Machine Learning · Cross-listed from cs.CR
Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG
Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy et al. (+8 more)
Current stateless defences for
multimodal agentic RAG fail to detect
adversarial strategies that distribute malicious semantics across
retrieval, planning, and generation components. We formulate this security challenge as a Partially Observable Markov Decision Process (POMDP), where
adversarial intent is a latent variable inferred from noisy multi-stage observations. We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust
Agent (MTA) that maintains an approximate belief state via structured LLM
reasoning. Operating as a model-agnostic overlay, MMA-RAGT mediates a configurable set of internal checkpoints to enforce stateful defence-in-depth. Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost. Crucially, a factorial ablation validates our theoretical bounds: while statefulness and spatial coverage are individually necessary (26.4 pp and 13.6 pp gains respectively), stateless multi-point intervention can yield zero marginal benefit under homogeneous stateless filtering when checkpoint detections are perfectly correlated.
Read the full abstract ▾
All authors Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andrés Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga
Machine Learning · Cross-listed from stat.ML
ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding
Ziyi Liang, Hamed Poursiami, Zhishun Yang et al. (+5 more)
Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision boundaries and, consequently, vulnerability to outliers,
adversarial perturbations, and out-of-distribution inputs. To address these limitations, we introduce ConformalHDC, a unified framework that combines the statistical guarantees of conformal prediction with the computational efficiency of HDC. For this framework, we propose two complementary variations. First, the set-valued formulation provides finite-sample, distribution-free coverage guarantees. Using carefully designed conformity scores, it forms enclosed decision boundaries that improve robustness to non-conforming inputs. Second, the point-valued formulation leverages the same conformity scores to produce a single prediction when desired, potentially improving accuracy over traditional HDC by accounting for class interactions. We demonstrate the broad applicability of the proposed framework through evaluations on multiple real-world
datasets. In particular, we apply our method to the challenging problem of decoding non-spatial stimulus information from the spiking activity of hippocampal
neurons recorded as subjects performed a sequence
memory task. Our results show that ConformalHDC not only accurately decodes the stimulus information represented in the neural activity data, but also provides rigorous uncertainty estimates and correctly abstains when presented with data from other behavioral states. Overall, these capabilities position the framework as a reliable, uncertainty-aware foundation for neuromorphic computing.
Read the full abstract ▾
All authors Ziyi Liang, Hamed Poursiami, Zhishun Yang, Keiland Cooper, Akhilesh Jaiswal, Maryam Parsa, Norbert Fortin, Babak Shahbaba
Machine Learning
MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
Jesse He, Helen Jenne, Max Vargas et al. (+4 more)
The recent field of neural algorithmic
reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical
algorithms like Bellman-Ford, a phenomenon known as algorithmic
alignment. At the same time, recent advances in large
language models (LLMs) have spawned the study of mechanistic interpretability, which aims to identify granular model components like
circuits that perform specific computations. In this work, we introduce Mechanistic Interpretability for Neural Algorithmic
Reasoning (MINAR), an efficient
circuit discovery toolbox that adapts attribution patching methods from mechanistic interpretability to the GNN setting. We show through two case studies that MINAR recovers faithful
neuron-level
circuits from GNNs trained on algorithmic tasks. Our study sheds new light on the process of
circuit formation and
pruning during training, as well as giving new insight into how GNNs trained to perform multiple tasks in parallel reuse
circuit components for related tasks. Our code is available at https://github.com/pnnl/MINAR.
Read the full abstract ▾
All authors Jesse He, Helen Jenne, Max Vargas, Davis Brown, Gal Mishne, Yusu Wang, Henry Kvinge
Machine Learning
Shiwei Tan, Hengyi Wang, Weiyi Qin et al. (+3 more)
Multimodal Large
Language Models (MLLMs) deliver detailed responses on
vision-
language tasks, yet remain susceptible to object
hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts often rely on heuristic penalties, post-hoc correction, or generic decoding tweaks, which do not directly intervene in the mechanisms that trigger object
hallucination and thus yield limited gains. To address this challenge, we propose a causal decoding framework that applies targeted causal interventions during generation to curb spurious object mentions. By reshaping the decoding dynamics to attenuate spurious dependencies, our approach reduces false object
tokens while maintaining descriptive quality. Across captioning and QA
benchmarks, our framework substantially lowers object-
hallucination rates and achieves state-of-the-art faithfulness without degrading overall output quality.
Read the full abstract ▾
All authors Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang
Machine Learning · Cross-listed from stat.ML
Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
Arnab Maiti, Claire Jie Zhang, Kevin Jamieson et al. (+3 more)
In this paper, we study last-iterate convergence of learning
algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning
algorithm that guarantees last-iterate convergence to the Nash
equilibrium with high probability. We establish a convergence rate of $\tilde{O}(T^{-1/4})$ up to
polynomial factors in problem parameters. Crucially, our proposed
algorithm is computationally efficient, requiring only an efficient linear optimization oracle over the players' compact action sets. The
algorithm is obtained by combining techniques from experimental design and the classic Follow-The-Regularized-Leader (FTRL) framework, with a carefully chosen regularizer function tailored to the geometry of the action set of each learner.
Read the full abstract ▾
All authors Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff
Machine Learning
Provably Safe Generative Sampling with Constricting Barrier Functions
Darshan Gadginmath, Ahmed Allibhoy and Fabio Pasqualetti
Flow-based generative models, such as
diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy hard constraints. We propose a safety filtering framework that acts as an online shield for any pre-trained generative model. Our key insight is to cooperate with the generative process rather than override it. We define a constricting safety tube that is relaxed at the initial noise distribution and progressively tightens to the target safe set at the final data distribution, mirroring the coarse-to-fine structure of the generative process itself. By characterizing this tube via Control Barrier Functions (CBFs), we synthesize a feedback control input through a convex Quadratic Program (QP) at each sampling step. As the tube is loosest when noise is high and intervention is cheapest in terms of control energy, most constraint enforcement occurs when it least disrupts the model's learned structure. We prove that this mechanism guarantees safe sampling in discrete-time. The minimum-norm control synthesized at each step minimizes the per-step contribution to the KL divergence between the safe and original distributions. Across all experiments, we observe 100% constraint satisfaction. Our framework applies to any pre-trained flow-based sampling scheme requiring no retraining or architectural modifications. We validate the approach across constrained image generation, physically-consistent trajectory sampling, and safe robotic manipulation policies, achieving 100% constraint satisfaction while preserving semantic fidelity.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
Binesh Sadanandan and Vahid Behzadan
Medical
Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a
benchmark of 26,850 chest X-ray questions paired with 92,856 meaning-preserving paraphrases across MIMIC-CXR, PadChest, and VinDr-CXR, spanning clinical populations in the US, Spain, and Vietnam. Every paraphrase is validated by an LLM judge using a bidirectional clinical entailment rubric, with 91.6% cross-family agreement. Across nine VLMs, including general-purpose models, we find flip rates from 3% to 37%. However, low flip rate does not imply visual grounding: text-only baselines show that some models stay consistent even when the image is removed, suggesting they rely on
language priors. To study mechanisms in one model, we apply GemmaScope 2 Sparse Autoencoders (SAEs) to MedGemma 4B and analyze FlipBank, a curated set of 158 flip cases. We identify a sparse feature at layer 17 that correlates with
prompt framing and predicts decision margin shifts. In causal patching, removing this feature's contribution recovers 45% of the yes-minus-no logit margin on average and fully reverses 15% of flips. Acting on this finding, we show that clamping the identified feature at inference reduces flip rates by 31% relative with only a 1.3 percentage-point accuracy cost, while also decreasing text-prior reliance. These results suggest that flip rate alone is not enough; robustness evaluations should test both paraphrase stability and image reliance.
Read the full abstract ▾
Machine Learning
Proximal-IMH: Proximal Posterior Proposals for Independent Metropolis-Hastings with Approximate Operators
Youguang Chen and George Biros
We consider the problem of sampling from a posterior distribution arising in
Bayesian inverse problems in science, engineering, and imaging. Our method belongs to the family of independence Metropolis-Hastings (IMH) sampling
algorithms, which are common in
Bayesian inference. Relying on the existence of an approximate posterior distribution that is cheaper to sample from but may have significant bias, we introduce Proximal-IMH, a scheme that removes this bias by correcting samples from the approximate posterior through an auxiliary optimization problem. This yields a local adjustment that trades off adherence to the exact model against stability around the approximate reference point. For idealized settings, we prove that the proximal correction tightens the match between approximate and exact posteriors, thereby improving acceptance rates and mixing. The method applies to both linear and nonlinear input-output operators and is particularly suitable for inverse problems where exact posterior sampling is too expensive. We present numerical experiments including
multimodal and data-driven priors with nonlinear input-output operators. The results show that Proximal-IMH reliably outperforms existing IMH variants.
Read the full abstract ▾
Machine Learning
On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
Alexander Galozy
Reinforcement learning (RL)
agents under partial observability often condition actions on internally accumulated information such as
memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of $\epsilon$-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results. First, the set of policies exhibiting non-trivial behavioural dependency is not closed under convex aggregation. Second, behavioural distance contracts under convex combination. Third, we prove a sufficient local condition under which gradient ascent on a skewed mixture objective decreases behavioural distance when a dominant-mode gradient aligns with the direction of steepest contraction. Minimal bandit and partially observable gridworld experiments provide controlled witnesses of these mechanisms. In the examined settings, behavioural distance decreases under convex aggregation and under continued optimisation with skewed latent priors, and in these experiments it precedes degradation under latent prior shift. These results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
ECHOSAT: Estimating Canopy Height Over Space And Time
Jan Pauls, Karsten Schrödter, Sven Ligensa et al. (+7 more)
Forest monitoring is critical for
climate change mitigation. However, existing global tree height maps provide only static snapshots and do not capture temporal forest dynamics, which are essential for accurate carbon accounting. We introduce ECHOSAT, a global and temporally consistent tree height map at 10 m resolution spanning multiple years. To this end, we resort to multi-sensor satellite data to train a specialized
vision transformer model, which performs pixel-level temporal regression. A self-supervised growth loss regularizes the predictions to follow growth curves that are in line with natural tree development, including gradual height increases over time, but also abrupt declines due to forest loss events such as fires. Our experimental evaluation shows that our model improves state-of-the-art accuracies in the context of single-year predictions. We also provide the first global-scale height map that accurately quantifies tree growth and disturbances over time. We expect ECHOSAT to advance global efforts in carbon monitoring and disturbance assessment. The maps can be accessed at https://github.com/ai4forest/echosat.
Read the full abstract ▾
All authors Jan Pauls, Karsten Schrödter, Sven Ligensa, Martin Schwartz, Berkant Turan, Max Zimmer, Sassan Saatchi, Sebastian Pokutta, Philippe Ciais, Fabian Gieseke
Machine Learning
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Yuanda Xu, Hejian Sang, Zhengze Zhou et al. (+2 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing
reasoning in Large
Language Models (LLMs). However, standard RLVR
algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened sampling, they simultaneously narrow the model's
reasoning boundary and reduce generation diversity. We identify a root cause that existing methods overlook: the uniform penalization of errors. Current approaches – whether data-filtering methods that select
prompts by difficulty, or advantage normalization schemes – treat all incorrect rollouts within a group identically. We show that this uniformity allows overconfident errors (incorrect
reasoning paths that the RL process has spuriously reinforced) to persist and monopolize probability mass, ultimately suppressing valid exploratory trajectories. To address this, we propose the Asymmetric Confidence-aware Error Penalty (ACE). ACE introduces a per-rollout confidence shift metric, c_i = log(pi_theta(y_i|x) / pi_ref(y_i|x)), to dynamically modulate negative advantages. Theoretically, we demonstrate that ACE's gradient can be decomposed into the gradient of a selective regularizer restricted to overconfident errors, plus a well-characterized residual that partially moderates the regularizer's strength. We conduct extensive experiments fine-tuning Qwen2.5-Math-7B, Qwen3-8B-Base, and Llama-3.1-8B-Instruct on the DAPO-Math-17K
dataset using GRPO and DAPO within the VERL framework. Evaluated on MATH-500 and AIME 2025, ACE composes seamlessly with existing methods and consistently improves the full Pass@k spectrum across all three model families and
benchmarks.
Read the full abstract ▾
All authors Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang
Machine Learning
Benchmarking State Space Models, Transformers, and Recurrent Networks for US Grid Forecasting
Sunki Hong and Jisoo Lee
Selecting the right deep learning model for power grid
forecasting is challenging, as performance heavily depends on the data available to the operator. This paper presents a comprehensive
benchmark of five modern neural architectures: two state space models (PowerMamba, S-Mamba), two
Transformers (iTransformer, PatchTST), and a traditional LSTM. We evaluate these models on hourly electricity demand across six diverse US power grids for forecast windows between 24 and 168 hours. To ensure a fair comparison, we adapt each model with specialized temporal processing and a modular layer that cleanly integrates weather
covariates. Our results reveal that there is no single best model for all situations. When
forecasting using only historical load, PatchTST and the state space models provide the highest accuracy. However, when explicit weather data is added to the inputs, the rankings reverse: iTransformer improves its accuracy three times more efficiently than PatchTST. By controlling for model size, we confirm that this advantage stems from the architecture's inherent ability to mix information across different variables. Extending our evaluation to
solar generation, wind power, and wholesale prices further demonstrates that model rankings depend on the forecast task: PatchTST excels on highly rhythmic signals like
solar, while state space models are better suited for the chaotic fluctuations of wind and price. Ultimately, this
benchmark provides grid operators with actionable guidelines for selecting the optimal
forecasting architecture based on their specific data environments.
Read the full abstract ▾
Machine Learning
Generative Bayesian Computation as a Scalable Alternative to Gaussian Process Surrogates
Nick Polson and Vadim Sokolov
Gaussian process (GP) surrogates are the default tool for emulating expensive computer experiments, but cubic cost, stationarity assumptions, and Gaussian predictive distributions limit their reach. We propose Generative
Bayesian Computation (GBC) via Implicit
Quantile Networks (IQNs) as a surrogate framework that targets all three limitations. GBC learns the full conditional
quantile function from input–output pairs; at test time, a single forward pass per
quantile level produces draws from the predictive distribution. Across fourteen
benchmarks we compare GBC to four GP-based methods. GBC improves CRPS by 11–26% on piecewise jump-process
benchmarks, by 14% on a ten-dimensional Friedman function, and scales linearly to 90,000 training points where dense-covariance GPs are infeasible. A boundary-augmented variant matches or outperforms Modular Jump GPs on two-dimensional jump
datasets (up to 46% CRPS improvement). In active learning, a randomized-prior IQN ensemble achieves nearly three times lower RMSE than deep GP active learning on Rocket LGBB. Overall, GBC records a favorable point estimate in 12 of 14 comparisons. GPs retain an edge on smooth surfaces where their smoothness prior provides effective regularization.
Read the full abstract ▾
Machine Learning
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
Alina Devkota, Jacob Thrasher, Donald Adjeroh et al. (+2 more)
Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based
federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily available public
datasets, ensuring accessibility and consistency across clients without compromising
privacy. In contrast to conventional approaches that prioritize client
dataset volume, FedVG assesses the generalization ability of client models by measuring the magnitude of validation gradients across layers. Specifically, we compute layerwise gradient norms to derive a client-specific score that reflects how much each client needs to adjust for improved generalization on the global validation set, thereby enabling more informed and adaptive
federated aggregation. Extensive experiments on both natural and medical image benchmarking
datasets, across diverse model architectures, demonstrate that FedVG consistently improves performance, particularly in highly heterogeneous settings. Moreover, FedVG is modular and can be seamlessly integrated with various state-of-the-art FL
algorithms, often further improving their results. Our code is available at https://github.com/alinadevkota/FedVG.
Read the full abstract ▾
All authors Alina Devkota, Jacob Thrasher, Donald Adjeroh, Binod Bhattarai, Prashnna K. Gyawali
Machine Learning · Cross-listed from cs.CV
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh et al. (+1 more)
Prompt learning has become a dominant paradigm for adapting
vision-
language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending
prompts to both
vision and text encoders across multiple
transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes
prompt tuning attractive. In this work, we propose MMLoP (Multi-Modal Low-Rank Prompting), a framework that achieves deep multi-modal prompting with only 11.5K trainable parameters, comparable to early text-only methods like CoOp. MMLoP parameterizes
vision and text
prompts at each
transformer layer through a low-rank factorization that constrains
prompts to a compact subspace, providing parameter efficiency while motivating the need for our complementary regularization components. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global
embedding shift induced by
prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples
vision and text
prompts through a common low-rank factor to enforce cross-modal
alignment. Extensive experiments across three
benchmarks and 11 diverse
datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70% on base-to-novel generalization. Code is available at https://github.com/sajjad-ucsb/MMLoP.
Read the full abstract ▾
All authors Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani
Machine Learning
Defensive Generation
Gabriele Farina and Juan Carlos Perdomo
We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient
algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation
Daniel Tamayo, Iñaki Lacunza, Paula Rivera-Hidalgo et al. (+4 more)
We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35
languages and code. Through targeted adaptation, this model family achieves state-of-the-art results on Catalan- and Spanish-specific tasks, while establishing robust performance across specialized biomedical and legal domains. To bridge the gap between research and production, we incorporate Matryoshka Representation Learning (MRL), enabling flexible vector sizing that significantly reduces inference and storage costs. Ultimately, the MrBERT family demonstrates that modern encoder architectures can be optimized for both localized linguistic excellence and efficient, high-stakes domain specialization. We open source the complete model family on Huggingface.
Read the full abstract ▾
All authors Daniel Tamayo, Iñaki Lacunza, Paula Rivera-Hidalgo, Severino Da Dalt, Javier Aula-Blasco, Aitor Gonzalez-Agirre, Marta Villegas
Machine Learning · Cross-listed from cs.CL
Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages
Mohammadreza Ghaffarzadeh-Esfahani, Nahid Yousefian, Ebrahim Heidari-Farsani et al. (+4 more)
Extracting clinical information from medical transcripts in low-resource
languages remains a significant challenge in healthcare natural
language processing (NLP). This study evaluates a two-step pipeline combining Aya-expanse-8B as a Persian-to-English translation model with five open-source small
language models (SLMs) – Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Qwen2.5-1.5B-Instruct, and Gemma-3-1B-it – for binary extraction of 13 clinical features from 1,221 anonymized Persian transcripts collected at a cancer palliative care call center. Using a few-shot prompting strategy without fine-tuning, models were assessed on macro-averaged F1-score, Matthews Correlation Coefficient (MCC), sensitivity, and specificity to account for class imbalance. Qwen2.5-7B-Instruct achieved the highest overall performance (median macro-F1: 0.899; MCC: 0.797), while Gemma-3-1B-it showed the weakest results. Larger models (7B–8B parameters) consistently outperformed smaller counterparts in sensitivity and MCC. A bilingual analysis of Aya-expanse-8B revealed that translating Persian transcripts to English improved sensitivity, reduced missing outputs, and boosted metrics robust to class imbalance, though at the cost of slightly lower specificity and precision. Feature-level results showed reliable extraction of physiological symptoms across most models, whereas psychological complaints, administrative requests, and complex somatic features remained challenging. These findings establish a practical,
privacy-preserving blueprint for deploying open-source SLMs in
multilingual clinical NLP settings with limited infrastructure and annotation resources, and highlight the importance of jointly optimizing model scale and input
language strategy for sensitive healthcare applications.
Read the full abstract ▾
All authors Mohammadreza Ghaffarzadeh-Esfahani, Nahid Yousefian, Ebrahim Heidari-Farsani, Ali Akbar Omidvarian, Sepehr Ghahraei, Atena Farangi, AmirBahador Boroumand
Machine Learning
The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging
Sameer Ambekar, Reza Nasirigerdeh, Peter J. Schuffler et al. (+3 more)
Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private data, producing domain-specific models that differ by scanner, protocol, and population. When deployed at an unseen clinical site, test cases arrive in unlabeled, non-i.i.d. batches, and the model must adapt immediately without labels. In this work, we introduce an
entropy-adaptive, fully online model-merging method that yields a batch-specific merged model via only forward passes, effectively leveraging target information. We further demonstrate why mean merging is prone to failure and misaligned under heterogeneous domain shifts. Next, we mitigate encoder classifier mismatch by decoupling the encoder and classification head, merging with separate merging coefficients. We extensively evaluate our method with state-of-the-art baselines using two backbones across nine medical and natural-domain generalization image classification
datasets, showing consistent gains across standard evaluation and challenging scenarios. These performance gains are achieved while retaining single-model inference at test-time, thereby demonstrating the effectiveness of our method.
Read the full abstract ▾
All authors Sameer Ambekar, Reza Nasirigerdeh, Peter J. Schuffler, Lina Felsner, Daniel M. Lang, Julia A. Schnabel
Machine Learning
Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal et al. (+6 more)
Multi-Head
Attention (MHA) is the core computational primitive underlying modern Large
Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$
attention heads produce exactly $H$ independent
attention matrices, with no communication between heads during
attention computation. This becomes problematic for multi-step
reasoning, where correct answers depend on aggregating evidence from multiple parts of the context and composing latent
token-to-
token relations over a chain of intermediate inferences. To address this, we propose Interleaved Head
Attention (IHA), which enables cross-head mixing by constructing $P$ pseudo-heads per head (typically $P=H$), where each pseudo query/key/value is a learned linear combination of all $H$ original queries, keys and values respectively. Interactions between pseudo-query and pseudo-key heads induce up to $P^2$
attention patterns per head with modest parameter overhead $\mathcal{O}(H^2P)$. We provide theory showing improved efficiency in terms of number of parameters on the synthetic
Polynomial task (IHA uses $\Theta(\sqrt{k}n^2)$ parameters vs. $\Theta(kn^2)$ for MHA) and on the synthetic order-sensitive CPM-3 task (IHA uses $\lceil\sqrt{N_{\max}}\rceil$ heads vs. $N_{\max}$ for MHA). On real-world
benchmarks, IHA improves Multi-Key
retrieval on RULER by 10-20% (4k-16k) and, after fine-tuning for
reasoning on OpenThoughts, improves GSM8K by 5.8% and MATH-500 by 2.8% (Majority Vote) over full
attention.
Read the full abstract ▾
All authors Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal, Rishabh Tiwari, Devvrit Khatri, David Brandfonbrener, Paul Liang, Inderjit Dhillon, Manzil Zaheer
Machine Learning
Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration
Charafeddine Mouzouni
Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level – a single number per system-task pair, derived from self-consistency sampling and conformal calibration, that serves as a black-box deployment gate with exact, finite-sample, distribution-free guarantees. Self-consistency sampling reduces uncertainty exponentially; conformal calibration guarantees correctness within 1/(n+1) of the target level, regardless of the system's errors – made transparently visible through larger answer sets for harder questions. Weaker models earn lower reliability levels (not accuracy – see Definition 2.4): GPT-4.1 earns 94.6% on GSM8K and 96.8% on TruthfulQA, while GPT-4.1-nano earns 89.8% on GSM8K and 66.5% on MMLU. We validate across five
benchmarks, five models from three families, and both synthetic and real data. Conditional coverage on solvable items exceeds 0.93 across all configurations; sequential stopping reduces API costs by around 50%.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Towards Controllable Video Synthesis of Routine and Rare OR Events
Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri et al. (+8 more)
Purpose: Curating large-scale
datasets of operating room (OR) workflow, encompassing rare, safety-critical, or atypical events, remains operationally and ethically challenging. This data bottleneck complicates the development of ambient intelligence for detecting, understanding, and mitigating rare or safety-critical events in the OR. Methods: This work presents an OR
video diffusion framework that enables controlled synthesis of rare and safety-critical events. The framework integrates a
geometric abstraction module, a conditioning module, and a fine-tuned
diffusion model to first transform OR scenes into abstract
geometric representations, then condition the synthesis process, and finally generate realistic OR event
videos. Using this framework, we also curate a synthetic
dataset to train and validate AI models for detecting near-misses of sterile-field violations. Results: In synthesizing routine OR events, our method outperforms off-the-shelf
video diffusion baselines, achieving lower FVD/LPIPS and higher SSIM/PSNR in both in- and out-of-domain
datasets. Through qualitative results, we illustrate its ability for controlled
video synthesis of counterfactual events. An AI model trained and validated on the generated synthetic data achieved a RECALL of 70.13% in detecting near safety-critical events. Finally, we conduct an ablation study to quantify performance gains from key design choices. Conclusion: Our solution enables controlled synthesis of routine and rare OR events from abstract
geometric representations. Beyond demonstrating its capability to generate rare and safety-critical scenarios, we show its potential to support the development of ambient intelligence models.
Read the full abstract ▾
All authors Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri, Vishalroshan Anil, Aiza Maksutova, Yiqing Shen, Jan Emily Mangulabnan, Hao Ding, Jose L. Porras, Masaru Ishii, Mathias Unberath
Machine Learning · Cross-listed from physics.optics
A unified self-supervised framework for single-frame Fresnel CDI and overlapped ptychography
Oliver Hoidn, Steven Henke, Albert Vong et al. (+3 more)
Ptychographic imaging at synchrotron and X-ray free-electron
laser sources requires densely overlapping scans, which limits throughput and increases dose; extending coherent diffractive imaging to overlap-free operation on extended samples remains an open problem. We present a self-supervised inverse-mapping network for single-frame Fresnel coherent diffraction imaging (CDI) and overlapped ptychography with fixed, pre-estimated probes. The learned neural network reconstructs individual object patches from either one diffraction frame or several overlapping measurements at a time. In single-frame mode, the phase diversity provided by the curved-wavefront probe at the off-focus sample position removes the requirement for overlap constraints, enabling sparser scans and proportionally lower dose at fixed exposure. On synthetic line patterns, reconstructed amplitude SSIM exceeds 0.90 in single-frame mode with the curved probe and reaches 0.952-0.968 with overlap constraints. Optimization of the network via a Poisson negative log likelihood objective, rather than the more common mean absolute error, yields 10-fold improved
photon-dose efficiency at doses below $10^5$
photons per image, where shot noise typically limits resolution. In addition to these synthetic studies, we demonstrate robust single-frame reconstruction of extended samples using ptychographic
datasets from APS and LCLS, with end-to-end reconstruction of a 10,304-frame workload approximately $36\times$ faster than a highly optimized iterative solver. Together, these results unify single-frame Fresnel CDI and overlapped ptychography within one self-supervised framework, supporting dose-efficient, high-throughput imaging at modern light sources.
Read the full abstract ▾
All authors Oliver Hoidn, Steven Henke, Albert Vong, Aashwin Mishra, Apurva Mehta, Matthew Seaberg
Machine Learning · Cross-listed from stat.ML
Conditional neural control variates for variance reduction in Bayesian inverse problems
Ali Siahkoohi and Hyunwoo Oh
Bayesian inference for inverse problems involves computing expectations under posterior distributions–e.g., posterior means, variances, or predictive quantities–typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates demand many samples–a cost often prohibitive for partial differential equation-constrained problems. To address this challenge, we introduce conditional neural control variates, a modular method that learns amortized control variates from joint model-data samples to reduce the variance of MC
estimators. To scale to high-dimensional problems, we leverage Stein's identity to design an architecture based on an ensemble of hierarchical coupling layers with tractable Jacobian trace computation. Training requires: (i) samples from the joint distribution of unknown parameters and observed data; and (ii) the posterior score function, which can be computed from physics-based likelihood evaluations, neural operator surrogates, or learned generative models such as conditional normalizing flows. Once trained, the control variates generalize across observations without retraining. We validate our approach on stylized and partial differential equation-constrained Darcy flow inverse problems, outperforming classical Stein control variates and achieving substantial variance reduction, even when the analytical score is replaced by a learned surrogate.
Read the full abstract ▾
Machine Learning
Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls
Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas et al. (+2 more)
Representation learning has been essential for graph machine learning tasks such as link prediction, community detection, and network visualization. Despite recent advances in achieving high performance on these downstream tasks, little progress has been made toward self-explainable models. Understanding the patterns behind predictions is equally important, motivating recent interest in explainable machine learning. In this paper, we present GraphHull, an explainable generative model that represents networks using two levels of convex hulls. At the global level, the vertices of a convex hull are treated as archetypes, each corresponding to a pure community in the network. At the local level, each community is refined by a prototypical hull whose vertices act as representative profiles, capturing community-specific variation. This two-level construction yields clear multi-scale explanations: a node's position relative to global archetypes and its local prototypes directly accounts for its edges. The geometry is well-behaved by design, while local hulls are kept disjoint by construction. To further encourage diversity and stability, we place principled priors, including determinantal point processes, and fit the model under MAP estimation with scalable subsampling. Experiments on real networks demonstrate the ability of GraphHull to recover multi-level community structure and to achieve competitive or superior performance in link prediction and community detection, while naturally providing interpretable predictions.
Read the full abstract ▾
All authors Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos
Machine Learning
HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models
Jack Goffinet, Casey Hanks and David E. Carlson
Representing the past in a compressed, efficient, and informative manner is a central problem for systems trained on sequential data. The HiPPO framework, originally proposed by Gu & Dao et al., provides a principled approach to sequential compression by projecting signals onto orthogonal
polynomial (OP) bases via structured linear ordinary differential equations. Subsequent works have embedded these dynamics in state space models (SSMs), where HiPPO structure serves as an initialization. Nonlinear successors of these SSM methods such as Mamba are state-of-the-art for many tasks with long-range dependencies, but the mechanisms by which they represent and prioritize history remain largely implicit. In this work, we revisit the HiPPO framework with the goal of making these mechanisms explicit. We show how
polynomial representations of history can be extended to support capabilities of modern SSMs such as adaptive
memory allocation and associative
memory, while retaining direct interpretability in the OP basis. We introduce a unified framework comprising five such extensions, which we collectively refer to as a "HiPPO zoo." Each extension exposes a specific modeling capability through an explicit, interpretable modification of the HiPPO framework. The resulting models adapt their
memory online and train in streaming settings with efficient updates. We illustrate the behaviors and modeling advantages of these extensions through a range of synthetic sequence modeling tasks, demonstrating that capabilities typically associated with modern SSMs can be realized through explicit, interpretable
polynomial memory structures.
Read the full abstract ▾
Machine Learning
Efficient Opportunistic Approachability
Teodor Vanislavov Marinov, Mehryar Mohri, Princewill Okoroafor et al. (+2 more)
We study the problem of opportunistic approachability: a generalization of Blackwell approachability where the learner would like to obtain stronger guarantees (i.e., approach a smaller set) when their adversary limits themselves to a subset of their possible action space. Bernstein et al. (2014) introduced this problem in 2014 and presented an
algorithm that guarantees sublinear approachability rates for opportunistic approachability. However, this
algorithm requires the ability to produce calibrated online predictions of the adversary's actions, a problem whose standard implementations require time exponential in the ambient dimension and result in approachability rates that scale as $T^{-O(1/d)}$. In this paper, we present an efficient
algorithm for opportunistic approachability that achieves a rate of $O(T^{-1/4})$ (and an inefficient one that achieves a rate of $O(T^{-1/3})$), bypassing the need for an online calibration subroutine. Moreover, in the case where the dimension of the adversary's action set is at most two, we show it is possible to obtain the optimal rate of $O(T^{-1/2})$.
Read the full abstract ▾
All authors Teodor Vanislavov Marinov, Mehryar Mohri, Princewill Okoroafor, Jon Schneider, Julian Zimmert
Machine Learning
Equitable Evaluation via Elicitation
Elbert Du, Cynthia Dwork, Lunjia Hu et al. (+3 more)
Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of equally qualified job-seekers with different self-presentation styles is therefore problematic. We build an interactive AI for skill elicitation that provides accurate determination of skills while simultaneously allowing individuals to speak in their own voice. Such a system can be deployed, for example, when a new user joins a professional networking platform, or when matching employees to needs during a company reorganization. To obtain sufficient training data, we train an LLM to act as synthetic humans. Elicitation mitigates endogenous bias arising from individuals' own self-reports. To address systematic model bias we enforce a mathematically rigorous notion of equitability ensuring that the covariance between self-presentation manner and skill evaluation error is small.
Read the full abstract ▾
All authors Elbert Du, Cynthia Dwork, Lunjia Hu, Reid McIlroy-Young, Han Shao, Linjun Zhang
Machine Learning
Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
Quan Xiao, Jindan Li, Zhaoxian Wu et al. (+2 more)
Analog in-
memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large
vision and
language models. However, non-ideal analog device properties make the training on AIMC devices challenging. In particular, its update asymmetry can induce a systematic drift of weight updates towards a device-specific symmetric point (SP), which typically does not align with the optimum of the training objective. To mitigate this bias, most existing works assume the SP is known and pre-calibrate it to zero before training by setting the reference point as the SP. Nevertheless, calibrating AIMC devices requires costly pulse updates, and residual calibration error can directly degrade training performance. In this work, we present the first theoretical characterization of the pulse complexity of SP calibration and the resulting estimation error. We further propose a dynamic SP estimation method that tracks the SP during model training, and establishes its convergence guarantees. In addition, we develop an enhanced variant based on chopping and filtering techniques from digital signal processing. Numerical experiments demonstrate both the efficiency and effectiveness of the proposed method.
Read the full abstract ▾
All authors Quan Xiao, Jindan Li, Zhaoxian Wu, Tayfun Gokmen, Tianyi Chen
Machine Learning
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
Emre Can Acikgoz, Cheng Qian, Jonas Hübotter et al. (+3 more)
Large
language models (LLMs) are becoming the foundation for autonomous
agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically under tightly controlled training setups. It often depends on carefully constructed task-solution pairs and substantial human supervision, which creates a fundamental obstacle to open-ended self-
evolution toward superintelligent systems. In this paper, we propose Tool-R0 framework for training general purpose tool-calling
agents from scratch with self-play RL, under a zero-data assumption. Initialized from the same base LLM, Tool-R0 co-evolves a Generator and a Solver with complementary rewards: one proposes targeted challenging tasks at the other's competence frontier and the other learns to solve them with real-world tool calls. This creates a self-evolving cycle that requires no pre-existing tasks or
datasets. Evaluation on different tool-use
benchmarks show that Tool-R0 yields 92.5 relative improvement over the base model and surpasses fully supervised tool-calling baselines under the same setting. Our work further provides empirical insights into self-play LLM
agents by analyzing co-
evolution, curriculum dynamics, and scaling behavior.
Read the full abstract ▾
All authors Emre Can Acikgoz, Cheng Qian, Jonas Hübotter, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur