Machine Learning
ExecuTorch – A Unified PyTorch Solution to Run AI Models On-Device
Mergen Nachin, Digant Desai, Sicheng Stephen Jia et al. (+36 more)
Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model conversion or complete reimplementation outside the PyTorch ecosystem where the model was originally authored. We introduce ExecuTorch, a unified PyTorch-native deployment framework for edge AI. ExecuTorch enables seamless deployment of machine learning models across heterogeneous compute environments. It scales from embedded microcontrollers to complex system-on-chips (SoCs) with dedicated accelerators, powering devices ranging from wearables and smartphones to large compute clusters. ExecuTorch preserves PyTorch semantics while allowing customization, support for optimizations like quantization, and pluggable execution "backends". These features together enable fast experimentation, allowing researchers to validate deployment behavior entirely within PyTorch, bridging the gap between research and production.
Read the full abstract ▾
All authors Mergen Nachin, Digant Desai, Sicheng Stephen Jia, Chen Lai, Mengwei Liu, Jacob Szwejbka, Raziel Alvarez, RJ Ascani, Dave Bort, Manuel Candales, Andrew Caples, Yanan Cao, Zhengxu Chen, Soumith Chintala, Gregory Comer, Tanvir Islam, Songhao Jia, Tarun Karuturi, Jack Khuu, Abhinay Kukkadapu, Tugsbayasgalan Manlaibaatar, Andrew Or, Kimish Patel, Siddartha Pothapragada, Lucy Qiu, Supriya Rao, Orion Reblitz-Richardson, Max Ren, Scott Roy, Anthony Shoumikhin, Scott Wolchok, Guang Yang, Angela Yi, Martin Yuan, Hansong Zhang, Jack Zhang, Jerry Zhang, Shunting Zhang, C. Cagatay Bilgin
Machine Learning · Cross-listed from cs.CY
NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims
Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka et al. (+1 more)
Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or suitable for release - increasingly shape model deployment, governance, and public trust. Yet the artefacts needed to evaluate them are routinely withheld, producing an evidential inversion: the most consequential claims in AI safety are often the least reproducible. This position paper argues that NeurIPS should require reproducibility standards for papers making such claims, treating non-reproducibility not as a transparency preference but as an evaluation-methodology failure. The 2026 International AI Safety Report [Bengio et al., 2026] concludes that reliable pre-deployment safety testing has become harder to conduct and that models now distinguish test from deployment contexts; the 2025 Foundation Model Transparency Index [Wan et al., 2025] reports a sector-average transparency score of 40/100 with no major developer adequately disclosing train-test overlap; contemporaneous measurement-theory work shows that attack-success-rate comparisons across systems are often founded on low-validity measurements [Chouldechova et al., 2025]. We propose a three-tier disclosure framework, distinguishing public, controlled, and claim-restricted disclosure, paired with a mandatory claim inventory, scope statements, and a phased implementation path with graduated sanctions. The framework treats secrecy and openness as endpoints of a spectrum, with controlled review (via a
federated colloquium of qualified secure-review hosts) covering claims whose artefacts cannot be released publicly, and right-scaling claims whose artefacts cannot be reviewed even confidentially. The standard the community applies to its most consequential claims should be at least as high as the standard it applies to its least.
Read the full abstract ▾
All authors Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka, Ivan Flechais
Machine Learning
Synergistic Simplex: Cooperative Runtime Assurance for Safety-Critical Autonomous Systems
Ayoosh Bansal, Mikael Yeghiazaryan, Artyom Khachatryan et al. (+4 more)
Autonomous systems increasingly rely on machine-learning (ML) components for safety-critical tasks such as perception and control in autonomous vehicles (AVs). While ML enables essential capabilities, it inevitably exhibits long-tail faults that make it unsuitable for safety-critical tasks. Runtime assurance (RTA) mitigates this issue by pairing ML components with verifiable safety monitors, e.g., Control Simplex and Perception Simplex architectures. However, the limited performance of safety monitors remains a major bottleneck. The Synergistic Simplex (SS) architecture improves system performance by enabling bidirectional integration between ML components and safety monitors while preserving formal safety guarantees. The key innovation here is allowing safety monitors to use ML outputs, which is typically prohibited in RTA systems. We formally derive conditions under which this integration preserves safety and demonstrate the performance benefits. We present the design, analysis, and evaluation of SS for AV obstacle detection.
Read the full abstract ▾
All authors Ayoosh Bansal, Mikael Yeghiazaryan, Artyom Khachatryan, Tianyi Zhu, Hunmin Kim, Naira Hovakimyan, Lui Sha
Machine Learning · Cross-listed from eess.SP
Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements
Philip Franz, Max von Danwitz, Gregory Duthé et al. (+2 more)
The increasing flexibility of modern large wind turbine blades necessitates cost-efficient and reliable structural monitoring solutions. For this purpose, we propose to use aerodynamic pressure measurements obtained via Aerosense, a novel, non-intrusive and economical sensing system. In former work [Franz et al., 2025], we investigated the potential of aerodynamic pressure measurements for structural damage detection on elastic and aerodynamically loaded structures. An experimental campaign was conducted on a NACA 633418 airfoil mounted on a vertically vibrating cantilever beam within an open wind tunnel. Structural damage was introduced progressively through controlled saw cuts near the beam support. Aerodynamic pressure distributions were recorded under varying inflow conditions and structural states. Based on this data set, we developed a convolutional neural network to detect structural damage and classify its severity using only aerodynamic pressure signals. The results demonstrate that pressure measurements can effectively enable real-time detection and quantification of damage in elastic, beam-like structures subjected to mildly turbulent flow and varying operational conditions. Recognizing the limitations of pure black-box classification, in this study, we further incorporate physics-based insights and explainable machine learning methods to interpret how structural damage influences both the dynamic response and the aerodynamic pressure field. This leads to an enhanced damage detection pipeline, aiming to improve transparency, robustness, and physical consistency in data-driven monitoring of elastic, aerodynamically loaded structures.
Read the full abstract ▾
All authors Philip Franz, Max von Danwitz, Gregory Duthé, Alexander Popp, Eleni Chatzi
Machine Learning · Cross-listed from eess.AS
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin et al. (+1 more)
Test-Time Adaptation (TTA) via
entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoretically fragmented. Existing approaches typically rely on distinct heuristics, such as teacher forcing with pseudo labels or policy-gradient-based reinforcement learning, without a unified mathematical foundation. In this work, we resolve this discrepancy by deriving a rigorous formulation of EM tailored to autoregressive models. We show that the exact objective naturally decomposes into a
token-level policy gradient loss and a
token-level
entropy loss, and we reinterpret prior methods as partial realizations of this unified formulation. Using Whisper ASR as a testbed, we demonstrate that our approach consistently improves performance across more than 20 diverse domains, including acoustic noise, accents, and
multilingual settings.
Read the full abstract ▾
All authors Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin, Hung-yi Lee
Machine Learning · Cross-listed from cs.CV
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Bo Ye, Kai Gan, Tong Wei et al. (+1 more)
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonly leverage transferable representations from pre-trained models, adapting to downstream
datasets via partial fine-tuning (updating only the final ViT block) and visual
prompt tuning (appending learnable vectors to inputs). However, conventional partial fine-tuning offers limited flexibility, as it fails to adapt the entire model; meanwhile, visual
prompt tuning is prone to overfitting, due to its sensitivity to initialization and inherently constrained capacity. To address these limitations, we propose LAGCD, a simple yet effective GCD approach that embeds a residual linear adapter into each ViT block. From the perspective of feature sparsity, we systematically show that non-linearity in conventional adapters impairs performance, whereas our linear adapter enhances it by enabling more flexible model capacity. We further introduce an auxiliary distribution
alignment loss to mitigate the negative impact of biased predictions between seen and novel categories. Extensive experiments on both generic and fine-grained
datasets confirm that LAGCD consistently improves performance over many sophisticated baselines. The source code is available at https://github.com/yebo0216best/LAGCD
Read the full abstract ▾
All authors Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang
Machine Learning
Quantile Geometry Regularization for Distributional Reinforcement Learning
Zhaofan Zhang, Minghao Yang, Rufeng Chen et al. (+2 more)
Quantile-based distributional reinforcement learning methods learn return distributions through sampled
quantile regression, but their bootstrapped target
quantiles may induce distorted or degenerate distribution estimates. We propose Robust
Quantile-based Implicit
Quantile Networks (RQIQN), a lightweight Wasserstein distributionally robust enhancement boosted from a
quantile estimation perspective. We first reinterpret a snapshot of IQN loss as a collection of local empirical
quantile estimation problems over sampled current fractions. We then robustify each local slot with a Wasserstein distributionally robust
quantile estimation formulation, yielding a closed-form, fraction-dependent correction to the Bellman target. This correction directly addresses distributional degeneration: its median antisymmetry preserves the risk-neutral
quantile average, while its monotonicity enlarges upper-lower
quantile gaps and counteracts collapsed distributional spread. RQIQN thus regularizes
quantile geometry without changing the underlying value objective or requiring additional sample set reconstruction. Finally, we empirically show that the proposed RQIQN outperforms other existing
quantile-based distributional reinforcement learning
algorithms in risk-sensitive
navigation and Atari games.
Read the full abstract ▾
All authors Zhaofan Zhang, Minghao Yang, Rufeng Chen, Sihong Xie, Hui Xiong
Machine Learning · Cross-listed from cs.CV
Text-Guided Multi-Scale Frequency Representation Adaptation
Weicai Yan, Xinhua Ma, Wang Lin et al. (+1 more)
Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods have shown promising results, they exhibit notable limitations. First, most existing methods operate in the signal space domain, which results in substantial information redundancy. Second, most existing methods utilize fixed
prompts or adaptation layers, failing to fully account for the multi-scale characteristics of signals. To address these challenges, we propose the Multi-Scale Frequency Adapter (FreqAdapter), which integrates textual information and performs multi-scale fine-tuning of signals in the frequency domain. Additionally, we introduce a multi-scale adaptation strategy to optimize receptive fields across different frequency ranges, further enhancing the model's representational capacity. Extensive experiments on
multimodal models, including CLIP and LLaVA, demonstrate that FreqAdapter significantly improves both performance and efficiency. FreqAdapter improves performance with minimal cost and fast convergence within one epoch. Code is available at https://github.com/Kelvin-ywc/FreqAdapter.
Read the full abstract ▾
All authors Weicai Yan, Xinhua Ma, Wang Lin, Tao Jin
Machine Learning · Cross-listed from cs.IT
Information Density as a Quantitative Measure for AI-enabled Virtual Sensing: Feasibility and Limits
Hrishikesh Dutta, Roberto Minerva, Reza Farahbakhsh et al. (+1 more)
Modern IoT and sensor networks generate vast amounts of data, posing significant challenges for storage, transmission, and real-time processing. Traditional approaches, such as compressive sensing and machine learning-based compression, often suffer from computational inefficiencies and irreversible data loss. This paper introduces Information Density as a quantitative metric to support sensor deployment and enable AI-driven virtual sensing. We propose a framework that leverages spatial, temporal and inter-modal correlations among sensor signals to perform sensing tasks even in the absence of physical sensors. Two complementary measures: (i) Phase in Eigen Space and (ii) Mutual Information, are developed to quantify and assess information density, enabling the selection of optimal sensor configurations across both intra-modality and cross-modality scenarios. Validated using real-world data from Madrid's smart city infrastructure, this framework demonstrates the feasibility of replacing physical sensors with virtual ones under bounded error conditions (e.g., achieving $<3.21\%$ mean error with a single sensor). The results highlight the potential for scalable and energy-efficient sensing systems in smart environments.
Read the full abstract ▾
All authors Hrishikesh Dutta, Roberto Minerva, Reza Farahbakhsh, Noel Crespi
Machine Learning · Cross-listed from eess.SP
Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data
Jordy Dal Corso, Annalena Kofler, Marco Cortellazzi et al. (+2 more)
Radar sounders are electromagnetic instruments that can probe deep into the subsurface of Earth and other planetary bodies by processing the echo of transmitted radar waves. Conventional approaches for analyzing such data rely on approximate assumptions and often produce point estimates that ignore parameter correlations as well as
galactic and measurement noise. We propose a simulation-based inference approach to terrain parameter inversion from radar sounder data, where synthetic observations from a GPU-based simulator are used to train a neural network-based density
estimator for neural posterior estimation (NPE). By explicitly conditioning on reference surface assumptions, the proposed framework allows systematic evaluation of posterior robustness to reference surface variability. We demonstrate that our NPE model is well calibrated on simulated data and transferable to real Mars radar profiles, where we analyze terrain parameters using literature-informed reference values.
Read the full abstract ▾
All authors Jordy Dal Corso, Annalena Kofler, Marco Cortellazzi, Lorenzo Bruzzone, Bernhard Schölkopf
Machine Learning
Generalized Category Discovery in Federated Graph Learning
Zhongzheng Yuan, Lianshuai Guo, Xunkai Li et al. (+2 more)
Federated Graph Learning (FGL) enables collaborative learning over distributed graph data, yet existing approaches largely rely on a closed-world assumption, limiting their applicability in dynamic environments where novel categories continuously emerge. To bridge this gap, we target the practical scenario of
Federated Graph Generalized Category Discovery (FGGCD), aiming to collaboratively discover novel categories across decentralized graph clients while retaining knowledge of known categories. We observe that FGGCD introduces two fundamental challenges: (1) the Neighborhood Absorption Effect, where structural fragmentation leads to biased neighborhood aggregation, causing novel nodes to be misclassified as known categories; and (2) Global Semantic Inconsistency, where the aforementioned local biases propagate to the server and are amplified by heterogeneous subgraph distributions, hindering cross-client knowledge integration. To address these issues, we propose GCD-FGL, an FGL framework for GCD that integrates a client-side
Topology-Reliable Semantic
Alignment and Discovery process to mitigate the neighborhood absorption effect, and a server-side Hierarchical Prototype
Alignment strategy to resolve global semantic inconsistency. Extensive experiments on five real-world graph
datasets demonstrate that GCD-FGL consistently outperforms state-of-the-art baselines, achieving an average absolute gain of +4.86 in HRScore.
Read the full abstract ▾
All authors Zhongzheng Yuan, Lianshuai Guo, Xunkai Li, Wenyu Wang, Meixia Qu
Machine Learning
Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
Yihang Peng, Peng Jin, Jie Gong et al. (+4 more)
Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large
language models to downstream tasks, with LoRA-style methods being particularly attractive because they are inexpensive to train and easy to deploy. Most LoRA variants, however, revise the update rule within the weight space of each layer and leave the intermediate representations formed by deeper layers largely unused. We propose Echo-LoRA, a cross-layer representation injection method for parameter-efficient fine-tuning. During training, Echo-LoRA collects boundary hidden states from deeper source layers, aggregates them into a sample-level echo representation, and uses lightweight projection and gating networks to inject the resulting signal into shallow LoRA or DoRA modules. Answer-only masking, masked
distillation, and
stochastic routing are used to keep this auxiliary path stable and to reduce the gap between training and inference. On eight commonsense
reasoning benchmarks, Echo-LoRA exceeds the reported LoRA baselines by 5.7 percentage points on average across LLaMA-7B, LLaMA2-7B, and LLaMA3-8B. Under reproduced LoRA baselines in our unified implementation, the average gain is 3.0 points; when combined with DoRA, the gain is 2.7 points. The Echo path is discarded after training, so the deployed model keeps the original low-rank LoRA/DoRA form and adds neither inference-time parameters nor inference computation.
Read the full abstract ▾
All authors Yihang Peng, Peng Jin, Jie Gong, Xingyuan Chen, Lingjiao Xu, Ning Su, Yan Ran
Machine Learning
Physics-Modeled Neural Networks
Raul Felipe-Sosa, Angel Martin del Rey and Maria Flores Ceballos
We introduce Dynamical Physics-Modeled Neural Networks (DynPMNNs), a continuous-time deep learning architecture in which each hidden layer is defined as the solution of an ordinary differential equation. Unlike classical feed-forward networks, this approach replaces static activation functions with time-evolving dynamical systems, providing a biologically inspired interpretation of hidden-layer behavior and enabling the integration of physically meaningful models. The framework is rigorously grounded in Reproducing Kernel
Banach Spaces (RKBSs), allowing DynPMNNs to be characterized as finite-dimensional solutions of an abstract training problem and revealing structural connections with standard neural networks. We present a concrete implementation based on the FitzHugh–Nagumo model for neuronal activation, where numerical ODE solvers are embedded into the computational graph via Euler-type schemes. Both network weights and dynamical parameters are trained jointly. Through experiments on the California Housing
dataset, we compare DynPMNNs with Neural ODEs (NODEs) and Closed-form Continuous-Time Networks (CfCs). Despite using fewer trainable parameters, DynPMNNs achieve competitive performance. These results position DynPMNNs as a principled bridge between dynamical systems and deep learning, with promising directions for further research in expressivity, stability, and physics-based modeling.
Read the full abstract ▾
Machine Learning
CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning
Jingze Ge, Xue Geng, Yun Liu et al. (+6 more)
To mitigate the
memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank updates. However, such updates fail to fully capture the rank characteristics of the weight modifications observed in full-parameter fine-tuning, resulting in a performance gap. Furthermore, LoRA and other existing PEFT methods still require substantial
memory to store the full set of frozen weights, limiting their efficiency in resource-constrained settings. To addres these limitations, we introduce Cumulative Energy-Retaining Subspace Adaptation (CERSA), a novel fine-tuning paradigm that leverages singular value decomposition (SVD) to retain only the principal components responsible for 90% to 95% of the spectral energy. By fine-tuning low-rank representations derived from this principal subspace, CERSA significantly reduces
memory consumption. We conduct extensive evaluations of CERSA across models of varying scales and domains, including image recognition, text-to-image generation, and natural
language understanding. Empirical results demonstrate that CERSA consistently outperforms state-of-the-art PEFT methods while achieving substantially lower
memory requirements. The code will be publicly released.
Read the full abstract ▾
All authors Jingze Ge, Xue Geng, Yun Liu, Wanqi Dong, Wang Zhe Mark, Min Wu, Ngai-Man Cheung, Bharadwaj Veeravalli, Xulei Yang
Machine Learning · Cross-listed from cs.CV
CASISR: Circular Arbitrary-Scale Image Super-Resolution
Honggui Li, Zhengyang Zhang, Dingtai Li et al. (+11 more)
The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training
datasets and unlimited testing
datasets. It is vitally significant to enhance the GP of the pretrained ASISR models by making full use of the testing samples. The ASISR models usually employ an open-loop architecture from low-resolution (LR) images to super-resolution (SR) images. The degradation model from SR samples to LR samples is known bicubic down-sampling for the classical ASISR, is supposed down-sampling with additive random noise for the blind ASISR, and is learnable for the real-world ASISR. Combining the ASISR and degradation models, it is potentially possible to adopt a closed-loop architecture based on the automatic control theory for strengthening the GP of the ASISR methods. Therefore, this paper proposes a closed-loop architecture, circular ASISR (CASISR), to lift the capability of image reconstruction. A mathematical nonlinear loop equation is established to describe the CASISR, the reasonability of the CASISR is proven by conditional probability theory, and the stability of the CASISR is proven by Taylor series approximation. The first-order and second-order absolute difference images are defined to compare the image reconstruction performance of the ASISR and the CASISR methods. Comprehensive simulation experiments show that the proposed CASISR approach outperforms the eight state-of-the-art ASISR approaches in the quality of image reconstruction. Especially, the proposed CASISR is extraordinarily suitable for fractional SR scale factors and is extremely effective for text and stripe images with drastically changed edges.
Read the full abstract ▾
All authors Honggui Li, Zhengyang Zhang, Dingtai Li, Sinan Chen, Nahid Md Lokman Hossain, Xinfeng Xu, Yinlu Qin, Ruobing Wang, Hantao Lu, Yuting Feng, Maria Trocan, Dimitri Galayko, Amara Amara, Mohamad Sawan
Machine Learning · Cross-listed from cs.AI
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
Siyuan Guo, Yali Du, Hechang Chen et al. (+2 more)
Large
language models (LLMs) have become a central foundation of modern artificial intelligence, yet their lifecycle remains constrained by a rigid separation between training and deployment, after which learning effectively ceases. This limitation contrasts with natural intelligence, which continually adapts through interaction with its environment. In this paper, we formalise deployment-time learning (DTL) as the third stage in the LLM lifecycle that enables LLM
agents to improve from experience during deployment without modifying model parameters. We present CASCADE (CASe-based Continual Adaptation during DEployment), a general and principled framework that equips LLM
agents with an explicit, evolving episodic
memory. CASCADE formulates experience reuse as a contextual bandit problem, enabling principled exploration-exploitation trade-offs and establishing no-regret guarantees over long-term interactions. This design allows
agents to accumulate, select, and refine task-relevant cases, transforming past experience into actionable knowledge. Across 16 diverse tasks spanning medical diagnosis, legal analysis, code generation, web search, tool use, and
embodied interaction, CASCADE improves macro-averaged success rate by 20.9% over zero-shot prompting while consistently outperforming gradient-based and
memory-based baselines. By reframing deployment as an adaptive learning process, this work establishes a foundation for continually improving AI systems.
Read the full abstract ▾
All authors Siyuan Guo, Yali Du, Hechang Chen, Yi Chang, Jun Wang
Machine Learning · Cross-listed from eess.IV
Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention
Daniel Mensing, Jan Kapar, Jochen G. Hirsch et al. (+3 more)
We propose a
multimodal latent
diffusion model that jointly synthesizes volumetric
magnetic resonance imaging (MRI) and tabular clinical data within a shared latent space via cross-
attention. This approach enables coherent joint representation learning of MRI and tabular modalities for generative modeling. Our model utilizes a variational autoencoder to fuse the two modalities before
diffusion-based synthesis, allowing modality-appropriate reconstruction with separate decoders for MRI and tabular data. We evaluated the framework on data from the German National Cohort (NAKO Gesundheitsstudie), comprising over 10,000 participants with MRI scans and clinical tabular features such as age, sex, body measurements, and ethnicity. The generated MRI volumes exhibited anatomical plausibility and body composition consistent with the synthesized tabular attributes. Quantitative evaluation using Fréchet distance and precision-recall metrics confirmed high-fidelity image generation. In the tabular modality, our model outperformed CTGAN across standard evaluation metrics and achieved results comparable to TVAE, demonstrating competitive performance relative to established unimodal baselines. This work is, to our knowledge, the first to demonstrate the feasibility of jointly modeling MRI and mixed-type tabular data in a single latent
diffusion framework, offering a proof-of-concept for generating coherent synthetic
multimodal patient data and aligning with the broader goal of developing digital twins in healthcare.
Read the full abstract ▾
All authors Daniel Mensing, Jan Kapar, Jochen G. Hirsch, Matthias Günther, Horst Hahn, Marvin N. Wright
Machine Learning · Cross-listed from cs.CR
Identifier-Free Code Embedding Models for Scalable Search
Eric Wolos and Michael Doyle
Function association is a useful process for binary reverse engineers. Search tools exist to perform association at scale, but they do not utilize the full range of capabilities that AI-enabled search provides. Prior work has explored the development of
embedding models for association between certain reverse engineering code representations, but that work does not cover bidirectional association between source code and decompiled, stripped code with standard preprocessing requirements. To bridge this gap, we formalize this function association problem and evaluate the extent to which
embedding models can bidirectionally associate between these two representations. To improve model performance at this task, we fine-tune a Qwen3-
Embedding model with contrastive learning. We find that our new model outperforms other models on all function association baselines by a substantial margin and generalizes to a constant-
algorithm association task it is not explicitly trained on.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Intermediate Representations are Strong AI-Generated Image Detectors
Zhenhan Huang, Pin-Yu Chen, Tejaswini Pedapati et al. (+1 more)
The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data
embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image
embeddings and perturbed image
embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive
benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different
datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small
benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.
Read the full abstract ▾
All authors Zhenhan Huang, Pin-Yu Chen, Tejaswini Pedapati, Jianxi Gao
Machine Learning · Cross-listed from cs.DC
Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
Yixuan Mei, Zikun Li, Zixuan Chen et al. (+5 more)
The landscape of large
language models (LLMs) has become increasingly fragmented, with no single model dominating the field. Meanwhile, cloud providers offer a diverse array of mid-tier and older-generation GPUs. These heterogeneous resources provide better availability and deliver comparable performance-per-dollar to top-tier hardware. To efficiently harness these GPUs for concurrent multi-LLM serving, we introduce Coral: an adaptive, heterogeneity-aware serving system. The key idea behind Coral is the joint optimization of resource allocation and replica serving strategies across all models. To keep pace with shifting throughput demands and resource availability, Coral employs a lossless, two-stage decomposition. This approach preserves joint optimality while reducing online solve times from hours to mere tens of seconds. Evaluations across 6 models and 20 GPU configurations demonstrate that Coral reduces serving costs by up to 2.79$\times$ compared to the strongest baseline, while delivering up to 2.39$\times$ higher goodput under scarce resource constraints.
Read the full abstract ▾
All authors Yixuan Mei, Zikun Li, Zixuan Chen, Shiqi Pan, Mengdi Wu, Xupeng Miao, Zhihao Jia, K. V. Rashmi
Machine Learning
Efficiently Aligning Language Models with Online Natural Language Feedback
Christine Ye and Joe Benton
Reinforcement learning with verifiable rewards has been used to elicit impressive performance from
language models in many domains. But, broadly beneficial deployments of AI may require us to train models with strong capabilities in "fuzzy", hard-to-supervise domains. In this paper, we develop methods to align
language models in fuzzy domains where human experts are still able to provide high-quality supervision signal, but only for a small number of model outputs, using online natural
language feedback. Specifically, we train models by iteratively optimizing against proxy reward signals, stopping at the point of over-optimization, collecting fresh expert supervision, and updating the proxy reward. We construct proxy reward models from
language models using in-context learning (ICL) and fine-tuning. We test our methods by eliciting creative writing and
alignment research capabilities in Qwen3-8B and Haiku 4.5 respectively. For Qwen3-8B, ICL methods recover up to 35% of performance with 50x fewer expert samples, while fine-tuning methods recover 80% with up to 20x fewer samples and 100% with 3x fewer samples. For Haiku 4.5, ICL methods recover up to 35% of performance with 30x fewer samples, and fine-tuning methods recover 100% with 10x fewer samples. Our results suggest that online natural
language feedback can substantially improve the data efficiency of expert supervision.
Read the full abstract ▾
Machine Learning
Probing Structural Mathematical Reasoning in Language Models with Algebraic Trapdoors
Igor Rivin
We introduce a
benchmark suite for evaluating structural mathematical
reasoning in
language models, built on subgroup-construction problems in SL(3, Z) with cryptographic-style verifier-prover asymmetry. Each instance presents a finitely generated subgroup as a list of integer
matrices and asks for an arithmetic invariant – index, surjection-at-
prime, or membership – that the construction-time information (N, K) pins down in O(1) closed form, but that the solver, lacking that information, must derive by either Aschbacher-classification analysis or by a membership query in SL(3, Z) of unknown decidability. The
benchmark therefore distinguishes models with internalized algebraic priors (Aschbacher classes, McLaughlin's
theorem, Property (T), the congruence subgroup property) from models that rely on general-purpose computation. We report empirical results across five representative
reasoning traces from two state-of-the-art models. The headline result: on the index variant, one model spent 152 minutes of
reasoning, explicitly identified the kernel-side membership question as the bottleneck, attempted constructive verification, and abstained with "DON'T KNOW" rather than commit to its computed cokernel candidate – demonstrating calibrated meta-cognition on the open-decidability boundary that the
benchmark was designed to probe. We argue that the
benchmark exposes a four-way classification of model behavior (commit-correct, commit-wrong, abstain-correct, abstain-wrong) that standard answer-key scoring conflates.
Read the full abstract ▾
Machine Learning
Covariance-Aware Goodness for Scalable Forward-Forward Learning
Xiaoyi Jiang, Bashir M. Al-Hashimi and Kai Xu
The Forward-Forward
algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly under-perform backpropagation on complex
benchmarks such as ImageNet-100 and Tiny-ImageNet. We identify this gap as a structural bottleneck in goodness extraction: standard sum-of-squares formulation collapses feature volumes into channel-wise activation energies which omits critical second-order dependencies. To address this, we propose a framework centered on three key components. First, Bi-axis Covariance Goodness(BiCovG) explicitly augments the standard goodness function with structured second-order information along two axes: cross-channel projections that model inter-feature covariance, and nested multi-scale aggregation that encodes spatial correlation statistics. This provides a tractable approximation to covariance-aware goodness without the prohibitive O(C^2) complexity of explicit
matrix estimation. Second, a lightweight Logistic Fusion module aggregates layer-wise predictions, amplifying the contribution of deeper representations. Third, the Feature
Alignment Layer(FAL) introduces a zero-initialized correction at block boundaries to mitigate representation misalignment in deep locally trained networks. By introducing these three components, we effectively double the depth of viable Forward-Forward learning, extending robust layer utilization from shallow baselines to 16 layer architectures like VGG-16. The resulting BP-free model achieves 73.01% on ImageNet-100 and 50.30% on Tiny-ImageNet. As a practical extension, Hybrid Goodness Blocks control the scope of gradient propagation via configurable block sizes, further narrowing the ImageNet-100 gap to 3.6% and matching BP on Tiny-ImageNet, while still reducing peak
memory by approximately 50% relative to BP.
Read the full abstract ▾
Machine Learning
Structural Equivalence and Learning Dynamics in Delayed MARL
Jules Sintes, Ana Bušić and Jiamin Zhu
We formally establish the equivalence between Observation Delay (OD) and Action Delay (AD) in cooperative partially observable multi-
agent systems using observation-action histories. We show that both systems generate identical admissible joint-policy sets, and their induced state-action-observation trajectories are identical in distribution, leading to identical optimal solutions in Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). This formally generalizes existing infinite-horizon single-
agent results to any-horizon partially observable cooperative multi-
agent problems with decentralized policy execution, and allows any mixed-delay configuration to be reduced to a pure OD system. We further prove that in Transition-Independent MDPs (TI-MDPs), the observation-action history reduces to a tractable minimal local augmented state. However, we show through numerical experiments that although the optimal solution spaces are structurally isomorphic, the practical learning dynamics are fundamentally different. First, using the minimal local augmented state, the equivalence no longer holds when transitions are not independent. Second, operational constraints and causal credit-assignment errors in Temporal Difference (TD)
algorithms induce different learning behaviors across regimes. Finally, leveraging this structural equivalence to bypass these learning challenges, we demonstrate successful multi-
agent zero-shot policy transfer from OD to AD, paving the way for unified, efficient solution methods in complex delayed systems.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Perturbation is All You Need for Extrapolating Language Models
Zetai Cen, Jin Zhu, Xinwei Shen et al. (+1 more)
This paper develops a statistical theory of extrapolation for large
language models, by reinterpreting them through pre-post-additive noise models. In contrast to the standard autoregressive next-
token prediction based on an exact prefix, we introduce a perturbation-based procedure that first transforms the prefix into a semantic neighbour and then conditions on this perturbed variant for next-
token prediction. This yields a hierarchical model with a pre-post-additive noise structure. Within this framework, we develop a rigorous theory of extrapolability, namely, the capacity of a model class to make reliable predictions for
token sequences that lie outside the empirical support of the training corpus, by establishing five properties of the proposed procedure: adaptivity, contractivity, robustness, extrapolability, and double robustness. We evaluate the finite sample performance of the proposed procedure using both synthetic and real world
language data. Results show that the proposed method consistently improves out-of-support prediction while maintaining competitive in-support performance, demonstrating that perturbation offers a practical route to
language modelling.
Read the full abstract ▾
All authors Zetai Cen, Jin Zhu, Xinwei Shen, Chengchun Shi
Machine Learning
Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
Mohammed Sabry and Anya Belz
We study
distillation for large
language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally efficient at inference time. While prior approaches to parameter-efficient
distillation, such as LoRA, reduce adaptation cost, they leave the dense backbone unchanged and therefore fail to deliver meaningful inference savings. We propose Budgeted LoRA, a
distillation framework that treats model compression as a structured compute allocation problem. Instead of using a fixed student architecture, we introduce a global compute budget that sets the final target fraction of dense computation retained. Under this constraint, the model redistributes capacity across dense and low-rank pathways via (i) module-level dense retention coefficients, (ii) adaptive low-rank allocation, and (iii) post-training compression that selectively removes, approximates, or preserves dense components. This formulation yields a family of students controlled by a single budget dial. Empirically, Budgeted LoRA matches standard LoRA perplexity at a moderate budget with a 1.74x compressed-module speedup; at an aggressive budget it achieves a 4.05x speedup with moderate perplexity degradation, and it preserves higher accuracy on function-style in-context learning probes. These results suggest that, under compute-constrained
distillation, retaining behavior is less about matching perplexity or removing more parameters than it is about controlling how dense computation is transferred to low-rank pathways.
Read the full abstract ▾
Machine Learning
Learning-based Statistical Refinement for Denoising
Rihuan Ke
This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many existing successful denoising approaches for handling different kinds of noise, they typically require accurate modelling of the images and the noise (implicitly or explicitly), and hence the denoising results can be suboptimal due to different practical factors such as imperfect models, unreliable noise assumptions, or low quality data. In particular, when clean image samples are not available and there is a lack of knowledge of the underlying noise distribution, which is the case in various practical situations, the results may not well align with the noise statistics. The unawareness of the useful statistical information leads to suboptimal results. This work aims to make the best use of the statistical information to improve the consistency between the given denoising results and the noise statistics, under the assumption that the noise is conditionally pixel-wise independent given the clean signal. A method, based on a
Bayesian formulation of an auxiliary signal in the noisy data, is proposed for evaluating the consistency of the denoising results, without precise information on noise distribution. By leveraging the statistical information from noisy data, the method enhances the statistical noise consistency and improves denoising quality.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.NC
A foundation model of vision, audition, and language for in-silico neuroscience
Stéphane d'Ascoli, Jérémy Rapin, Yohann Benchetrit et al. (+5 more)
Cognitive neuroscience is fragmented into specialized models, each tailored to specific experimental paradigms, hence preventing a unified model of cognition in the human
brain. Here, we introduce TRIBE v2, a tri-modal (
video, audio and
language) foundation model capable of predicting human
brain activity in a variety of naturalistic and experimental conditions. Leveraging a unified
dataset of over 1,000 hours of fMRI across 720 subjects, we demonstrate that our model accurately predicts high-resolution
brain responses for novel stimuli, tasks and subjects, superseding traditional linear encoding models, delivering several-fold improvements in accuracy. Critically, TRIBE v2 enables in silico experimentation: tested on seminal visual and neuro-linguistic paradigms, it recovers a variety of results established by decades of empirical research. Finally, by extracting interpretable latent features, TRIBE v2 reveals the fine-grained topography of multisensory integration. These results establish artificial intelligence as a unifying framework for exploring the functional organization of the human
brain.
Read the full abstract ▾
All authors Stéphane d'Ascoli, Jérémy Rapin, Yohann Benchetrit, Teon Brooks, Katelyn Begany, Joséphine Raugel, Hubert Banville, Jean-Rémi King
Machine Learning
On the Architectural Complexity of Neural Networks
Nicholas J. Cooper, François G. Meyer, Michael L. Roberts et al. (+3 more)
We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations – lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the
evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a
dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.
Read the full abstract ▾
All authors Nicholas J. Cooper, François G. Meyer, Michael L. Roberts, Carlos Zapata-Carratalá, Lijun Chen, Danna Gurari
Machine Learning
DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation
Rebecca Clain, Eduardo Fernandes Montesuma and Fred Ngole Mboula
Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target domain in a decentralized setting. We address this challenge through a fully decentralized
federated approach, DeFed-GMM-DaDiL, an extension of the GMM-
Dataset Dictionary Learning (DaDiL) framework. Each client models its
dataset as a Gaussian Mixture Model (GMM), and the federation jointly approximates them via labeled Wasserstein barycenters of shared, learnable GMM atoms. This design enables adaptation without a central server while preserving clients'
privacy. We empirically study the stability of the learned representations in scenarios where the target domain has missing classes. Empirical results demonstrate that DeFed-GMM-DaDiL maintains stable and consistent shared representations across clients, effectively reconstructs missing classes, and achieves competitive performance on multi-source domain adaptation
benchmarks.
Read the full abstract ▾