Machine Learning
ReRAM-aware Model Finetuning addressing I-V Non-linearity and Retention Errors
Ching-Yi Lin, Shamik Kundu, Arnab Raha et al. (+1 more)
Traditional CPU, GPU, and NPU architectures are increasingly limited by the von Neumann bottleneck. While In-
Memory Computing (IMC) using ReRAM crossbar arrays offers a high-density, energy-efficient alternative, its practical deployment is constrained through their non-idealities. Existing hardware-aware training frameworks often require training from scratch, which is computationally prohibitive for modern large-scale models. In this work, we propose a finetuning-based hardware-aware training
algorithm that enables robust DNN deployment on ReRAM with minimal training overhead. Our approach mitigates I-V non-linearity by applying a range-shrunk sinh transformation and incorporates retention errors directly into a regularization loss during the finetuning process. We evaluate our framework across models and tasks such as image classification and question-answering (QA). Experimental results demonstrate that our method achieves similar accuracy on large-scale models like ResNet18 and DeiT-Tiny as the base model. In-case of ImageNet for MobileNetV3 families the technique has only less than 2% accuracy degradation. Further, applying the technique on the SQuAD v2
dataset results in only 1 point degradation of F-1 score.
Read the full abstract ▾
All authors Ching-Yi Lin, Shamik Kundu, Arnab Raha, Sahil Shah
Machine Learning
Perron–Frobenius Operator Matching for Generative Modeling
Shiqi Zhang, Wuwei Wu, Jaemin Oh et al. (+2 more)
We introduce Perron–Frobenius Operator Matching (PFOM), a generative framework that matches density
evolution via the integral PF operator, subsuming flow,
diffusion, and jump models. We prove that among Bregman divergences, only Kullback–Leibler divergence preserves equality between density-level and sample-conditioned objectives, yielding a practical loss equivalent to Koopman path matching. We further develop Nesterov-accelerated training and sampling that stabilize discretization and accelerate convergence. %On Gaussian mixtures and two-moons, PFOM achieves faster KL/$W_2$/MMD decrease and improved wall-clock efficiency with empirical validation. PFOM unifies operator-theoretic identification with modern generative modeling and opens paths to adaptive dictionaries and high-dimensional applications.
Read the full abstract ▾
All authors Shiqi Zhang, Wuwei Wu, Jaemin Oh, Jie Chen, Xiaoning Qian
Machine Learning
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
Jeffrey G. Wang, Jason Wang, Marvin Li et al. (+1 more)
Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's
privacy properties. Although several attempts have been made to evaluate MIAs on
language models, the extant literature has suffered numerous difficulties in constructing clean evaluations to test new techniques. In particular, subtle distribution shifts between member and non-member sets can undermine the statistical validity of MIAs; recent work has underscored this by showing that "blind" methods with no access to the underlying model can perform far better than published methods on the same
benchmarks. This paper constructs a
benchmark for principled evaluation of MIAs against LLMs, by leveraging the insight that training data before and after a fixed point during training are drawn from the same distribution. Therefore, all open-source models with intermediate checkpoints and public training data can be converted into MIA testbeds. We apply our framework to a half-dozen published attacks on the Pythia and OLMo family of models, from 70M to 7B parameters. To facilitate further
privacy research, we open-source a modular library for designing and implementing attacks in this setting: https://github.com/safr-ai-lab/pandora_llm.
Read the full abstract ▾
All authors Jeffrey G. Wang, Jason Wang, Marvin Li, Seth Neel
Machine Learning
ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation
Chongru Fan, Wei Wang, Wentao Huang et al. (+5 more)
While Website Fingerprinting (WF) attacks achieve high accuracy in controlled laboratory settings, they often degrade substantially in real-world environments due to spatio-temporal drift, browser heterogeneity, proxy obfuscation and etc. This limitation stems from their sole reliance on low-level traffic features that are noisy and highly sensitive to environmental perturbations. To address this problem, we propose ResAware, a cross-environment resource-aware
distillation framework under a training-rich/inference-poor asymmetric setting. Specifically, ResAware trains a teacher model on resource-level features, and then distills the resulting privileged knowledge into a student model through heterogeneous knowledge
distillation. At deployment time, the student model performs inference using only encrypted traffic, incurring zero additional cost. We evaluate ResAware on a large-scale
dataset collected over five months from six globally distributed vantage points, comprising more than $160{,}000$ paired samples. The results show that ResAware significantly enhances the cross-environment robustness of diverse WF baselines. Under a 150-day temporal drift, for example, ResAware improves the F1-score of Var-CNN from $72.77\%$ to $81.49\%$ and the open-world $TPR@1\%FPR$ from $22.40\%$ to $27.20\%$. Our results demonstrate that resource-level supervision improves WF robustness without expanding online observation capabilities.
Read the full abstract ▾
All authors Chongru Fan, Wei Wang, Wentao Huang, Zhenquan Ding, Jinqiao Shi, Lei Cui, Zhiyu Hao, Xiaochun Yun
Machine Learning · Cross-listed from cs.AR
AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting
Yiting Wang, Chenhui Deng, Chia-Tung Ho et al. (+6 more)
Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, yet current FGCG optimization flows remain largely manual. Recent LLM-based RTL optimization approaches remain limited by two key drawbacks: (1) the inability to process long waveform traces spanning millions of cycles, and (2) the difficulty of scaling optimization to large hierarchical codebases while preserving correctness. In this work, we present AUTOGATE, the first agentic framework for industry-grade RTL power optimization, enabling workload-aware clock-gating optimization across large hierarchical codebases. AUTOGATE introduces a Machine Learning (ML)-LLM co-design that bridges waveform-level analysis and RTL rewriting. Specifically, we design an ML-based clustering
algorithm that distills raw toggling traces into compact, structured representations that guide LLM-based RTL rewriting. This enables accurate identification and application of clock-gating opportunities without requiring LLMs to directly process raw waveform data. To enhance scalability, AUTOGATE employs a hierarchical multi-
agent architecture that decomposes large designs into independently optimizable modules, enabling coordinated optimization across deep design hierarchies. We evaluate AUTOGATE on a diverse set of designs ranging from small RTL designs to large industrial-grade codebases. Experimental results show that AUTOGATE consistently reduces dynamic power relative to baselines. Across the small-design suite, AUTOGATE reduces dynamic power by 49.31% on average. On industry-scale designs, it achieves 19.34% and 7.96% dynamic power reductions on NVDLA and BlackParrot, respectively, and up to 6.86% on highly optimized proprietary production designs.
Read the full abstract ▾
All authors Yiting Wang, Chenhui Deng, Chia-Tung Ho, Yanqing Zhang, Zhuo Feng, Cunxi Yu, Ang Li, Gang Qu, Brucek Khailany
Machine Learning
Operator Boosting Produces Pareto-Efficient PDE Surrogates
Lennon J. Shikhman
Neural operators are widely used as surrogate solution maps for partial differential equations (PDEs), but full-size models can be costly to store, deploy, and evaluate in many-query scientific workflows. This work introduces Operator Boosting, a stagewise residual-learning framework for constructing compact neural-operator surrogates directly, rather than training a large model and compressing it afterward. Starting from the empirical mean predictor in normalized output coordinates, the method trains a sequence of tiny same-family neural operators on residual fields and incorporates each correction through validation-selected shrinkage. We instantiate the framework with
Fourier neural operators (FNOs), DeepONets, and convolutional neural operators (CNOs), and compare boosted tiny stacks against full-size monolithic baselines across one-, two-, and three-dimensional PDE
benchmarks from PDEBench, APEBench, and The Well. Across 30
dataset-architecture pairs, 21 show positive mean accuracy gains and 17 have positive confidence intervals, while all boosted stacks reduce trainable parameter count by approximately 72-95%. Best-model comparisons show empirical Pareto improvements on 7 of 10 completed PDE
benchmarks, including two-dimensional Navier-Stokes, shallow-water dynamics, Darcy flow, one-dimensional transport and reaction systems, and three-dimensional compressible Navier-Stokes. These results show that Operator Boosting often improves the empirical accuracy-parameter Pareto frontier of neural PDE surrogates, while also exposing PDE- and architecture-dependent regimes where residual boosting fails to offset compression.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Dissecting model behavior through agent trajectories
Gaurav Gupta, Vatshank Chaturvedi, Sudipta Sengupta et al. (+2 more)
AI
agent performance is not just a modeling problem, it is fundamentally a systems problem. The advanced capabilities of models are realized through
agent harnesses. Therefore, a gap between model assumptions and harness behavior can easily prevent the model's full capabilities from translating into
agent performance. We formalize this as the `intent-execution' gap: the mismatch between what the model intends and what the harness executes, and vice versa. We argue that minimizing this intent-execution gap is as important as other aspects of harness design such as tools and execution loops. To illustrate the impact of this harness-model
alignment, we develop a simple and customizable harness called `Simple Strands
Agent' (SSA). SSA aims to find the bulk of common patterns which generalize across different model families (such as Claude, Gemini, GPT, Grok, Qwen), as well as a small number of model-specific preferences. We make two contributions: (i) we reproduce or improve on the pass@1 performance reported by diverse model-provider families on popular agentic
benchmarks (SWE-Pro, SWE-Verified, Terminal-Bench-2, and Deep-SWE), and (ii) building on an \textbf{analysis of 154k trajectories generated by SSA}, we look beyond the pass@1 numbers which tend to be relatively even across frontier models. By representing
agent trajectories in code state-spaces, we compute solution distance and backtracking to observe model-level differences in problem-solving behavior. Finer-grained metrics such as edit frequency, testing activity, and phase-transitions reveal how individual models allocate effort across different stages of problem solving.
Read the full abstract ▾
All authors Gaurav Gupta, Vatshank Chaturvedi, Sudipta Sengupta, Jun Huan, Anoop Deoras
Machine Learning
Credibility-Weighted Pricing of Autonomous Vehicle Liability Under Operational Design Domain Shift
Doyeon Jang
Automated Driving System deployments create a foundational ratemaking challenge: sparse experience, shifting operational design domains, and non-stationary risk across software releases. We propose a hierarchical
Bayesian credibility framework pooling across cities, software versions, and territories via a learned ODD-similarity kernel, nesting Buhlmann-Straub as a limiting case. Demonstrated on 648 verified-engaged Waymo crashes across four U.S. metros from the NHTSA Standing General Order database against 116 million matched miles, city-aggregate credibility weights are moderate (0.12-0.46), partial pooling decisively outperforms no pooling, and a power analysis shows the learned kernel's advantage becomes detectable at approximately twelve deployed cities.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation
Zehang Wei, Jiaxin Dai, Jiamin Yan et al. (+1 more)
While
Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large
Vision-
Language Models, it remains highly susceptible to cross-modal
hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal
reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these
hallucinations, we propose a Multi-
Agent system, MODE-RAG, driven by Variational Free Energy (VFE) and internal
attention states to dynamically gate interventions. High-risk queries are routed to five stage-specific
agents, integrating Monte Carlo Tree Search (MCTS) for rigorous causal derivation and logit perturbations to penalize sycophancy. Dedicated Correction and Overseer
agents ensure formatting stability and perform post-hoc factual verification. To objectively evaluate our approach, we introduce ModeVent, a challenging subset derived from the MultiVent
dataset. Extensive experiments indicate that our system effectively reduces
hallucination rates and logical fabrication, significantly improving the robustness of M-RAG systems.
Read the full abstract ▾
All authors Zehang Wei, Jiaxin Dai, Jiamin Yan, Xiang Xiang
Machine Learning
Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining
Dong Hyeon Mok, Jonggeol Na and Seoin Back
Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone. Although machine learning-based high-throughput screening has accelerated catalyst discovery, its efficiency inevitably declines as the search space grows, motivating the development of generative models that can directly construct catalysts with target properties. Here, we present a conditional catalyst generative model based on the Generative Pretrained
Transformer architecture with a numerical
embedding layer that enables the generation of catalyst structures conditioned on both categorical and continuous properties within a single autoregressive framework. The model was pretrained on 133 million catalyst structures and subsequently fine-tuned on approximately 460,000 optimized structures with associated categorical properties and binding energies for conditional generation. The resulting model achieved 98% structural validity, 95% optimization validity, and high categorical condition fidelity, with a 93 % joint match rate for adsorbate type and composition. For binding energy conditioning, the match rate of approximately 20% represents a four-fold improvement over the baseline training distribution, and the generated distributions shift systematically toward the target values, enabling a 1.5 to 4-fold improvement in screening efficiency for reaction-targeted catalyst discovery without additional fine-tuning. These results show that large-scale autoregressive pre-training, combined with explicit property conditioning, provides a practical route toward controllable catalyst generation and accelerated catalysts discovery.
Read the full abstract ▾
Machine Learning
MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense
Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan et al. (+5 more)
Time-series
forecasting models remain vulnerable to gradient-based
adversarial attacks while existing defense mechanisms typically incur a trade-off in robustness for bounded response and compute cost. The problem is pronounced in Moving Target Defense where maintaining multiple randomized model instances substantially exacerbates the training overhead. In this work, we introduce MorphStrata, a student generation strategy with selective, layer-specific
stochastic noise injection that extends the traditional Morphence defense. MorphStrata uses a
Transformer backbone as the teacher and perturbs randomly selected architectural blocks to create structured heterogeneity across student models in response to varied data distributions and threat models. We evaluate against vanilla
Transformer and Morphence backbones on a suite of
benchmarks including the Jena
Climate, Electricity Load Diagrams, and Appliances Energy Prediction using FGSM, BIM and PGD attacks across multiple attack strengths. Across
datasets and attack regimes, the proposed ensemble maintains comparable
adversarial RMSE. Specifically, for high
entropy, periodic
datasets as in the case of the AEP data, MorphStrata achieves the lowest RMSE across all attacks and perturbation budgets, improving over the static baseline by up to 24.11% and 97.97% under FGSM and BIM respectively at an epsilon value of 0.5 over 30 randomized trials. Targeting the layers to generate MorphStrata students accounts for less than 1% increase in train-times over the Morphence MTD baseline for most of the experiments, while accounting for double digit gains in
adversarial RMSE reduction. We also observe a positive correlation between higher pairwise L2 distance (among generated students) and overall defense effectiveness. In summary, MorphStrata maintains
adversarial robustness as an MTD defense at marginal cost deltas when compared to existing baselines.
Read the full abstract ▾
All authors Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan, Thanh Quynh Nhu Ta, Mohammad Masum, Robert Chun, Jaydip Sen, Saptarshi Sengupta
Machine Learning · Cross-listed from stat.ML
Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty
Fangyuan Lin, Spencer Frei and Victor H. de la Pena
We consider the concentration properties of functions of infinitely exchangeable random variables. By conditioning on the de Finetti directing measure, we show that the deviation of any function with bounded-difference constants $c_1, \dots, c_n$ decomposes into a conditional sampling fluctuation and a latent mixture fluctuation. When this latent mixture is $\sigma_{\mathrm{mix}}^2$-subgaussian, we establish a concentration inequality with an effective variance proxy of $\frac{1}{4}\sum_i c_i^2 + \sigma_{\mathrm{mix}}^2$. Crucially, we demonstrate that for zero-sum linear contrasts, such as the difference between a subsample mean and a full population mean, the latent mixture term cancels exactly. This cancellation yields a tight, mixture-free Hoeffding-type bound that provides a direct de Finetti mechanism for the infinite-extendibility limit of recent finite-exchangeable concentration results. We apply this framework to quantify uncertainty in composite AI
benchmarks, such as MMLU, where question items naturally exhibit exchangeable dependence across domains. Our results provide both a domain-stratified hierarchical model for bounding the uncertainty of accuracy scores, and a distribution-free, cost-saving statistical guarantee for accurately estimating full
benchmark scores from random subsets.
Read the full abstract ▾
Machine Learning
Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces
Yahong Yang, Zecheng Zhang, Wei Zhu et al. (+2 more)
We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input function, our framework allows multiple input functions defined on possibly different domains, with different dimensions and Sobolev regularities. The derived rates explicitly quantify the contribution of each input space to the final error bound. In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders, while the dependence on the model complexity retains a \(\log\log/\log\)-type structure. Our analysis provides a general theoretical framework for multi-input operator learning, including Sobolev training, and is applicable to operator learning problems arising from partial differential equations and scientific computing.
Read the full abstract ▾
All authors Yahong Yang, Zecheng Zhang, Wei Zhu, Wenjing Liao, Hao Liu
Machine Learning · Cross-listed from cs.SD
A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models
Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh et al. (+3 more)
Large Audio
Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal
reasoning, a fundamental capability central to human auditory perception. Understanding the causes of these failures remains challenging as existing
benchmarks report performance gaps without probing underlying mechanisms. To address this, we introduce a
benchmark with 1,657 questions across three foundational tasks designed specifically for mechanistic analysis. Examining model outputs across varying input settings (behavioral analysis) reveals that models often under-utilize audio when textual cues are available. We also provide the first causal mechanistic analysis of temporal
reasoning failures in LALMs. Comparing
attention upweighting against scaling, we find that redistributing
attention across audio
tokens is more effective than increasing audio
attention. Targeting task-relevant
tokens yields further gains. These findings suggest that modality imbalance alone cannot explain failures.
Attention scaling at bottleneck layers improves accuracy from 55.9% to 59.1% without fine-tuning, demonstrating a promising direction for future work.
Read the full abstract ▾
All authors Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Sarah Wiegreffe, Dinesh Manocha, Ramani Duraiswami
Machine Learning
Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations
Alejandro Posadas-Nava, Richard Linares and Minduli Wijayatunga
Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-$\mathcal{K}$ functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term
Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training
algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of
adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.
Read the full abstract ▾
Machine Learning
Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows
Alejandro Calle-Saldarriaga, Felix Jimenez, Jack Grosskreuz et al. (+3 more)
Space-based monitoring of atmospheric carbon dioxide (CO$_2$) constrains the global carbon budget. NASA's Orbiting Carbon Observatory-2 (OCO-2) estimates column-averaged dry-air mole fractions of CO$_2$ (XCO$_2$) from high-resolution spectra, but operational
retrievals are computationally expensive and impose stringent Gaussianity assumptions on the retrieved posterior. We present a deep learning framework that addresses both through amortized probabilistic inference. Lacking ground truth for real observations, we train and evaluate on a high-fidelity OCO-2 simulation ensemble with calibrated forward-model errors, comparing against the version-10 ACOS full-physics
retrieval on the same radiances. Our architecture encodes each spectral band separately and estimates posteriors of the full CO$_2$ column, or summaries thereof, with Laplace approximations and conditional normalizing flows. Once trained, inference costs milliseconds per sounding rather than minutes, and calibrated posteriors are attainable at that cost. Trained on simulations that explicitly include forward-model discrepancy, our
retrievals are more accurate than the operational one for XCO$_2$ on both data partitions we consider, and competitive on profiles. The flow represents asymmetric posteriors that a Gaussian cannot, a gain attributable to shape rather than scale, and its advantage in predictive density persists where its accuracy advantage does not. These results are established on a land-only ensemble against one configuration of the operational
algorithm. On reference soundings withheld from training and on two unseen months the XCO$_2$ and density advantages persist while calibration degrades under sparsely sampled observing conditions, pointing to the diversity of the simulated scene population rather than the method as the main obstacle.
Read the full abstract ▾
All authors Alejandro Calle-Saldarriaga, Felix Jimenez, Jack Grosskreuz, Jiazheng Wang, Jonathan Hobbs, Matthias Katzfuss
Machine Learning
Discrete Autoregressive Transformer for Generative Mechanism Synthesis
Anar Nurizada and Anurag Purwar
Planar path synthesis requires mechanisms whose coupler curves match a prescribed trajectory; the mapping from curve to linkage is inherently one-to-many across four-, six-, and eight-bar
topologies. We address this design problem with simulation-grounded evaluation on a curated corpus of over one million mechanisms, reporting Chamfer distance and dynamic time warping after forward kinematics and
geometric alignment. We formulate synthesis as conditional autoregressive sequence modeling: joint coordinates are uniformly quantized to
tokens and generated by a decoder-only
transformer with a variational-autoencoder (VAE) latent of the target curve and an explicit mechanism-type
token. Training combines
token cross-
entropy with a Gaussian-smoothed bin auxiliary loss that respects ordinal structure among bins. At inference, a bounded latent-noise schedule decodes all mechanism types at each noise level; we retain the top five candidates by
geometric error, yielding diverse accurate families without
dataset lookup. On held-out tests, aggregate mean Chamfer distance is $0.0132$ and mean dynamic time warping is $0.153$; a latent $k$-nearest-neighbor baseline that conditions on training-set neighbor latents in VAE space achieves matched-
topology mean Chamfer distance $0.0071$ and mean dynamic time warping $0.117$ using the same decoder.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies
Meipo Dai, Qiyuan Zhuang, He-Yang Xu et al. (+4 more)
Generative
robot policies typically begin action generation from an observation-independent standard Gaussian distribution, leaving the choice of source distribution underexplored. This work asks a simple question: where should action generation begin? We propose LeaP, a Learnable source Prior that replaces the standard Gaussian with a proprioception-conditioned diagonal Gaussian over action chunks. Parameterized by a lightweight MLP, LeaP jointly predicts the mean and state-adaptive variance of the source distribution, while keeping the downstream generator architecture and inference solver unchanged. This design provides an observation-informed yet
stochastic initialization, allowing the generator to focus on precise action refinement rather than transporting samples from an uninformed noise source. On 15 RoboTwin manipulation tasks, LeaP achieves an average success rate of 81.6%, outperforming four representative baselines – including deterministic-source methods, a no-prior counterpart, and a
diffusion-bridge policy – by 6.5 to 25.5 percentage points. The same prior consistently improves both flow-matching and
diffusion-bridge generators, while using fewer parameters and converging faster. The advantage carries over to real-world deployment, where LeaP attains the best performance. These results suggest that the source distribution is an independent and reusable design axis for generative
robot policies, complementary to the choice of generative dynamics.
Read the full abstract ▾
All authors Meipo Dai, Qiyuan Zhuang, He-Yang Xu, Ying-Jie Shuai, Yijun Wang, Qi Dou, Xiu-Shen Wei
Machine Learning
The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
Huu Danh Nguyen
When small
transformers grok modular multiplication, prior work reports that the learned
embedding has a "dense"
Fourier spectrum requiring all frequencies. This contrasts with modular addition, where only a sparse set of key frequencies suffices. We show this density is an artifact of analyzing in the wrong basis. The natural
Fourier transform for multiplication is not the standard additive DFT but the multiplicative character transform, which decomposes functions on the multiplicative group $(\mathbb{Z}/p\mathbb{Z})^*$ into its irreducible representations. Applying this transform to a grokked
transformer trained on $a \cdot b \bmod 113$, we find the
embedding spectrum becomes highly sparse (Gini coefficient 0.58 vs. 0.07 in the additive basis) with only 4 key frequencies carrying significant energy. Furthermore, 96.9% of MLP
neurons are cleanly tuned to a single multiplicative frequency, and
neuron activation heatmaps reveal 2D-periodic structure when reordered by the discrete logarithm. These results demonstrate the
transformer reduces multiplication to addition in discrete-log space, implementing a "Discrete-Log Clock"
algorithm analogous to Nanda et al.'s Clock
algorithm for addition. The methodology generalizes: matching the analysis basis to the algebraic structure of the task reveals interpretable structure where standard tools see noise.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Damage Adaptation in Seconds for Architected Materials
James Avtges, Jake Ketchum, Helena Young et al. (+3 more)
Adaptation to damages and in-situ physical repairs is essential for long-term
robot autonomy, yet challenging outside of narrowly defined and well-anticipated bounds. In this work we proprioceptively adapt to catastrophic damage in soft-actuated systems in under one minute. Architected materials are well equipped for adaptation: actuator failure occurs gradually rather than acutely, and damage can be described in a low-dimensional, discrete coordinate space. Surprisingly, latent damage representations plus a simple yet robust ensemble method is sufficient for adapting to unseen damage in real-time. Moreover, we identify conditions under which exponential sample complexity collapses to linear sample complexity for learned representations of architected materials, a concrete advantage over rigid components or continuum soft mechanisms. We demonstrate LEAP, our method for adaptive proprioception, via a tracing task for a 6DoF soft wrist based on Handed Shearing Auxetic (HSA) actuators. Our
algorithm is able to adapt to cuts, burns, and actuator repairs, enabling simulation-free real-time adaptation that is critical for realizing the promise of soft
robots outside the lab.
Videos and more information are available at https://murpheylab.github.io/leap.
Read the full abstract ▾
All authors James Avtges, Jake Ketchum, Helena Young, Taekyoung Kim, Ryan Truby, Todd Murphey
Machine Learning · Cross-listed from cs.CL
NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama
Logan Mann, Abdur Rahman, Mohammad Saifullah et al. (+2 more)
Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large
language models (LLMs) fail. We
benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and
reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open
benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, with cross-lingual evaluation across four Indic
languages (Hindi, Tamil, Telugu, Marathi). We introduce N-VSSM, a Narrative Variational State-Space Model that maintains a structured 256-dimensional latent world state over more than 200 episodes via a Mamba-2 backbone with an event-conditioned posterior and an 8B decoder. N-VSSM holds plot-beat F1 >= 0.84 across all horizons at 4x lower compute than the closed-frontier band. A learned Cultural Transfer Function lifts cross-
language fidelity by +0.20 to +0.23 Likert points. In a within-subjects writer study (n = 12 professional authors, 240 trials), N-VSSM is preferred over Claude Opus 4.5 on long-arc consistency 71% of the time and rated +1.3 Likert points higher on controllability.
Read the full abstract ▾
All authors Logan Mann, Abdur Rahman, Mohammad Saifullah, Taaha Kazi, Vasu Sharma
Machine Learning · Cross-listed from cs.CV
Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models
Logan Mann, Yi Xia, Ajit Saravanan et al. (+6 more)
Multimodal Foundation Models are increasingly used as
reasoning agents, making reliability, knowing when a model may hallucinate, critical. A common intuition, which we call the
Attention-Confidence Assumption, holds that reliability follows from "structural" visual perception: tight
attention on relevant regions should signal a trustworthy answer, while scattered
attention signals confusion. We challenge this through the VLM Reliability Probe (VRP), a systematic cross-family study of reliability signals in contemporary
Vision-
Language Models (VLMs). We introduce structural-
attention metrics, cluster counts (C_k) and spatial
entropy (H_s), to quantify the visual encoder's gaze, and track its
evolution (Delta H_s) across layers. This reveals a "Symbolic Detachment": models often "Early Lock" visual features only to diffuse
attention later, severing early perception from final generation. Contrary to the grounding hypothesis, we find a "Cluster Failure": spatial
attention has near-zero correlation (R approx 0.001) with accuracy. Instead, reliability is a phenomenon of generation dynamics and internal-state distributions. Self-Consistency, the agreement rate across sampled
reasoning paths, is the dominant predictor of truth (R = 0.429). Scaling causal interventions exposes a sharp architectural divergence: LLaVA locks its prediction in a fragile late-stage bottleneck, whereas PaliGemma and Qwen2-VL distribute reliability globally, staying resilient even when ~50% or more of their most predictive layer is destroyed. For current VLMs, reliability signals are detached from visual grounding maps and are best inferred from generation-time dynamics and hidden-state probes.
Read the full abstract ▾
All authors Logan Mann, Yi Xia, Ajit Saravanan, Ishan Dave, Saadullah Ismail, Shikhar Shiromani, Emily Huang, Ruizhe Li, Kevin Zhu
Machine Learning · Cross-listed from q-fin.RM
Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation
Matthew Francis Dixon
Agentic artificial intelligence systems introduce a new class of model risk. Unlike traditional predictive models, autonomous
agents continuously acquire information, form beliefs regarding latent states of the environment, generate forecasts, select actions, and adapt their behavior over time. Existing validation methodologies focus primarily on predictive accuracy and therefore provide limited insight into the quality of the underlying decision process. This paper proposes a model validation framework for agentic AI based on Partially Observable Markov Decision Processes (POMDPs). The framework decomposes autonomous decision making into information, beliefs, forecasts, actions, and utility, allowing each component to be validated independently. Large
language models (LLMs) are formalized as approximate
Bayesian filtering operators, and a model-risk taxonomy is developed encompassing state-space, filtering, forecast, policy, utility-specification, and parameter risks. The model risk validation methodology is demonstrated through a portfolio-management case study in which an
agent infers latent
market regimes from
market and macroeconomic information, generates belief-conditioned forecasts, and constructs portfolios using a Black–Litterman framework. Empirical validation combines performance analysis, belief calibration diagnostics, coverage tests, ablation studies, and parameter-sensitivity analysis. The results indicate that latent-state inference contributes independently to decision quality and that the principal conclusions remain robust across a broad range of parameter values. The principal contribution of the paper is a practical framework for extending established model risk management concepts to autonomous AI systems and providing a rigorous foundation for their validation, governance, and monitoring.
Read the full abstract ▾
Machine Learning
Performance-Driven Environment Abstraction with Multi-Timescale Learning
Yue Guan, Dipankar Maity and Panagiotis Tsiotras
We study performance-driven environment abstraction for decision-making in large Markov decision processes. Rather than preserving
geometric or topological structure, we seek abstractions that directly optimize decision quality. We model abstraction as a controlled approximation obtained by aggregating the state space and enforcing a shared action distribution within each aggregated state. For a fixed partition, we establish a performance guarantee that separates value-function approximation error from the loss introduced by action sharing. Guided by this analysis, we develop a multi-timescale reinforcement learning framework that jointly adapts the policy and a tree-structured environment abstraction. The resulting
algorithm refines and coarsens regions of the state space based on Q-value discrepancies, balancing performance against abstraction size and complexity. Empirical results demonstrate substantial state compression, improved sample efficiency, and faster replanning compared to actor-critic baselines.
Read the full abstract ▾