Machine Learning · Cross-listed from cs.CL
KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context
Nahyun Lee, Guijin Son, Hyunwoo Ko et al. (+4 more)
Multimodal evaluation is strengthened when
benchmarks reflect the
languages, institutions, and disciplinary conventions that shape expert visual
reasoning. We introduce KMMMU, a native Korean
benchmark built from Korean-native examination materials. KMMMU contains 3,466 questions spanning nine disciplines and nine visual modality categories. For targeted evaluation on challenging questions and Korean-specific knowledge, we additionally provide KMMMU-Adv and KMMMU-Local, respectively. Experiments show that the strongest evaluated open-weight model reaches 42.05% on the KMMMU, while the best evaluated proprietary model achieves 52.42% on the KMMMU-Adv. Performance varies substantially across disciplines and answer formats, with Korean-specific questions showing gaps of up to 13.43%. Error analysis suggests that inspected failures often involve convention-to-label mapping, few-shot symbolic induction, localized knowledge recall, and domain-specific standards, not
reasoning depth alone. KMMMU provides a testbed for native Korean expert-level
multimodal understanding beyond English-centric or translation-based evaluation.
Read the full abstract ▾
All authors Nahyun Lee, Guijin Son, Hyunwoo Ko, Chanyoung Kim, JunYoung An, Kyubeen Han, Il-Youp Kwak
Machine Learning · Cross-listed from cs.CY
Investigating Vaccine Buyer's Remorse: Post-Vaccination Decision Regret in COVID-19 Social Media Using Politically Diverse Human Annotation
Miles Stanley, Soumyajit Datta, Ashutosh Kumar et al. (+1 more)
A significant gap exists in
datasets regarding post-COVID-19 vaccination experiences, particularly “vaccine buyer's remorse”. Understanding the prevalence and nature of vaccine regret, whether based on personal or vicarious experiences, is vital for addressing vaccine hesitancy and refining public health communication. In this paper, we curate a novel
dataset from a large YouTube news corpus capturing COVID-19 vaccination experiences, and construct a
benchmark subset focused on vaccine regret, annotated by a politically diverse panel to account for the subjective and often politicized nature of the topic. We utilize large
language models (LLMs) to identify posts expressing vaccine regret, analyze the reasons behind this regret, and quantify its occurrence in both first and second-person accounts. This paper aims to (1) quantify the prevalence of vaccine regret; (2) identify common reasons for this sentiment; (3) analyze differences between first-person and vicarious experiences; and (4) assess potential biases introduced by different LLMs. We find that while vaccine buyer's remorse appears in only $<2\%$ of public discourse, it is disproportionately concentrated in vaccine-skeptic influencer communities and is predominantly expressed through first-person narratives citing adverse health events.
Read the full abstract ▾
All authors Miles Stanley, Soumyajit Datta, Ashutosh Kumar, Ashiqur R. KhudaBukhsh
Machine Learning · Cross-listed from cs.CL
Self-Calibrating Language Models via Test-Time Discriminative Distillation
Mohamed Rissal Hedna, Jan Strich, Martin Semmann et al. (+1 more)
Large
language models (LLMs) are systematically overconfident: they routinely express high certainty on questions they often answer incorrectly. Existing calibration methods either require labeled validation data, degrade under distribution shifts, or incur substantial inference costs. Recent work has shown that LLMs already contain a better-calibrated signal than the one they verbalize: the
token probability of "True" when the model is asked "Is this answer correct?" ($P(\text{True})$) consistently outperforms their stated confidence, a gap that is theoretically grounded as generative error is lower-bounded by roughly twice the corresponding discriminative error. We introduce $\textbf{SECL}$ ($\textbf{SE}$lf-$\textbf{C}$alibrating $\textbf{L}$anguage Models), a test-time training (TTT) pipeline that exploits this gap as label-free self-supervision, requiring no labeled data or human supervision. SECL adapts only when the input distribution shifts, training on just 6–26% of the question stream at lower cost than the baseline it distills from. Across four small
language models from three model families and four diverse domains, SECL reduces Expected Calibration Error (ECE) by 56–78%, outperforming its own supervision signal and matching or outperforming recent inference-time methods. SECL is the first method to apply TTT to calibration; seven ablations covering signal quality, gating strategy, weight accumulation, loss design, domain ordering, hyperparameter sensitivity, and layer selection confirm that each component is crucial and robust across configurations. Code: https://anonymous.4open.science/r/secl-emnlp26-submission-C890
Read the full abstract ▾
All authors Mohamed Rissal Hedna, Jan Strich, Martin Semmann, Chris Biemann
Machine Learning · Cross-listed from cs.CL
Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
Amr Eleraqi, Hager H. Mustafa and Abdul Hadi N. Ahmed
This study examines how different artificial intelligence architectures interpret sentiment in conflict-related media discourse, using the 2023 Gaza War as a case study. Drawing on a corpus of 10,990 Arabic news headlines (Eleraqi 2026), the research conducts a comparative analysis between three large
language models and six fine-tuned Arabic BERT models. Rather than evaluating accuracy against a single human-annotated gold standard, the study adopts an epistemological approach that treats sentiment classification as an interpretive act produced by model architectures. To quantify systematic differences across models, the analysis employs information-theoretic and distributional metrics, including Shannon
Entropy, Jensen-Shannon Distance, and a Variance Score measuring deviation from aggregate model behavior. The results reveal pronounced and non-random divergence in sentiment distributions. Fine-tuned BERT models, particularly MARBERT, exhibit a strong bias toward neutral classifications, while LLMs consistently amplify negative sentiment, with LLaMA-3.1-8B showing near-total collapse into negativity. Frame-conditioned analysis further demonstrates that GPT-4.1 adjusts sentiment judgments in line with narrative frames (e.g., humanitarian, legal, security), whereas other LLMs display limited contextual modulation. These findings suggest that the choice of model constitutes a choice of interpretive lens, shaping how conflict narratives are algorithmically framed and emotionally evaluated. The study contributes to media studies and computational social science by foregrounding algorithmic discrepancy as an object of analysis and by highlighting the risks of treating automated sentiment outputs as neutral or interchangeable measures of media tone in contexts of war and crisis.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Dynamic sparsity in tree-structured feed-forward layers at scale
Reza Sedghi, Robin Schiewer, Anand Subramoney et al. (+1 more)
At typical context lengths, the feed-forward MLP block accounts for a large share of a
transformer's compute budget, motivating sparse alternatives to dense MLP blocks. We study sparse, tree-structured feed-forward layers as drop-in replacements for MLP blocks in deep
transformer architectures, enabling conditional computation via hard hierarchical routing without a separate router network. We demonstrate for the first time that this form of tree-structured conditional sparsity can be applied for autoregressive
language modeling and downstream question answering, including zero- and few-shot settings, and its scalability beyond 1B parameters. Despite activating fewer than 5% of the feed-forward block's units per
token, our models match dense baselines under controlled training and fine-tuning protocols. We further analyze training dynamics and identify an emergent auto-
pruning effect: the interaction of hard routing with asymmetric nonlinearities progressively deactivates unused paths, yielding partial conversion of dynamic routing into static structural sparsity. We show that simple architectural choices can modulate this behavior and recover balanced trees without auxiliary losses. Overall, our work demonstrates that tree-structured feed-forward layers provide a scalable and controllable mechanism for sparsifying large
transformer models.
Read the full abstract ▾
All authors Reza Sedghi, Robin Schiewer, Anand Subramoney, David Kappel
Machine Learning · Cross-listed from cs.CL
Yuyan Zhou, Kai Syun Hou, Weiyu Chen et al. (+1 more)
Auto-regressive models (ARMs) have established a dominant paradigm in
language modeling. However, their strictly sequential sampling paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address these limitations,
diffusion-based large
language models (dLLMs) have been proposed, offering the potential for parallel sampling and flexible
language modeling. Despite these advantages, current dLLMs sampling strategies rely primarily on
token level information, which fails to account for global sequence structure and often yields suboptimal results. In this paper, we study the sampling order selection problem from the perspective of log-likelihood maximization. We show that this problem is NP-hard and propose an optimal sampling-rank-based approximation that makes the objective computationally tractable. We further prove that the tractable objective is optimized by sampling
tokens in descending order of their
attention-
matrix column sums. This finding provides a principled justification for
attention-guided sampling and offers a theoretically grounded alternative to greedy search. We instantiate this theoretical insight in a new training-free sampling
algorithm, termed Attn-Sampler, and further propose dynamic
attention thresholding for practical acceleration. Extensive experiments across multiple
benchmarks validate the effectiveness of our proposed method, demonstrating that it achieves superior generation quality while enhancing the sampling parallelism.
Read the full abstract ▾
All authors Yuyan Zhou, Kai Syun Hou, Weiyu Chen, James Kwok
Machine Learning · Cross-listed from cs.CL
Temperature-Dependent Performance of Prompting Strategies in Extended Reasoning Large Language Models
Mousa Salah and Amgad Muneer
Extended
reasoning models represent a transformative shift in Large
Language Model (LLM) capabilities by enabling explicit test-time computation for complex problem solving. However, the optimal configuration of sampling temperature and prompting strategy for these systems remains largely underexplored. We systematically evaluate chain-of-thought and zero-shot prompting across four temperature settings (0.0, 0.4, 0.7, and 1.0) using Grok-4.1 with extended
reasoning on 39 mathematical problems from AMO-Bench, a challenging International Mathematical Olympiad-level
benchmark. We find that zero-shot prompting achieves peak performance at moderate temperatures, reaching 59% accuracy at T=0.4 and T=0.7, while chain-of-thought prompting performs best at the temperature extremes. Most notably, the benefit of extended
reasoning increases from 6x at T=0.0 to 14.3x at T=1.0. These results suggest that temperature should be optimized jointly with prompting strategy, challenging the common practice of using T=0 for
reasoning tasks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
Emergent Compositional Communication for Latent World Properties
Tomek Kaszyński
Can multi-
agent communication pressure extract discrete, compositional representations of invisible physical properties from frozen
video features? We show that
agents communicating through a Gumbel-Softmax bottleneck with iterated learning develop positionally disentangled protocols for latent properties (elasticity, friction, mass ratio) without property labels or supervision on message structure. With 4
agents, 100% of 80 seeds converge to near-perfect compositionality (PosDis=0.999, holdout 98.3%). Controls confirm multi-
agent structure – not bandwidth or temporal coverage – drives this effect. Causal intervention shows
surgical property disruption (~15% drop on targeted property, <3% on others). A controlled backbone comparison reveals that the perceptual prior determines what is communicable: DINOv2 dominates on spatially-visible ramp physics (98.3% vs 95.1%), while V-JEPA 2 dominates on dynamics-only collision physics (87.4% vs 77.7%, d=2.74). Scale-matched (d=3.37) and frame-matched (d=6.53) controls attribute this gap entirely to
video-native pretraining. The frozen protocol supports action-conditioned planning (91.5%) with counterfactual velocity
reasoning (r=0.780). Validation on Physics 101 real camera footage confirms 85.6% mass-comparison accuracy on unseen objects, temporal dynamics contributing +11.2% beyond static appearance,
agent-scaling compositionality replicating at 90% for 4
agents, and causal intervention extending to real
video (d=1.87, p=0.022).
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller
Anna Tegon, Nicholas Lehmann, Yawei Li et al. (+3 more)
Objective: To enable continuous, long-term neuro-monitoring on wearable devices by overcoming the computational bottlenecks of
Transformer-based Electroencephalography (
EEG) foundation models and the quantization challenges inherent to State-Space Models (SSMs). Methods: We present FEMBA, a bidirectional Mamba architecture pre-trained on over 21,000 hours of
EEG. We introduce a novel Physiologically-Aware pre-training objective, consisting of a reconstruction with low-pass filtering, to prioritize neural oscillations over high-frequency artifacts. To address the activation outliers common in SSMs, we employ Quantization-Aware Training (QAT) to compress the model to 2-bit weights. The framework is deployed on a parallel ultra-low-power RISC-V microcontroller (GAP9) using a custom double-buffered
memory streaming scheme. Results: The proposed low-pass pre-training improves downstream AUROC on TUAB from 0.863 to 0.893 and AUPR from 0.862 to 0.898 compared to the best contrastive baseline. QAT successfully compresses weights with negligible performance loss, whereas standard post-training quantization degrades accuracy by approximately 30%. The embedded implementation achieves deterministic real-time inference (1.70~s per 5~s window) and reduces the
memory footprint by 74% (to $\approx$2~MB), achieving competitive accuracy with up to \textbf{27$\times$} fewer FLOPs than
Transformer benchmarks. Conclusion: FEMBA demonstrates that Mamba-based foundation models can be effectively quantized and deployed on extreme-edge hardware without sacrificing the representation quality required for robust clinical analysis. Significance: This work establishes the first full-stack framework for deploying large-scale
EEG foundation models on ultra-low-power wearables, facilitating continuous, SSM based monitoring for epilepsy and sleep disorders.
Read the full abstract ▾
All authors Anna Tegon, Nicholas Lehmann, Yawei Li, Andrea Cossettini, Luca Benini, Thorir Mar Ingolfsson
Machine Learning
Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition
Guangli Li, Canbiao Wu, Na Tian et al. (+2 more)
Electroencephalography (
EEG)-based
emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous
datasets due to physiological variability, experimental paradigm differences, and device inconsistencies. Existing domain
adversarial methods primarily enforce global marginal
alignment and often overlook class-conditional mismatch and decision boundary distortion, limiting cross-corpus generalization. In this work, we propose a unified Prototype-driven
Adversarial Alignment (PAA) framework for cross-corpus
EEG emotion recognition. The framework is progressively instantiated in three configurations: PAA-L, which performs prototype-guided local class-conditional
alignment; PAA-C, which further incorporates contrastive semantic regularization to enhance intra-class compactness and inter-class separability; and PAA-M, the full boundary-aware configuration that integrates dual relation-aware classifiers within a three-stage
adversarial optimization scheme to explicitly refine controversial samples near decision boundaries. By combining prototype-guided subdomain
alignment, contrastive discriminative enhancement, and boundary-aware aggregation within a coherent
adversarial architecture, the proposed framework reformulates
emotion recognition as a relation-driven representation learning problem, reducing sensitivity to label noise and improving cross-domain stability. Extensive experiments on SEED, SEED-IV, and SEED-V demonstrate state-of-the-art performance under four cross-corpus evaluation protocols, with average improvements of 6.72%, 5.59%, 6.69%, and 4.83%, respectively. Furthermore, the proposed framework generalizes effectively to clinical depression identification scenarios, validating its robustness in real-world heterogeneous settings. The source code is available at https://github.com/WuCB-BCI/PAA
Read the full abstract ▾
All authors Guangli Li, Canbiao Wu, Na Tian, Li Zhang, Zhen Liang
Machine Learning
Full waveform inversion method based on diffusion model
Caiyun Liu, Siyang Pei, Qingfeng Yu et al. (+1 more)
Seismic full-waveform inversion is a core technology for obtaining high-resolution subsurface model parameters. However, its highly nonlinear characteristics and strong dependence on the initial model often lead to the inversion process getting trapped in local minima. In recent years, generative
diffusion models have provided a way to regularize full-waveform inversion by learning implicit prior distributions. However, existing methods mostly use unconditional
diffusion processes, ignoring the inherent physical coupling relationship between velocity and density and other physical properties. This paper proposes a full-waveform inversion method based on conditional
diffusion model regularization. By improving the backbone network structure of the
diffusion model, two-dimensional density information is introduced as a conditional input into the U-Net network. Experimental results show that the full-waveform inversion method based on the conditional
diffusion model significantly improves the resolution and structural fidelity of the inversion results, and exhibits stronger stability and robustness when dealing with complex situations. This method effectively utilizes density information to constrain the inversion and has good practical application value. Keywords: Deep learning;
Diffusion model; Full waveform inversion.
Read the full abstract ▾
All authors Caiyun Liu, Siyang Pei, Qingfeng Yu, Jie Xiong
Machine Learning
CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News
Liyuan Chen, Shilong Li, Jiangpeng Yan et al. (+3 more)
Large
Language Models (LLMs) are rapidly transitioning from static Natural
Language Processing (NLP) tasks including sentiment analysis and event extraction to acting as dynamic decision-making
agents in complex financial environments. However, the
evolution of LLMs into autonomous financial
agents faces a significant dilemma in evaluation paradigms. Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static
benchmarks are often confined to entity-level stock picking and ignore broader
market attention. To facilitate the rigorous analysis of these challenges, we introduce CN-Buzz2Portfolio, a reproducible
benchmark grounded in the Chinese
market that maps daily trending news to macro and sector asset allocation. Spanning a rolling horizon from 2024 to mid-2025, our
dataset simulates a realistic public
attention stream, requiring
agents to distill investment logic from high-exposure narratives instead of pre-filtered entity news. We propose a Tri-Stage CPA
Agent Workflow involving Compression, Perception, and Allocation to evaluate LLMs on broad asset classes such as Exchange Traded Funds (ETFs) rather than individual stocks, thereby reducing idiosyncratic
volatility. Extensive experiments on nine LLMs reveal significant disparities in how models translate macro-level narratives into portfolio weights. This work provides new insights into the
alignment between general
reasoning and financial decision-making, and all data, codes, and experiments are released to promote sustainable financial
agent research.
Read the full abstract ▾
All authors Liyuan Chen, Shilong Li, Jiangpeng Yan, Shuoling Liu, Qiang Yang, Xiu Li
Machine Learning · Cross-listed from cs.IR
FastPFRec: A Fast Personalized Federated Recommendation with Secure Sharing
Zhenxing Yan, Jidong Yuan, Yongqi Sun et al. (+2 more)
Graph neural network (GNN)-based
federated recommendation systems effectively capture user-item relationships while preserving data
privacy. However, existing methods often face slow convergence on graph data and
privacy leakage risks during collaboration. To address these challenges, we propose FastPFRec (Fast Personalized
Federated Recommendation with Secure Sharing), a novel framework that enhances both training efficiency and data security. FastPFRec accelerates model convergence through an efficient local update strategy and introduces a
privacy-aware parameter sharing mechanism to mitigate leakage risks. Experiments on four real-world
datasets (Yelp, Kindle, Gowalla-100k, and Gowalla-1m) show that FastPFRec achieves 32.0% fewer training rounds, 34.1% shorter training time, and 8.1% higher accuracy compared with existing baselines. These results demonstrate that FastPFRec provides an efficient and
privacy-preserving solution for scalable
federated recommendation.
Read the full abstract ▾
All authors Zhenxing Yan, Jidong Yuan, Yongqi Sun, Haiyang Liu, Zhihui Gao
Machine Learning
FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions
Chloe H. Choi, Alison L. Marsden and Daniele E. Schiavazzi
Boundary condition tuning is a fundamental step in patient-specific cardiovascular modeling. Despite an increase in offline training cost, recent methods in data-driven variational inference can efficiently estimate the joint posterior distribution of boundary conditions, with amortization of training efforts over clinical targets. However, even the most modern approaches fall short in two important scenarios: open-loop models with known mean flow and assumed waveform shapes, and anatomies affected by vascular lesions where
segmentation influences the reachability of pressure or flow split targets. In both cases, boundary conditions cannot be tuned in isolation. We introduce a general amortized inference framework based on probabilistic flow that treats clinical targets, inflow features, and point cloud
embeddings of patient-specific anatomies as either conditioning variables or quantities to be jointly estimated. We demonstrate the approach on two patient-specific models: an aorto-iliac bifurcation with varying stenosis locations and severity, and a coronary arterial tree.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.QM
Mathematical Modeling of Cancer-Bacterial Therapy: Analysis and Numerical Simulation via Physics-Informed Neural Networks
Ayoub Farkane and David Lassounon
Bacterial cancer therapy exploits anaerobic bacteria's ability to target hypoxia tumor regions, yet the interactions among tumor growth, bacterial colonization, oxygen levels, immunosuppressive cytokines, and bacterial communication remain poorly quantified. We present a mathematical model of five coupled nonlinear reaction-
diffusion equations in a two-dimensional tissue domain. We proved the global well-posedness of the model and identified its steady states to analyze stability. Furthermore, a physics-informed neural network (PINN) solves the system without a mesh and without requiring extensive data. It provides convergence guarantees by combining residual stability and Sobolev approximation error bounds. This results in an overall error rate of O(n^-2 ln^4(n) + N^-1/2), which depends on the network width n and the number of collocation points N. We conducted several numerical experiments, including predicting the tumor's response to therapy. We also performed a sensitivity analysis of certain parameters. The results suggest that long-term therapeutic efficacy may require the maintenance of hypoxia regions in the tumor, or using bacteria that tolerate oxygen better, may be necessary for long-lasting tumor control.
Read the full abstract ▾
Machine Learning
Epistemic Generative Adversarial Networks
Muhammad Mubashar and Fabio Cuzzolin
Generative models, particularly Generative
Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN loss function based on Dempster-Shafer theory of evidence, applied to both the generator and discriminator. Additionally, we propose an architectural enhancement to the generator that enables it to predict a mass function for each image pixel. This modification allows the model to quantify uncertainty in its outputs and leverage this uncertainty to produce more diverse and representative generations. Experimental evidence shows that our approach not only improves generation variability but also provides a principled framework for modeling and interpreting uncertainty in generative processes.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
HRI-SA: A Multimodal Dataset for Online Assessment of Human Situational Awareness during Remote Human-Robot Teaming
Hashini Senaratne, Richard Attfield, Samith Widhanapathirana et al. (+4 more)
Maintaining situational awareness (SA) is critical in human-
robot teams. Yet, under high workload and dynamic conditions, operators often experience SA gaps. Automated detection of SA gaps could provide timely assistance for operators. However, conventional SA measures either disrupt task flow or cannot capture real-time fluctuations, limiting their operational utility. To the best of our knowledge, no publicly available
dataset currently supports the systematic evaluation of online human SA assessment in human-
robot teaming. To advance the development of online SA assessment tools, we introduce HRI-SA, a
multimodal dataset from 30 participants in a realistic search-and-rescue human-
robot teaming context, incorporating eye movements, pupil diameter, biosignals, user interactions, and
robot data. The experimental protocol included predefined events requiring timely operator assistance, with ground truth SA latency of two types (perceptual and comprehension) systematically obtained by measuring the time between assistance need onset and resolution. We illustrate the utility of this
dataset by evaluating standard machine learning models for detecting perceptual SA latencies using generic eye-tracking features and contextual features. Results show that eye-tracking features alone effectively classified perceptual SA latency (recall=88.91%, F1=67.63%) using leave-one-group-out cross-validation, with performance improved through contextual data fusion (recall=91.51%, F1=80.38%). This paper contributes the first public
dataset supporting the systematic evaluation of SA throughout a human-
robot teaming mission, while also demonstrating the potential of generic eye-tracking features for continuous perceptual SA latency detection in remote human-
robot teaming.
Read the full abstract ▾
All authors Hashini Senaratne, Richard Attfield, Samith Widhanapathirana, David Howard, Cecile Paris, Dana Kulic, Leimin Tian
Machine Learning · Cross-listed from cs.RO
Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
Yanchuan Tang, Taowen Wang, Yuefei Chen et al. (+3 more)
Vision-
Language-Action (VLA) models enable general-purpose robotic policies by mapping visual observations and
language instructions to low-level actions, but they often lack reliable introspection. A common practice is to compute a
token-level uncertainty signal and take its mean over a rollout. However, mean aggregation can dilute short-lived but safety-critical uncertainty spikes in continuous control. In particular, successful rollouts may contain localized high-
entropy segments due to benign noise or non-critical micro-adjustments, while failure rollouts can appear low-
entropy for most timesteps and only exhibit brief spikes near the onset of failure. We propose a unified uncertainty quantification approach for predicting rollout success versus failure that (1) uses max-based sliding window pooling to preserve transient risk signals, (2) applies motion-aware stability weighting to emphasize high-frequency action oscillations associated with unstable behaviors, and (3) performs DoF-adaptive calibration via
Bayesian Optimization to prioritize kinematically critical axes. Experiments on the LIBERO
benchmark show that our method substantially improves failure prediction accuracy and yields more reliable signals for failure detection, which can support downstream human-in-the-loop interventions.
Read the full abstract ▾
All authors Yanchuan Tang, Taowen Wang, Yuefei Chen, Boxuan Zhang, Qiang Guan, Ruixiang Tang
Machine Learning · Cross-listed from cs.SE
Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
Zichen Xie and Wenxi Wang
As Large
Language Models (LLMs) increasingly assist secure software development, their ability to meet the rigorous demands of Rust program verification remains unclear. Existing evaluations treat Rust verification as a black box, assessing models only by binary pass or fail outcomes for proof hints. This obscures whether models truly understand the logical deductions required for verifying nontrivial Rust code. To bridge this gap, we introduce VCoT-Lift, a framework that lifts low-level solver
reasoning into high-level, human-readable verification steps. By exposing solver-level
reasoning as an explicit Verification Chain-of-Thought, VCoT-Lift provides a concrete ground truth for fine-grained evaluation. Leveraging VCoT-Lift, we introduce VCoT-Bench, a comprehensive
benchmark of 1,988 VCoT completion tasks for rigorously evaluating LLMs' understanding of the entire verification process. VCoT-Bench measures performance along three orthogonal dimensions: robustness to varying degrees of missing proofs, competence across different proof types, and sensitivity to the proof locations. Evaluation of ten state-of-the-art models reveals severe fragility, indicating that current LLMs fall well short of the
reasoning capabilities exhibited by automated
theorem provers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
MemArchitect: A Policy Driven Memory Governance Layer
Lingavasan Suresh Kumar, Yang Ba and Rong Pan
Persistent Large
Language Model (LLM)
agents expose a critical governance gap in
memory management. Standard
Retrieval-Augmented Generation (RAG) frameworks treat
memory as passive storage, lacking mechanisms to resolve contradictions, enforce
privacy, or prevent outdated information ("zombie
memories") from contaminating the context window. We introduce MemArchitect, a governance layer that decouples
memory lifecycle management from model weights. MemArchitect enforces explicit, rule-based policies, including
memory decay, conflict resolution, and
privacy controls. We demonstrate that governed
memory consistently outperforms unmanaged
memory in agentic settings, highlighting the necessity of structured
memory governance for reliable and safe autonomous systems.
Read the full abstract ▾
Machine Learning
A Family of Adaptive Activation Functions for Mitigating Failure Modes in Physics-Informed Neural Networks
Krishna Murari
Physics-Informed Neural Networks(PINNs) are a powerful and flexible learning framework that has gained significant
attention in recent years. It has demonstrated strong performance across a wide range of scientific and engineering problems. In parallel, wavelets have been extensively used as efficient computational tools due to their strong approximation capabilities. Motivated by the common failure modes observed in standard PINNs, this work introduces a novel family of adaptive wavelet-based activation functions. The proposed activation functions significantly improve training stability and expressive power by combining trainable wavelet functions with either trainable or fixed
hyperbolic tangent and softplus functions. Five distinct activation functions are developed within the PINN framework and systematically evaluated across four representative classes of partial differential equations (PDEs). Comprehensive comparisons using bar plots demonstrate improved robustness and accuracy compared to traditional activation functions. Furthermore, the proposed approach is validated through direct comparisons with baseline PINNs,
transformer-based architectures such as PINNsFormer, and other deep learning models, highlighting its effectiveness and generality.
Read the full abstract ▾
Machine Learning
Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration
Amirhossein Roknilamouki, Arnob Ghosh, Eylem Ekici et al. (+1 more)
While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an
agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement learning, exploring near the boundary of regions well covered by the offline
dataset and reliably modeled by the simulator allows an
agent to take manageable risks–venturing into informative but moderate-uncertainty states while remaining close enough to familiar regions for safe recovery. However, naively rewarding this boundary-seeking behavior can lead to a degenerate parking behavior, where the
agent simply stops once it reaches the frontier. To solve this, we propose a novel vector-field reward shaping paradigm designed to induce continuous, safe boundary exploration for non-adaptive deployed policies. Operating on an uncertainty oracle trained from offline data, our reward combines two complementary components: a gradient-
alignment term that attracts the
agent toward a target uncertainty level, and a rotational-flow term that promotes motion along the local tangent plane of the uncertainty
manifold. Through theoretical analysis, we show that this reward structure naturally induces sustained exploratory behavior along the boundary while preventing degenerate solutions. Empirically, by integrating our proposed reward shaping with Soft Actor-Critic on a 2D continuous
navigation task, we validate that
agents successfully traverse uncertainty boundaries while balancing safe, informative data collection with primary task completion.
Read the full abstract ▾
All authors Amirhossein Roknilamouki, Arnob Ghosh, Eylem Ekici, Ness B. Shroff
Machine Learning
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
Nived Rajaraman, Audrey Huang, Miro Dudik et al. (+3 more)
Chain-of-thought
reasoning, where
language models expend additional computation by producing thinking
tokens prior to final responses, has driven significant advances in model capabilities. However, training these
reasoning models is extremely costly in terms of both data and compute, as it involves collecting long traces of
reasoning behavior from humans or synthetic generators and further post-training the model via reinforcement learning. Are these costs fundamental, or can they be reduced through better algorithmic design? We show that autocurriculum, where the model uses its own performance to decide which problems to focus training on, provably improves upon standard training recipes for both supervised fine-tuning (SFT) and reinforcement learning (RL). For SFT, we show that autocurriculum requires exponentially fewer
reasoning demonstrations than non-adaptive fine-tuning, by focusing teacher supervision on
prompts where the current model struggles. For RL fine-tuning, autocurriculum decouples the computational cost from the quality of the reference model, reducing the latter to a burn-in cost that is nearly independent of the target accuracy. These improvements arise purely from adaptive data selection, drawing on classical techniques from boosting and learning from counterexamples, and requiring no assumption on the distribution or difficulty of
prompts.
Read the full abstract ▾
All authors Nived Rajaraman, Audrey Huang, Miro Dudik, Robert Schapire, Dylan J. Foster, Akshay Krishnamurthy
Machine Learning
Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning
Kaiyang Li, Shihao Ji, Zhipeng Cai et al. (+1 more)
Approximate subgraph matching (ASM) is a task that determines the approximate presence of a given query graph in a large target graph. Being an NP-hard problem, ASM is critical in graph analysis with a myriad of applications ranging from database systems and network science to biochemistry and
privacy. Existing techniques often employ heuristic search strategies, which cannot fully utilize the graph information, leading to sub-optimal solutions. This paper proposes a Reinforcement Learning based Approximate Subgraph Matching (RL-ASM)
algorithm that exploits graph
transformers to effectively extract graph representations and RL-based policies for ASM. Our model is built upon the branch-and-bound
algorithm that selects one pair of nodes from the two input graphs at a time for potential matches. Instead of using heuristics, we exploit a Graph
Transformer architecture to extract feature representations that encode the full graph information. To enhance the training of the RL policy, we use supervised signals to guide our
agent in an imitation learning stage. Subsequently, the policy is fine-tuned with the Proximal Policy Optimization (PPO) that optimizes the accumulative long-term rewards over episodes. Extensive experiments on both synthetic and real-world
datasets demonstrate that our RL-ASM outperforms existing methods in terms of effectiveness and efficiency. Our source code is available at https://github.com/KaiyangLi1992/RL-ASM.
Read the full abstract ▾
All authors Kaiyang Li, Shihao Ji, Zhipeng Cai, Wei Li
Machine Learning · Cross-listed from cs.CV
Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction
Devjyoti Chakraborty, Zaki Sukma, Rakandhiya D. Rachmanto et al. (+6 more)
Neural Radiance Fields (NeRF) have emerged as a powerful approach for photorealistic 3D reconstruction from multi-view images. However, deploying NeRF for satellite imagery remains challenging. Each scene requires individual training, and optimizing architectures via Neural Architecture Search (NAS) demands hours to days of GPU time. While existing approaches focus on architectural improvements, our SHAP analysis reveals that multi-view consistency, rather than model architecture, determines reconstruction quality. Based on this insight, we develop PreSCAN, a predictive framework that estimates NeRF quality prior to training using lightweight
geometric and photometric descriptors. PreSCAN selects suitable architectures in < 30 seconds with < 1 dB prediction error, achieving 1000$\times$ speedup over NAS. We further demonstrate PreSCAN's deployment utility on edge platforms (Jetson Orin), where combining its predictions with offline cost profiling reduces inference power by 26% and latency by 43% with minimal quality loss. Experiments on DFC2019
datasets confirm that PreSCAN generalizes across diverse satellite scenes without retraining.
Read the full abstract ▾
All authors Devjyoti Chakraborty, Zaki Sukma, Rakandhiya D. Rachmanto, Kriti Ghosh, In Kee Kim, Suchendra M. Bhandarkar, Lakshmish Ramaswamy, Nancy K. O'Hare, Deepak Mishra
Machine Learning · Cross-listed from cs.HC
Auditing Preferences for Brands and Cultures in LLMs
Jasmine Rienecker, Katarina Mpofu, Naman Goel et al. (+4 more)
Large
language models (LLMs) based AI systems increasingly mediate what billions of people see, choose and buy. This creates an urgent need to quantify the systemic risks of LLM-driven
market intermediation, including its implications for
market fairness, competition, and the diversity of information exposure. This paper introduces ChoiceEval, a reproducible framework for
auditing preferences for brands and cultures in large
language models (LLMs) under realistic usage conditions. ChoiceEval addresses two core technical challenges: (i) generating realistic, persona-diverse evaluation queries and (ii) converting free-form outputs into comparable choice sets and quantitative preference metrics. For a given topic (e.g. running shoes, hotel chains, travel destinations), the framework segments users into psychographic profiles (e.g., budget-conscious, wellness-focused, convenience), and then derives diverse
prompts that reflect real-world advice-seeking and decision-making behaviour. LLM responses are converted into normalised top-k choice sets. Preference and geographic bias are then quantified using comparable metrics across topics and personas. Thus, ChoiceEval provides a scalable audit pipeline for researchers, platforms, and regulators, linking model behaviour to real-world economic outcomes. Applied to Gemini, GPT, and DeepSeek across 10 topics spanning commerce and culture and more than 2,000 questions, ChoiceEval reveals consistent preferences: U.S.-developed models Gemini and GPT show marked favouritism toward American entities, while China-developed DeepSeek exhibits more balanced yet still detectable geographic preferences. These patterns persist across user personas, suggesting systematic rather than incidental effects.
Read the full abstract ▾
All authors Jasmine Rienecker, Katarina Mpofu, Naman Goel, Siddhartha Datta, Jun Zhao, Oscar Danielsson, Fredrik Thorsen
Machine Learning
ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis
Zhanqi Zhang, Shun Li, Bernardo L. Sabatini et al. (+2 more)
Intracortical
brain-computer interfaces (BCIs) can decode
speech from neural activity with high accuracy when trained on data pooled across recording sessions. In realistic deployment, however, models must generalize to new sessions without labeled data, and performance often degrades due to cross-session nonstationarities (e.g., electrode shifts, neural turnover, and changes in user strategy). In this paper, we propose ALIGN, a session-invariant learning framework based on multi-domain
adversarial neural networks for semi-supervised cross-session adaptation. ALIGN trains a feature encoder jointly with a phoneme classifier and a domain classifier operating on the latent representation. Through
adversarial optimization, the encoder is encouraged to preserve task-relevant information while suppressing session-specific cues. We evaluate ALIGN on intracortical
speech decoding and find that it generalizes consistently better to previously unseen sessions, improving both phoneme error rate and word error rate relative to baselines. These results indicate that
adversarial domain
alignment is an effective approach for mitigating session-level distribution shift and enabling robust longitudinal BCI decoding.
Read the full abstract ▾
All authors Zhanqi Zhang, Shun Li, Bernardo L. Sabatini, Mikio Aoi, Gal Mishne
Machine Learning
Path-Constrained Mixture-of-Experts
Zijin Gu, Tatiana Likhomanenko, Vimal Thilak et al. (+2 more)
Sparse Mixture-of-Experts (MoE) architectures route each
token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of expert paths – the sequence of expert selections a
token makes across all layers. This perspective reveals that, despite $N^L$ possible paths for $N$ experts across $L$ layers,
tokens in practice cluster into a small fraction of paths that align with linguistic function, yet the vast majority of paths remain unexplored, representing a statistical inefficiency. This motivates architectures that constrain the effective path space to amplify this natural concentration. As one instantiation, we introduce \pathmoe{}, which shares router parameters across blocks of consecutive layers. Analysis confirms that \pathmoe{} amplifies the emergent path structure: it produces more concentrated path clusters, better cross-layer consistency, and greater robustness to routing perturbations. Experiments on 0.9B and 16B parameter \pathmoe{} models demonstrate consistent improvements on perplexity and downstream tasks over independent routing, while eliminating the need for auxiliary losses. These results establish expert paths as a useful design axis for MoE architectures, complementary to existing work on independent routing mechanisms.
Read the full abstract ▾
All authors Zijin Gu, Tatiana Likhomanenko, Vimal Thilak, Jason Ramapuram, Navdeep Jaitly
Machine Learning
On Additive Gaussian Processes for Wind Farm Power Prediction
Simon M. Brealy, Lawrence A. Bull, Daniel S. Brennan et al. (+4 more)
Population-based Structural Health Monitoring (PBSHM) aims to share information between similar machines or structures. This paper takes a population-level perspective, exploring the use of additive Gaussian processes to reveal variations in turbine-specific and farm-level power models over a collected wind farm
dataset. The predictions illustrate patterns in wind farm power generation, which follow intuition and should enable more informed control and decision-making.
Read the full abstract ▾
All authors Simon M. Brealy, Lawrence A. Bull, Daniel S. Brennan, Pauline Beltrando, Anders Sommer, Nikolaos Dervilis, Keith Worden
Machine Learning
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
Gregory N. Frank
Current
alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where
alignment often operates: routing from concept detection to behavioral policy. We study political censorship in Chinese-origin
language models as a natural experiment, using probes,
surgical ablations, and behavioral tests across nine open-weight models from five labs. Three findings follow. First, probe accuracy alone is non-diagnostic: political probes, null controls, and permutation baselines can all reach 100%, so held-out category generalization is the informative test. Second,
surgical ablation reveals lab-specific routing. Removing the political-sensitivity direction eliminates censorship and restores accurate factual output in most models tested, while one model confabulates because its architecture entangles factual knowledge with the censorship mechanism. Cross-model transfer fails, indicating that routing geometry is model- and lab-specific. Third, refusal is no longer the dominant censorship mechanism. Within one model family, hard refusal falls to zero while narrative steering rises to the maximum, making censorship invisible to refusal-only
benchmarks. These results support a three-stage descriptive framework: detect, route, generate. Models often retain the relevant knowledge;
alignment changes how that knowledge is expressed. Evaluations that audit only detection or refusal therefore miss the routing mechanism that most directly determines behavior.
Read the full abstract ▾