretability. We further provide theoretical analysis supporting the reliability of our approach. Extensive experiments show that HCPD consistently outperforms state-of-the-art baselines, offering an effective and explainable solution for zero-source
hallucination detection. Code is available at https://github.com/TRISKEL10N/HCPD.
Read the full abstract ▾
All authors Jiahao Yang, Shuhai Zhang, Hailong Kang, Feng Liu, Qi Chen, Mingkui Tan
Machine Learning
PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent
Junfeng Guo Heng Huang
While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more
attention and exploration. In particular, recent work has revealed that RL
agents are vulnerable to
backdoor attacks, where a victim
agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing
backdoor defenses for RL either require access to the
agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL
agents, we propose PolicyGuard, a test-time step-level
backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-
agent attacks.
Read the full abstract ▾
Machine Learning
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
Xinrui He, Qiyu Kang, Xuhao Li et al. (+1 more)
Spiking Neural Networks (SNNs) are well-regarded for their biological plausibility and energy efficiency in processing sequential data. However, dominant SNN architectures typically rely on first-order Ordinary Differential Equations (ODEs) to govern neuronal state transitions. This first-order assumption imposes a "memoryless" bottleneck, limiting the model's capacity to capture the complex, long-range dependencies inherent in long-sequence tasks. In this work, we propose LongSpike, a novel SNN framework that integrates fractional-order State-Space Modeling, or f-SSM, from control theory into the spiking domain. By extending traditional integer-order SSMs to the fractional-calculus regime, LongSpike enables the hierarchical integration of neuronal dynamics with long-
memory kernels. To mitigate the computational overhead and parallelization challenges typically associated with fractional operators, we leverage a state-space formulation that supports efficient, parallel training. Empirical evaluations on challenging
benchmarks, including Long Range Arena (LRA), large-scale WikiText-103, and
Speech Commands, demonstrate that LongSpike outperforms state-of-the-art SNNs in accuracy while preserving sparse synaptic computation. The code is available at https://github.com/xinruihe389-commits/LongSpike.
Read the full abstract ▾
All authors Xinrui He, Qiyu Kang, Xuhao Li, Zheng-Jun Zha
Machine Learning · Cross-listed from stat.ML
Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression
Masahiro Kato
This study investigates semiparametric efficient estimation of causal and structural parameters in a semi-supervised setting. In our setting, unlabeled auxiliary regressors are available in addition to labeled observations consisting of outcomes and regressors. Our goal is to construct
estimators of causal and structural parameters whose asymptotic variances are smaller than those of
estimators constructed using only labeled data. We refer to this framework as prediction-powered causal inference (PPCI). We first derive the efficient influence function and the efficiency bound, which imply that the use of auxiliary regressors can attain a smaller asymptotic variance than the efficiency bound attainable from labeled observations alone. Then, by combining the efficient influence function with the debiased machine learning (DML) framework, we propose methods that we call DML-PPCI. If we construct an estimating-equation
estimator, we refer to the method as EE-DML-PPCI; if we construct a targeted-learning
estimator, we refer to the method as TMLE-DML-PPCI. The asymptotic variances of both
estimators match our derived efficiency bound. In the construction of the
estimators, estimation of the efficient influence function plays an important role. In our study, the efficient influence function is also a Neyman orthogonal score, which depends on the Riesz representer and the regression function. For Riesz representer estimation, we develop semi-supervised generalized Riesz regression with convergence rate guarantees.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study
Dezhi Yu, Yvonne Qiu and ShuoJia Fu
We present an approach to fine-tuning large
language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability.
Read the full abstract ▾