Machine Learning · Cross-listed from cs.DC
FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving
Yaqi Qiao, Ping He, Songrun Xie et al. (+4 more)
Diffusion models have become the central backbone for modern image,
video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding,
diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoising steps. This all-region execution pattern makes generation latency high and limits serving throughput. Existing multi-GPU parallelization methods can reduce per-step computation, but often introduce substantial activation exchange overhead, causing communication to offset or even outweigh the benefits of parallel execution. This paper presents FlashDiff, a
diffusion serving system that improves inference efficiency through adaptive regional execution and scheduling. FlashDiff is based on the observation that
diffusion refinement is not uniform across latent regions or denoising steps: different regions often stabilize at different rates, while neighboring steps exhibit strong temporal correlation. FlashDiff leverages these properties to selectively execute only regions that require further refinement and to reallocate the resulting compute slack across concurrent serving requests. FlashDiff consists of three mechanisms. First, it decomposes the latent representation into coherent execution regions using early-stage
attention signals, preserving semantic structure while exposing fine-grained parallelism. Second, it uses a lightweight runtime controller to estimate region activity and bypass low-impact updates when further refinement is unlikely to affect output quality. Third, it applies an affinity-aware online scheduler that co-locates dependent regions, balances residual load across GPUs, and reuses reclaimed compute capacity to improve serving efficiency. Across real-world image,
video, and audio workloads, FlashDiff reduces end-to-end serving latency by 30-97% and improves throughput by 1.2-2.2x.
Read the full abstract ▾
All authors Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, Fan Lai
Machine Learning
Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning
Jing Liu, Chenxuanyin Zou, Jiayang Ren et al. (+5 more)
Federated fine-tuning of
Multimodal Large
Language Models (MLLMs) across distributed networks enables
privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynamic environments: catastrophic forgetting, wherein sequential task updates erase previously acquired knowledge across visual, linguistic, and cross-modal representations. Addressing this challenge is especially critical for autonomous networked AI operating in safety-sensitive domains, such as content moderation, where reliable retention of prior knowledge underpins system integrity. To overcome this, we propose
Federated Continual
Multimodal Learning (FedCMM), a framework that embeds continual-learning safeguards into the
federated optimization loop at three complementary levels. At the parameter level, modality-aware elastic weight consolidation computes separate Fisher information
matrices for the
vision encoder,
language backbone, and cross-modal projector, providing granular, asymmetry-aware protection against modality-specific forgetting. At the data level, each client trains a lightweight local generative replay module to synthesize raw-data-free
embedding-level
multimodal replay tuples without any raw data sharing. At the aggregation level, Task-similarity-aware gradient aggregation autonomously filters and reweights client updates by gradient cosine similarity, suppressing conflicting directions and stabilizing the global learning trajectory. Extensive experiments on two
benchmarks demonstrate that FedCMM consistently outperforms recent baselines on accuracy and backward transfer, confirming that holistic, modality-aware optimization enables robust evolutive adaptation across heterogeneous networked AI deployments.
Read the full abstract ▾
All authors Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang, Chengfang Li, Yan Wang, Zhenchao Ma, Bo Hu
Machine Learning
PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs
Jing Liu, Kun Yang, Yan Wang et al. (+5 more)
Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent
agents capable of collaborative learning while maintaining data
privacy at network edges. Within distributed network environments,
Multimodal Large
Language Models (MLLMs) serve as cognitive engines for edge devices, yet
federated fine-tuning faces substantial challenges in balancing global knowledge aggregation with local adaptation under heterogeneous network conditions. Conventional
federated protocols typically rely on uniform parameter aggregation, which conflates domain-invariant features with client-specific nuances, thereby resulting in suboptimal personalization and excessive communication overhead. To address these challenges, we propose PFAdapter, a communication-efficient framework introducing hierarchical LoRA decomposition to explicitly separate adapter parameters into global-shared and local-private components. Query and key projections are assigned to global synchronization for capturing universal
multimodal semantics across the network, while value and output projections remain localized for edge-specific adaptation. Additionally, orthogonality regularization based on the Frobenius norm enforces strict separation between these components, preventing redundant feature learning. Selective aggregation protocols synchronize only global-shared components across the
federated network, preserving local expertise and reducing communication costs by nearly 50%. Extensive experiments on VQA-RAD, SLAKE, Hateful Memes, and CrisisMMD
datasets demonstrate that PFAdapter consistently outperforms state-of-the-art baselines, achieving accuracy improvements ranging from 2.4% to 4.8% across diverse edge intelligence tasks. Consequently, our framework establishes an efficient solution for agentic AI deployment in resource-constrained communication networks.
Read the full abstract ▾
All authors Jing Liu, Kun Yang, Yan Wang, Dingkang Yang, Xiaoshuai Hao, Wei Zhang, Yang Liu, Wei Zhou
Machine Learning · Cross-listed from cs.RO
Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design
Yifei Chen, Shihan Lu, Ed Colgate et al. (+1 more)
In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by
gravity. While reinforcement learning has shown promise in learning complex finger gaiting, existing approaches do not prioritize maintaining well-conditioned grasps for sustained manipulation. We introduce two complementary physics priors for robust in-hand rolling: a global grasp-quality prior derived from classical grasp analysis and a local contact-geometry prior based on fingertip
curvature. The grasp-quality prior is used as a dense reward-shaping term that encourages well-distributed contacts with improved worst-case wrench resistance. The contact-geometry prior is expressed in the fingertip geometry that mechanically shapes the contact interface toward task-aligned rolling while reducing off-axis drift. We evaluate the effect of these priors on learning in-hand rolling manipulation for a multifingered robotic hand manipulating three different objects at four palm orientations. Results show significant improvement in rotation efficiency, grasp stability, and disturbance rejection, suggesting that physics priors embedded in both learning and fingertip morphology improve task robustness and sim-to-real transfer. An overview
video can be found at https://youtu.be/pdd1wHxQnJM?si=dM-U5kiiPTYsk3Pk.
Read the full abstract ▾
All authors Yifei Chen, Shihan Lu, Ed Colgate, Kevin Lynch
Machine Learning · Cross-listed from cs.SE
TraceSynth: Generating Production-Quality Kernel Traces with Constraint-Guided Diffusion Models
Yuvraj Sehgal, Sneh Patel, Mahsa Panahandeh et al. (+2 more)
Machine learning models for system diagnostics rely on kernel execution traces to capture fine-grained system behavior, but collecting production traces in industrial systems is costly due to runtime overhead, storage demands, and
privacy constraints. We present TraceSynth, a
diffusion-based framework for generating synthetic kernel traces that augment limited real data for downstream ML tasks. TraceSynth models traces as multi-channel sequences (event types, timestamps, CPU affinity, thread identifiers, and process metadata) using a
Transformer-based denoising
diffusion process with constraint-guided repair to enforce system invariants. Across six
benchmarks, results show strong workload dependence. For deterministic, compute-heavy workloads (scimark2), synthetic augmentation achieves 87.2% F1-Macro at context length L=4096, only 2.6 percentage points below real-only baselines. Context length is the dominant quality factor, with L=4096 yielding a +104% relative improvement over L=256, while constraint-guided repair improves synthetic data quality by up to 4.3%. Ablation studies show that lightweight 2-channel models retain 97-99% of the performance of full 6-channel models at roughly half the computational cost. TraceSynth supports cost-effective augmentation of kernel execution traces in production observability pipelines and helps identify when synthetic data can substitute for limited real traces.
Read the full abstract ▾
All authors Yuvraj Sehgal, Sneh Patel, Mahsa Panahandeh, Naser Ezzati-Jivan, Francois Tetreault
Machine Learning · Cross-listed from eess.SP
Dynamic Online Processor-Native Inference for State Estimation
Orestis Kaparounakis
Sensor-rich data-driven applications increasingly use
Bayesian approaches to infer latent states of dynamic systems from noisy sensor measurements and physical models. Yet the computation of the likelihood remains an essential bottleneck for accurate posteriors and performant inference. This paper presents a
Bayesian filtering technique that uses processor-native uncertainty tracking for both uncertainty propagation and inference. The technique implements deterministic hierarchical importance restructuring through a native operation, giving deterministic latency and bounded
memory use for arbitrary models written as program code.
Benchmarks across three nonlinear state-space systems compare the approach against particle filters and Monte-Carlo-based likelihood
estimators. The technique enables deterministic approximate filtering with as high as 805$\times$ average speedup against direct Monte Carlo work at matched result quality for model evaluation, and Pareto-dominant accuracy-latency trade-offs for posterior inference while remaining competitive in RMSE with baseline particle filters.
Read the full abstract ▾
Machine Learning
Sparse Autoencoders for Interpretable Out-of-Distribution Detection
Ayush Karmacharya, Luke Luschwitz, Lucia Romero et al. (+2 more)
Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce overconfident predictions for inputs that deviate from their training data, leading to significant degradation in performance. While many OOD detection methods focus on the final output layer, they neglect the rich hierarchical information present in intermediate network layers. This paper introduces a novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from these intermediate activations. We find that in-distribution (ID) and OOD data activate distinct sets of these sparse features. We propose a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes. Our post-hoc detection method not only achieves state-of-the-art performance on standard OOD detection
benchmarks, but yields interpretable insights into how distribution shift affects learned representations.
Read the full abstract ▾
All authors Ayush Karmacharya, Luke Luschwitz, Lucia Romero, Yanan Niu, Joseph Campbell
Machine Learning
Institutional Equity Holdings Prediction Using Node Affinities of Dynamic Graphs
Emad Izadifar and Zahed Rahmati
Institutional equity holdings disclosed in SEC Form 13F filings provide a rich temporal record of portfolio decisions by large investment managers. However,
forecasting future allocations and modeling future demand remains challenging due to disclosure lags, reporting noise, and strong persistence in institutional behavior. We introduce the first
benchmark for these tasks using temporal graph machine learning, framing holdings prediction as node affinity prediction – i.e.,
forecasting portfolio weights – on a discrete-time temporal bipartite graph of managers and securities extracted from preprocessed filings. On a sampled
dataset comprising 99 managers and the S&P 500 index (503 securities, 209,351 temporal edges across 48 quarters from 2013–2025), Node Affinity prediction model using Virtual State (NAVIS) achieves a state-of-the-art test Normalized Discounted Cumulative Gain (NDCG) of 0.9127 with features (0.9121 without), outperforming all dynamic graph representation learning competitors by a substantial margin, and outperforming all heuristic methods. Remarkably, a simple Exponential Moving Average baseline achieves 0.8882, surpassing all dynamic graph models except NAVIS and all heuristics except Persistent Forecast (0.8891), highlighting the strong smoothness and persistence of institutional portfolios. Domain-specific node features provide only marginal gains (<1.2%), indicating that temporal and structural signals in the 13F ownership graph already capture most of the predictable information. By benchmarking a suite of Temporal Graph
Benchmark (TGB) models under the node affinity prediction setting, both with and without features, on real-world 13F data, this work provides a reproducible foundation for temporal graph machine learning in holdings prediction and portfolio allocation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Learning from Complementary Ultrasound Representations for Liver Disease Classification
Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun et al. (+5 more)
Differentiating non-alcoholic steatohepatitis (NASH) from non-alcoholic fatty liver disease (NAFLD) using ultrasound remains challenging due to subtle tissue alterations and the limited information available in conventional B-mode imaging. In this work, we investigate whether complementary ultrasound representations derived from the same acquisition can improve NASH versus NAFLD classification. Specifically, we combine conventional B-mode ultrasound with physics-guided and local phase-based image representations and evaluate their effectiveness using self-supervised masked autoencoders (MAEs) and graph convolutional networks (GCNs). Experiments were conducted on a multi-site Mayo Clinic cohort consisting of 2,547 liver ultrasound scans from 125 patients. Compared with conventional B-mode ultrasound alone, complementary ultrasound representations consistently improved classification performance, yielding gains of up to 32.4% in accuracy and 91.2% in F1-score. Furthermore, performance improvements were consistently observed across age groups, sex, race, ethnicity,and acquisition sites.
Read the full abstract ▾
All authors Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun, Senanur Sahin, Harvey Castro, Soner Hacihaliloglu, Halley P. Letter, Ilker Hacihaliloglu
Machine Learning · Cross-listed from eess.IV
Analyzing Image Encoder Choices and Graph Homophily in GCN Frameworks for Breast Ultrasound Classification
Sabahattin Mert Daloglu, Ceren Coskun, Harvey Castro et al. (+2 more)
Breast ultrasound is widely used for screening, yet automated analysis remains challenging due to speckle noise, acquisition variability, and weak separation of benign and malignant cases in standard ultrasound imaging. Graph convolutional networks (GCNs) have recently emerged as a promising approach by leveraging relationships among similar patient samples. However, it remains unclear how the choice of image encoder influences graph construction and downstream classification performance. In this work, we systematically evaluate five image encoders spanning convolutional and
transformer-based architectures for GCN-based breast ultrasound classification. Image
embeddings are used to construct cosine similarity k-nearest-neighbor graphs, which are classified using a single-layer GCN with a linear classification head. Across three patientwise cross-validation folds, higher-capacity encoders consistently improve graph homophily and downstream classification performance, yielding gains in accuracy, AUC, sensitivity, specificity, and F1-score. Moreover, test-set graph homophily exhibits a strong linear correlation with classification accuracy, with higher-capacity encoders consistently occupying the high-homophily, high-accuracy region suggesting that encoder-driven improvements in graph structure are a key mechanism underlying the observed performance gains. These findings establish encoder selection as a critical factor in graph-based breast ultrasound classification and identify graph homophily as a key indicator linking representation quality to downstream classification performance.
Read the full abstract ▾
All authors Sabahattin Mert Daloglu, Ceren Coskun, Harvey Castro, Soner Hacihaliloglu, Ilker Hacihaliloglu
Machine Learning · Cross-listed from cs.CV
SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning
Jinxiu Liu, Jianru Li, Tanqing Kuang et al. (+4 more)
Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/
video synthesis to
multimodal interactive creation. Yet prevailing monolithic models remain fundamentally constrained by their inability to learn cumulatively and evolve autonomously, which is a limitation we term the "perpetual novice" problem. They lack mechanisms for structuring experience into reusable knowledge and therefore rely on brittle, "from-scratch"
reasoning for each task, resulting in poor compositional generalization and inefficient knowledge retention. Motivated by these limitations, we propose SymbOmni, an agentic omni-model designed for cumulative
evolution through Symbolic Concept Learning. At its core is the Symbolic Concept Box, an optimizable
memory module that abstracts low-level operations into reusable Symbolic Workflow Instructions. SymbOmni operates through an induction-transduction cycle: experiences are abstracted into symbolic concepts (induction), which are then adaptively composed to solve novel tasks (transduction). The training is done by verbalized backpropagation with
language-based feedback to enable continuous self-improvement without gradient-based model fine-tuning. Comprehensive experiments validate that (I) SymbOmni significantly outperforms existing
agent-based systems for iterative creation and also surpasses closed-source models (e.g., Nano Banana, GPT-Image-1) in both image quality and task success rates; (II) SymbOmni effectively reduces
token consumption by over 40% while maintaining competitive generation quality; and (III) SymbOmni enables effective continual learning by achieving cumulative gains across multiple online-learning
benchmarks and setting a new state of the art.
Read the full abstract ▾
All authors Jinxiu Liu, Jianru Li, Tanqing Kuang, Xuanming Liu, Kangfu Mei, Yandong Wen, Weiyang Liu
Machine Learning · Cross-listed from stat.ML
Learning the Graphical Nature of Symmetries
Rashid Barket, Enrico Grimaldi, Yacoub Hendi et al. (+3 more)
Finite groups are rigid algebraic objects, whose Cayley graphs expose a rich network geometry through which group-theoretic structure can be measured, compared, and learned. In this paper, a
dataset of $131{,}406$ Cayley graphs is constructed, covering all groups of order at most $767$ except order $512$, recording exact algebraic labels for group properties together with a broad collection of graph, cycle, distance, and spectral statistics. This census aims to provide novel
benchmarks for studying how finite-group properties are reflected in Cayley graph observables. It also yields new enumerative contributions: alongside recovering known OEIS sequences for standard group classes, new sequences for monolithic groups and for groups generated by at most three, four, and five elements are contributed to the OEIS. The accompanying network analysis identifies several empirical regularities and formulates testable
conjectures, including relationships involving square clustering, Cayley graph diameter, average graph disorder, and spectral eigengaps of nilpotent groups. Finally, a comparison between classical models, an MLP, and graph neural network architectures is performed for predicting algebraic group properties directly from Cayley graph data. The results show that engineered graph statistics are highly informative, while GNNs, especially GIN and in some fixed-order settings GCN, can recover substantial structural signal directly from the graph. Such that graph-aware architectures show phases of optimality on these group-theoretic graph representations.
Read the full abstract ▾
All authors Rashid Barket, Enrico Grimaldi, Yacoub Hendi, Edward Hirst, Adam Onus, Harmeet Singh
Machine Learning · Cross-listed from eess.IV
HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning
Abubakar Hamisu Kamagata, Dharm Singh Jat, Attlee Munyaradzi Gamundani et al. (+3 more)
High deployment cost, poor spatial coverage and susceptibility to storm conditions are all challenges faced by traditional in-situ methods. This paper presents a
video-based and high performance computing (HPC) enabled deep learning framework for joint sensor free estimation of five coastal wave parameters, namely significant wave height (Hs), maximum wave height (Hmax), peak period (Tp), zero upcrossing period (Tz) and wave direction (theta) from
monocular coastal
video. The proposed architecture comprises of a V-JEPA (self supervised) ViT Small backbone for robust spatiotemporal feature extraction in visually challenging scenarios, a dual-stream SlowFast temporal encoder for broad bandwidth representation of wave motion in both hydrodynamic breaking and swell regimes, an optical flow stream based on Farneback optical flow
algorithm for adding saliency information to the structure with emphasis on hydrodynamically active wavelength bands of waves, and a multi-task regression layer with dispersion constraints (Airy wave dispersion lambda_p = 0.1). The model was trained on an NVIDIA DGX A100 cluster and was early stopped at epoch 31 and achieved Pearson correlation coefficients of 0.451, 0.578, 0.643, 0.680 and 0.832 for Hs, Hmax, Tp, Tz and wave direction respectively, with generalization ability to geographically diverse held out test data sites. While operating in a data-limited regime (6 annotated training scenes), the framework demonstrates statistically significant temporal correlations (PCC of 0.451 to 0.832), confirming proof of concept feasibility; R2 values (max 0.246) indicate that variance capture will improve with larger annotated
datasets.
Read the full abstract ▾
All authors Abubakar Hamisu Kamagata, Dharm Singh Jat, Attlee Munyaradzi Gamundani, Saravanakumar Paramasivam, Babangida Sani, Aliyu Zakariyya
Machine Learning
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
Nikita Kozodoi, Zainab Afolabi and Jack Butler
Multi-task model merging combines separately trained expert models into a single model that handles all tasks without co-training. Standard practice merges experts at their optimal validation loss. We challenge this convention by systematically studying how training duration of domain experts affects the quality of the merged model. We fine-tune experts on five domains (Math, Code, Instruction Following,
Multilingual, and Safety) across three model sizes (Qwen 3.5 0.8B, 2B, and 4B), saving checkpoints from 25% to 500% of the optimal training steps and evaluating five merging methods at each duration. Our findings reveal a striking method-dependent pattern: simple averaging degrades sharply with overfitting, while sparsification-based methods achieve their best performance well past the validation optimum. We formalize this through bias-variance decomposition analysis, drawing a parallel to random forests where averaging benefits from high-variance individual learners. These results suggest that training duration and merging method should be chosen jointly rather than independently.
Read the full abstract ▾
Machine Learning
Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure
Bipin Chhetri, Deepika Giri, Avishek Kadel et al. (+2 more)
Classifying cybersecurity vulnerabilities using the Common Weakness Enumeration (CWE) taxonomy is challenging due to extreme class imbalance and strong hierarchical dependencies among weakness categories. Although oversampling techniques such as Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) are widely adopted to mitigate class imbalance, their effectiveness for hierarchical CWE text classification remains largely unexplored. This paper proposes a Hierarchy-Aware RoBERTa framework that explicitly incorporates CWE structural information through learnable parent-class
embeddings, preserving taxonomic consistency. Our experiments demonstrate that synthetic interpolation in high-dimensional
embedding spaces violates the inherent parent-child constraints of the CWE hierarchy, offering only marginal benefits for classical ML models while consistently degrading deep learning architectures. Evaluated on a CWE Research Concept
dataset, the proposed model achieves a weighted F1-score of 0.76 without data augmentation, outperforming all baselines with notable gains on minority classes, including the Class category whose F1-score improved from 0.40 to 0.60 over the BERT baseline. Our results suggest that hierarchy-aware representation learning is a more principled alternative to oversampling for structured vulnerability classification.
Read the full abstract ▾
All authors Bipin Chhetri, Deepika Giri, Avishek Kadel, Rabin Kumar Karki, Akbar Siami Namin
Machine Learning
Sparse Inter-Layer Dependencies of Transformer FFN Neurons
Johannes Knittel and Hanspeter Pfister
Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in
Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream. We examine whether the activation of an FFN
neuron can be explained by a sparse set of preceding
neuron activations and
attention outputs. We introduce a training-free attribution method that estimates the relative influence of upstream
neurons and
attention outputs on a target
neuron's activation. Empirically, across models and layers, we find that small subsets of preceding activations and
attention outputs suffice to preserve
neuron activations with high fidelity when all remaining inputs are masked with their average values. Effective sparsity is even greater when accounting for the inherent activation sparsity of upstream layers. Moreover, applying the
neuron-specific masks in all layers simultaneously, such that the induced deviations propagate through the network, leaves model perplexity largely unchanged at moderate sparsity levels. These results demonstrate that, despite dense parameterization, FFNs exhibit sparse and structured inter-layer dependencies at the
neuron level. Our method provides a practical, scalable tool for
circuit-level interpretability and identifies candidate sparse pathways with potential implications for efficient inference.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SpikeDS: Dual Sparsity Spikformer for Perineural Invasion Prediction in 3D MRI
Induk Um, Youngung Han, Kyeonghun Kim et al. (+14 more)
Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA). However, its detection from 3D MRI remains challenging due to the subtle and spatially heterogeneous imaging signatures at the tumor periphery. Capturing such spatially sparse cues necessitates volumetric analysis of 3D MRI, but existing deep learning approaches incur prohibitive computational costs on volumetric medical images, limiting their clinical deployment. We propose Dual Sparsity Spikformer (SpikeDS), a spiking neural network architecture that jointly exploits activation sparsity from binary spike communication and spatial sparsity from window
pruning based on firing rates. SpikeDS introduces Dual Sparsity Spiking
Attention (DSSA), which combines two complementary mechanisms. The first is Window-based Expert Mixture Spiking
Attention (W-EMSA), which selectively applies
attention only to salient windows identified by their firing rates. The second is Cross-Window Spiking Self-
Attention (CW-SSA), which enables global context exchange through an asymmetric scheme in which pruned windows still contribute as key-value sources. Evaluated on a clinical cohort of 139 CCA patients via 5-fold cross-validation, SpikeDS achieves an AUC of 0.753 while consuming only 14.4 mJ, surpassing the best baseline in both AUC and energy efficiency. These results suggest that dual sparsity provides an effective hardware-aware strategy for improving the efficiency of 3D spiking
transformers without compromising diagnostic performance.
Read the full abstract ▾
All authors Induk Um, Youngung Han, Kyeonghun Kim, Yului Jeong, Jina Jeong, Hyunsu Go, Dohyun Kweon, Sungha Park, Junga Kim, Anna Jung, Suah Park, Hyuk-Jae Lee, Pa Hong, Woo Kyoung Jeong, Won Jae Lee, Ken Ying-Kai Liao, Nam-Joon Kim
Machine Learning · Cross-listed from quant-ph
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
Anton Firc, Martin Perešíni, Vojtěch Mrázek et al. (+7 more)
Hybrid
quantum-classical machine learning workflows repeatedly evaluate many small parametrized
circuits during training and model exploration. In this regime, framework dispatch and orchestration overhead often dominate runtime. Prior simulators accelerate execution but leave open the question of when compile-once specialization is the right choice for static variational
circuits. We answer this question with VQCSim, a compile-once, PyTorch-native statevector execution path with native autograd. In a systematic MQT Bench study, VQCSim compiles all tested static
circuits and provides 87.7% end-to-end semantic validation. Across a five-GPU evaluation set, VQCSim delivers pooled median speedups of 4.49x for native inference and 26.78x for native training, while retaining a 3.31x advantage under matched finite-difference training. Ablation identifies native autograd as the dominant source of acceleration (27.6x), with compile-once caching and batch vectorization contributing additional gains. The speedup trades higher GPU
memory (VQCSim is
memory-limited at the high end) for lower runtime. We derive a hardware-aware regime map and release vqcsim-oracle, an open-source backend selector with 91.1%-97.7% top-1 agreement (including cross-GPU transfers), enabling automatic simulator selection in QML design loops.
Read the full abstract ▾
All authors Anton Firc, Martin Perešíni, Vojtěch Mrázek, Kamil Malinka, Vojtěch Staněk, Zbyněk Lička, Nouhaila Innan, Walid El Maouaki, Alberto Marchisio, Muhammad Shafique
Machine Learning · Cross-listed from econ.EM
Removable Defects: The Economics and Limits of Deliberate Deficiency
Cheng Qian
A specialist tolerates blind spots that a generalist does not. Usually this is treated as a cost to be minimized. We treat it as a design variable: a deficiency can be kept because it pays and removed on demand in the rare situation where it would be fatal, by routing to a compensation channel. We give three results. First, an advantage condition under which keeping the deficiency is a computable economic position; structurally it is the Ehrlich-Becker
market-vs-self-insurance margin applied to a competence gap, with the detector as a Townsend costly-state-verification technology. Second, a two-sided characterization of removability. A coupling lemma shows that when the deficiency is a coarsening of perception, no switch can separate benefit from harm, yielding a converse (a confounded detector earns zero premium, and any within-defect policy insisting on positive premium is driven, under multiplicative dynamics, to negative long-run growth) and an achievability result (a detector outside the deficiency earns a positive premium). Together, over structured uncertainty classes with severity capped or miss rate O(1/L): a defect is profitably removable iff the detector-relevant distinction survives the restriction and the advantage condition holds; the premium is the support function of the class's ROC set at an economic price vector. Third, observation defects and capacity defects differ exactly on whether access to the deployment distribution rescues them; the gap decomposes as cross-leak plus a closure deficit, and per-task randomization buys back the latter, never the former. The detector can be learned from declared fatal categories at a training bill linear in loss severity (up to a log factor). The results synthesize Chow's reject option, Kelly growth under ruin, and selective prediction.
Read the full abstract ▾
Machine Learning
Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design
Hang Yuan, Chen Li, Wenjun Ma et al. (+2 more)
Precision molecular design aims to discover personalized drug candidates through joint control of multiple conditions, such as biological relevance and molecular design strategies. Biological relevance reflects cellular functional states under disease or perturbation conditions, while molecular design strategies provide complementary guidance in terms of structural intentions and property optimization. In this study, we propose JoPMol, a jointly controlled precision molecular generative model that integrates biological states encoded by gene expression profiles with molecular structure information expressed in text, and chemical properties quantified by numerical values within a unified modeling framework. This formulation enables coordinated generation and optimization of candidate molecules under joint condition control. Experimental results show that JoPMol outperforms state-of-the-art methods across multiple evaluation metrics. Moreover, JoPMol demonstrates strong generalization ability in both transfer tasks and biologically grounded simulation scenarios, validating its effectiveness for precision molecular design. The source code is publicly available at https://github.com/hala-yh/JoPMol.
Read the full abstract ▾
All authors Hang Yuan, Chen Li, Wenjun Ma, Tadahiko Murata, Yuncheng Jiang
Machine Learning
LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention
Ziqi Yin, Jianyang Gao, Peiqi Yin et al. (+2 more)
Indexer-TopK, which computes scores and selects the top-$k$ candidates, is a key primitive in long-context sparse
attention for large
language models and vector
retrieval for recommendation systems and vector databases. However, existing GPU-based Indexer-TopK kernels like DeepSeek Sparse
Attention (DSA) typically separate scoring from selection and materialize the full score
matrix in high-bandwidth
memory. This strategy is inefficient for large score
matrices, such as those encountered in long-context sparse
attention, due to excessive global-
memory traffic, costly synchronization, and prohibitive
memory overhead. In this study, motivated by the curse of dimensionality, we observe that sparse
attention scores exhibit a concentration phenomenon, with scores falling within a narrow range. Based on this observation, we propose LiteTopK, an efficient fused Indexer-TopK kernel. LiteTopK samples a small subset of data to estimate query-data score ranges, then partitions candidates into bins accordingly. This design allows LiteTopK to maintain a slightly relaxed threshold online and write back only promising candidates, reducing unnecessary I/O and
memory overhead while preserving exact top-$k$ correctness. Building on LiteTopK, we further propose LiteDSA, which packs the overlapping candidates of neighboring query
tokens into a shared key/value list for joint
attention and uses per-query masks to preserve each
token's original top-$k$ membership while reducing
memory traffic. We integrate LiteTopK into three widely used LLM training and inference systems: vLLM, SGLang, and Megatron-LM. Experiments in a production environment with eight NVIDIA B200 GPUs demonstrate prefill speedups of up to $1.49\times$ across GLM-5.2, DeepSeek-V4-Flash, and Hy-4-Preview at a context length of 1M
tokens, without compromising model capabilities.
Read the full abstract ▾
All authors Ziqi Yin, Jianyang Gao, Peiqi Yin, Jiangneng Li, Gao Cong
Machine Learning
Signal-Guided Optimization for Machine Unlearning
Xujia Li, Dan Li, Jian Lou et al. (+1 more)
Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies. They lack precise pilot signals to guide the unlearning process and fail to provide differentiable guidance across different unlearning tasks. Due to the varying memorization strengths of samples during original training, such a uniform strategy leads to two problems: some samples are over-unlearned, which harms model utility; while others are under-unlearned, leaving residual information that can be exploited by
privacy attacks. In this paper, we propose GSUO, a guidance-signal-aware unlearning optimization framework that designs task-specific fine-grained guidance signals to steer the unlearning process and is applicable to both random-subset and class-wise forgetting tasks. Extensive experiments demonstrate that GSUO outperforms 14 baselines in terms of both unlearning effectiveness and generalization, while achieving high efficiency and significant speedups, validating its effectiveness for reliable machine unlearning.
Read the full abstract ▾
All authors Xujia Li, Dan Li, Jian Lou, Wenjie Feng
Machine Learning
Learning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance
Zixuan Shen, Bingchuan Wang, Zhi Wang et al. (+1 more)
Most neural partial differential equation (PDE) surrogates learn how fields evolve after a grid has already been chosen. However, before any operator is applied, the grid has already determined how modeling capacity is allocated across space, resolution, and spectral bandwidth. We argue that this hidden design choice should itself be learnable, leading to a question different from standard operator learning: can a surrogate learn where resolution should exist before predicting field
evolution? We formulate adaptive discretization as a physics-constrained conditional generation problem over valid mesh displacements. The success of
diffusion models in PDE field prediction suggests their potential for learning adaptive discretizations under similar structured constraints. This leads to a two-stage
diffusion framework: Stage 1 learns an r-adaptive displacement mesh conditioned on the observed dynamics, while Stage 2 predicts the solution
evolution from the mesh-informed representation. The mesh generator is regularized by physics-aware proxy channels,
geometric validity constraints, and local spectral concentration so that adaptation remains physically interpretable and numerically legal. Across five PDE regimes, the results show that
diffusion-based learned discretization is competitive with adaptive-mesh and reduced-order baselines, with particularly strong gains in regimes where fixed or handcrafted allocation is insufficient. The main conclusion is not that there exists a universal optimal mesh rule, but that discretization should be learned in a regime-dependent manner: different spatial and spectral structures favor different allocation behaviors. This reframes adaptive meshing for neural PDE solvers from a solver-specific heuristic into a generative representation-learning problem.
Read the full abstract ▾
All authors Zixuan Shen, Bingchuan Wang, Zhi Wang, Yong Wang
Machine Learning
Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems
Yubo Zhang and Xiaodong Wang
We develop an enhanced in-context learning (ICL) framework to improve the performance of pilot-based beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed scheme integrates the ICL-
Transformer backbone with the pilot encoder-decoder network (EDN) and the beamformer EDN. A crucial feature of our ICL network is that it can handle multiple channel models without retraining, enabled by the construction of model-specific context
datasets. To improve convergence and robustness, we introduce three key innovations: (a) a curriculum learning (CL) strategy that smoothly transitions from supervised LMMSE-labeled imitation to unsupervised sum-rate maximization, (b) a self-evolving mechanism that dynamically expands and refines the context
datasets for all channel models during CL-based training, and (c) a mismatch-aware extension that incorporates several mismatches into the general ICL framework and bypasses explicit channel calibrations. Ablation studies validate the effectiveness of the in-context architecture and enhanced training strategies. Simulation results over diverse communication environments show that the proposed scheme is able to rapidly adapt to both seen and unseen channel models without gradient-based parameter updates, and can mitigate the mismatch issues via intelligent context constructions. Furthermore, our scheme consistently outperforms the existing beamforming schemes under pilot-based settings, including the WMMSE
benchmark and the recent
Transformer-based methods.
Read the full abstract ▾
Machine Learning
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Shikai Qiu, Marc Finzi, Yujia Zheng et al. (+2 more)
Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that realize this simplicity. Parameter-based methods such as quantization produce code lengths that scale with model size, insensitive to how much information the parameters store. Prequential coding bypasses this issue by compressing the training trajectory, but codes the exact data sequence regardless of how much the model learns, yielding large codes when the data has high
entropy. We introduce requential coding, where a teacher model selects training samples drawn from the student's own distribution. The student's code records only these selections, which cost bits only where teacher and student disagree. The resulting code length is independent of parameter count and data
entropy, and often orders of magnitude shorter than the prequential counterpart, with an advantage that grows with scale. This compression sheds light on phenomena inaccessible to prior compressors. Holding loss fixed, larger models and ensembles compress to much smaller sizes despite more parameters. Plugged into a PAC-Bayes bound, the requential code yields state-of-the-art generalization guarantees for billion-parameter LLMs, outperforming bounds built on aggressive post-training quantization even granted zero error. The bound tightens with scale in the compute-optimal regime, as models become increasingly compressible relative to
dataset size. The same code predicts that models gradually overfit when trained for multiple epochs. It also isolates the learnable information in a
dataset from its unpredictable, random content, revealing that lower-
entropy text holds far more learnable structure than higher-
entropy image data.
Read the full abstract ▾
All authors Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang, Andrew Gordon Wilson
Machine Learning
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet et al. (+1 more)
We present a theoretical framework to explain the emergence of inductive
reasoning abilities in
Transformer language models. While previous works on
Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop
reasoning. In this class, we theoretically prove that the training dynamics of
attention models can be confined to a highly interpretable, low-dimensional invariant
manifold. On this
manifold, the learning dynamics are captured by a handful of interpretable coordinates rather than millions of parameters, making both theoretical and empirical analysis more tractable. Using this framework, we characterize how data statistics govern the competition between in-context and in-weights learning, we study how random initializations determine the `winning'
circuit when multiple solutions are possible, and we demonstrate that the coordinate frame associated with the
manifold can be used to automatically detect which
circuits have been learned in trained models. By casting
circuit formation as a low-dimensional dynamical phenomenon, we take a step toward a predictive theory of how
Transformers learn.
Read the full abstract ▾
All authors Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet, Thomas Hofmann
Machine Learning · Cross-listed from cs.RO
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
Yunhai Feng, Natalie Leung, Jiaxuan Wang et al. (+3 more)
Recent work in
humanoid whole-body control has found success with a simple recipe: retarget human motion to
robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation? The answer is not obvious, as manipulation involves complex, contact-rich dynamics and requires delicate regulation of contact modes and forces. We present REGRIND, a minimalist retargeting-guided RL pipeline that learns dexterous manipulation policies from a single human demonstration. REGRIND retargets human hand-object motion to a
robot reference that preserves hand-object spatial and contact relationships, trains a residual RL policy in simulation to track object-centric keypoints along that reference, and transfers the resulting policy zero-shot to hardware with careful system identification. The resulting policies produce fluid, human-like behavior on two different multi-fingered hands across contact-rich tool-use tasks, including operating a pair of scissors and turning a screwdriver. Through systematic hardware experiments, we identify and analyze the key factors that govern sim-to-real transfer in dexterous manipulation, offering practical guidance for retargeting-based learning in contact-rich settings.
Videos and code are available at https://yunhaifeng.com/REGRIND.
Read the full abstract ▾
All authors Yunhai Feng, Natalie Leung, Jiaxuan Wang, Lujie Yang, Haozhi Qi, Preston Culbertson
Machine Learning · Cross-listed from cs.CL
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
Esteban U. Vega Barajas
Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design. Two questions limit its reuse: whether a protocol fixed to 2019-era frozen
embeddings stays competitive as representation methods advance, and whether it transfers to a second
language. We re-run it on the original Spanish data across three representation generations, sparse lexical features, frozen
transformer embeddings, and prompted large
language models, and transfer its sentiment task to English with a balanced 45,000-comment corpus checked against an aspect-labeled education
dataset. Treating paired comparisons as descriptive, we find the protocol durable: a 2026 frontier model posts the highest thematic F1 on the hardest Spanish task, yet shows no sentiment advantage over a cheap model and no descriptive separation from it on English, so model choice is a deployment decision, not a property of the method.
Read the full abstract ▾
Machine Learning
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
Zixiang Xu, Sixian Li, Huaxing Liu et al. (+4 more)
Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose
prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-output view and operationally useful in ways it does not afford. We report three findings, across seven judges, seven bias types, and nine
benchmarks. Geometry: baseline judging inputs occupy a tight activation
manifold while biased inputs are displaced along a low-dimensional, type-specific subspace that sharpens with depth and is recovered consistently by three families of
estimators. Causal control: steering hidden states along this subspace drives scoring in both directions, forward shifts reproducing biased scoring on clean inputs and reverse shifts restoring baseline scoring on biased ones, while matched-norm random directions produce shifts an order of magnitude smaller. Operational: a simple linear projection onto the same bias-direction features anticipates judge failures on three entirely unseen
benchmarks, substantially outperforming text-based alternatives. Reading bias as activation geometry, rather than as input-output noise, unifies
geometric structure, causal control, and operational prediction within a single framework. The project page is available at https://xzx34.github.io/unfair-judge/
Read the full abstract ▾
All authors Zixiang Xu, Sixian Li, Huaxing Liu, Xiang Wang, Shuai Li, Zirui Song, Xiuying Chen
Machine Learning · Cross-listed from quant-ph
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
Junrui Zhang, Zemin Chen, Lusi Li et al. (+3 more)
Quantum Neural Networks (QNNs) are a promising framework for
quantum machine learning on near-term
quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to
backdoor attacks, yet existing
quantum backdoors mostly rely on a fixed trigger shared by all poisoned inputs. This fixed-trigger design is a major weakness because many defenses detect or weaken the repeated patterns such triggers leave in data representations. Although input-aware dynamic
backdoors have been studied in classical neural networks, transferring them to QNNs is difficult because
quantum learning introduces new obstacles. In particular, measurement compresses the post-ansatz
quantum state into a limited classical output, weakening supervision for a trigger generator, while individual density
matrices fluctuate with the input and make per-sample contrastive learning unstable. To address these challenges, we propose Q-DIBA, the first input-aware dynamic
backdoor attack for QNNs. Q-DIBA jointly trains a classical trigger generator and a victim QNN through a three-mode mini-batch strategy that supports clean behavior, attack activation, and trigger specificity. To provide stable
quantum-level supervision, Q-DIBA introduces an ensemble density contrastive loss that operates on post-ansatz
quantum states before measurement and contrasts mode-averaged density
matrices rather than individual samples. Experiments on MNIST and Fashion-MNIST across multiple QNN architectures show that Q-DIBA achieves high clean accuracy, strong attack success, and high cross-trigger accuracy, demonstrating effectiveness, stealthiness, and input specificity. The attack also remains resilient against defenses including visual inspection, spectral-signature detection, and fine-tuning, suggesting that input-aware
quantum backdoors are an important threat to secure QNN deployment.
Read the full abstract ▾
All authors Junrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol, Daniel Takabi, Rui Ning