Machine Learning
Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
Haoming Chen, Nicolas Zilberstein, Santiago Paternain et al. (+1 more)
Graph reconstruction from partial observations often comes with structural side information, such as degree bounds, triangle counts, or an edge-density band. Prior-Informed Flow Matching (PIFM) reconstructs graphs by transporting a local prior toward the graph distribution, but it provides no mechanism to incorporate this side information. We put forth Constrained Primal-Dual PIFM (CPD-PIFM), which augments the sampler with Lagrange multipliers that evolve along each trajectory. The multipliers respond to constraint violations at a predicted endpoint and guide subsequent sampling steps without retraining. We prove that the sampler inherits PIFM's permutation equivariance and bound its expected terminal slack by a term that decays as the inverse square root of the number of steps, plus two approximation terms. On three link-prediction
benchmarks and nine combinations of
datasets and constraints, CPD-PIFM raises feasibility by 11-26 percentage points and remains competitive with fixed guidance without selecting a separate multiplier for each constraint.
Read the full abstract ▾
All authors Haoming Chen, Nicolas Zilberstein, Santiago Paternain, Santiago Segarra
Networking
Analyzing 10 Petabit/s Network Data with Accelerated Associative (Token) Arrays
Jeremy Kepner, Hayden Jananthan, LaToya Anderson et al. (+19 more)
As networks expand and become an ever more critical infrastructure to modern society the need to analyze these networks with the highest regard for
privacy is essential to ensure their proper function. Depending on the level of the network layer to be analyzed, sources and destinations can be any combination of physical, logical, or persona/agentic endpoints, which requires the ability to handle diverse data. Invaluable to these analyses are mathematical tools that enable sophisticated mathematical
algorithms to be expressed succinctly while achieving scalable vertical (within a compute node), horizontal (across compute nodes), and temporal (over different generations of hardware) performance. Associative (
token) array mathematics and corresponding libraries is one approach that can meet these requirements. Accelerating these libraries with GPUs enables the analysis of the largest networks. The MIT/IEEE/Amazon Anonymized Network Sensing Graph Challenge provides a venue for highlighting the applicability of accelerated associative arrays for these types of problems. The D4M associative library has been implemented in a number of
languages. This work
benchmarks a prototype Matlab D4M GPU accelerated implementation of the Anonymized Network Sensing challenge across a wide range of CPU and GPU hardware. Scalable performance is demonstrated within and across CPU cores, CPU nodes, and GPU nodes. Horizontal scaling across multiple nodes was linear. Running on hundreds of GPU nodes simultaneously achieved a sustained processing rate sufficient to potentially analyze a 10 Petabit/s network.
Read the full abstract ▾
All authors Jeremy Kepner, Hayden Jananthan, LaToya Anderson, William Arcand, David Bestor, William Bergeron, Chansup Byun, Alex Bonn, Daniel Burrill, Vijay Gadepally, Michael Houle, Matthew Hubbell, Michael Jones, Piotr Luszczek, Peter Michaleas, Lauren Milechin, Julie Mullen, Andrew Prout, Albert Reuther, Antonio Rosa, Charles Yee, Alex Pentland
Machine Learning
Adaptive Ensemble Selection for Noisy Labels on Tabular Data
Faizaan Ali, Inwon Kang and Oshani Seneviratne
Incorrect or corrupted labels in tabular
datasets can significantly degrade supervised learning performance, particularly when mislabeling is subtle and not easily detectable from feature space alone. In the context of automated or AI-augmented data science workflows, robust detection of such label noise is critical for building reliable models. We propose a data-centric
reasoning module for AI data science systems that automatically diagnoses
dataset quality and selects appropriate cleaning strategies. Given a
dataset, a meta-model predicts weights over a diverse set of detectors, including confidence-based, neighborhood-based, and distributional methods. Across
benchmark datasets with controlled noise, our approach achieves performance comparable to a Confident Learning baseline on average, with
dataset-dependent gains and losses, particularly in heterogeneous regimes. We further show that detector effectiveness is systematically linked to
dataset properties. These results demonstrate the value of descriptor-driven, data-centric ensembling as a component of AI-assisted data-science pipelines for robust
dataset assessment and model reliability.
Read the full abstract ▾
Human-Computer Interaction
Exploring the Effects of Olfactory Cues and Ventilation on Teleportation-based Navigation in VR
Dongyun Han, Heecheol Kim, Siyeon Bak et al. (+3 more)
Spatial cognition supports how people interpret spatial relationships and navigate their surroundings. Although
vision plays a dominant role, other sensory modalities, including olfaction, may also contribute under limited visual conditions. This paper investigates the role of olfactory cues in location recognition during virtual reality (VR)
navigation. We conducted two formal studies using a wearable olfactory prototype. Study 1 examined whether olfactory cues and ventilation influenced users' recognition of encountered locations during \HDY{teleportation-} and dash-based
navigation. Study 2 extended this investigation to repeated
navigation and examined whether ventilation duration influenced recognition performance and user experience across successive movements. Results show that olfactory cues can support recognition of encountered locations during
navigation, while ventilation was associated with reduced residual interference and improved usability. However, longer ventilation did not clearly improve recognition accuracy in repeated
navigation. These findings suggest the potential of olfactory cues as contextual signals during VR
navigation, while also highlighting the importance of scent management for maintaining perceptual clarity and user comfort.
Read the full abstract ▾
All authors Dongyun Han, Heecheol Kim, Siyeon Bak, Chang-Guen Song, Sun-Jeong Kim, Isaac Cho
Distributed Computing
Time Semantics and Liveness Artifacts in Adversarial Consensus Simulation
Nasit S Sony and Xianzhong Ding
Adversarial consensus simulators require not only a model of message delivery but also a model of time. For timeout-sensitive protocols, coupling protocol-time progression to scheduler activity can allow communication scheduling to influence when failure detectors expire. We study this interaction in VeriProtocol using controlled Multi-Paxos and Raft experiments. In the primary Multi-Paxos study, we compare EventCoupled timing, where every scheduler opportunity advances protocol time, with RoundTick timing, which decouples individual scheduler events from timeout progression. At N=5, increasing the bounded message-delay budget from K=6 to K=14 increased the observed EventCoupled leadership-instability rate from 5% to 100% across the tested grid, while no additional valid leader elections occurred in any of the corresponding 140 RoundTick executions. At K=0, neither model produced additional elections. Matched-trace analysis identifies the mechanism: under EventCoupled timing, scheduler activity used to perturb communication also directly advances failure-detector state. Under RoundTick, comparable scheduler activity does not imply equivalent protocol-time progression. A targeted heartbeat-delay control confirms that RoundTick does not suppress timeout-driven elections; an additional election remains reachable when leader contact is unavailable across sufficient logical time.
Read the full abstract ▾
Computer Vision
Distributed Hydrological Modeling in the Feature Space
Mohamad Hakam Shams Eddin, Maria Luisa Taccari, Yikui Zhang et al. (+3 more)
Accurate
forecasting of river discharge and floods is very challenging. River dynamics are affected by storage, meteorological forcing, and flow propagation at different spatial and temporal scales.
Forecasting thus requires a framework that considers the upstream-to-downstream flow through river networks across grid
cells and catchments. This modeling is known in hydrology as distributed modeling and routing. Existing deep learning approaches either ignore this
topology, operate on lumped catchments, or route predicted physical quantities through a separate graph or physical routing model. We instead introduce feature-space routing: a
topology-aware state-space operator embedded directly in the
forecasting dynamics. At every forecast step, the operator gathers latent states from upstream grid
cells and causally updates the downstream state according to the known river network. This preserves the physical connectivity of the river system while allowing the propagated state itself to be learned end-to-end and allows the model to predict river discharge considering both local dynamics and neighboring upstream contributions. To address uncertainty and provide probabilistic forecasts, we minimize the fair continuous ranked probability score (fCRPS) as a training objective. Our experiments on the European Flood Awareness System (EFAS) and observational data for river discharge
forecasting demonstrate that encoding the physical structure of river networks explicitly in the feature space substantially improves the
forecasting skill, particularly in an ungauged setting. Our approach achieves state-of-the-art results on both reanalysis and observational data and is able to forecast maps of river discharge at 1 arcminute and 6-hourly resolution up to 10 days lead time.
Read the full abstract ▾
All authors Mohamad Hakam Shams Eddin, Maria Luisa Taccari, Yikui Zhang, Shijie Jiang, Juergen Gall, Markus Reichstein
Numerical Analysis
Finite Element Analysis of Maxwell's Equations with Time-Varying Coefficients and Nonlinear E-H Coupling: Convergence and Exponential Decay
Jan Renner and Irwin Yousept
This paper analyzes finite element approximations for Maxwell's equations with time-dependent coefficients and nonlinear E-H coupling in both the total current density and the Silver-Müller-type boundary condition. The nonlinear coupling and the time-varying material parameters prevent the use of standard analytical tools, including the discrete compactness property and the Minty-Browder argument, making the numerical analysis particularly challenging. As the main novelty, we establish two primary contributions: Uniform convergence on every finite time interval $[0,T]$ and exponential stability on the infinite time horizon $[0,\infty)$. The uniform convergence is established via a Cauchy-type argument within a time-dependent
Hilbert space framework that entirely bypasses Minty's trick and the discrete compactness argument. Furthermore, under a positive homogeneity assumption on the nonlinearities, the exponential stability is analyzed by means of a nonlinear sup-max problem arising from ratios of consecutive discrete energies. With this strategy, we ultimately prove a fully discrete unconditional exponential decay result under a specific sufficient condition. In the absence of this condition, a concrete counterexample shows that the energy decay fails to hold. Numerical experiments are provided to validate the theoretical findings.
Read the full abstract ▾
Machine Learning
Self-Confirming Superposition Traps in Reinforcement Learning
Dai Shi, Andi Han, Feng Chen et al. (+3 more)
Reinforcement learning (RL) trains representations on data selected by the
agent's policy, which then uses the resulting returns to guide its next choices. We show that this loop can sustain a lower-return policy even when representation fitting is globally optimal on those data. In a self-confirming superposition trap, every optimal code assigns overlapping directions to features that rarely occur together under the current policy. An alternative action brings them together, causing interference that lowers its return and reinforces avoidance, although refitting to that action would yield more return at the same capacity. We characterize the dimensions admitting a trap in a tied two-step model and show separately that equal feature frequencies, continued visitation, and independent controller learning need not prevent it. Because fitting weights errors by visitation, an avoided action can lose its return advantage at little cost to the objective. In a finite-action model, we bound this distortion and derive a replay condition: sufficient training weight on the best separately adapted action preserves its ranking despite residual error. Neural PPO experiments show how the feedback develops during learning:
agents initialized toward different actions develop different interference patterns, opposite mean return rankings, and different final policies at the same capacity. We therefore test whether retaining access to neglected states can improve control. Keeping these states in training reduces measured interference and improves sequential return, with gains even when the encoder is frozen. Related interventions on state access, replay weights, and feature overlap improve control on MiniGrid and DMControl. For
agents that learn through a world model, protected fitting improves DreamerV3–Crafter's cumulative training scores at unchanged capacity.
Read the full abstract ▾
All authors Dai Shi, Andi Han, Feng Chen, Yiqun Duan, Junbin Gao, José Miguel Hernández-Lobato
Artificial Intelligence
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
Hongyi Du, Tianyi Zhang, Weijia Zhang et al. (+9 more)
Multiple
agents may often conflict in an organization: for example, one coding
agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. A conversation can resolve the episode, but when the participants change, what makes the lesson continue to govern the team? We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols. Members reflect on visible work, propose rules, and govern their adoption. Adopted protocols bind triggers, responsibilities, required evidence, and execution consequences to the runtime, while remaining open to revision and retirement. In one traced case, repeated integration friction produces an interface-review rule that governs later pull requests and is revised as work continues. Across 360 controlled runs over ten software workloads and three models, Relic raises complete-contract delivery from 14.06% to 19.76% (+5.71 percentage points) over a matched structured team without the protocol lifecycle, improving all four verified production endpoints in every model stratum. Under fresh-member transfer, behavioral correctness is 25.4% with no inherited protocol, 34.6% with the same rules provided as readable text, and 41.2% with executable bindings, a +6.5-point advantage over text alone. On the full CooperBench
benchmark, after excluding 183 broken
benchmark pairs, Relic achieves 371/469 (79.1%), establishing the best reported result among peer-structured systems. On the 47-pair same-model subset, Relic also exceeds Solo (28/47 vs. 26/47), reversing the coordination loss exhibited by the official peer baseline. Together, these results show how collaboration experience can become persistent organizational state that remains useful beyond the members who created it.
Read the full abstract ▾
All authors Hongyi Du, Tianyi Zhang, Weijia Zhang, Yi Yang, Haofei Yu, Kunlun Zhu, Tianxiang Dai, Shang Jiang, Zhelun Gao, Jiaxin Pei, Shang Zhu, Jiaxuan You
Artificial Intelligence
The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
Vy Nguyen, Ziqi Xu, Jeffrey Chan et al. (+5 more)
Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to answer reliably. A large body of existing work mitigates
hallucination through detection or abstention mechanisms, but leaves open how models internally arrive at the decision to commit or abstain in the first place. We study this decision through mechanistic analysis, framing
hallucination as unsupported commitment: the model commits despite exhibiting signals of unanswerability. Using causal gating, we identify a Commit-Abstain
Circuit (CAC), a sparse, causally localised subset of
attention heads and MLP sublayers underlying this decision. Across ten LMs (3B-14B) from five families and three
benchmarks, the CAC exhibits a recurring accumulate-yet-undercorrect pattern: commitment-promoting components build up commitment in earlier layers, while abstention-promoting components act later as corrective signals that are often insufficient to overturn the accumulated commitment. Building on this finding, a lightweight policy trained on CAC activations improves decision accuracy by 12.2 points over the model's intrinsic commit-abstain margin, reduces false abstentions by 2.5 times, transfers to unseen
benchmarks, and extends to larger models (27B-35B). The CAC is both diagnostic, clarifying how models overcommit, and practical, enabling improved abstention decisions.
Read the full abstract ▾
All authors Vy Nguyen, Ziqi Xu, Jeffrey Chan, Estrid He, Feng Xia, Renqiang Luo, Erik Cambria, Xiuzhen Zhang
Digital Libraries
More of the same? Are scientific papers losing originality?
Ilan Doron-Arad and Elchanan Mossel
Scientific output is growing rapidly, but it is unclear whether the expanding literature remains original or is increasingly repeating itself. Originality has many dimensions. One dimension can now be measured directly: how textually distinct a paper is from the work that came before it. Using semantic
language models, we screened more than 26,000 full-text papers across eight fields in the CORE database (2015–2025) for passages resembling recent literature. We compared every paper against a fixed-size sample of earlier work, so increases in resemblance are not a by-product of literature growth. We find that the share of a paper's text resembling recent work was stable before 2021, then rose sharply, more than tripling by 2025. The increase came not from a few papers borrowing more heavily but from resemblance spreading across the literature: more papers now contain passages that echo recent work, and almost none of this growth is explained by cited work. We also found an analogous increase in passages expressing the same scientific idea. The pattern held across robustness checks and replicated in a second, independent database. Along this one measurable axis of originality, scientific writing has become less distinct from the work preceding it.
Read the full abstract ▾
Machine Learning
Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise
Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh et al. (+5 more)
Gradient clipping is widely used to stabilize training, but it need not improve the statistical accuracy of averaged SGD, even under heavy-tailed noise. We derive a finite-sample comparison of clipped and unclipped Polyak-Ruppert averaged SGD under finite conditional $p$-th moments, $p\ge2$. Our main result gives explicit accuracy and confidence conditions under which, for $p>2$, the Gaussian term dominates the unclipped deviation bound, so clipping need not improve its leading order. By balancing clipping bias and concentration, we obtain a bound in which the heavy-tail correction depends logarithmically rather than polynomially on the inverse failure probability. At $p=2$, this improves the confidence dependence of the leading bound. We establish sharpness of the unclipped heavy-tail term through an exact one-dimensional quadratic recursion and extend the comparison to projected convex SGD. We also prove concrete costs of clipping: every fixed finite threshold increases asymptotic variance on a scalar Gaussian quadratic, while whole-gradient clipping can shift the limiting point under asymmetric noise.
Read the full abstract ▾
All authors Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh, Artem Agafonov, Mohammad Alkousa, Yuriy Dorn, Vladislav Matyukhin, Alexander Gasnikov
Machine Learning
Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents
Ritul Satish, Prasoon Sinha, Akiho Kawada et al. (+1 more)
As LLM
agents tackle longer tasks, they increasingly compress growing histories of
reasoning, actions, and tool outputs. Compression can reduce
token use, but it also changes the information available for later decisions. Existing agentic harnesses bundle decisions about what to compress, when to compress, and how much to remove into fixed policies. A systematic characterization is needed to disentangle these decisions and reveal how each affects task success and execution cost. We systematically vary these decisions across three open-weight models on SWE-bench Verified and Terminal-Bench 1.0. Across nearly 35,000
agent runs, we measure task success,
token use, end-to-end latency, and estimated cost. We find that fewer
tokens need not mean faster or cheaper execution: on Terminal-Bench with Qwen, policies using roughly one-third as many
tokens can take 20-80% longer than the uncompressed
agent. Policies with similar overall success can solve different tasks, while the same policy can perform quite differently across models. Our results motivate evaluating compression by its effects on
agent execution and tailoring policies to the task, model, and workload.
Read the full abstract ▾
All authors Ritul Satish, Prasoon Sinha, Akiho Kawada, Neeraja J. Yadwadkar
Computers and Society
Environmental Impact of Generative and Agentic AI: An in-Depth Analysis and Green Solutions
Abderaouf Bahi, Amel Ourici and Ibtissem Gasmi
The proliferation of generative and agentic artificial intelligence (AI) systems has introduced computational demands whose environmental consequences are substantial yet underexamined. This paper examines the environmental footprint of modern AI systems across energy consumption, carbon emissions, water usage, and electronic waste over the full lifecycle of large
language models,
multimodal foundation models, and agentic workflows, from hardware fabrication and training through fine-tuning and inference to end-of-life disposal. This work provides a conceptual analysis, utilizing order-of-magnitude estimations based on published data, without conducting original physical measurements. We contribute a lifecycle taxonomy that crosses lifecycle phases with five impact dimensions and emission scopes; a Sustainability Assessment Framework for AI Systems (SAFIA) comprising nine indicators; a comparative analysis of traditional, generative, and agentic AI; seven open challenges; policy recommendations for regulators, cloud providers, hardware manufacturers, and AI developers; and a research roadmap to 2035. The analysis indicates that inference can rival or exceed training energy over a deployment lifetime, that agentic workflows can multiply the energy of equivalent single-pass inference by one to several orders of magnitude depending on the number of model and tool calls, that indirect water use and
embodied carbon are systematically underreported, and that measurement tools, disclosure practices, and regulation have not kept pace with agentic deployment. These findings call for
agent-aware energy measurement, lifecycle-based carbon and water accounting, and mandatory disclosure for large-scale AI training and deployment.
Read the full abstract ▾
Computational Complexity
Accepting-Path Counting at the One-Tape $n\log n$ Threshold
Ondřej Kuželka
We observe that the classical $n\log n$ time threshold for one-tape Turing machines is also a threshold for their accepting-path counts. Below it, every nondeterministic one-tape machine running in strong $o(n\log n)$ time has a rational ordinary generating function of accepting-path counts. At strong $O(n\log n)$ time, the situation changes completely: there is a fixed one-tape machine whose accepting-path function is complete for $\#\mathsf P_1$, the tally analogue of $\#\mathsf P$, under parsimonious
polynomial-time tally reductions. A second construction within the same time bound gives positive accepting-path counts with a noncomputable exponential growth rate. The rationality result combines the one-tape time gap with the linear-time counting
theorem of Tadaki, Yamakami and Lin. The completeness proof adapts the linear-time universal counting machine of Beame et al. to the one-tape setting.
Read the full abstract ▾
Robotics
Learning Geometry-Aware Virtual Fixtures From Sparse Demonstrations
Maximilian Mühlbauer, Marcella Piacentino, Raffaella Mancino et al. (+10 more)
In many teleoperation applications, collecting a large number of demonstrations as required for traditional probabilistic learning from demonstration (LfD) approaches may not be feasible. To still give operators the ability to intuitively create trajectories as Virtual Fixtures (VFs), we propose to leverage a motion prior in the learning process. Particularly, by using Linear Quadratic Tracking (LQT), users are able to define guiding trajectories from the demonstration of just a few via points. To account for orientation guidance, we further reformulate classical LQT on Riemannian
manifolds, introducing an additional
geometric prior. Through a probabilistic interpretation of the LQT solution, we derive a covariance estimate at each trajectory point which we use to modulate the stiffness of the resulting fixture, resulting in strong guidance around the via points and softer guidance when far away. The covariance information is also used to define a validity region of the fixture, allowing the operator to leave its influence area and conduct unmodeled tasks. We evaluate the proposed Riemannian LQT formulation in a set of toy examples and the full framework on a cutting task requiring high precision in a minimally invasive surgery setting on the da Vinci Research Kit (dVRK).
Read the full abstract ▾
All authors Maximilian Mühlbauer, Marcella Piacentino, Raffaella Mancino, Paolino De Risi, Bernhard Weber, Margarida Campos, Thomas Hulin, Sylvain Calinon, Freek Stulp, Alin Albu-Schäffer, Julian Klodmann, Fanny Ficuciello, João Silvério
Computer Vision
DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis
Jiahui Li, Yutong Guo, Nan Yang et al. (+3 more)
Diagnosing a patient from
video requires more than recognizing the sign: a
vision-
language model must turn what it sees into hypotheses, questions and tests. DynamicDx evaluates each step in 71 neurological consultations across 11 sign categories, linking authentic patient
videos to confirmed diagnoses and fixed charts built from the same case reports, so that every model queries the same evidence. Across five such models,
video improves accuracy by 9.9-22.5 percentage points over blind input, but neither recognition alone nor temporal order explains the gain: the cause is usually missing from the model's
video-only differential diagnosis even when the sign is recognized, and shuffling the frames produces no reliable accuracy loss. Instead, a trajectory replay traces most of the gain to the investigation results the
video prompts. Evidence acquisition is the bottleneck: supplying the decisive investigations raises accuracy to 73.2-93.0%. Two interventions act on it. A post-trained 4B
video describer improves sign descriptions, especially from a short, densely sampled segment, and source-clean literature
retrieval expands initial hypotheses; both bring the tests a model orders closer to those the treating clinicians documented and, through them, raise accuracy. For
video-based diagnosis, seeing better helps when it leads to asking better.
Read the full abstract ▾
All authors Jiahui Li, Yutong Guo, Nan Yang, Wenzhan Song, Jin Lu, Fei Dou
Machine Learning
Efficient Message Passing for Partial Differential Equation Priors
Anna Kazachkova, Leonhard Hennicke, Rainer Schlosser et al. (+1 more)
Prior information for real-world physical quantities is most elegantly expressed via partial differential equations (PDEs). In this paper, we propose a novel way to solve PDEs using probabilistic inference on a factor graph. In general, factor graphs provide a natural way to encode prior knowledge into a model as explicit factors; here, this knowledge is provided by a governing PDE, which narrows the solution space, while observed data further shape the posterior over the parameters. The approximate parameter posterior is inferred using message passing based on moment matching, without posterior sampling or global gradient-based optimization. We demonstrate our approach on the first-order advection and the second-order semi-linear Fisher-KPP equations, where it achieves predictive accuracy comparable to a standard baseline while providing structured predictive uncertainty. Moreover, the inferred posterior marginal means and uncertainty structure match more closely those obtained using
Hamiltonian Monte Carlo than the evaluated mean-field variational inference baseline, while requiring up to 10x less training time in our experiments, with inference speed comparable to variational inference.
Read the full abstract ▾
All authors Anna Kazachkova, Leonhard Hennicke, Rainer Schlosser, Ralf Herbrich
Machine Learning
Constrained Flow Policy Updates: A Generalized Schrödinger Bridge View
Boyang Li, Matthew Kim and Sylvia Herbert
Online safe reinforcement learning (RL) seeks policies that maximize reward while satisfying safety constraints. Reward and safety can induce
multimodal action distributions, challenging the prevailing primal-dual methods: Gaussian actors may collapse onto a single suboptimal mode, and optimization over the nonconvex Lagrangian landscape can be unstable.
Diffusion and flow policies can represent such distributions, but recent work with a
diffusion actor relies on estimating and matching the score of an augmented-Lagrangian target policy. Instead, we differentiate the augmented objective directly through the generation path of a flow policy, so no score needs to be estimated. Because a flow policy lacks a readily available action log-density for
entropy regularization, we build on the density-free kinetic-energy regularizer of FLAC, a recent reward-only method, and propose Reparameterized Augmented-Lagrangian Flow Actor with Least Energy (RAFALE), an off-policy actor-critic method for safe RL. We formulate its update as a constrained one-ended generalized Schrödinger bridge and show that, for each source draw, this path-space problem is exactly an
entropy-regularized problem in action space. At positive noise, its solution reweights the reward-only action distribution only where the estimated cost exceeds a threshold set by the Lagrange multiplier. As the noise vanishes, the optimal value converges to that of a least-energy map objective that the flow policy optimizes directly. Across seven Safety-Gymnasium tasks, RAFALE achieves competitive reward with mean final cost within budget on every task, whereas strong baselines trade one for the other; ablations support the necessity of both its augmented objective and its flow actor.
Read the full abstract ▾
Machine Learning
Optimal Nonparametric Dynamic Pricing with Censored Demand and Adversarial Inventory
Mengxiao Zhang, Yingfei Wang and Haipeng Luo
We study online dynamic pricing with censored demand, where an arbitrary inventory level is revealed before pricing and may adapt to past observations, while demand follows an unknown, price-dependent distribution that is stationary over time. For a horizon of $T$ rounds, Xu et al. [2026] achieved $\widetilde{\mathcal{O}}(\sqrt{T})$ regret under restrictive structural assumptions including linear demand, price-independent additive noise, and conditions relating inventory levels to the noise support. Our first contribution is to extend this framework to a substantially more general and statistically harder nonparametric setting, requiring only the natural assumption that expected sales are nonincreasing in price and allowing nonlinear demand curves and price-dependent noise. For this model, we first propose a simple baseline, Double-Grid-UCB, which discretizes both price and inventory and achieves $\widetilde{\mathcal{O}}(T^{3/4})$ expected regret using separate revenue estimates for each price-inventory grid pair. Then, we develop Threshold-UCB, which improves the expected regret to $\widetilde{\mathcal{O}}(T^{2/3})$. Unlike Double-Grid-UCB, Threshold-UCB reuses sales observations across inventory levels through shared estimates of demand-tail probabilities, allowing the same data to support revenue upper bounds for multiple inventories rather than a single inventory bin. We also complement this upper bound with an $\Omega(T^{2/3})$ lower bound via a reduction from
stochastic posted pricing, establishing its minimax optimality. Finally, extensive experiments across inventory processes, demand functions, and noise models demonstrate consistently superior performance of Threshold-UCB over
benchmark algorithms.
Read the full abstract ▾
Computer Vision
Synthetic Thermal Image Generation for Real-Time Animal Detection Under Low-Visibility Conditions
James Momoh and Khandaker Mamun Ahmed
Wildlife-vehicle collisions remain a significant road safety concern, particularly during nighttime and low-visibility conditions when RGB-based perception systems are often unreliable. Thermal imaging offers a promising alternative for detecting animals under poor illumination. However, the limited availability of annotated infrared animal
datasets restricts the development of robust deep learning-based detection models. This paper investigates synthetic thermal image generation as a scalable approach for real-time animal detection under low-visibility conditions. A subset of 514 annotated visible-spectrum animal images from the NTLNP
dataset is translated into synthetic thermal representations using CycleGAN-Turbo, while a limited real thermal
dataset of 60 images is expanded through thermal-focused augmentation. Multiple object detection architectures, including YOLOv8, YOLOv9, YOLOv10, and RT-DETR, are trained independently on synthetic and real thermal
datasets and evaluated using precision, recall, mAP@0.5, mAP@0.5:0.95, model size, and inference latency. Experimental results show that synthetic thermal images provide competitive detection performance, with RT-DETR achieving the highest synthetic-data mAP@0.5 of 0.9613. Models trained on augmented real thermal data achieve the strongest overall performance, with YOLOv10s obtaining 0.9879 mAP@0.5 and 0.9571 mAP@0.5:0.95. Computational analysis further indicates that lightweight YOLO variants provide favorable inference latency, supporting their potential for real-time deployment. These findings demonstrate that synthetic thermal imagery can reduce dependence on scarce infrared
datasets and support the development of efficient animal detection systems for future vehicle-mounted wildlife collision mitigation applications.
Read the full abstract ▾
Computation and Language
The Key Handoff: Retrieval in Hybrid Language Models
Kaan Kale, Oguzhan Baser and Sriram Vishwanath
A two-hop question makes a
language model retrieve twice: once to produce a bridge entity, and once to retrieve with it.
Transformers resolve that entity in their early layers. Hybrid models replace most of the
attention with a recurrent state, so where the key becomes usable, and where it is spent on an answer, is not known. Answering "Where is the ball?" from "the ball belongs to Alice" and "Alice is in the garden" turns on Alice, a name the question does not mention. A model could reach garden through Alice, the key it computed, or through where the fact sits in the
prompt. Across twelve models, dense and hybrid, we move a hidden state from one story into another where the two routes lead to different places, and read off which place the model gives. An
attention layer converts the key in every model we tested, and crossing that layer removes its usable effect, all of it where no
attention follows. In sequential hybrids this makes the answer a handoff: recurrent layers carry the key forward, and
attention spends it.
Retrieval does not always stop there. Writing a different fact into the
memory of the recurrent layers that follow the last
attention layer can move the answer toward that fact, multiplying its odds by 1.3 to 2.7, and which hybrids do this is not settled by their architecture or training. That read is addressed by the key, not by position: recurrent state in a hybrid is not only a carrier, but a
memory that later layers can query.
Read the full abstract ▾
Machine Learning
Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs
Pengyu Zhang, Mark Girolami and Arnaud Vadeboncoeur
Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitative data and qualitative data. Quantitative data may be represented by noisy sensor measurements, simulation data, re-analysis data; qualitative data may be in the form of text descriptions of experimental setups, expected experiment outcomes, and human-perceived system behaviours. The task we address in this paper is the following. Given a training set of paired qualitative text and quantitative QoI data, we learn to exploit the inherent correlation between the two modalities to learn a highly informative data-driven natural-
language-conditional
Bayesian prior, such that when presented with a new physical system, we can coherently combine (i) the training
dataset, (ii) qualitative text describing the new system, and (iii) a small number of noisy sensor readings from that new system, to perform inference and uncertainty quantification (UQ) over the QoI. To achieve this task, we develop two parallel approaches, one uses conditional
diffusion and the other conditional autoencoders, and compare both against classical
Bayesian methodology, unconditional generative models and deterministic supervised methods. Each approach has specific strengths and tradeoffs; conditional autoencoder offers theoretical tractability, allows for fast posterior sampling, and provides better-calibrated UQ, whereas conditional
diffusion is explored for greater expressiveness and capturing complex posteriors with irregular QoI fields. The approach is tested on the steady-state heat equation, damped Helmholtz equation, and UK weather reanalysis data.
Read the full abstract ▾
Machine Learning
TwinS-GCN: Spectral conjugate for Spectral Graph Convolutional Networks
Chun Hei Michael Chan, Flavia Petruso and Dimitri Van De Ville
Graph convolutional networks propagate information by repeated local aggregation through a graph shift operator; i.e., a $K$-layer network reaches $K$ hops neighborhood. On the one hand, such spreading can lead to oversmoothing. On the other hand, long-range dependencies demand the depth. Transporting information on long distances and without attenuation requires the shift to distinguish a direction of flow, which a symmetric operator cannot perform but a directed one can fulfill. A natural way to extract pure-directionality is to take the skew-symmetric part of the shift operator through the Cartesian split, which, however, generally does not commute with the shift itself, meaning that the filters built on it are not shift-invariant. We instead use the spectral conjugate; i.e., the image of the operator under $\tau:z\mapsto \bar{z}$, which commutes with the shift and splits it into a dissipative and a non-dissipative part. Two filter families follow: a sum filter, whose non-dissipative component transports signal without energy loss, and a ratio filter, ratio in the pair of components rather than
polynomial in the shift. Both arise from non-holomorphic kernels, placing them outside the holomorphic class underlying classical spectral convolution. On the directed cycle, the ratio filter becomes an IIR filter with global impulse response, for which we prove a long-range reach gap against every degree-$K$
polynomial filter. Chebyshev reparameterization gives stable vertex-domain layers with real coefficients, yielding TwinS-GCN, which solves graph transfer tasks at reduced depth and is competitive with state-of-the-art graph convolutional networks on node classification
benchmarks.
Read the full abstract ▾
Machine Learning
Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination
Liangqi Yuan, Wenzhi Fang, Shiqiang Wang et al. (+1 more)
Multi-
agent systems built on large
language models (LLMs) are largely homogeneous, as their
agents behave alike even across distinct LLMs. We show that when such
agents act concurrently without communication, they collide on targets they must split and diverge on targets they must take together, a double failure we term the
symmetry trap. Theory of Mind (ToM), widely used for coordination without communication, cannot escape this trap, since homogeneous
agents form the same prediction of one another and respond to it in the same way. We propose Theory of Scene (ToS), a training-free
reasoning schema in which each
agent reads its public role, the only difference between the
agents, and the task context they all observe. Homogeneous
agents thereby derive one division of labor, each taking the part its role fixes, which turns homogeneity from the cause of the trap into the cure. ToS reads the role together with the scene through role gating, which determines whether ownership overlaps or is already divided, and the task context through task coupling, which infers whether the team must converge on each target, divide it, or take its stages in turn. We evaluate on DivvyBench, a controlled environment we introduce, whose target types make an episode Competitive, Cooperative, or Mixed across Tabletop, Airspace, and Household scenarios, and on two established agentic
benchmarks, GovSim and Overcooked. ToS outperforms all six baselines on every
benchmark, and each baseline falls far behind it in at least one setting. Against ToM given the same inputs, ToS raises the DivvyBench success rate from 71.1% to 99.6%, the GovSim total gain from 207 to 400, and the Overcooked level-normalized throughput from 1.41 to 1.67.
Read the full abstract ▾
All authors Liangqi Yuan, Wenzhi Fang, Shiqiang Wang, Christopher G. Brinton
Robotics
Communication-Aware Heterogeneous Graph Learning for Decentralized Multi-Human Multi-Robot Task Allocation
Ziqin Yuan, Ruiqi Wang, Baijian Yang et al. (+1 more)
Multi-human multi-
robot (MH-MR) teams combine robotic autonomy with human expertise, but effective task allocation requires coordinating scarce, dynamically available human support with distributed
robot execution. Limited
robot-
robot and human-
robot communication further complicates this coupling by delaying information exchange and supervisory intervention. We introduce CommHG, a communication-aware heterogeneous graph learning framework for decentralized MH-MR task allocation. CommHG represents coupled human-
robot-task interactions through local graphs conditioned on information availability and age. Learned communication actions enable
robots to decide when and which operator to query, and when to share information with peers. Allocation and communication are jointly optimized through cooperative multi-
agent reinforcement learning, allowing the team to acquire useful information while managing limited communication and supervisory resources. We also introduce a
benchmark integrating heterogeneous humans and
robots, dynamic tasks and operational states, and constrained
robot-
robot and bidirectional human-
robot links. Experiments across heterogeneous teams with up to 16
robots, 6 humans, and 112 tasks show that CommHG improves timely weighted mission completion as coordination scale increases, outperforming the strongest baseline in the Large scenario.
Read the full abstract ▾
All authors Ziqin Yuan, Ruiqi Wang, Baijian Yang, Byung-Cheol Min
Machine Learning
The Impact of Stochasticity on the Rashomon Effect in Machine Learning
Andrea Apicella, Francesco Isgrò, Andrea Pollastro et al. (+1 more)
Neural network training is inherently
stochastic, with factors such as weight initialization leading to distinct models despite comparable predictive performance. This phenomenon is commonly associated with the Rashomon effect, which describes the existence of multiple near-optimal models for the same task. Although the Rashomon effect has received increasing
attention, it remains unclear whether different sources of training stochasticity contribute similarly or differently to its manifestations. In this work, we present an empirical study of the Rashomon phenomenon along three complementary dimensions: solution-space multiplicity, predictive multiplicity, and decision-basis multiplicity. These dimensions are quantified through the size of the empirical Rashomon set, predictive ambiguity, and agreement between XAI attribution maps, respectively. By independently controlling three standard sources of stochasticity, namely weight initialization, mini-batch data ordering, and dropout, we isolate their respective contributions to each dimension of the Rashomon phenomenon. Experiments on tabular and image classification
benchmarks reveal that these sources affect the three dimensions in different ways. In particular, larger empirical Rashomon sets do not necessarily correspond to greater predictive disagreement or lower explanation agreement, indicating that solution-space, predictive, and decision-basis multiplicity capture complementary rather than interchangeable aspects of the Rashomon effect. Overall, our results show that training stochasticity influences not only predictive performance but also the stability of predictions and explanations, highlighting the importance of identifying the specific sources of stochasticity responsible for different manifestations of the Rashomon phenomenon when assessing the reliability, reproducibility, and interpretability of neural network models.
Read the full abstract ▾
All authors Andrea Apicella, Francesco Isgrò, Andrea Pollastro, Roberto Prevete
Machine Learning
Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPs
Nam Phuong Tran, Trinh Ha Mai Huynh, Tuyen Pham Le et al. (+3 more)
In safety-critical applications, deployment uses a single policy, whose performance and constraint satisfaction should hold directly rather than only for an average or mixture of training policies. This motivates last-iterate guarantees in constrained reinforcement learning. Recent progress has established such guarantees in exact-gradient or tabular online settings, yet scalable results for structured large-state problems remain open. We develop a general, statistically efficient framework for last-iterate convergence in structured Constrained MDPs (CMDPs). Our analysis separates contraction of the regularised primal-dual dynamics from actor approximation and statistical errors in policy evaluation under online exploration. This enables model-free on- and off-policy learning with structured function approximation: optimistic policy evaluation avoids explicit transition-model construction, while a compact parametric actor avoids maintaining mixtures or histories of past policies. We instantiate the framework for linear CMDPs and general function approximation, obtaining representation-dependent complexity and improved target-accuracy dependence over prior optimistic regularised primal-dual analyses. We further validate the stabilising effect predicted by our theory on a synthetic linear CMDP: the regularised method exhibits stable last-iterate behaviour, whereas its unregularised counterpart shows larger oscillations.
Read the full abstract ▾
All authors Nam Phuong Tran, Trinh Ha Mai Huynh, Tuyen Pham Le, Van-Truong Nguyen, Quan Nguyen, Long Tran-Thanh
Machine Learning
Counting on Thinking: Tracing Evidence Integration in Language Models
Jingming Xue, Robert C. Wilson and Huadong Xiong
Finite computational resources force a tradeoff between automatic System 1 processes and costly System 2 thinking. Large
language models (LLMs) can spend extra computation on hard problems, yet direct answers struggle even with counting, an elementary operation humans and animals perform automatically. We ask why this requires thinking in LLMs. Evidence integration has long been used in psychology and neuroscience to probe decision-making. Our evidence-integration task presents one letter per conversational turn and asks which of two target letters appeared more often. A running count difference solves the task optimally by weighting every letter equally;
tokens at each turn could represent and update this difference. Direct responses instead weighted evidence unevenly, with strong recency effects, and assigned less probability to the correct answer as difficulty increased. Thinking improved performance and made integration weights nearly uniform, yet final-query
attention remained concentrated on the sequence ends in both modes.
Reasoning trajectories showed models revisiting input, recounting letters, and checking intermediate counts that informed the answer, suggesting that thinking constructs the accumulated count that direct responses lack rather than reading out one already formed.
Reasoning-
token costs grew with the number of letters far more than with coherence. Outcome feedback did not bring this computation into direct responses: under in-context reinforcement learning (ICRL), performance deteriorated over repeated games and recency effects strengthened, yet models grew more confident. Humans and animals amortize such computations into automatic processes, whereas current LLMs still pay for them with thinking on every trial. Which operations learning can make directly available remains central to how future models allocate computation.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
EEG-Based Motor Imagery BCI Algorithms and Technologies: A Review
Mohammad Hossein Koohi Ghamsari, Seyede Fatemeh Ghamkhari, Siavash Bayat et al. (+1 more)
Brain-computer interfaces (BCIs) have emerged as transformative technologies that enable direct communication between the
brain and external devices. Among various BCI paradigms,
EEG-based motor imagery (MI) has gained prominence due to its simplicity, non-invasiveness, and potential to restore motor function and facilitate rehabilitation for patients with motor impairments. This paper presents a comprehensive review of the most practical processing
algorithms developed over the past decade for decoding
brain sensorimotor cortex signals. Specifically, this paper discusses the integration of artificial intelligence (AI)-based
algorithms, particularly machine learning and deep learning techniques, and their contributions to improving the performance and efficiency of MI-BCI systems in detail. Furthermore, the paper reviews state-of-the-art hardware platforms and emerging converging technologies, including system-on-chip (SoC) architectures, application-specific integrated
circuits (ASICs), field-programmable gate arrays (FPGAs), wearable devices, the Internet of Things (IoT), and augmented/virtual reality (AR/VR), and discusses their integration with advanced signal processing
algorithms to enable next-generation MI-BCI systems. By highlighting current achievements of
EEG-based MI-BCI technology and predicting future research directions that could further enhance real-time capabilities, this paper aims to provide valuable insights for researchers and practitioners, fostering innovation in high-performance
EEG-based MI-BCI systems.
Read the full abstract ▾
All authors Mohammad Hossein Koohi Ghamsari, Seyede Fatemeh Ghamkhari, Siavash Bayat, Ahmed Hemani