Machine Learning
Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
Brice Valentin Kok-Shun, Johnny Chan, Gabrielle Peko et al. (+1 more)
Agentopic is a novel
agent-based workflow for explainable topic modeling that leverages the
reasoning capabilities of Large
Language Models (LLMs). Existing topic modeling approaches such as Latent Dirichlet Allocation (LDA) and BERTopic often lack transparency on how topics are assigned or grouped. Agentopic addresses this by using multiple
agents that collaboratively perform topic identification, validation, hierarchical grouping, and natural
language explanation. This design enables users to trace the
reasoning behind topic assignments, enhancing interpretability without sacrificing accuracy. When seeded with topics from the British Broadcasting Corporation (BBC)
dataset, Agentopic achieves an F1-score of 0.95, matching GPT-4.1, improving on LDA (0.93), and close to BERTopic (0.98). We used Agentopic to augment the BBC
dataset with generated explanations to improve the
dataset's richness and context. The unseeded Agentopic generated 2045 semantically coherent topics organized across six hierarchical levels, vastly enriching the original five-category structure. By
embedding explainability throughout the workflow, Agentopic offers an interpretable alternative to black-box models, making it particularly valuable for crucial applications like finance and healthcare.
Read the full abstract ▾
All authors Brice Valentin Kok-Shun, Johnny Chan, Gabrielle Peko, David Sundaram
Machine Learning · Cross-listed from cs.CY
Epicure: Multidimensional Flavor Structure in Food Ingredient Embeddings
Jakub Radzikowski and Josef Chen
A chef's intuition about
flavor, texture, and cultural identity represents tacit knowledge that is difficult to articulate yet central to culinary practice. We show that this knowledge is already encoded in FlavorGraph's 300-dimensional ingredient
embeddings, trained on recipe cooccurrence and food chemistry, and that it can be systematically recovered. An LLM-augmented curation pipeline consolidates 6,653 raw FlavorGraph ingredients into 1,032 canonical entries, substantially strengthening the recoverable structure. We identify at least fifteen independently classifiable dimensions spanning taste, texture, geography, food processing, and culture.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements
Yifei Wang, Tianlin Li, Xiaohan Zhang et al. (+4 more)
Large
language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g., bfloat16 and float16) and quantized integer formats (e.g., int16 and int8), to meet efficiency and resource constraints. However, minor inconsistencies between LLMs of different precisions are difficult to detect and are often overlooked by existing evaluation methods. In this paper, we present PrecisionDiff, an automated differential testing framework for systematically detecting precision-induced behavioral disagreements in LLMs. PrecisionDiff generates precision-sensitive test inputs and performs cross-precision comparative analysis to uncover subtle divergences that remain hidden under conventional testing strategies. To demonstrate its practical significance, we instantiate PrecisionDiff on the
alignment verification task, where precision-induced disagreements manifest as jailbreak divergence-inputs that are rejected under one precision may produce harmful responses under another. Experimental results show that such behavioral disagreements are widespread across multiple open-source aligned LLMs and precision settings, and that PrecisionDiff significantly outperforms vanilla testing methods in detecting these issues. Our work enables automated precision-sensitive test generation, facilitating effective pre-deployment evaluation and improving precision robustness during training.
Read the full abstract ▾
All authors Yifei Wang, Tianlin Li, Xiaohan Zhang, Xiaoyu Zhang, Wei Ma, Mingfei Cheng, Li Pan
Machine Learning · Cross-listed from cs.IR
Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty
Enock O. Ayiku, Evelyn Osei and Emebo Onyeka
Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms that promote novelty and diversity. In practice, the strength of such interventions is typically controlled using global hyperparameters, fixed regularization weights, heuristic caps, or offline tuning strategies. These approaches implicitly assume that a single level of exploration is appropriate across users, contexts, and stages of interaction. In this work, we study exploration saturation as a user-dependent phenomenon arising from
fairness- and novelty-driven recommendation strategies. We define exploration saturation as the point at which further increases in exploration no longer improve user utility and may instead reduce engagement or perceived relevance. Rather than proposing a new
fairness-aware
algorithm or optimizing a specific objective, we empirically analyze how increasing exploration affects users across varied recommendation models. Through longitudinal experiments using MovieLens-1M and Last.fm
datasets, our results indicate that
fairness-induced exploration exhibits diminishing or non-monotonic returns and varies substantially across users. In particular, users with limited interaction histories tend to reach saturation earlier, suggesting that uniform
fairness or novelty pressure can disproportionately disadvantage certain users. These findings reveal a trade-off between
fairness and user experience, suggesting that recommendation systems should adapt not only to relevance but also to the amount of
fairness-driven exploration applied to individual users.
Read the full abstract ▾
Machine Learning
Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments
Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti et al. (+1 more)
Autonomous AI
agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive
Memory Crystallization (AMC), a
memory architecture for progressive experience consolidation in continual reinforcement learning. AMC is conceptually inspired by the qualitative structure of synaptic tagging and capture (STC) theory, the idea that
memories transition through discrete stability phases, but makes no claim to model the underlying molecular or synaptic mechanisms. AMC models
memory as a continuous crystallization process in which experiences migrate from plastic to stable states according to a multi-objective utility signal. The framework introduces a three-phase
memory hierarchy (
Liquid–Glass–
Crystal) governed by an Itô
stochastic differential equation (SDE) whose population-level behavior is captured by an explicit Fokker–Planck equation admitting a closed-form Beta stationary distribution. We provide proofs of: (i) well-posedness and global convergence of the crystallization SDE to a unique Beta stationary distribution; (ii) exponential convergence of individual crystallization states to their fixed points, with explicit rates and variance bounds; and (iii) end-to-end Q-learning error bounds and matching
memory-capacity lower bounds that link SDE parameters directly to
agent performance. Empirical evaluation on Meta-World MT50, Atari 20-game sequential learning, and MuJoCo continual locomotion consistently shows improvements in forward transfer (+34–43% over the strongest baseline), reductions in catastrophic forgetting (67–80%), and a 62% decrease in
memory footprint.
Read the full abstract ▾
All authors Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti, Satyasaran Changdar
Machine Learning
A Comparative Theoretical Analysis of Entropy Control Methods in Reinforcement Learning
Ming Lei and Christophe Baehr
Reinforcement learning (RL) has become a key approach for enhancing
reasoning in large
language models (LLMs), yet scalable training is often hindered by the rapid collapse of policy
entropy, which leads to premature convergence and performance saturation. This paper provides a comparative theoretical analysis of two
entropy control strategies: traditional
entropy regularization and the recently proposed covariance-based mechanism. We establish a unified framework for
entropy dynamics under softmax parameterization, showing that
entropy change is governed by the covariance between log-probabilities and logit updates. Our analysis reveals that traditional
entropy regularization introduces a dense, persistent bias that modifies the stationary condition, leading to suboptimal policies, while covariance-based methods selectively regularize a sparse subset of high-covariance
tokens and achieve asymptotic unbiasedness when the regularization coefficient is annealed. These results provide principled guidelines for
entropy control in LLM posttraining, with implications for scaling RL to larger models and more complex
reasoning tasks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Real-Time Voicemail Detection in Telephony Audio Using Temporal Speech Activity Features
Kumar Saurav
Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted
agent interactions and dropped calls. We present a lightweight approach that extracts 15 temporal features from the
speech activity pattern of a pre-trained neural voice activity detector (VAD), then classifies with a shallow tree-based ensemble. Across two evaluation sets totaling 764 telephony recordings, the system achieves a combined 96.1% accuracy (734/764), with 99.3% (139/140) on an expert-labeled test set and 95.4% (595/624) on a held-out production set. In production validation over 77,000 calls, it maintained a 0.3% false positive rate and 1.3% false negative rate. End-to-end inference completes in 46 ms on a commodity dual-core CPU with no GPU, supporting 380+ concurrent WebSocket calls. In our search over 3,780 model, feature, and threshold combinations, feature importance was concentrated in three temporal variables. Adding transcription keywords or beep-based features did not improve the best real-time configuration and increased latency substantially. Our results suggest that temporal
speech patterns are a strong signal for distinguishing voicemail greetings from live human answers.
Read the full abstract ▾
Machine Learning
Active Inference with a Self-Prior in the Mirror-Mark Task
Dongmin Kim, Hoshinori Kanazawa and Yasuo Kuniyoshi
The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an indicator of self-awareness. In this study, we present a computational model in which this behavior emerges spontaneously through a single mechanism, the self-prior, without any external reward. The self-prior, implemented with a
Transformer, learns the density of familiar multisensory experiences; when a novel mark appears, the discrepancy from this learned distribution drives mark-directed behavior through active inference. A simulated infant, relying solely on
vision and proprioception without tactile input, discovered a sticker placed on its own face in the mirror and removed it in approximately 70% of cases without any explicit instruction. Expected free energy decreased significantly after sticker removal, confirming that the self-prior operates as an internal criterion for distinguishing self from non-self. Cross-modal sampling further demonstrated that the self-prior captures visual–proprioceptive associations, functioning as a probabilistic body schema. These results provide a concise computational account of the key behavior observed in the mirror test and suggest that the free energy principle can serve as a unifying hypothesis for investigating the developmental origins of self-awareness. Code is available at: https://github.com/kim135797531/self-prior-mirror
Read the full abstract ▾
Machine Learning
Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing
Yilong Dai, Shengyu Chen, Xiaowei Jia et al. (+1 more)
Partial differential equations (PDEs) govern nearly every physical process in science and engineering, but solving them at scale remains prohibitively expensive. Generative AI has transformed
language,
vision, and
protein science, but learned PDE solvers have not undergone a comparable shift. Existing paradigms each capture part of the problem. Physics-informed neural networks embed residual structure, although they are often difficult to optimize in stiff, multiscale, or large-domain regimes. Neural operators amortize across instances, although they commonly inherit a snapshot-prediction view of solving and can degrade over long rollouts.
Diffusion-based solvers model uncertainty, although they are often built on a solver template that still centers on state regression. We argue that the core issue is the abstraction used to train learned solvers. Many models are asked to predict states, while many scientific settings require modeling how uncertainty moves through constrained dynamics. The relevant object is transport over physically admissible futures. This motivates flow learners: models that parameterize transport vector fields and generate trajectories through integration, echoing the continuous dynamics that define PDE
evolution. This physics-to-physics
alignment supports continuous-time prediction, native uncertainty quantification, and new opportunities for physics-aware solver design. We explain why transport-based learning offers a stronger organizing principle for learned PDE solving and outline the research agenda that follows from this shift.
Read the full abstract ▾
All authors Yilong Dai, Shengyu Chen, Xiaowei Jia, Runlong Yu
Machine Learning · Cross-listed from cs.CV
AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection
Damith Chamalke Senadeera, Dimitrios Kollias and Gregory Slabaugh
Automatic violence detection from
video is challenging because violent interactions may be distant, occluded, or only partially visible. Audio can provide complementary evidence for violent events that are difficult to recognize from visual information alone. However, audio itself may be absent, dubbed, or dominated by environmental noise, making the central challenge not whether to incorporate audio but how to adapt reliance on it according to the visual scene. We introduce AViS-Mamba, an audiovisual Mamba-based architecture in which the visual stream directly governs the behavior of the audio stream. At each layer of the audio encoder, a compact visual representation produces a modulation vector that conditions the encoder's internal temporal operators together with a routing gate that regulates the strength of this visual intervention. Rather than fusing or reweighting features after they have been extracted, visual context directly shapes the temporal dynamics of the audio encoder. We further propose Adaptive AV-InfoNCE, a contrastive objective that learns to balance the audio-to-
video and
video-to-audio
alignment directions rather than weighting them uniformly. On the audio-valid NTU-CCTV and DVD
benchmarks, AViS-Mamba establishes state-of-the-art results, attaining 88.59% and 75.74% accuracy. We demonstrate that adaptive visual conditioning consistently outperforms fixed routing and improves performance under degraded and missing-audio conditions. Layer-wise analysis further reveals that the model adapts the audio stream selectively across network depth rather than applying a single global routing policy.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AR
InsightBoard: An Interactive Multi-Metric Visualization and Fairness Analysis Plugin for TensorBoard
Ray Zeyao Chen and Christan Grant
Modern machine learning systems deployed in safety-critical domains require visibility not only into aggregate performance but also into how training dynamics affect subgroup
fairness over time. Existing training dashboards primarily support single-metric monitoring and offer limited support for examining relationships between heterogeneous metrics or diagnosing subgroup disparities during training. We present InsightBoard, an interactive TensorBoard plugin that integrates synchronized multi-metric visualization with slice-based
fairness diagnostics in a unified interface. InsightBoard enables practitioners to jointly inspect training dynamics, performance metrics, and subgroup disparities through linked multi-view plots, correlation analysis, and standard group
fairness indicators computed over user-defined slices. Through case studies with YOLOX on the BDD100k
dataset, we demonstrate that models achieving strong aggregate performance can still exhibit substantial demographic and environmental disparities that remain hidden under conventional monitoring. By making
fairness diagnostics available during training, InsightBoard supports earlier, more informed model inspection without modifying existing training pipelines or introducing additional data stores.
Read the full abstract ▾
Machine Learning
General Explicit Network (GEN): A novel deep learning architecture for solving partial differential equations
Genwei Ma, Ting Luo, Ping Yang et al. (+1 more)
Machine learning, especially physics-informed neural networks (PINNs) and their neural network variants, has been widely used to solve problems involving partial differential equations (PDEs). The successful deployment of such methods beyond academic research remains limited. For example, PINN methods primarily consider discrete point-to-point fitting and fail to account for the potential properties of real solutions. The adoption of continuous activation functions in these approaches leads to local characteristics that align with the equation solutions while resulting in poor extensibility and robustness. A general explicit network (GEN) that implements point-to-function PDE solving is proposed in this paper. The "function" component can be constructed based on our prior knowledge of the original PDEs through corresponding basis functions for fitting. The experimental results demonstrate that this approach enables solutions with high robustness and strong extensibility to be obtained.
Read the full abstract ▾
All authors Genwei Ma, Ting Luo, Ping Yang, Xing Zhao
Machine Learning · Cross-listed from stat.ML
Learning interacting particle systems from unlabeled data
Viska Wei and Fei Lu
Learning the potentials of interacting particle systems is a fundamental task across various scientific disciplines. A major challenge is that unlabeled data collected at discrete time points lack trajectory information due to limitations in data collection methods or
privacy constraints. We address this challenge by introducing a trajectory-free self-test loss function that leverages the weak-form
stochastic evolution equation of the empirical distribution. The loss function is quadratic in potentials, supporting parametric and nonparametric regression
algorithms for robust estimation that scale to large, high-dimensional systems with big data. Systematic numerical tests show that our method outperforms baseline methods that regress on trajectories recovered via label matching, tolerating large observation time steps. We establish the convergence of parametric
estimators as the sample size increases, providing a theoretical foundation for the proposed approach.
Read the full abstract ▾
Machine Learning
VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
Yan Zheng and Florian Bordes
Evaluating code generation models for 3D spatial
reasoning requires executing generated code in realistic environments and assessing outputs beyond surface-level correctness. We introduce a platform VoxelCode, for analyzing code generation capabilities for 3D understanding and environment creation. Our platform integrates natural
language task specification, API-driven code execution in Unreal Engine, and a unified evaluation pipeline supporting both automated metrics and human assessment. To demonstrate its utility, we construct VoxelCodeBench, a
benchmark of voxel manipulation tasks spanning three
reasoning dimensions: symbolic interpretation,
geometric construction, and artistic composition. Evaluating leading code generation models, we find that producing executable code is far easier than producing spatially correct outputs, with
geometric construction and multi-object composition proving particularly challenging. By open-sourcing our platform and
benchmark, we provide the community with extensible infrastructure for developing new 3D code generation
benchmarks and probing spatial
reasoning in future models.
Read the full abstract ▾
Machine Learning
ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models
Gonzalo Uribarri
We introduce ROMAN (ROuting Multiscale representAtioN), a deterministic operator for time series that maps temporal scale and coarse temporal position into an explicit channel structure while reducing sequence length. ROMAN builds an anti-aliased multiscale pyramid, extracts fixed-length windows from each scale, and stacks them as pseudochannels. ROMAN provides a training-free mechanism to control the inductive bias of downstream models: it can reduce temporal invariance, make temporal pooling implicitly coarse-position-aware, and expose multiscale interactions through channel mixing, while often improving computational efficiency by shortening the processed time axis. We formally analyze the operator and evaluate it as preprocessing for four convolutional classifiers: MiniRocket, MultiRocket, a standard CNN-based classifier, and a fully convolutional network (FCN) classifier. Synthetic mechanism studies that isolate coarse position, long-range correlation, multiscale interaction, and full positional invariance show that ROMAN behaves as intended, and comparisons with coordinate augmentation and single-scale routing distinguish the benefits of positional routing from those of the multiscale cascade across the evaluated backbones. On long-sequence subsets of the UCR and UEA archives, ROMAN's effect on accuracy varies across
datasets while its effect on efficiency is often favorable. At \(S=4\) on UCR, accuracy changes are positively correlated across the pooled backbones, consistent with the proposed role of task structure. We give practical guidance for choosing the operator's two hyperparameters and illustrate its use on very long sequences, where it is both more accurate and several times cheaper, and as a source of representation diversity for ensembles. The ROMAN operator library is available at \href{https://github.com/gon-uri/ROMAN}{github.com/gon-uri/ROMAN
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Understanding the Effects of Safety Unalignment on Large Language Models
John T. Halloran
Safety
alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety
alignment for deployed frontier models, two separate lines of recent work–jailbreak-tuning (JT) and weight orthogonalization (WO)–have shown that safety guardrails may be largely disabled, resulting in LLMs which comply with harmful requests they would normally refuse. In spite of far-reaching safety implications, analysis has largely been limited to refusal rates of each unalignment method in isolation, leaving their relative effects on
adversarial LLM capabilities unknown. To fill this gap, we study the impact of unaligning six popular LLMs of various sizes across a large number of malicious and benign tasks, using both JT and WO. Across the evaluated models, we show that while refusal degradation is split between the two methods, WO produces LLMs far more capable of aiding in malicious activity; in contrast to JT, the majority of WO unaligned models are far less prone to
hallucinations, better retain their original natural-
language performance, and are more effective at state-of-the-art
adversarial and cyber attacks. To thus help mitigate the malicious risks of WO unalignment, we conclude by showing that supervised fine-tuning effectively limits the
adversarial attack abilities enabled by WO, without drastically affecting
hallucination rates or natural
language performance.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
Haiyu Wang, Yutong Wang, Jack Jiang et al. (+1 more)
Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of
Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although multiple prior works have proposed efficient SVD variants to enable low-rank operations, we find that in practice it remains difficult to achieve substantial latency reduction during model execution. To address this limitation, we introduce a new computational pattern and apply SVD at a finer granularity, enabling real and measurable improvements in execution latency. Furthermore, recognizing that weight elements differ in their relative importance, we adaptively allocate relative importance to each element during SVD process to better preserve accuracy, then extend this framework with quantization applied to both weights and activations, resulting in a highly efficient VLM. Collectively, we introduce~Weighted SVD (WSVD), which outperforms other approaches by achieving over $1.8\times$ decoding speedup while preserving accuracy. We open source our code at: \href{https://github.com/SAI-Lab-NYU/WSVD}{https://github.com/SAI-Lab-NYU/WSVD
Read the full abstract ▾
All authors Haiyu Wang, Yutong Wang, Jack Jiang, Sai Qian Zhang
Machine Learning
Communication-Efficient Distributed Learning with Differential Privacy
Xiaoxing Ren, Yuwen Ma, Nicola Bastianello et al. (+3 more)
We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an
algorithm that is both communication-efficient and that guarantees the
privacy of the
agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting
algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical
privacy guarantees within a differential
privacy framework that ensure
agents' training data cannot be inferred from the trained model shared over the network. We show the
algorithm's superior performance on a classification task under the same
privacy budget, compared with state-of-the-art methods.
Read the full abstract ▾
All authors Xiaoxing Ren, Yuwen Ma, Nicola Bastianello, Karl H. Johansson, Thomas Parisini, Andreas A. Malikopoulos
Machine Learning
Fast NF4 Dequantization Kernels for Large Language Model Inference
Xiangbo Qi, Chaoyi Jiang and Murali Annavaram
Large
language models (LLMs) have grown beyond the
memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$
memory reduction, inference on current NVIDIA GPUs (e.g., Ampere A100) requires expensive dequantization back to FP16 format, creating a critical performance bottleneck. This paper presents a lightweight shared
memory optimization that addresses this gap through principled
memory hierarchy exploitation while maintaining full ecosystem compatibility. We compare our technique against the open-source BitsAndBytes implementation, achieving 2.0–2.2$\times$ kernel speedup across three models (Gemma 27B, Qwen3 32B, and Llama3.3 70B) and up to 1.54$\times$ end-to-end improvement by leveraging the 12–15$\times$ latency advantage of shared
memory over global
memory access. Our optimization reduces instruction counts through simplified indexing logic while using only 64 bytes of shared
memory per thread block, demonstrating that lightweight optimizations can deliver substantial performance gains with minimal engineering effort. This work provides a plug-and-play solution for the HuggingFace ecosystem that democratizes access to advanced models on existing GPU infrastructure.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DS
Robust Learning with Optimal Error
Guy Blanc
We construct
algorithms with optimal error for learning with
adversarial noise. The overarching theme of this work is that the use of randomized hypotheses can substantially improve upon the best error rates achievable with deterministic hypotheses. - For $\eta$-rate malicious noise, we show the optimal error is $\frac{1}{2} \cdot \eta/(1-\eta)$, improving on the optimal error of deterministic hypotheses by a factor of $1/2$. This answers an open question of Cesa-Bianchi et al. (JACM 1999) who showed randomness can improve error by a factor of $6/7$. - For $\eta$-rate nasty noise, we show the optimal error is $\frac{3}{2} \cdot \eta$ for distribution-independent learners and $\eta$ for fixed-distribution learners, both improving upon the optimal $2 \eta$ error of deterministic hypotheses. This closes a gap first noted by Bshouty et al. (Theoretical Computer Science 2002) when they introduced nasty noise and reiterated in the recent works of Klivans et al. (NeurIPS 2025) and Blanc et al. (SODA 2026). - For $\eta$-rate agnostic noise and the closely related nasty classification noise model, we show the optimal error is $\eta$, improving upon the optimal $2\eta$ error of deterministic hypotheses. All of our learners have sample complexity linear in the VC-dimension of the concept class and
polynomial in the inverse excess error. All except for the fixed-distribution nasty noise learner are time efficient given access to an oracle for empirical risk minimization.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.ST
Financial Anomaly Detection for the Canadian Market
Luigi Caputi and Nicholas Meadows
In this work we evaluate the performance of three classes of methods for detecting financial anomalies: topological data analysis (TDA), principal component analyis (PCA), and Neural Network-based approaches. We apply these methods to the TSX-60 data to identify major financial stress events in the Canadian stock
market. We show how neural network-based methods (such as GlocalKD and One-Shot GIN(E)) and TDA methods achieve the strongest performance. The effectiveness of TDA in detecting financial anomalies suggests that global topological properties are meaningful in distinguishing financial stress events.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
RGB-Pointmap Pretraining for Unified 3D Scene Understanding
Ye Mao, Weixun Luo, Ranran Huang et al. (+2 more)
Pretraining 3D encoders through
alignment with Contrastive
Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a
transformer-based framework that learns unified 3D scene representations from multi-view RGB-Pointmap inputs by leveraging the priors of a pretrained 2D foundation model. For robust RGB-Pointmap representation learning, we introduce cross-view
geometric alignment and grounded view
alignment to enforce
geometric and semantic consistency across views. Extensive low-shot and task-specific fine-tuning on viewpoint grounding, scene
retrieval, scene classification, and 3D visual question answering demonstrates state-of-the-art performance. These results establish UniScene3D as an effective framework for unified 3D scene understanding. Project page: https://yebulabula.github.io/UniScene3D/
Read the full abstract ▾
All authors Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
Machine Learning · Cross-listed from cs.CV
Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
Ji Young Byun, Young-Jin Park, Jean-Philippe Corbeil et al. (+1 more)
As
vision-
language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust their predictions is equally critical. Yet, a comprehensive and systematic investigation into the overconfidence of these models remains notably scarce in the medical domain. We address this gap through a comprehensive empirical study of confidence calibration in VLMs, spanning three model families (Qwen3-VL, InternVL3, LLaVA-NeXT), three model scales (2B–38B), and multiple confidence estimation prompting strategies, across three medical visual question answering (VQA)
benchmarks. Our study yields three key findings: First, overconfidence persists across model families and is not resolved by scaling or prompting, such as chain-of-thought and verbalized confidence variants. Second, simple post-hoc calibration approaches, such as Platt scaling, reduce calibration error and consistently outperform the
prompt-based strategy. Third, due to their (strict) monotonicity, these post-hoc calibration methods are inherently limited in improving the discriminative quality of predictions, leaving AUROC at the same level. Motivated by these findings, we investigate
hallucination-aware calibration (HAC), which incorporates
vision-grounded
hallucination detection signals as complementary inputs to refine confidence estimates. We find that leveraging these
hallucination signals improves both calibration and AUROC, with the largest gains on open-ended questions. On closed-ended questions, format-specific signals such as the logit margin show more informative. Overall, our findings suggest post-hoc calibration as standard practice for medical VLM deployment over raw confidence estimates, and highlight the practical usefulness of
hallucination signals to enable more reliable use of VLMs in medical VQA.
Read the full abstract ▾
All authors Ji Young Byun, Young-Jin Park, Jean-Philippe Corbeil, Asma Ben Abacha
Machine Learning · Cross-listed from cs.IR
Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization
Ansel Kaplan Erol, Seohee Yoon, Keenan Hom et al. (+1 more)
Modern recruitment platforms operate under severe information imbalance: job seekers must search over massive, rapidly changing collections of postings, while employers are overwhelmed by high-volume, low-relevance applicant pools. Existing recruitment recommender systems typically rely on keyword matching or single-stage semantic
retrieval, which struggle to capture fine-grained
alignment between candidate experience and job requirements under real-world scale and cost constraints. We present Synapse, a multi-stage semantic recruitment system that separates high-recall candidate generation from high-precision semantic reranking, combining efficient dense
retrieval using FAISS with an ensemble of contrastive learning and Large
Language Model (LLM)
reasoning. To improve transparency, Synapse incorporates a
retrieval-augmented explanation layer that grounds recommendations in explicit evidence. Beyond
retrieval, we introduce a novel evolutionary resume optimization framework that treats resume refinement as a black-box optimization problem. Using Differential
Evolution with LLM-guided mutation operators, the system iteratively modifies candidate representations to improve
alignment with screening objectives, without any labeled data. Evaluation shows that the proposed ensemble improves nDCG@10 by 22% over
embedding-only
retrieval baselines, while the evolutionary optimization loop consistently yields monotonic improvements in recommender scores, exceeding 60% relative gain across evaluated profiles. We plan to release code and data upon publication.
Read the full abstract ▾
All authors Ansel Kaplan Erol, Seohee Yoon, Keenan Hom, Xisheng Zhang
Machine Learning
A Spectral Decomposition Framework for Multiscale Nonlinear Dimensionality Reduction
Zeyang Huang, Angelos Chatzimparmpas, Thomas Höllt et al. (+1 more)
Dimensionality reduction (DR) involves two longstanding trade-offs. First, preserving local neighborhoods can come at the cost of global structure. Neighbor
embedding methods such as t-SNE and UMAP prioritize local similarity preservation but do not explicitly constrain global organization, whereas standard spectral methods such as
Laplacian Eigenmaps capture smooth, coarse-scale graph structure but offer limited flexibility to depict finer local structure. Second, the flexibility of nonlinear DR methods often comes at the cost of analytical transparency. Many methods do not explicitly reveal how high-dimensional structure produces patterns in the
embedding. We introduce SDMP (Spectral Decomposition for Multiscale Projection), a nonlinear DR framework built on an explicit spectral decomposition. In this formulation, each
embedding dimension is expressed as a weighted combination of
Laplacian eigenvectors derived from a neighborhood graph, with the weights learned via a UMAP-style cross-
entropy objective. By progressively expanding the spectral subspace to capture increasingly fine graph structure, SDMP produces a sequence of
embeddings, making the evolving balance between global organization and local detail explicit, controllable, and inspectable. The explicit decomposition also reveals which spectral scales shape the overall
embedding and how individual eigenvectors influence point positions. Quantitative evaluations on synthetic, image, and single-
cell data show competitive local and global structure preservation, while case studies illustrate how the decomposition supports interpretation of clusters and developmental trajectories across spectral scales.
Read the full abstract ▾
All authors Zeyang Huang, Angelos Chatzimparmpas, Thomas Höllt, Takanori Fujiwara
Machine Learning · Cross-listed from cs.CV
Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?
Kamalasankari Subramaniakuppusamy and Jugal Gajjar
Post-hoc feature attribution methods are widely deployed in safety-critical
vision systems, yet their stability under realistic input perturbations remains poorly characterized. Existing metrics evaluate explanations primarily under additive noise, collapse stability to a single scalar, and fail to condition on prediction preservation, conflating explanation fragility with model sensitivity. We introduce the Feature Attribution Stability Suite (FASS), a
benchmark that enforces prediction-invariance filtering, decomposes stability into three complementary metrics: structural similarity, rank correlation, and top-k Jaccard overlap-and evaluates across
geometric, photometric, and compression perturbations. Evaluating four attribution methods (Integrated Gradients, GradientSHAP, Grad-CAM, LIME) across four architectures and three
datasets-ImageNet-1K, MS COCO, and CIFAR-10, FASS shows that stability estimates depend critically on perturbation family and prediction-invariance filtering.
Geometric perturbations expose substantially greater attribution instability than photometric changes, and without conditioning on prediction preservation, up to 99% of evaluated pairs involve changed predictions. Under this controlled evaluation, we observe consistent method-level trends, with Grad-CAM achieving the highest stability across
datasets.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization
Seyyed Amirhossein Moayyedi and David Y. Yang
The new Specifications for the National Bridge Inventory (SNBI), in effect from 2022, emphasize the use of element-level condition states (CS) for risk-based bridge management. Instead of a general component rating, element-level condition data use an array of relative CS quantities (i.e., CS proportions) to represent the condition of a bridge. Although this greatly increases the granularity of bridge condition data, it introduces challenges to set up optimal life-cycle policies due to the expanded state space from one single categorical integer to four-dimensional probability arrays. This study proposes a new interpretable reinforcement learning (RL) approach to seek optimal life-cycle policies based on element-level state representations. Compared to existing RL methods, the proposed
algorithm yields life-cycle policies in the form of oblique decision trees with reasonable amounts of nodes and depth, making them directly understandable and auditable by humans and easily implementable into current bridge management systems. To achieve near-optimal policies, the proposed approach introduces three major improvements to existing RL methods: (a) the use of differentiable soft tree models as actor function approximators, (b) a temperature annealing process during training, and (c) regularization paired with
pruning rules to limit policy complexity. Collectively, these improvements can yield interpretable life-cycle policies in the form of deterministic oblique decision trees. The benefits and trade-offs from these techniques are demonstrated in both supervised and reinforcement learning settings. The resulting framework is illustrated in a life-cycle optimization problem for steel girder bridges.
Read the full abstract ▾
Machine Learning
Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits
Adam Bayley, Xiaodan Zhu, Raquel Aoki et al. (+2 more)
The recent advancement of Large
Language Models (LLMs) offers new opportunities to generate user preference data to warm-start bandits. Recent studies on contextual bandits with LLM initialization (CBLI) have shown that these synthetic priors can significantly lower early regret. However, these findings assume that LLM-generated choices are reasonably aligned with actual user preferences. In this paper, we systematically examine how LLM-generated preferences perform when random and label-flipping noise is injected into the synthetic training data. For aligned domains, we find that warm-starting remains effective up to 30% corruption, loses its advantage around 40%, and degrades performance beyond 50%. When there is systematic misalignment, even without added noise, LLM-generated priors can lead to higher regret than a cold-start bandit. To explain these behaviors, we develop a theoretical analysis that decomposes the effect of random label noise and systematic misalignment on the prior error driving the bandit's regret, and derive a sufficient condition under which LLM-based warm starts are provably better than a cold-start bandit. We validate these results across multiple conjoint
datasets and LLMs, showing that estimated
alignment reliably tracks when warm-starting improves or degrades recommendation quality.
Read the full abstract ▾
All authors Adam Bayley, Xiaodan Zhu, Raquel Aoki, Yanshuai Cao, Kevin H. Wilson
Machine Learning
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
Seonggon Kim, Alireza Khodamoradi, Pranathi Vasireddy et al. (+2 more)
Hadamard transforms have become a key tool for stabilizing low-precision training, but existing methods apply them uniformly across tensors and computation paths. We show that this one-size-fits-all strategy is inherently limited: Hadamard smoothing reduces quantization error only when its direction is properly aligned with the operand's outlier structure. Through a systematic study of weights, activations, and gradients in LLM training, we identify three stable outlier patterns, Row-wise, Column-wise, and None, and show that each outlier pattern pair in
matrix multiplication requires a distinct transform or outlier-handling strategy. We propose AdaHOP, Adaptive Hadamard transform with Outlier-Pattern-aware strategy, which applies Inner Hadamard Transform (IHT) when inner-dimension mixing properly suppresses the operands' outliers, and selectively applies Outlier Extraction (OE) that extracts dominant outlier rows or columns into a high-precision path when it does not. With fused, hardware-aware Triton kernels, AdaHOP enables training from scratch at MXFP4 precision with BF16-level quality, while achieving up to 3.6X
memory compression, 1.46X end-to-end training speedup over BF16.
Read the full abstract ▾
All authors Seonggon Kim, Alireza Khodamoradi, Pranathi Vasireddy, Kristof Denolf, Eunhyeok Park