Machine Learning
The Evaluation Game: Beyond Static LLM Benchmarking
Paul Wang, Jade Garcia-Bourrée, Anne-Marie Kermarrec et al. (+1 more)
As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large
Language Models, practitioners increasingly rely on fine-tuning as a defensive strategy. Yet the theoretical foundations underlying this robustness fine-tuning remain underexplored. We introduce a game-theoretic framework in which the interaction between an evaluator (
auditing the model for jailbreaks) and a trainer is formalized as a two-player game. A key feature of our approach is the use of group actions, a mathematical structure that captures
symmetries and transformations, to formally represent data augmentation. The simplest non-trivial instance is the circle with cyclic translation groups, where we exhibit various regimes depending on the trainer's generalization range. Below a critical threshold, the evaluator maintains a constant miss ratio for linearly many rounds, whereas other settings can yield very different behaviors. We further provide empirical evidence supporting locality-dependence of the model: for the three model families we tested (Llama, Qwen and Mistral), we have significant evidence that fine-tuning on
adversarial prompts induces only local generalization, with refusal rates on test examples highly correlated with the distance to the fine-tuning
prompts. Our framework recasts the central object of
adversarial evaluation: a
benchmark is not a static set of
prompts but an orbit under the evaluator's group action, and audit protocols that ignore trainer-side adaptation cannot distinguish a genuine fix from a memorized patch.
Read the full abstract ▾
All authors Paul Wang, Jade Garcia-Bourrée, Anne-Marie Kermarrec, Vincent Corruble
Machine Learning · Cross-listed from cs.CV
Concept-Guided Noisy Negative Suppression for Zero-Shot Classification and Grounding of Chest X-Ray Findings
Chenyu Lian, Hong-Yu Zhou, Chun-Ka Wong et al. (+1 more)
Vision-
language alignment using chest X-rays and radiology reports has emerged as an advanced paradigm for zero-shot classification and grounding of chest X-ray findings. However, standard contrastive learning typically treats radiographs and reports from different patients simply as negative pairs. This assumption introduces noisy negatives, as different patients frequently exhibit similar findings. Such noisy negatives cause semantic ambiguity and degrade performance in zero-shot understanding tasks. To address this challenge, we propose CoNNS, a concept-guided noisy-negative suppression framework. To support the negative suppression mechanism, unlike previous methods that use raw reports or templatized texts, we construct a hierarchical concept ontology using large
language models. The ontology structures 41 key clinical concepts by explicitly modeling presence, attributes (location and characteristics), and texts (evidential segment and presence statement). Leveraging this ontology, we implement a cross-patient pair relabeling strategy comprising three steps: (1) Fine-Grained Breakdown to categorize pairs based on finding presence; (2) Noisy Negative Filtering to resolve semantic conflicts by removing false negatives; and (3) Hard Negative Mining to identify subtle attribute discrepancies using a lightweight
language model. Finally, we propose a Concept-Aware NCE loss to align visual features with text while suppressing the identified noisy negatives. Extensive experiments across multi-granularity zero-shot grounding tasks and five zero-shot classification
datasets validate that CoNNS outperforms existing state-of-the-art models. The code is available at https://github.com/DopamineLcy/conns.
Read the full abstract ▾
All authors Chenyu Lian, Hong-Yu Zhou, Chun-Ka Wong, Jing Qin
Machine Learning
Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems
Jimeng Shi
Environmental science plays a pivotal role in safeguarding ecosystems, a domain driven by large-scale, heterogeneous data. In the big data era, artificial intelligence (AI) has emerged as a transformative tool for learning patterns and supporting decision-making. This dissertation develops AI-based approaches tailored to complex environmental science problems to achieve Environmental Intelligence, studying three specific challenges. First, we focus on flood prediction and management in coastal river systems. Conventional physics-based models are computationally intensive, limiting real-time application. To overcome this, we propose a deep learning (DL)-based model, WaLeF, for water level
forecasting, and a forecast-informed DL model, FIDLAr, to manage water levels. Evaluated in a flood-prone coastal system in South Florida characterized by extreme rainfall and sea level fluctuations, FIDLAr outperforms baselines in accuracy and efficiency while providing interpretable outputs. Second, we target global weather prediction, which is challenged by massive data scale. Traditional physics methods are deterministic and computationally heavy. We propose CoDiCast, a conditional
diffusion model tailored for probabilistic weather
forecasting. Adapted from generative AI for predictive tasks, experiments show CoDiCast achieves accurate, efficient forecasts with explicit uncertainty quantification. Lastly, we address scientific question-answering in environmental science. When answering in-domain questions, large
language models (LLMs) often suffer from
hallucinations due to out-of-date or limited knowledge. While
retrieval-augmented generation (RAG) retrieves domain-specific knowledge, existing methods trade off accuracy, efficiency, or explainability. We propose Hypercube-RAG, built on a structured text cube framework, which successfully exhibits all three properties simultaneously.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection
Parnian Ghapandar Kashani, Shiqi Chen and Aydogan Ozcan
The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing deep learning-based detection methods rely on computationally intensive and energy-demanding inference
algorithms, limiting their scalability. Here, we present a hybrid digital-analog deepfake
video detection framework that combines a lightweight digital front-end with a spatially multiplexed optical decoding back-end for massively parallel analog inference through a programmable spatial light modulator. By simultaneously processing 15 or more
video streams within a single optical propagation pass, the system enables high-throughput and accurate
video-level authenticity prediction at reduced computational cost compared with purely digital methods. We validated this hybrid deepfake
video processor using different
datasets spanning classical face-swapping, real-world deepfake recordings, and fully AI-generated
videos. Using a spatially multiplexed experimental set-up operating in the visible spectrum, we achieved average deepfake detection accuracy, sensitivity and specificity of 97.79%, 99.86% and 95.72%, respectively, on the Celeb-DF
video dataset with 15
videos tested in parallel in a single optical pass per inference. The multiplexed optical decoder also demonstrates resilience against various types of
video degradation, noise, compression, experimental misalignments and black-box
adversarial attacks. Our results show that integrating optical computation into AI inference enables simultaneous gains in throughput, energy efficiency, and
adversarial robustness - three properties that are difficult to achieve together in purely digital systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification
Halil Ibrahim Gulluk and Olivier Gevaert
Deep learning methods have demonstrated promising results in predicting BI-RADS scores from mammography images. However, the interpretation of these images can vary, leading to discrepancies even among radiologists. Given the inherent complexity of mammograms, training classification models solely on image labels often yields limited performance. To address this challenge, we curated 2313 mammogram images and their corresponding captions from two mammography atlases. Our proposed approach employs a multi-modal model that uses a pretrained PubMedBERT as the
language component. By training this model on image-text pairs with contrastive learning, we enable the
vision encoder to absorb the rich information contained in the captions, thereby improving its understanding of mammography findings. We then fine-tune the
vision encoder on two
datasets for BI-RADS prediction, achieving superior performance compared with models trained without this pretraining, particularly when labeled samples are scarce. The improvement in the 3-class average F1 score ranges from +1% to +14%: a +1% increase with 40K training samples, and a +14% increase with 1K samples. Furthermore, our experiments reveal that 2K image-text pairs from mammography atlases can be more informative than 2K labeled samples for label prediction, with an average margin of +1.1% when more than 10K training samples are available. Overall, our work provides a
vision-
language model for mammography and highlights the value of textual information from mammography atlases. In addition, we publicly release preprocessed mammography images of the TEKNOFEST
dataset. The training code, pre-trained model weights, data extraction scripts, and the released
dataset are publicly available at: https://github.com/igulluk/MAM-CLIP
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GR
Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
Soojin Choi, Seokhyeon Hong, Chaelin Kim et al. (+3 more)
Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body proportions. In this paper, we present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, the proposed method dynamically repositions anchors to reachable regions on the target character. This is achieved via a
Transformer-based anchor refinement strategy that predicts anchor displacements and constrains the translated anchors to remain on the target character geometry through differentiable soft projection. By incorporating pose-dependent spatial structures from the source character, the adapted anchors provide structurally coherent guidance for interaction-aware retargeting. Conditioned on these anchors, a graph-based autoencoder predicts target skeletal motion that preserves the spatial configuration of the source. To encourage task-aligned optimization between anchor adaptation and motion retargeting, we adopt an alternating training scheme in which each module is optimized in turn. Through extensive evaluations, we demonstrate that our method outperforms state-of-the-art approaches in preserving interaction fidelity across diverse character geometries.
Read the full abstract ▾
All authors Soojin Choi, Seokhyeon Hong, Chaelin Kim, Junghyun Nam, Junhyuk Jeon, Junyong Noh
Machine Learning · Cross-listed from q-bio.NC
Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa et al. (+4 more)
Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection of neuroscience and machine learning. Most
brain-encoding studies focus on aligning artificial models with
brain activity during
language comprehension or passive visual processing, while interactive
brain alignment studies have to date been largely limited to reinforcement-learning (RL)
agents and theory-based models. To address this gap, we study
brain alignment of representative models from two foundation-model types, namely
vision-
language models (VLMs) and large-action models (LAMs), using fMRI recordings from participants playing naturalistic Atari-style
video games. Specifically, we examine how action-focused and
reasoning-focused
prompts shape the models' internal representations and their
alignment with fMRI
brain activity. First, we find that both VLMs and LAMs achieve significantly higher voxel-wise encoding performance than RL baselines, with the advantage holding even under matched feature dimensionality. Second, compared to a no-
prompt baseline,
prompt-driven gains are larger in higher-order frontal-parietal and motor-planning regions than in early visual cortex, roughly 2-2.5$\times$ when averaged over region-of-interest (ROI) groups, although individual regions are heterogeneous. Third, variance partitioning reveals a qualitatively different representational organization. VLM representations are
prompt-symmetric (12.4% unique action vs. 9.5% unique
reasoning), whereas LAM representations are action-dominant (25.6% unique action vs.-8.2% unique
reasoning), with the asymmetry strongest in frontal-motor cortex. Together, these results associate action specialization with distinct cortical
alignment patterns in
multimodal game-state representations, revealing differences hidden by similar prediction accuracy.
Read the full abstract ▾
All authors Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa, Satya Sai Srinath Namburi, Tanmoy Chakraborty, Bapi S. Raju, Manish Gupta
Machine Learning · Cross-listed from cs.GR
CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control
Habib Slim, Shariq Farooq Bhat, Mohamed Elhoseiny et al. (+2 more)
Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our method takes as input a set of coarse
geometric primitives (e.g., bounding boxes) that represent distinct object parts arranged in a particular spatial configuration, and synthesizes as output part-separated 3D objects that support localized granular (i.e., compositional) editing of individual parts. The key insight that enables our method is our use of a
diffusion transformer architecture that alternates between processing each part locally and aggregating contextual information across parts globally, and features a novel conditioning technique that ensures strong adherence to the user's input. Importantly, our method learns to infer part semantics and
symmetries directly from the user's coarse layout guidance, and does not require part-level text
prompts. We demonstrate that our method enables powerful part-level editing capabilities, including context-aware substitution, addition, deletion, and style-preserving resizing operations. We show through extensive experiments that our method significantly outperforms existing approaches on guided synthesis, as measured by objective metrics and LLM-based evaluations.
Read the full abstract ▾
All authors Habib Slim, Shariq Farooq Bhat, Mohamed Elhoseiny, Yifan Wang, Mike Roberts
Machine Learning · Cross-listed from cs.CL
IMLJD: A Computational Dataset for Indian Matrimonial Litigation Analysis
Joy Bose
We present IMLJD, an open
dataset of 3,613 Indian court judgments covering matrimonial disputes under IPC Section 498A, the Protection of Women from Domestic Violence Act, and CrPC Section 482. The
dataset covers the Supreme Court of India from 2000 to 2024 (1,474 cases) and the Karnataka High Court from 2018 to 2024 (2,139 cases), with structured outcome labels, metadata-derived indicators, and a knowledge graph. We find that 57.6% of quashing petitions succeed at the Supreme Court level compared to 39.7% at the Karnataka High Court level. On a matched 2018 to 2024 period, the SC quash rate is 59.3%, widening the differential to 19.6 percentage points and confirming the finding is robust to temporal adjustment. The
dataset, code, and knowledge graph are released openly at https://github.com/joyboseroy/imljd and https://huggingface.co/
datasets/joyboseroy/imljd.
Read the full abstract ▾
Machine Learning
What Makes a Representation Good for Single-Cell Perturbation Prediction?
Wenkang Jiang, Yuhang Liu, Yichao Cai et al. (+5 more)
Single-
cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approaches, from causal representation learning to foundation models, often struggle with an overlooked challenge: gene expression is dominated by perturbation-invariant information, while perturbation-specific signals are intrinsically sparse. As a result, learned representations either entangle invariant and perturbation-specific information, leading to spurious and non-generalizable predictors, or suppress perturbation-specific signals altogether, rendering them ineffective for prediction. To address this, we propose PerturbedVAE, a general framework designed to resolve this signal imbalance. The framework explicitly separates perturbation-specific information from dominant invariant structure and recovers causal representations to effectively utilize such information for prediction. We further provide an identifiability analysis that characterizes the conditions under which sparse perturbation effects can be reliably recovered, thereby clarifying how the framework can be concretely specified under such conditions. Empirically, PerturbedVAE achieves state-of-the-art performance on a widely used
benchmark across multiple evaluation settings, yielding significant gains on out-of-distribution combinatorial predictions and uncovering interpretable perturbation-response programs.
Read the full abstract ▾
All authors Wenkang Jiang, Yuhang Liu, Yichao Cai, Erdun Gao, Jiayi Dong, Ehsan Abbasnejad, Lina Yao, Javen Qinfeng Shi
Machine Learning · Cross-listed from cs.CL
HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
Emmy Liu, Varun Gangal, Michael Yu et al. (+4 more)
Hallucination remains a central failure mode of large
language models, but existing
benchmarks operationalize it inconsistently across summarization, question answering,
retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting reduces
hallucinations across contexts. Current
benchmarks either require human annotation and fixed references that may be memorized, or rely on observations in settings that are difficult to reproduce. To study root causes, we introduce HalluWorld, an extensible
benchmark grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this world. Building on this view, we construct synthetic and semi-synthetic environments in which the reference world is fully specified, the model's view is controlled, and
hallucination labels are generated automatically. HalluWorld spans gridworlds, chess, and realistic terminal tasks, enabling controlled variation of world complexity, observability, temporal change, and source-conflict policy, and disentangling
hallucinations into fine-grained error categories. We evaluate frontier and open-weight
language models across these settings and find consistent patterns: perceptual
hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation remain difficult and are not generally solved by extended thinking. In the terminal setting, models also struggle with when to abstain. The uneven profile of failures across probe types and domains suggests that
hallucinations arise from distinct failure modes rather than a single capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing
hallucinations in modern
language models.
Read the full abstract ▾
All authors Emmy Liu, Varun Gangal, Michael Yu, Zhuofu Tao, Karan Singh, Sachin Kumar, Steven Y. Feng
Machine Learning · Cross-listed from cs.AI
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
Md Mehrab Tanjim, Jayakumar Subramanian, Branislav Kveton et al. (+6 more)
LLM
agents organize behavior through skills – structured natural-
language specifications that govern how an
agent reasons, retrieves, and responds. Unlike monolithic
prompts, skills are multi-field artifacts with platform limits: descriptions are indexed for routing, instruction bodies are loaded into a shared context window, and every extra line costs the
agent context it could spend elsewhere. Skill optimization is therefore inherently multi-objective: a skill should be accurate and economical at once. Existing
prompt optimizers collapse these goals into a single score, and we find that this makes them stall: in most of their runs, 1000 rollouts yield zero progress over the seed skill. We introduce MOCHA (Multi-Objective CHebyshev Annealing), which selects skills to improve by Chebyshev scalarization and accepts improvements that expand the Pareto front, annealing from exploration to exploitation. Chebyshev scalarization scores a skill by its largest weighted shortfall from a perfect skill; with random weights, it can select any skill on the Pareto front for improvement, including trade-offs that an average would never favor. Across six diverse skills and two models, MOCHA escapes the seed in nearly every run, achieving 7.9% higher mean accuracy than the strongest baseline (up to 23.7% on DebugBench with GPT 5.5 and 14.9% on FEVER with Claude Haiku 4.5) while discovering Pareto fronts with the highest hypervolume and nearly twice as many Pareto-optimal skills.
Read the full abstract ▾
All authors Md Mehrab Tanjim, Jayakumar Subramanian, Branislav Kveton, Xiang Chen, Subhojyoti Mukherjee, Anlan Zhang, Sungchul Kim, Sunav Choudhury, Somdeb Sarkhel
Machine Learning
An Exterior Method for Nonnegative Matrix Factorization
Qiujing Lu, Tonmoy Monsoor, Ehsan Ebrahimzadeh et al. (+2 more)
Nonnegative
matrix factorization (NMF) seeks a low-rank approximation $X \approx UV^T$ with nonnegative factors and is commonly solved using interior methods that enforce feasibility throughout optimization. We show that such constraint-driven approaches can impede progress in the nonconvex landscape, leading to slow convergence or convergence to suboptimal stationary points. We propose an exterior framework for NMF (eNMF) that separates low-rank approximation from nonnegativity enforcement. Our method initializes from the optimal unconstrained factorization and introduces a rotation procedure that maps unconstrained factors to an exterior point closest to the nonnegative orthant. This viewpoint yields an algorithmic framework in which simple iterative updates converge to KKT-satisfying stationary points on the boundary of the positive orthant. The exterior formulation also enables a
geometric interpretation of NMF solutions, clarifying equivalence classes of factorizations under permutation and orthogonal transformations. An intriguing numerical result, involving 400 NMF experiments across both real and synthetic
datasets, show that in 99% of the cases, different
algorithms tend to converge towards equivalent factor
matrices. We
benchmark eNMF against 9 state-of-the-art NMF
algorithms with 9 initialization schemes across 3 real-world and 2 synthetic
datasets. eNMF consistently outperforms all 81 competitors, achieving up to 30% lower reconstruction error under equal-time settings and up to 150% speedup under equal-error settings. The downstream experiments further demonstrate substantial performance gains in audio processing and recommendation tasks, corroborating the practical benefits of the proposed exterior optimization framework. Code is available at https://github.com/roychowdhuryresearch/eNMF
Read the full abstract ▾
All authors Qiujing Lu, Tonmoy Monsoor, Ehsan Ebrahimzadeh, Kartik Sharma, Vwani Roychowdhury
Machine Learning
BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics
Siddharth Viswanath, Panayiotis Ketonis, Cassidy All et al. (+10 more)
Brain activity unfolds as coordinated patterns across regions over time, and modeling these dynamics is a central goal in computational neuroscience. Because activity is distributed over connected
brain regions, it is naturally represented on a graph whose nodes are
brain regions or recording electrodes and whose edges capture relationships between these nodes, with message-passing modeling regional communication. However, standard message-passing networks place every node in a single shared feature space and typically aggregate messages from neighbors by scalar summation, which does not align with neurobiological evidence of
brain communication. In order to model the heterogeneous nature of the
brain, we introduce BrainDyn, a graph ordinary differential equation (ODE) network built on a cellular sheaf with dynamic restriction maps, recomputed from the
forecasting context window rather than fixed once, mediating region-to-region communication through learned linear transformations that drive the time
evolution of neural activity. We evaluate BrainDyn on resting-state fMRI,
EEG, and simulated activity from the NEST simulator. Across these modalities, we test multi-region
forecasting and autoregressive generation of
brain transients, and, using NEST, prediction of altered transients following controlled perturbations. BrainDyn outperforms competing models across modalities, while analysis of the learned features shows that they are expressive, interpretable, and biologically aligned.
Read the full abstract ▾
All authors Siddharth Viswanath, Panayiotis Ketonis, Cassidy All, William Dai, Gabriel Escobedo, Christine Gao, Jeffrey Lee, Joao Felipe Rocha, Andrew J Steindl, Ian Adelstein, Michael Perlmutter, Dhananjay Bhaskar, Smita Krishnaswamy
Machine Learning
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
Taegu Kang, Jaesik Yoon and Sungjin Ahn
Inference-time scaling has emerged as a major approach for improving
reasoning capabilities, and has been increasingly applied to
diffusion models. However, existing inference-time scaling methods for
diffusion models typically rely on external verifiers or reward models to rank and select samples, limiting their scalability to settings where such evaluators are available and reliable. Moreover, while recent
diffusion models perform sequential inference with region-wise, mixed-noise conditioning, inference-time scaling tailored to this setting remains relatively underexplored. We propose Iterative Partial Refinement (IPR), an inference-time scaling method for sequential
diffusion that requires no external verifier. Starting from an already-generated sample, IPR re-noises a subset of regions and regenerates them conditioned on the remaining regions, enabling the model to revise earlier decisions under a richer context than was available during the initial generation. This iterative partial refinement produces more globally consistent samples without external verification. On
reasoning tasks requiring global constraint satisfaction, IPR consistently improves performance: on MNIST Sudoku, the valid solution rate increases from 55.8% to 75.0%. These results show that iterative partial refinement alone can serve as an effective inference-time scaling strategy for
diffusion models in sequential, mixed-noise settings. Code is available at: https://github.com/ahn-ml/IPR
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning
Honglin Du, Muxuan Liang and Xiang Zhong
In complex multivariate systems, interactions among variables are defined by dependency structures, often encoded as directed acyclic graphs ($\text{DAGs}$). However, dependency structures can vary across subjects, and ignoring this structural heterogeneity introduces bias and obscures subpopulation-specific dependencies. To address this, we propose Directed Acyclic Graph-based Dependency Clustering via Alternating Direction Method of Multipliers (DAG-DC-ADMM), a unified framework built upon Structural Equation Modeling (SEM) that jointly learns cluster assignments and cluster-specific dependency structures. We encode acyclicity via a smooth constraint and integrate a groupwise truncated Lasso fusion penalty (gTLP) to cluster subjects based on their structural similarity. This yields a nonconvex optimization problem that incorporates sparsity, acyclicity, and structural consensus constraints. We address the nonconvexity by using the augmented Lagrangian method and solve it with an adapted version of the Alternating Direction Method of Multipliers (ADMM) for difference-of-convex programs. For certain graph structures, such as upper triangular adjacency
matrices, our
algorithm is guaranteed to converge to a Karush-Kuhn-Tucker (KKT) point. Experiments demonstrate that our method recovers cluster-specific causal dependency structures with a high true positive rate and a low false discovery rate. This capability enables the robust discovery of heterogeneous dependencies across subjects where the subpopulation label is unknown.
Read the full abstract ▾
Machine Learning
An Objective Performance Evaluation of the LSTM Networks in Time Series Classification
Sooraj Sunil and Balakumar Balasingam
The rapid adoption of deep learning has increasingly led to data-driven models replacing classical model-based
algorithms, even in domains governed by well-understood physical laws. While data-driven models, such as long short-term
memory (LSTM) networks, have become a popular choice for time-series analysis, their performance relative to model-based approaches in structured environments is rarely evaluated objectively. This paper presents a performance evaluation framework comparing an LSTM classifier against a model-based expectation maximization (EM) classifier for binary time-series classification. The evaluation is conducted on two scalar linear Gaussian state space models differing only in their noise statistics, where the Kalman filter likelihood ratio test with true parameters serves as a reference for the best achievable classification performance.Through Monte Carlo simulations, the classifiers are evaluated across three axes: task difficulty, controlled by the separation in process or measurement noise between the two models; sequence length; and training
dataset size. The results show that the EM classifier, which exploits the known model structure, performs strongly when the data conform to the assumed model class. The LSTM classifier requires a larger separation in noise statistics to achieve reliable classification, and its performance saturates below the reference classifier when the models differ only in measurement noise, regardless of sequence length or training
dataset size.
Read the full abstract ▾
Machine Learning
A Two-Phase Adaptive Balanced Penalty Method for Controllable Pareto Front Learning under Split Feasibility Conditions
Nguyen Viet Hoang, Dung D. Le and Tran Ngoc Thang
We address the open problem of training hypernetworks for Controllable Pareto Front Learning (CPFL) under split feasibility conditions with rigorous theoretical guarantees. We reformulate the constrained Pareto problem as a Bi-Level Scalarized Split Problem (BSSP) and propose the Adaptive Balanced Penalty (ABP)
algorithm, whose three gradient components – optimality, set feasibility, and image feasibility – are blended through an adaptive indicator driven by a computable lower bound. Using a novel convex surrogate technique, we prove full-sequence convergence under standard convexity and Robbins-Monro step-size assumptions. The ABP penalty structure is then translated into a two-phase, feasibility-first training strategy for Hyper-MLP and HyperTrans architectures (ABP-HyperNet). To evaluate constrained CPFL, we introduce the Expected Feasible Hypervolume (EFHV), which jointly captures solution quality and constraint satisfaction. Experiments on five multi-objective
benchmarks validate the ABP solver against ground truth, while three multi-task learning
datasets demonstrate that ABP-HyperNet achieves up to 2.3x higher EFHV than unconstrained baselines by raising feasibility from 36-49% to 87-100%.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GR
Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes
Tianshu Kuai, Arman Maesumi, Daniel Ritchie et al. (+1 more)
This paper tackles the task of learning to generate signals over triangle meshes in a triangulation-agnostic manner, meaning the trained model can be applied to different meshes and triangulations effectively. Practically, the paper adapts the flow matching (FM) paradigm to a mesh-based, triangulation-agnostic setting. Theoretically, it proposes a specific noise distribution which is triangulation agnostic, to be used inside the FM model's denoising process. While noise distributions are usually trivial to devise for, e.g., images, devising a triangulation-agnostic distribution proves to be a much more difficult task. We formulate a mathematical definition of triangulation agnosticism of distributions, via their spectrum. We then show that a discretization of a specific Gaussian random field called a Matérn process holds these desired properties, and provides a simple and efficient sampling
algorithm. We use it as our noise model, and adapt FM to the triangulation-agnostic setting by using a state-of-the-art approach for learning signals on meshes in the gradient domain – PoissonNet – as the denoiser. We conduct experiments on elaborate tasks such as sampling elastic rest states, and generating poses of
humanoids. Our method is shown to be capable of producing highly realistic results for meshes of over one million triangles, significantly exceeding the state-of-the-art in quality and diversity.
Read the full abstract ▾
All authors Tianshu Kuai, Arman Maesumi, Daniel Ritchie, Noam Aigerman
Machine Learning
Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications
Mahdi Naser Moghadasi
The exponential growth of big data has intensified the need for efficient and interpretable machine learning models that can handle diverse data characteristics while maintaining computational efficiency. Knowledge
distillation has primarily focused on neural network-to-neural network transfer, leaving cross-paradigm knowledge transfer largely unexplored. This paper presents the first comprehensive study of bidirectional knowledge
distillation between Random Forests (RF) and Deep Neural Networks (DNN), addressing critical gaps in ensemble learning and model compression for big data applications. We propose novel methodologies including progressive multi-stage
distillation, multi-teacher ensemble
distillation from diverse tree models, and uncertainty-aware cross-paradigm transfer mechanisms. Through 144 comprehensive experiments across 6 diverse
datasets encompassing classification and regression tasks, we demonstrate that bidirectional RF-DL
distillation achieves competitive performance while providing complementary benefits: interpretability from tree models and expressiveness from neural networks. Our results show that multi-teacher ensemble
distillation consistently outperforms traditional approaches, with NN-COMPACT achieving 98.13% classification accuracy and NN-WIDE reaching 92.6% R^2 score in regression tasks. The proposed framework enables deployment flexibility in big data environments, allowing optimal model selection based on computational constraints and interpretability requirements. This work establishes a new research direction in cross-paradigm knowledge transfer with significant implications for interpretable AI and scalable model deployment in resource-constrained big data systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IT
Domain-Adaptive Communication-Rate Optimization for Sim-to-Real Humanoid-Robot Wireless XR Teleoperation
Caolu Xu, Zhiyong Chen, Meixia Tao et al. (+3 more)
Wireless extended reality (XR) teleoperation provides
embodied interaction capability for collecting
humanoid robot demonstrations, but the large-scale adoption is restricted by the overhead of high-frequency motion transmission. This paper develops a system framework that integrates sampling, transmission, interpolation, and reconstruction and formulates a communication-rate optimization that aims to minimize the communication energy while maintaining the reconstruction accuracy of
robot motion trajectories through dimension-wise sampling-rate control. Since acquiring real-time feedback from physical
robots is limited by hardware costs, it is necessary to solve the problem through simulator interaction with offline real-domain data correction. To guide sim-to-real adaptation, we provide a PAC-Bayes generalization characterization that reveals the effects of latent density-ratio estimation, finite-sample deviation, and encoder bias. Building on this analysis, we propose a proximal policy optimization (PPO) method with density-ratio weighting and trust-region regularization. Experiments on public
humanoid teleoperation
dataset show that the proposed method improves the tradeoff between reconstruction error and communication energy consumption under sim-to-real distribution shift. We further analyze the effectiveness of the proposed
algorithm across various wireless channels and dynamic motion trajectories.
Read the full abstract ▾
All authors Caolu Xu, Zhiyong Chen, Meixia Tao, Li Song, Feng Yang, Wenjun Zhang
Machine Learning · Cross-listed from stat.ML
Factor Augmented High-Dimensional SGD
Shubo Li, Yuefeng Han and Xiufan Yu
Stochastic gradient descent (SGD) is a fundamental optimization
algorithm widely used in modern machine learning. In this paper, we propose Factor-Augmented SGD (FSGD), a new optimization method that leverages latent factor representations in high-dimensional learning tasks. Unlike standard two-stage dimension reduction approaches that rely on offline representation learning and full data storage, a key novelty of FSGD is that it operates purely on streaming data, making it scalable to large-scale and high-dimensional problems. Furthermore, we establish the first theoretical framework that explicitly incorporates latent factor estimation error into the analysis of SGD, and provide moment convergence in $\ell^s$ norm under decaying step sizes and mini-batch updates. Our results provide a new foundation for employing SGD reliably and scalably in high-dimensional machine learning systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Language models struggle with compartmentalization
Thomas Vincent Howe and David Wingate
In the training data used by large
language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear in English and Swahili; many functions can be expressed in both Python and Haskell; we can express propositions in both formal and natural
language. We show that LLMs can exhibit compartmentalization, where they fail to identify and share statistical strength between distinct presentations of unified concepts. In the worst case, LLMs simply learn parallel internal representations of each presentation of the concept, saturating model capacity with redundancies and decreasing sample efficiency with the number of such presentations. We also demonstrate that synthetic parallel data can fail to improve this despite being easily learned itself. Under this framework, we find that, for small models, early
multilingual learning is nearly entirely compartmentalized. Finally, all interventions that we study exhibit a phase transition in which their effectiveness depends on the number of distinct presentations, suggesting that the
language modeling objective may only inconsistently unify representations.
Read the full abstract ▾
Machine Learning
EviTrack: Selection over Sampling for Delayed Disambiguation
Omer Haq
Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations remain plausible until sufficient evidence accumulates. Standard approaches based on marginal inference struggle in this setting, either collapsing uncertainty prematurely or failing to recover once informative evidence arrives. We introduce EviTrack, a test-time inference framework that operates over latent trajectories rather than marginal states. EviTrack maintains a set of competing trajectory hypotheses and applies evidence- and likelihood-ratio-based selection to delay commitment until supported by data, drawing inspiration from hypothesis management in multiple hypothesis tracking and track-before-detect. To evaluate this setting, we construct a controlled synthetic
benchmark with known latent ground truth that explicitly exhibits delayed disambiguation. At matched inference budget, EviTrack substantially outperforms sampling-based baselines, achieving faster post-disambiguation recovery. These results show that, in delayed disambiguation regimes, moderate trajectory-level selection is more effective than increasing sampling coverage, highlighting selection over sampling as a key principle for reliable sequential inference.
Read the full abstract ▾
Machine Learning
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Chongyu Fan, Gaowen Liu, Mingyi Hong et al. (+2 more)
Muon is a
matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral gradient orthogonalization by driving all singular values of the momentum
matrix toward 1. While this uniform spectral whitening enhances exploration and outperforms AdamW in LLM pretraining, we show it could lead to fundamental limitations beyond pretraining in two regimes: (i) cross-modality
vision-
language-action (VLA) training, where inherently low-rank action-module gradients cause amplification of noisy tail directions, and (ii) reinforcement learning with verifiable rewards (RLVR), where low-SNR gradients and the need to preserve per-head specialization from prior training make whitening unstable. To address these challenges, we propose Pion, a drop-in replacement for
Muon that preserves its computational efficiency while replacing uniform spectral whitening with a two-stage Promotion+Suppression mechanism, which we call the high-pass NS iteration. This design induces a sharp spectral high-pass effect, anchoring dominant singular values at 1 while suppressing noisy tail components toward 0, with controllable filter strength. To preserve pretrained per-head heterogeneity, Pion also supports a per-head mode that applies updates independently across
attention heads via a simple reshape, at no extra cost. In VLA training on LIBERO and LIBERO-Plus, Pion consistently outperforms both baselines across l_1-regression (VLA-Adapter) and flow-matching (VLANeXt) architectures, e.g., reaching 100% success rate on LIBERO Object after 1,500 training steps with VLA-Adapter, vs. 97.0% for
Muon and only 32.2% for AdamW. The advantage of Pion further extends to a real Franka Research 3
robot with a pi_0.5 backbone under the DROID setup on three grasp-and-place tasks. In RLVR post-training on Qwen3-1.7B/4B with GRPO and GMPO, Pion also outperforms AdamW on MATH and GSM8K while
Muon collapses to zero.
Read the full abstract ▾
All authors Chongyu Fan, Gaowen Liu, Mingyi Hong, Ramana Rao Kompella, Sijia Liu
Machine Learning · Cross-listed from q-fin.PM
Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks
Rylan Wade
This paper tests whether graph neural networks improve realized
volatility forecasts and whether those forecasts improve portfolio performance. Using weekly realized
volatility for 465 S&P 500 equities from 2015-2025, Heterogeneous Autoregressive and Long Short-Term
Memory baselines are compared against GraphSAGE models built on rolling correlation, sector, and Granger-causal graphs, with and without macro regime features. The empirical finding is that the model with the lowest forecast MSE, the model with the highest cross-sectional ranking accuracy, and the model with the highest portfolio Sharpe ratio are three different models. Forecast accuracy, ranking quality, and portfolio performance are related but not interchangeable objectives. Graph
volatility models add value only when the portfolio rule can exploit the cross-sectional structure they encode.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
OpenCompass: A Universal Evaluation Platform for Large Language Models
Maosong Cao, Kai Chen, Haodong Duan et al. (+27 more)
In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large
language models (LLMs). With the rapid iteration of LLMs, objective, quantitative, and comprehensive evaluation of their capabilities has become a critical link in advancing technological development. Currently, the mainstream static
benchmark dataset-based evaluation methods face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing workflows, making it difficult to efficiently conduct cross-domain and large-scale model evaluation. To address the aforementioned issues, this paper proposes and open-sources OpenCompass, a one-stop, scalable, and high-concurrency-supported general-purpose LLM evaluation platform. Adhering to the design philosophy of modularization and component decoupling, the platform boasts three core advantages: high compatibility, flexibility, and high concurrency. The core architecture of OpenCompass comprises five key components: the Configuration System, Task Partitioning Module, Execution and Scheduling Module, Task Execution Unit, and Result Visualization Module. Its workflow provides rule-based, LLM-as-a-Judge, and cascaded evaluators to adapt to the requirements of different task scenarios. Supporting mainstream
benchmark datasets across multiple domains, including knowledge,
reasoning, computation, science,
language, code, etc., the platform offers a unified and efficient LLM evaluation tool for both academia and industry, facilitating the accurate identification of strengths and weaknesses of LLMs as well as their subsequent optimization.
Read the full abstract ▾
All authors Maosong Cao, Kai Chen, Haodong Duan, Yixiao Fang, Zhiwei Fei, Tong Gao, Ge Jiaye, Mo Li, Hongwei Liu, Junnan Liu, Yuan Liu, Chengqi Lyu, Han Lyu, Ningsheng Ma, Zerun Ma, Yu Sun, Zhiyong Wu, Linchen Xiao, Zhuozhi Xiong, Jun Xu, Haochen Ye, Zhaohui Yu, Yike Yuan, Songyang Zhang, Yufeng Zhao, Fengzhe Zhou, Peiheng Zhou, Dongsheng Zhu, Lin Zhu, Jingming Zhuo
Machine Learning
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Han Guo, Jack Zhang, Arjun Menon et al. (+4 more)
Transformer training systems are built around dense linear
algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding
memory-bound operators. Normalization, activations, residual updates, reductions, and related computations repeatedly move large intermediate tensors through global
memory while performing little arithmetic, making data movement an increasingly important bottleneck in otherwise highly optimized training stacks. We introduce CODA, a GPU kernel abstraction that expresses these computations as GEMM-plus-epilogue programs. CODA is based on the observation that many
Transformer operators exposed as separate framework kernels can be algebraically reparameterized to execute while a GEMM output tile remains on chip, before it is written to
memory. The abstraction fixes the GEMM mainloop and exposes a small set of composable epilogue primitives for scaling, reductions, pairwise transformations, and accumulation. This constrained interface preserves the performance structure of expert-written GEMMs while remaining expressive enough to cover nearly all non-
attention computation in the forward and backward pass of a standard
Transformer block. Across representative
Transformer workloads, both human- and LLM-authored CODA kernels achieve high performance, suggesting that GEMM-plus-epilogue programming offers a practical path toward combining framework-level productivity with hardware-level efficiency.
Read the full abstract ▾
All authors Han Guo, Jack Zhang, Arjun Menon, Driss Guessous, Vijay Thakkar, Yoon Kim, Tri Dao
Machine Learning
From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models
Jianan Yang, Yiran Wang, Shuai Li et al. (+3 more)
Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from gradient pathologies, spectral bias, and poor convergence, especially for problems with strong nonlinearity, sharp gradients, or multiscale features. We propose the Curriculum-Guided Gaussian Mixture Physics-Informed Neural Network (CGMPINN), which integrates Gaussian mixture modeling with dynamic curriculum learning. Specifically, a GMM is periodically fitted to the PDE residual distribution to quantify spatially varying learning difficulty. A smooth curriculum schedule progressively shifts training focus from easy to harder regions, while precision-based variance modulation suppresses unreliable clusters during early optimization. This dual curriculum is governed by a shared curriculum parameter and can be combined with self-adaptive loss balancing. We further establish theoretical guarantees, including sublinear convergence of the gradient norm for the induced time-varying loss, uniform equivalence between the curriculum-weighted and standard PDE losses, and a generalization bound with an explicit weighting-induced bias characterization. Experiments on six
benchmark PDEs spanning
elliptic,
parabolic,
hyperbolic, advection-dominated, and nonlinear reaction-
diffusion types show that CGMPINN consistently achieves the lowest relative $L_2$ and maximum absolute errors among all compared methods, reducing relative $L_2$ error by up to 97.8% over the standard PINN at comparable cost. Our code is publicly available at https://github.com/Mathematics-Yang/CGMPINN.
Read the full abstract ▾
All authors Jianan Yang, Yiran Wang, Shuai Li, Fujun Cao, Xuefei Yan, Junmin Liu
Machine Learning
Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou et al. (+3 more)
Masked
diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing
backdoor attacks on Gaussian
diffusion models or autoregressive
language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-right prediction. In this work, we present the first systematic study of training-time
backdoor attacks on MDLMs. We propose SHADOWMASK, a
backdoor attack that modifies the MDLM forward corruption process by replacing the standard all-mask terminal distribution with a trigger-mask mixture prior. This creates a dedicated denoising pathway from trigger-corrupted states to attacker-specified targets while preserving clean denoising behavior. We further provide a principled mathematical formulation by defining the backdoored forward process, deriving the reverse-time posterior, and obtaining the continuous-time training objective. Evaluations on DiT-based MDLM and LLaDA-8B-Instruct across WikiText-103, OpenWebText, and Alpaca show that SHADOWMASK achieves near-100% attack success, substantially outperforms standard data poisoning, largely preserves clean utility, remains effective under full-model and parameter-efficient fine-tuning, and is robust against representative defenses.
Read the full abstract ▾
All authors Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang, Pin-Yu Chen, Shengwei An