Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning

Friday 9 October

Machine Learning

Tabular Foundation Models Are Effectively Shallow

Irene Cannistraci and Julia E. Vogt

In-context-learning Tabular Foundation Models (TFMs) are uniquely suited to scenarios with limited resources or privacy constraints, as they solve new tasks without additional training. However, their architecture consists of multiple transformer blocks, resulting in high computational and memory footprints. Meanwhile, traditional alternatives like Gradient-Boosted Decision Trees (GBDTs) remain highly competitive and run efficiently on CPUs, suggesting that tabular tasks may not inherently require deep architectures. This contrast raises a fundamental question: can TFMs be simplified by removing architectural redundancies without sacrificing performance? To answer this, we introduce a closed-form, label-free affine translator that replaces a contiguous window of up to 96% of the blocks, leaving the rest unchanged. Evaluating eight frontier TFMs on 171 classification datasets, we reveal that tabular transformers are vastly overparameterized: replacing half of a model's blocks costs at most $0.002$ median AUROC across all architectures, with the half-depth TabFM still outperforming every other full-depth TFMs and tuned GBDTs. Furthermore, different model families are overparameterized in different ways: TabPFN-3 relies on its encoders, maintaining performance regardless of which single block is retained. Other single-axis models spread computation thinly, needing only their first block, while dual-axis models concentrate it in one critical block. Ultimately, removing depth saves up to 1.5B parameters, speeds up GPU inference by up to $6\times$ at a median cost of $0.03$ AUROC, while a single-block TabPFN-3 serves cached queries $2.4\times$ faster using $6\times$ less memory at negligible cost.
Read the full abstract

Machine Learning

State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents

Zhentao Zhang, Yanzhao Zheng, Yanlin Liu et al. (+9 more)

On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while extending its success to multi-turn agentic environments remains challenging. We study agentic OPD through interaction states, distinguishing the objective task and executed action-observation record from the internal semantic trajectory of student reasoning. Through this lens, we identify two roles of student reasoning in multi-turn OPD: prior reasoning distorts teacher supervision, while current reasoning shapes the action alternatives sampled at the same state. Specifically, at matched interaction states, removing prior student reasoning improves teacher continuation success and changes the teacher's token-level targets, with larger continuation gains at later turns. Meanwhile, resampling complete reasoning-action responses yields greater action diversity at the same state than resampling actions under a fixed reasoning trace. We introduce State-Grounded On-Policy Distillation, a framework that grounds teacher supervision in interaction states and reallocates the sampling budget to generate multiple complete reasoning-action responses at states with high response entropy, while retaining full-history student generation. Comprehensive evaluations across ALFWorld, ScienceWorld and WebShop demonstrate that State-OPD achieves the highest macro-average success rate among the evaluated methods for both Qwen3-1.7B and Qwen3-4B students. Notably, for Qwen3-4B, State-OPD raises macro-average success from 26.07% with the strongest baseline to 31.74% and surpasses its Qwen3-32B teacher on ALFWorld Seen. Further analyses reveal that State-OPD achieves higher task success with fewer supervised turn responses and substantially reduces persistent failed-action repetition; qualitative traces illustrate decision revision based on interaction feedback.
Read the full abstract

All authors Zhentao Zhang, Yanzhao Zheng, Yanlin Liu, Yuanqiang Yu, Tianze Xu, Chao Ma, Jihuai Zhu, Lelun Wu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu

Machine Learning · Cross-listed from eess.IV

The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging

Fabian Drexel, Bernhard Kainz, Jakob N. Kather et al. (+4 more)

Joint-embedding predictive architectures (JEPAs) learn by predicting teacher representations of masked regions from visible context. Point prediction summarizes the conditional target distribution and cannot reproduce variation that the context does not resolve. We call this constraint predictability bias. In computed tomography (CT), recurrent anatomy is predictable from context, whereas the sporadic, localized pathology that determines clinical interpretation often is not. We introduce TAP-JEPA, a ViT-B/3D trained on 113,611 CT volumes that is competitive with state-of-the-art encoders (COLIPRI, Merlin, VoxelFM) in scan-level classification. We then audit the learned predictive pathway by replaying the exact masking, teacher, and predictor computations used during training. Prediction lowers the mean Skill (prevalence-normalized average precision) from 0.388 to 0.271 for pathology, but only from 0.921 to 0.873 for anatomy. Along the teacher direction, separating pathology from matched control regions in the same organ, prediction moves pathology 34.7% toward the controls and controls 13.6% toward pathology, with larger shifts farther from visible context. Replacing visible matched-control representations increases surrounding-target prediction loss more than fully replacing pathology representations across four pathology categories. Downstream, removing all final-layer pathology tokens reduces the decision margin by at most 0.45% in four of seven scan-level probes. Together, these results show that contextual predictability is not a sufficient proxy for clinical relevance in medical representation learning. Training objectives should therefore retain diagnostic features regardless of their predictability from surrounding anatomy.
Read the full abstract

All authors Fabian Drexel, Bernhard Kainz, Jakob N. Kather, Daniel Rueckert, Lisa C. Adams, Keno K. Bressem, Cosmin I. Bercea

Machine Learning

Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks

Sukru Caglar, Sena Kalabalik, Abdullah Umut Hamzaogullari et al. (+1 more)

Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler–Lagrange equation, providing a variational inductive bias that improves physical consistency over purely data-driven models. LNNs have recently been extended to general relativistic settings, leaving Schwarzschild geodesics as an open challenge. Training on complex relativistic systems is hindered by the diversity of the dynamics, as well as numerical instabilities and the difficulty of adequately sampling physically relevant, diverse orbital regimes. We introduce two coordinated improvements: a decoupled position–velocity normalization scheme that independently rescales each coordinate and its time derivatives, reweighting acceleration targets to balance contributions across all channels; and an energy-constrained log-uniformly sampled dataset generation strategy informed by the innermost stable circular orbit (ISCO) structure. With these improvements, our model accurately reproduces perihelion precession and relativistic time dilation, conserves energy and angular momentum to within a few percent even after completing multiple orbits around the central mass and predicts orbital trajectories across eight orbital scenarios in close, medium, and far-field regimes. These results establish that LNNs, augmented with physically motivated normalization and sampling, can reliably learn geodesic dynamics in curved spacetime. Our work also represents the first successful training of LNNs on Schwarzschild geodesics and offers a promising direction for data-driven modeling of complex relativistic systems.
Read the full abstract

All authors Sukru Caglar, Sena Kalabalik, Abdullah Umut Hamzaogullari, Arkadas Ozakin

Machine Learning

ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation

Xiaohuan Jia, Renzhe Xu, Xiao Wang et al. (+2 more)

Generative modeling for discrete data has been significantly advanced by learning continuous vector fields on the statistical manifolds to transport simple priors to target discrete distributions. However, because these continuous-time flows are not constrained to follow geodesics on the statistical manifold, thereby requiring multi-step numerical integration for simulation and leading to substantial computational costs during inference. In this work, drawing inspiration from the "straight and fast" properties of Rectified Flow in continuous Euclidean space, we propose the Rectified Statistical Flow (ReSFlow) model, which enables one-step categorical generation on statistical manifolds by explicitly learning geodesic trajectories that adhere to the intrinsic Riemannian geometry. By rectifying the flow on the statistical manifold, we theoretically guarantee that trajectories between prior and target distributions approximate geodesics. This rectification significantly reduces the transport cost by aligning the learned trajectories directly along geodesics on the statistical manifold, allowing the model to map pure noise to target discrete data in a single step. Through extensive experiments on diverse real-world generative tasks, ranging from image and text to biological domains, we demonstrate ReSFlow's superior one-step generation quality, which truly embodies geodesically optimal and rapid categorical generation. Our code is available at https://github.com/xiaohuanjia/ReSFlow.
Read the full abstract

All authors Xiaohuan Jia, Renzhe Xu, Xiao Wang, Jiayun Wu, Shaohua Fan

Machine Learning

Tensor-based Fusion of Multi-modal Data for Predicting Cancer Risk Levels

Ali Anaissi, Yuanzhe Jia, Qishun Peng et al. (+3 more)

Cancer diagnosis and treatment increasingly rely on multi-modal diagnostic technologies that generate high-dimensional datasets. Although these datasets are rich in pathological information, they pose considerable challenges in interpretation, dimensionality reduction, and clinical applicability. Conventional machine learning approaches often fail to extract meaningful cross-modal features, thereby limiting predictive accuracy in patient risk stratification. To address these limitations, this paper proposes an unsupervised machine learning framework that integrates feature extraction, tensor decomposition, and clustering to improve cancer risk prediction. The framework employs tensor decomposition to fuse heterogeneous genomic and clinical data, enabling the extraction of latent, biologically meaningful features that outperform unimodal feature sets. Multiple feature extraction strategies are investigated, and the resulting features are subsequently clustered using a range of clustering algorithms. Comparative evaluations based on internal and external metrics are then used to identify the most effective configurations. The framework is validated on LinkedOmics data comprising 11,158 patients across 32 cancer types. For patient risk stratification, clinically relevant attributes such as tumor purity, pathological stage, and survival outcomes serve as ground-truth indicators. Experimental results demonstrate the superiority of tSVD+GMM, which consistently outperforms other configurations across clinical benchmarks.
Read the full abstract

All authors Ali Anaissi, Yuanzhe Jia, Qishun Peng, Weidong Huang, Ali Braytee, Junaid Akram

Machine Learning · Cross-listed from cs.CV

Golden Anchor for Video Generation

Jinyuan Xu, Shitong Shao, Lichen Bai et al. (+4 more)

Video generation supports digital content creation, with applications in virtual avatars, AI-driven filmmaking, interactive game engines, and world models. State-of-the-art systems achieve controllability primarily through image-to-video (I2V) generation, in which an injected anchor image determines the identity, composition, and style of the resulting video. In modern pipelines, this anchor is synthesized by a text-to-image (T2I) generator. This raises a largely overlooked question: Are images obtained directly from the T2I model truly suitable for current video models? Our analysis shows that anchor aesthetic and quality scores are weakly correlated with downstream video quality. The structure-and-texture score is negatively correlated with I2V video quality in both the visual and motion dimensions. Fine-tuning the T2I model on an image reward accordingly yields anchors with visibly denser structural and character detail: they score higher on image metrics, yet lower the video reward on every I2V model we test and change downstream motion unpredictably. We therefore introduce Golden Anchor Learning (GAL), to our knowledge the first framework for learning golden anchors by optimizing a T2I generator with downstream video feedback. GAL evaluates candidate anchors through the videos they induce under a frozen I2V model and converts video rewards into image-level preferences for DPO fine-tuning of the T2I generator. On all four I2V models, GAL raises the VBench average by $2.97\%$–$8.46\%$ over the untuned generator. The rendered clips also score higher under VideoReward-Overall, and their extracted frames under HPSv3 and UniPercept. GAL yields consistent motion gains across all four I2V models, as measured by a $5.62\%$–$38.24\%$ increase in VBench dynamic degree. Although GAL is trained only on HunyuanVideo-1.5 renders, these gains extend to the other three I2V models.
Read the full abstract

All authors Jinyuan Xu, Shitong Shao, Lichen Bai, Zikai Zhou, Guoxi Huang, Nantheera Anantrasirichai, Zeke Xie

Machine Learning

Monarch-MoE: Structured Experts for Multimodal Continual Instruction Tuning

Xi Zhang, Boyu Diao, Zesen Chen et al. (+3 more)

Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert LoRA distributes learning across experts, updates to a dense low-rank expert can still affect many output features. We introduce Monarch-MoE, which replaces the dense factors in LoRA experts with block-diagonal factors connected by a fixed permutation. This structure provides blockwise gradient isolation: individual block-pair updates affect only one output block, while connections between all input and output blocks are maintained. To make these compact experts practical on memory-limited hardware, we combine batched computation, fused forward operators, and an optimized backward pass. Across three continual-learning methods evaluated on MLLM-DCL and UCIT with LLaVA-1.5-7B, Monarch-MoE improves first-task retention while reducing adapter parameters by approximately 75% and 50%, respectively. In the main comparison, first-task forgetting is as low as 0.52 percentage points on MLLM-DCL and 0.10 on UCIT, with method-dependent trade-offs in final performance. Our implementation supports fine-tuning and inference on a single 24 GB RTX 4090, with lower measured memory use and competitive runtime in the evaluated settings. Together, these algorithmic and systems improvements make structured experts a practical option for continual adaptation on memory-limited hardware.
Read the full abstract

All authors Xi Zhang, Boyu Diao, Zesen Chen, Ruiqi Liu, Hangda Liu, Yongjun Xu

Machine Learning · Cross-listed from quant-ph

Verifiable Sampling for Delegated Generative Quantum Machine Learning

Matteo Inajetovic, Anna Pappa and Petros Wallden

Generative machine learning has shown remarkable results across a wide range of interdisciplinary tasks, motivating significant efforts toward Quantum Generative Models as a path to beyond-classical performance, given their capability of generating classically intractable distributions. However, comparatively little attention has been paid to securely delegating such computations to a powerful remote quantum server. In this work, we propose a blind and verifiable protocol for sampling that can be used for the inference phase of such quantum models. Such a protocol inherits blindness from Universal Blind Quantum Computing and achieves verifiability by exploiting known approaches based on trapification schemes. Alongside, to delegate the training phase, we discuss an extension of the previously proposed verifiable end-to-end Delegated Variational Quantum Algorithms (Inajetovic et al., Phys. Rev. Research, 2026). Beyond the usual Accept/Abort outcome characterizing verification protocols, the sampling protocol for inference also provides, even against a malicious server, an estimation of the amount of corrupted generated samples, i.e., a fine-grained feature describing the quality of the outcome connecting verification protocols and application-level benchmarking.
Read the full abstract

Machine Learning

How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models

Max Bourgeat

Time-series foundation models use the same network depth for every input, although forecasting windows differ in structure and difficulty. We test whether whole Transformer blocks can be removed at inference time in two pretrained models: Chronos-Bolt and TimesFM 2.5. Our bypasses avoid the original block computation and preserve the dense model exactly when all blocks are enabled. Masks are selected only on calibration windows and evaluated on 1,088 held-out windows from ETTh1, Traffic, Weather, and Exchange. At moderate sparsity, Chronos-Bolt with 7/11 candidate blocks and TimesFM with 16/20 blocks show little change in mean relative forecasting quality across datasets while reducing median A100 batch-1 latency by 11.2% and 13.4%. More aggressive TimesFM skipping accelerates inference further but substantially harms Traffic and Weather. Across both models, different equal-budget masks win on different windows, and a retrospective oracle significantly improves over the best static mask on every dataset. However, dataset-specific masks transfer inconsistently, and Chronos representations do not support reliable unseen-domain routing. These results establish cross-architecture structured redundancy and input-dependent opportunity, but not a deployable dynamic inference method.
Read the full abstract

Machine Learning

Rethinking Relative Policy Differences Transfer of On-Policy Distillation

Rong Wu, Daocheng Fu, Yu Yang et al. (+9 more)

On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target. Recent work relaxes this requirement by transferring the relative policy difference between an expert and a reference policy rather than the expert's absolute distribution. Yet it remains unclear which differences provide useful supervision and which targets can benefit from them. We develop a unified view in which the log-probability ratio between a proxy expert and a proxy reference defines an implicit reward for KL-regularized policy optimization. This formulation induces an on-policy update for the target, recovers conventional OPD as a special case, and enables any-to-any transfer across models that differ in scale, training stage or generation. Our systematic experiments yield three findings. First, a stronger expert is not necessarily a better source of supervision: differences induced by task-specific training, including reinforcement learning and supervised fine-tuning, transfer consistently, whereas those arising from model scale alone transfer weakly or not at all. Second, the expert and reference serve complementary roles: the expert provides the capability to be transferred, while the reference filters out shared behavior and isolates the relevant residual. Third, even a useful difference does not transfer to every target: success requires the induced update to move the target toward the expert and generalize beyond sampled rollouts. Raw policy distance does not predict transferability, whereas an appropriate reference can rescue otherwise unsuccessful transfer. These results characterize when relative policy differences provide effective supervision for OPD.
Read the full abstract

All authors Rong Wu, Daocheng Fu, Yu Yang, Xuemeng Yang, Siqi Li, Shu Zou, Yao Zhu, Botian Shi, Bo Zhang, Cong Zhang, Pinlong Cai, Jianbiao Mei

Machine Learning

S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding

Yuhang He, Hongyu Ge, Zihan Lin et al. (+2 more)

Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the response groups used for policy optimization. In our profiled RLVR workloads, attention accounts for 72–76% of autoregressive decoding kernel time. Sparse attention reduces these reads, but sampling directly from a sparse policy changes the response groups used for learning. For group-relative optimization, we show that even exact response-wise reweighting does not generally recover the expected dense-policy update because the advantage of each response depends on the rewards of other group members. We propose Self-Sparse Speculative Rollouts (S$^3$R). It uses sparse attention to propose tokens, then generates responses through full-attention verification and exact speculative sampling. Drafting and verification share the same policy parameter, eliminating the need to train or update a separate drafter. The resulting response groups follow the dense-policy distribution. Under S$^3$R, we characterize speedup conditions and the costs of drafting and verification. We found that dense verification still requires the complete historical KV cache. A KV-aware scheduler therefore limits KV-cache repeated offloading and restoration while maintaining rollout parallelism. % OR thrashing In a matched ablation with an aggressive sparse drafting budget, S$^3$R maintains stable training while direct sparse sampling with training-side correction becomes unstable. On long-context mathematical reasoning, S$^3$R achieves $1.39\times~1.35\times$ the end-to-end training throughput of autoregressive rollouts on Qwen3 model, with comparable task performance.
Read the full abstract

All authors Yuhang He, Hongyu Ge, Zihan Lin, Siyi Liu, Yongqi Zhang

Machine Learning

Does Learning Recurrent Networks Matter in Partially Observable RL?

Zekang Wang, Zhe He and Gaojie Jin

Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent module trained jointly with the policy or value function. This raises a natural question: is learning the recurrent network actually necessary? In this paper, we investigate whether a frozen recurrent network can provide sufficient memory for solving par- tially observable Markov decision processes (POMDPs). Motivated by the theoretical foundations of Reservoir Computing (RC) and Generalized Reservoir Computing (GRC), we study a simple archi- tecture that combines a fixed recurrent network with a trainable nonlinear output module. We evaluate this approach across tasks with varying memory demands, observation modalities, and action spaces. Surprisingly, frozen recurrent networks support recall over hundreds of steps and achieve competitive control performance across diverse POMDPs, while using less than half the number of trainable parameters required by their fully trainable counterparts. These results suggest that learning the recurrent memory module is not always necessary for solving POMDPs. Frozen recurrent networks therefore provide a simple, parameter-efficient, and sur- prisingly strong baseline for partially observable RL. Our source code is available at https://github.com/Aphlios/FRN-POMDP
Read the full abstract

Machine Learning · Cross-listed from cs.RO

Prediction-Informed Landing Window Planning for UAV Landing on USV in High Sea States

Kaizhen Li, Xi Zhou, Dan Zhang et al. (+1 more)

Autonomous landing of unmanned aerial vehicle (UAV) on unmanned surface vehicle (USV) is difficult in high sea states. Existing hierarchical landing methods often infer future USV motion only implicitly from short observation histories, which limits their ability to adapt to severe and rapidly changing sea conditions. This paper presents a prediction-informed hierarchical control framework. A pretrained model is developed to explicitly predict the USV attitude during high-level landing decisions. The prediction helps identify suitable landing windows and choose the right touchdown time, while a conventional low-level flight controller maintains UAV stability and tracks motion commands. To evaluate the framework under realistic disturbances, a real-sim validation setup is constructed in which USV-motion data collected in real sea conditions are transferred to a MuJoCo USV. The experiments demonstrate the feasibility of using explicit attitude prediction to improve landing-window selection and support timing-aware UAV landing planning in rapidly varying marine environments.
Read the full abstract

All authors Kaizhen Li, Xi Zhou, Dan Zhang, Xiaowei Li

Machine Learning

WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning

Alessandro Licciardi

Federated Learning (FL) enables collaborative model training without exposing raw data, yet remains vulnerable to malicious clients injecting poisoned datasets. Existing defenses are typically reactive (operating during training) or supervised (requiring prior knowledge of attack types) - assumptions that rarely hold in open-ended IoT deployments. We propose WaSA, a fully unsupervised, offline framework for malicious client detection. Before training, each client transmits a single, privacy-preserving spectral summary of its data to the server. A denoising autoencoder, trained solely on clean auxiliary data, scores clients based on their deviation from the learned benign manifold, identifying corruptions regardless of the attack type. WaSA requires no attack labels, generalizes to unseen anomalies, and introduces a Boltzmann sampling strategy for client selection that smoothly interpolates between hard exclusion and standard aggregation. Experiments on MNIST, CIFAR-10, and CIFAR-100 under diverse attack scenarios (up to 90 % malicious clients) demonstrate consistent improvements over supervised baselines and robust aggregation methods, with negligible communication overhead. Code is available at https://github.com/alelicciardi99/wavelet_autoencoders_malicious.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

Neurograf v1: An End-to-End Romanian-First Language Model Family

Ionut Adrian Rotaru

We present Neurograf v1, an experimental end-to-end Romanian-first language-model pipeline developed to investigate the feasibility of training language models from scratch for a lower-resource European language. The pipeline comprises RoSfera, a 635 GB Romanian corpus containing 175.7 million documents; an 80k byte-level BPE tokenizer; five decoder-only models ranging from 160M to 6B parameters, trained on 131 billion tokens; three instruction-tuned assistants; and two contrastively trained embedding models. Training and evaluation were conducted using computing infrastructure at ELI-NP/IFIN-HH. The model family exhibits consistent scaling of validation loss and increasing Romanian factual and cultural knowledge with model size. On the 1,000-question WWTBM benchmark, Neurograf-6B achieves 69.89% accuracy on Romanian-context questions, while Neurograf-3.2B reaches 67.38%. Compute-optimal analysis yields a parameter-scaling exponent of approximately 0.423. Neurograf v1 serves as an experimental demonstrator rather than a production system. The study identifies practical challenges involving diacritic preservation, corpus quality, data composition, and tokenization efficiency, while demonstrating the feasibility of developing Romanian-first base models, instruction-following assistants, and semantic embedding models within a unified training pipeline.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories

Zhenhao Huang, Li Sun and Philip S. Yu

Trajectory generation underpins urban applications such as traffic management and urban planning. Within road networks, vehicle movement along road segments is largely deterministic, whereas transitions at intersections are critical–multiple outgoing paths may appear equally plausible, yet they can lead to substantially different downstream routes. Existing generative methods such as diffusion models simulate location sequences and fail short of next transition selection, even producing trajectories that drift off the road network. To fill this gap, we advocate a fundamental shift: moving beyond location simulation toward behavior modeling on the road network. In this paper, we revisit trajectory generation through the lens of generative route planning, and introduce a new graph-constrained generative paradigm, Anticipatory Generative Modeling, which resolves next transition selection by incorporating the Anticipation of how the future route may unfold toward the destination. Concretely, we propose a novel generative model named Foresight that formulates a probabilistic model for an "anticipate–select–update–re-anticipate" loop that enables longer-term foresight while continuing sequential generation along the historical trajectory. Extensive experiments demonstrate that Foresight wins state-of-the-art baselines.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Fast Gradient-Based Approximation of Continuous Dynamic Time Warping

Pierre Houedry, Romain Tavenard, Nicolas Courty et al. (+1 more)

Dynamic Time Warping (DTW) is a common choice for measuring the discrepancy between time series. It proceeds by finding an optimal warping between timestamps through dynamic programming, which can be slow and is not differentiable. Consequently, several variants have been proposed. Among them, Soft-DTW proposes a smooth formulation of DTW, amenable to gradient computation, while Continuous-DTW (CDTW) introduces a continuous formulation through parametrizable warping functions. Yet, computational costs remain high for both methods and impractical for large datasets in modern machine learning pipelines. This paper revisits CDTW in several ways. After establishing its differentiability under mild conditions, we introduce FastCDTW, which is an efficient approximate solver with two different computational strategies: an exact closed-form scheme for piecewise-linear warping functions, and an unbiased Monte Carlo estimator for smooth ones, such as implicit neural networks. Both strategies provide gradients with respect to the warping function and the input time series, and the resulting algorithm is GPU-friendly. We demonstrate its benefits through its integration into more complex learning problems, including time series averaging, classification and deep domain adaptation.
Read the full abstract

All authors Pierre Houedry, Romain Tavenard, Nicolas Courty, Romaric Gaudel

Machine Learning · Cross-listed from stat.ML

Why Heavy-Tailed Weight Spectra Predict Model Quality

Joseph Wilson, Chris van der Heide, Liam Hodgkinson et al. (+3 more)

A solid understanding of the predictive success of deep neural networks (DNNs) remains elusive. For example, while many data-dependent metrics exist that seek to predict model quality of DNNs, these metrics may be expensive to compute for large datasets and/or may be impossible to compute when training datasets are not released. A practical and effective predictor of model quality involves analyzing DNN weight matrices, as prior work has established that heavy-tailed spectral distributions in trained weight matrices can be strongly predictive of model quality. However, such metrics lack a rigorous statistical justification. In this work, we aim to understand why these metrics perform well, from a statistical perspective. To do so, we employ a probabilistic framework to derive the marginal likelihood for a DNN, evaluated using only the final layer weights. Across large-scale convolutional DNNs and LLMs, we find that this marginal likelihood predicts model quality. To understand the role heavy-tailed spectra play in predictive performance, we derive the limiting log-marginal likelihood for spectra that follow the (heavy-tailed) High-Temperature Marchenko-Pastur (HTMP) distribution. We show that this limiting quantity is convex in a heaviness parameter, and we derive an optimal heaviness that empirically predicts over-fitting for large-scale DNNs.
Read the full abstract

All authors Joseph Wilson, Chris van der Heide, Liam Hodgkinson, Zhichao Wang, Fred Roosta, Michael W. Mahoney

Machine Learning

Continually Post-training Small Models via Synthetic Self-distillation

Woosung Koh, Hyunsoo Lee, Kyungjae Lee et al. (+4 more)

Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tuning (SDFT) mitigates this using self-supervision with in-context demonstrations, it relies on strong in-context learning and instruction-following abilities. Consequently, SDFT fails on smaller models critical for low-latency, on-device use. To enable continual learning at smaller scales, we first identify the root cause of failure. We show that poor acquisition and forgetting correlate linearly with the post-trained model's distribution shift, revealing the necessity of in-distribution learning. We thus introduce Synthetic Self-Distillation (SynthSelf), imitating SDFT's in-distribution rewrite by outsourcing the task to a minimally larger, same-family aligner. Coupled with off-policy supervision and rejection sampling, this provides the high-quality supervision small models require without breaking their original distribution. Evaluations spanning 4 acquisition datasets (including a mixture) and 14 retention benchmarks show SynthSelf consistently outperforms 6 methods (including off- and on-policy distillation) across 3 small model scales. Extensive further analyses confirm SynthSelf paves the way toward effective small-model continual learning.
Read the full abstract

All authors Woosung Koh, Hyunsoo Lee, Kyungjae Lee, Haeju Park, Dahyun Lee, Dasol Hwang, Moontae Lee

Machine Learning · Cross-listed from cs.AI

Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination

Mohammad Khalooei and Mohammad Sabokrou

Large audio-language models (LALMs) frequently exhibit object hallucination, affirming absent sounds. The dominant mitigation, Audio-Aware Decoding (AAD), contrasts logits under real audio against an all-zero "blank" waveform, flagged by prior review as out-of-distribution. We introduce a black-box causal test that isolates the claimed evidence itself: localize a claim's evidence region via CLAP similarity, remove it by spectral gating, and compare against a random-window control across a 2x2x2 grid on three LALMs. On Qwen2-Audio-7B, localized ablation's raw AUROC trails blank's (0.613 vs. 0.721); this is a duration confound, not a localization failure, since blank removes the entire clip versus the grid's 2-4 s. Holding duration fixed, localization beats random removal at every cell on both models. Raw detection value remains model-dependent, especially on Audio Flamingo 3. The same evidence corrects decoding: contrastive decoding combining blank and language-prior contrasts, gated and ensembled, raises Qwen2-Audio accuracy from 57.1% to 71.9%, beating AAD alone. A unified causal-grounding profile does not transfer between models, indicating different grounding regimes. The source code and a detailed report of our findings, including identified limitations, are available at https://github.com/khalooei/causa.
Read the full abstract

Machine Learning

Scaling RNA Foundation Models through Iterative Refinement

Pengan Chen, Liang Hong, Xinyuan Liu et al. (+6 more)

Biological function in RNA is encoded across scales, from local sequence motifs to long-range structural dependencies. Conventional RNA foundation models couple parameter capacity and inference depth within a fixed architecture, prescribing a fixed computation graph for each inference. Here we present Eco-RNA, an 80M-parameter RNA foundation model that makes inference depth adjustable through learned iterative refinement. Its shared, input-conditioned Transformer core refines sequence representations through repeated application. The iteration count is selected after training and controls effective depth at fixed model parameters. We train across recurrent depths with masked reconstruction, state regularization, and a one-sided loss that anchors deeper reconstruction to a shallow reference. On the 70-assay RNAGym fitness benchmark, increasing refinement from one to four iterations raises aggregate absolute Spearman correlation from 0.242 to 0.286, with the gain retained through eight iterations. At four iterations, Eco-RNA surpasses the current SOTA Evo 2 40B on all three aggregate fitness metrics despite 500x fewer parameters. Its iteration configurations advance the compute-performance Pareto frontier among the evaluated models. It also outperforms the evaluated baselines in non-coding RNA family classification, RNA secondary-structure prediction, and chemical probing profile prediction. These results establish internal inference computation as an effective scaling dimension for RNA foundation models.
Read the full abstract

All authors Pengan Chen, Liang Hong, Xinyuan Liu, Han Huang, Ziqian Lin, Jiayang Chen, Yimin Fan, Jiyue Jiang, Yu Li

Machine Learning

Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels

Do Nguyen-Thanh, Junlin Fang, Bing Li et al. (+2 more)

Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic systems. Existing methods rely on costly LLM prompting, step-level error annotations, or verified successful trajectories that lack failure signals for assistance. In this paper, we study failure attribution from step-unlabeled failure trajectories, where each trajectory is known to have failed but its decisive step is unknown. We propose SOAP (Spectral scOring with Attention-guided Propagation), an effective framework requiring neither step-level training labels nor a separate success-only reference set. SOAP first constructs a spectral reference space from LLM representations and assigns each step a base error score according to its projection behavior. Importantly, later steps may exhibit stronger failure signals because they inherit an earlier mistake, causing independent scorers to favor downstream consequences over the decisive error. To address this downstream contamination, SOAP derives soft step dependencies from attention patterns and propagates downstream error evidence toward its likely upstream sources. Extensive experiments show that SOAP consistently improves attribution performance over competitive baselines.
Read the full abstract

All authors Do Nguyen-Thanh, Junlin Fang, Bing Li, Zhen Fang, Sean Du

Machine Learning · Cross-listed from cs.CR

The Limits of Query Monitoring against Distributed Model Extraction

Snigdha Chandan Khilar

Model providers now face distillation campaigns run through thousands of accounts, each of which looks like an ordinary user. When network and payment metadata cannot link those accounts, the only evidence left is what they ask. We study what a provider can and cannot learn from those queries alone, using one million real chat turns for development and 17 later weeks that no design choice touched for a single frozen evaluation. The answer is set less by anything specific to extraction than by benign coordination: a campaign is visible only if it is more distinctive than the most distinctive group of ordinary users in the same week. We make this precise, show that a small but positive difference between campaign and users buys a detection time rather than detectability, and identify the campaign that is hardest to detect. Empirically, a calibrated monitor catches naive distributed extraction that per-account monitors miss (0.86-1.00 of weeks), and one variant - selecting accounts that move together after discounting how topical each one is - still catches campaigns padded with natural text (0.50-0.96 of weeks) where the other two spectral detectors catch none. Distilling each campaign into a small student shows that, in our testbed, campaigns that evaded every detector kept at most 42% of the capability of a detectable one. The limits are equally concrete: a campaign that ramps up slowly poisons every detector's calibration, benign evaluation pipelines look exactly like distillation, we found no deployable detector at colluder shares of 2.5% or below, and campaigns that relay real users' requests may be invisible to any query-only monitor.
Read the full abstract

Machine Learning

Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison

Mohammed Azeez Khan, Aaron Dsouza, Ashutosh Mishra et al. (+3 more)

Large language models (LLMs) are increasingly being explored as facilitators of group discussion and collaborative work, but the behavioral differences between LLM-generated and human facilitation remain insufficiently characterized. We compare human Project Manager facilitation turns from scenario-based collaborative design meetings with Llama 3.1 8B Instruct responses across 199 paired contexts from the AMI Meeting Corpus. The analysis covers five confirmatory dimensions: contextual semantic distance, a lexical elaboration proxy, empathyand-hedge lexical density, topic divergence, and phase-vocabulary alignment. An exploratory directiveness measure failed domain validation and is not interpreted. The sampled human Project Manager turns were higher on contextual semantic distance (r = 0.644) and on empathyand-hedge lexical density (r = 0.203). The second contrast is carried mainly by hedge terms, so we read it as lexical hedging rather than psychological empathy. Llama-generated facilitation was higher on topic divergence (r = 0.703), the lexical elaboration proxy (r = 0.288; lengthconfounded), and instruction-conditioned phase-vocabulary alignment (r = 0.382). A secondary no-phase check left the Llama-higher phase contrast in place. The system prompt still requested a facilitation move, so that check is not evidence of spontaneous phase awareness. These differences should not be interpreted as a ranking of facilitation quality. The resulting behavioral profile provides a reference point for later comparisons of LLM facilitators, human facilitators, prompts, models, and collaborative settings.
Read the full abstract

All authors Mohammed Azeez Khan, Aaron Dsouza, Ashutosh Mishra, Ummul Faiz Z. Bibi, Neha K. Nair, Arshaan Khan

Machine Learning

Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory

Vakul Raghavan, Utkarsh Grover, Mingyang Mao et al. (+2 more)

Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size memory must retain many associations, connect information across positions, and preserve relevant structure without being overwhelmed by everything it observes. These are distinct requirements: a memory may store more information without representing the relationships needed for retrieval, and it may transport those relationships without preserving the ones that matter. Thus, the challenge is not simply extending context length, but constructing a memory that remains usable as context grows. We study this problem in large-chunk test-time training (TTT) and identify two basic failures: single-step writes accumulate interference, limiting capacity, while self-associative writes cannot form cross-position bindings. We introduce Double-Take (DT), which repairs these failures with multi-step unpinned updates and cross-position mixing, and adds bidirectional change-sensitive writes for selective retention. Capacity alone leaves end-to-end recall at the $0.10$ chance floor; adding binding raises it to $0.92$. Trained only on $32\,\mathrm{kb}$ genomic contexts, DT reaches $0.927$ AUROC at $131\,\mathrm{kb}$ and $0.856$ near $1\,\mathrm{Mb}$, while transferring zero-shot from human to mouse. Together, these results identify capacity, binding, and selectivity as three requirements for usable long-range memory.
Read the full abstract

All authors Vakul Raghavan, Utkarsh Grover, Mingyang Mao, Chengwen Wang, Xiaomin Lin

Machine Learning

CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits

Jiahang Sun, Zhiwei Shang, Zhipiao Liu et al. (+4 more)

Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually designing these workflows is labor-intensive and lacks flexibility to adapt to diverse queries. While automated workflow optimization is a promising direction, existing methods often incur expensive API costs during training-phase feedback collection. Furthermore, they fail to adaptively reuse high-quality workflows, which creates a bottleneck for both performance and cost-effectiveness. To address these limitations, we propose CB-Orchestrator, an adaptive framework that decouples workflow generation from selection. In the first stage, we construct a diverse pool of candidate workflows via evolutionary search. In the second stage, we formulate workflow selection as a Contextual Bandit problem, which enables sample-efficient learning by balancing exploration and exploitation, thereby significantly reducing the feedback required for training. During inference, the model adaptively selects the optimal workflow tailored to each query. Evaluations across five diverse benchmarks demonstrate that CB-Orchestrator consistently outperforms all baselines. Notably, on the MATH dataset, CB-Orchestrator achieves better performance than strong recent baselines while reducing training-phase API token overhead by no less than 40.55% and total end-to-end training (including workflow pool generation) token overhead by no less than 29.73%.
Read the full abstract

All authors Jiahang Sun, Zhiwei Shang, Zhipiao Liu, Hongwei Yang, Guoqing Xie, Shuang Qiu, Zhongxiang Dai

Machine Learning · Cross-listed from cs.CL

CoBe: A Benchmark For Conversational Counterfactual Text Editing

Arvind Raghavan, Inwoo Hwang, Shreyas Havaldar et al. (+6 more)

Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by that change. When asked what would have happened if a doctor had not recommended surgery, the model output should retain the patient's medical history and modify only the consequences of the decision. This requires causal understanding: a model must determine, without being explicitly instructed to, what events are affected by the hypothetical change and what should remain fixed. This skill is central to human reasoning, especially in safety-critical domains like healthcare or law. By contrast, the task of associational text generation merely generates text statistically associated with the altered condition. In the medical example, an associational response might make the patient's symptoms less severe because milder cases correlate with no surgery. Such responses produce a plausible scenario, but not the counterfactual version of the given one. Prior counterfactual-text datasets do not clearly separate these modes of reasoning. We introduce the Counterfactual Benchmark (CoBe), a testbed for models' zero-shot ability to counterfactually edit a given textual scenario when prompted to do so in a conversationally natural way. CoBe contains 2000 questions spanning healthcare, science and engineering, business, and everyday scenarios. We test a suite of frontier and smaller models, with frontier systems achieving an average score of $58.05\%$. Our findings indicate that models frequently default to associational generation rather than preserving the causal structure of the original scenario. Moreover, performance does not scale consistently with either model size or output token length, suggesting that the failure may reflect model training objectives rather than insufficient model capacity.
Read the full abstract

All authors Arvind Raghavan, Inwoo Hwang, Shreyas Havaldar, Kai-Zhan Lee, Aurghya Maiti, Yushu Pan, Jeffrey Wu, Mingxuan Li, Elias Bareinboim

Machine Learning · Cross-listed from cs.CR

Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors

Arnab Dey and Mohammad Mahfuzul Islam

Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32 send 99.7% of triggered source-class images to the attacker's class. The usual defenses look for the poison inside a model trained on those same labels. So when they struggle, is the problem the test they run, or the space they run it in? We answer with a controlled swap: we keep the test, the labels and the metric fixed, change only the feature space, and judge each defense by retraining the victim on what it keeps. The space decides. On dog$\to$cat the same nearest-neighbor check scores AUROC 0.546 on the poisoned model's features, 0.967 on frozen DINOv2 features that never saw a label, and 0.995 on the same network trained on clean labels, an oracle control rather than a defense. We reproduce SPECTRE, the defense FLIP's authors recommend, to 90.94 / 0.97 against its published 91.47 / 1.7, then price it: on truck$\to$deer it deletes 20% of every class, while a prototype audit on the frozen features deletes 6% for higher clean accuracy and lower attack success. On three harder pairs that audit leaves about a quarter of the attack standing. A count read off encoder geometry and clean labels, before any attack is run, separates the pair where the audit removes the attack from those where it only partly does, though on a single zero-count pair. Three results warn against the easy story. A better detection score does not mean a safer model: on two of four pairs Confident Learning scores the higher AUROC, and on dog$\to$cat leaves 2.6 times the attack success. The prototype family, our best static performer, is the first an adaptive attacker slips past. And past a point, catching more poisons stops reducing attack success. Check labels in a space that never learned them, and judge a defense by the retrained model, not by its detection score.
Read the full abstract

Machine Learning · Cross-listed from eess.SP

Lightweight Time-Frequency Vibration Sensing for Consumer Device Condition Monitoring

Po-Heng Chou, Jen-Yu Chiu, Chun-Yu Yeh et al. (+2 more)

Consumer rotating devices, including washing machines, air conditioners, electric fans, robotic vacuum cleaners, and home fitness equipment, increasingly rely on vibration sensing for intelligent condition monitoring and predictive maintenance. Ensuring reliable operation in these resource-constrained appliances requires efficient, lightweight artificial intelligence (AI) solutions capable of processing non-stationary signals under real-world operational interference. This paper proposes a lightweight AI-assisted vibration sensing framework that employs continuous wavelet transform (CWT) and Hilbert-Huang transform (HHT) to convert one-dimensional (1-D) vibration time-series signals into two-dimensional (2-D) time-frequency representations. These representations are subsequently analyzed using lightweight deep learning architectures, specifically MobileNetV3-Small, ConvNeXt-Tiny, and the You Only Look Once version 11 classification model (YOLOv11-cls). Public bearing benchmark datasets, including Case Western Reserve University (CWRU), Paderborn University (PU), and Intelligent Maintenance Systems (IMS), are utilized as representative rotating components to investigate model generalization. The proposed framework is designed with eventual embedded deployment in consumer electronics in mind. Experimental results demonstrate that CWT combined with YOLOv11-cls achieves high diagnostic accuracy, while MobileNetV3-Small provides an attractive low-latency alternative for computationally constrained edge platforms. Conventional random splitting is also compared with dataset-specific structured isolation. The results highlight the importance of avoiding data leakage and quantify tradeoffs in classification accuracy, parameter count, floating-point operations (FLOPs), model footprint, preprocessing cost, and central processing unit (CPU) inference latency.
Read the full abstract

All authors Po-Heng Chou, Jen-Yu Chiu, Chun-Yu Yeh, Wei-Lung Mao, Walid Saad