Machine Learning
Instance Discrimination for Link Prediction
Valentin Cuzin-Rambaud, Mathieu Lefort and Rémy Cazabet
Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. However, fewer contributions have tackled the link prediction task. In this contribution, we propose to adapt existing methods to this context. We first provide a rigorous evaluation of existing self-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process (like in computer
vision). We then propose a new structural augmentation based on the community structure that is relevant for link prediction. Our main contribution introduces two new models, L-GRACE and L-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self-supervised contexts.
Read the full abstract ▾
Machine Learning
FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
Xikai Zhang, Yongzhi Li, Likang Xiao et al. (+6 more)
Reinforcement learning has become a cornerstone for aligning and unlocking the
reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants alternates between rollout sampling and policy update: the policy first samples rollouts from its action space, and then updates its parameters according to the advantages computed over them. Unlike supervised learning, where each gradient step is anchored to an explicit ground-truth target, the optimal gradient direction for updating model parameters in this setting is not known a priori; the high-quality rollouts drawn during the sampling stage therefore act as the implicit "teacher" that guides every parameter update. However, mainstream RL
algorithms such as GRPO adopt a simple sampling scheme that conditions all rollouts on the same original
prompt. When a task lies beyond the policy model's current capability, this sampling scheme rarely yields a high-quality rollout, leaving the policy model without a meaningful gradient direction when updating its parameters, which causes training to stall. To address this issue, we propose FBOS-RL. Specifically, we let the model perform Feedback-Guided Exploration Enhancement based on the feedback provided by the environment, and on top of this we design two mutually reinforcing training objectives: EPA and ECC. Extensive experiments demonstrate that EPA and ECC can mutually reinforce each other, forming a positive flywheel effect that significantly improves both the training efficiency and the final performance ceiling of reinforcement learning. Specifically, under both an identical number of rollouts and the same number of training steps, FBOS-RL learns substantially faster than GRPO and feedback-based baselines and ultimately attains a higher performance ceiling, while exhibiting higher policy
entropy and lower gradient norms throughout training.
Read the full abstract ▾
All authors Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang, Yanhua Cheng, Quan Chen, Peng Jiang, Wenjun Wu, Liu Liu
Machine Learning
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
Prakash Aryan, Kaushik Raghupathruni, Timo Kehrer et al. (+1 more)
Simulation-based testing of self-driving cars (SDCs) typically relies on scripted pedestrian models that do not capture the heterogeneity and uncertainty of real crossing behavior, limiting the realism of safety assessments, especially for jaywalking, which is governed by latent personality traits the vehicle cannot observe. We hypothesize that jointly training pedestrians and the SDC with multi-
agent reinforcement learning (MARL) yields more realistic interaction scenarios than training against fixed pedestrian policies, and that the behavior gap between predictable and unpredictable crossings can be measured directly from trajectories. We co-train an SDC and 12 pedestrians using Multi-
Agent Proximal Policy Optimization (MAPPO): pedestrian locomotion follows scripted Dijkstra pathfinding while an RL policy controls high-level go/wait decisions, and jaywalking probability depends on a per-pedestrian trait sampled at episode start and hidden from the SDC. In 500-episode evaluations, the co-trained SDC reached 78% of goals with a 14% collision rate, versus 35%/33% for the best rule-based baseline. A speed differential metric shows the SDC traveled 2.65 m/s faster near jaywalkers than near crosswalk users at close range (0-3 m), indicating jaywalking encounters were not anticipated. Jaywalking was 13% of crossing events but 62% of collisions, and co-training reduced collisions by 30% relative to single-
agent RL as pedestrians learned to wait when the SDC approached at speed.
Read the full abstract ▾
All authors Prakash Aryan, Kaushik Raghupathruni, Timo Kehrer, Sebastiano Panichella
Machine Learning · Cross-listed from cs.IR
Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
Amritansh Maurya, Navjot Singh, Mohammed Javed et al. (+1 more)
Large
Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research
attention, because Table Question-Answering (TQA) requires precise
cell retrieval and multi-step structured
reasoning. Existing work improves TQA either by fine-tuning or training LLMs on task-specific tabular data, but often lacks verifiable control over how the model navigates tables and derives answers. In this work, we propose a training-free TQA approach with two structured prompting frameworks: TableGrid
Navigation (TGN), which iteratively navigates rows and columns via a three-module loop to locate evidence and refine answers, and Progressive Inference Prompting (PIP), which enforces columns identification for explicit progressive row selection constraint according to the query. We evaluate 17 LLMs against 6 baselines on TableBench and FeTaQa
dataset. On TableBench, TGN improves over the strongest baseline by 3.8 points, and on FeTaQa, PIP achieves SOTA performance over ReAct and Chain-of-Thought. Beyond inference-time gains, PIP and TGN can also serve as supervision templates to fine-tune small models, narrowing the performance gap to much larger architectures in resource-constrained settings, offering versatile and cost-efficient solution for TQA.
Read the full abstract ▾
All authors Amritansh Maurya, Navjot Singh, Mohammed Javed, Omar Moured
Machine Learning
Physics-informed convolutional neural networks for fluid flow through porous media
Rafał Topolnicki, Paweł Dłotko and Maciej Matyka
Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-Stokes equations. This difficulty is particularly important when repeated simulations are required, as standard numerical solvers may converge slowly in intricate porous domains. We present a neural-network-based framework for predicting pore-scale velocity fields directly from sample geometry. The method uses a convolutional encoder-decoder architecture with skip connections to preserve spatial detail while extracting multi-scale features. Physical consistency is encouraged through a custom loss function combining velocity reconstruction with incompressibility, no-flow conditions inside solids, periodicity constraints, and agreement with the global tortuosity index. We analyze the influence of the corresponding loss weights and quantify the contribution of individual loss components to prediction accuracy. Several CNN backbones are evaluated to identify architectures providing accurate and robust predictions. The generalization ability of the trained model is tested on samples outside the training distribution, including changes in obstacle geometry, boundary conditions, porosity, and realistic porous structures. Finally, we demonstrate a practical use of the predicted velocity fields as initial conditions for
Lattice-Boltzmann simulations. This warm-start strategy accelerates solver convergence, reducing the number of iterations in over 90% of tested cases.
Read the full abstract ▾
Machine Learning
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
Taeyoung Yun, Woocheol Shin, Inhyuck Song et al. (+2 more)
Gaussian Process (GP) kernels are central to
Bayesian optimization (BO), yet designing effective kernels for high-dimensional problems still relies on extensive manual engineering. Existing automated approaches struggle in high dimensions for two bottlenecks: their kernel search space is limited to additions and multiplications of base kernels, and LLM-based approaches require conditioning on raw observations, which becomes infeasible due to context-length limits and the difficulty of extracting meaningful patterns. We introduce Kernel Discovery, a LLM-driven evolutionary framework for high-dimensional BO that searches a broader kernel space beyond predefined composition rules and does not require conditioning on observations. Motivated by the observation that directly prompting an LLM to generate kernel code yields syntactically varied but functionally identical kernels, we adopt a two-stage approach: an LLM first proposes novel mathematical forms, then a second LLM call converts each form into validated, executable code. We also propose a leave-one-out continuous ranked probability score (LOO-CRPS) as a selection criterion that penalizes overfitted kernels. On five high-dimensional BO
benchmarks, our method achieves an average rank of 1.2 out of 17, outperforming competitive baselines. We further analyze the discovered kernels to identify which kernels lead to improvements in high-dimensional BO.
Read the full abstract ▾
All authors Taeyoung Yun, Woocheol Shin, Inhyuck Song, Jaewoo Lee, Jinkyoo Park
Machine Learning
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Brown Zaz, Mar Gonzàlez I Català, Ferran Hernandez Caralt et al. (+2 more)
In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on architectural innovation. In this paper, we revisit an orthogonal axis: the training objective. We start from a simple observation: transductive models produce predictions for every node during training, including nodes without labels. These unlabeled-node predictions may contain useful training signal, but standard supervised objectives discard them because no ground-truth labels are available. Inspired by the decomposition of cross-
entropy into a label-dependent
alignment term and a label-independent
entropy term, we propose prediction confidence as a natural way to extract this signal in the absence of labels. This motivates Transductive Sharpening (TS): a loss-level modification that minimizes prediction
entropy on unlabeled nodes while counterbalancing this effect on labeled nodes. We evaluate Transductive Sharpening across a wide range of node-classification
benchmarks and observe consistent performance improvements without requiring any changes to the backbone architecture. Code is available at https://github.com/transductive-sharpening/tunedGNN.
Read the full abstract ▾
All authors Brown Zaz, Mar Gonzàlez I Català, Ferran Hernandez Caralt, Moshe Eliasof, Pietro Liò
Machine Learning
CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
Yang Liu, Toan Nguyen and Flora D. Salim
Catastrophic forgetting remains a major obstacle to continual learning in large
language models (LLMs) and
vision–
language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing LoRA-based MoE continual learning methods still face a fundamental trade-off: they either isolate experts too aggressively, limiting knowledge transfer across tasks, or allow task-specific updates to overwrite important existing parameters, leading to severe forgetting. To address this, we propose CP-MoE, a continual learning framework built around a transient expert that captures early task-specific updates and guides their integration into stable experts. CP-MoE introduces a consistency-preserving routing bias, which uses the transient expert to estimate representation similarity with stable experts and steer routing towards more compatible expert selection, and a transient expert-guided regularisation mechanism, which selectively protects important historical parameters during merging. Together, these components reduce parameter interference and forgetting while preserving cross-task knowledge transfer. We validate CP-MoE on both unimodal and
multimodal continual learning
benchmarks with LLM-based and VLM-based MoE models. On SuperNI
benchmark, spanning diverse sequential
language tasks, CP-MoE achieves state-of-the-art performance and stronger zero-shot transfer to unseen tasks. On VQA v2
dataset, it scales effectively to
multimodal visual
reasoning, consistently reduces forgetting, and outperforms strong MoE baselines.
Read the full abstract ▾
Machine Learning
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
Xiongbin Wu, Zhihao Luo, Shanzhe Lei et al. (+7 more)
Recently,
vision-
language model (VLM)
agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL)
algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context and noise. To address this issue, we propose GROW, a RL framework for open-world VLM
agents that decomposes collected trajectories into state-action samples, and computes advantages between these samples rather than treating a full trajectory as a single entity. We further provide a surrogate analysis indicating that, even though the grouped samples are conditioned on different local states rather than an identical
prompt context, the objective can preserve the core relative policy optimization signal of GRPO under simplifying assumptions. Experiments on more than 800 Minecraft tasks show that our method achieves state-of-the-art (SOTA) performance, demonstrating the effectiveness of our proposed RL framework for open-world VLM
agents.
Read the full abstract ▾
All authors Xiongbin Wu, Zhihao Luo, Shanzhe Lei, Lechao Zhang, Xuhong Wang, Jie Yang, Zhonglong Zheng, Yuanjie Zheng, Xin Tan, Wei Liu
Machine Learning · Cross-listed from cs.SI
Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection
Jiatong Xie
We introduce Prism, a framework for structural
symmetry diagnosis in complex networks. Given a graph
Laplacian $L$ and a duality operator $P$ (a symmetric involution), Prism computes the duality defect $\delta(L,P) = \|LP - PL\|_F / \|L\|_F$ – a scalar measuring how far the network deviates from structural self-consistency. When $P$ encodes the network's true
symmetry, $\delta$ starts near zero and rises monotonically as structure degrades; an arbitrary $P$ gives noise. We prove that the optimal $L'$ satisfying $[L', P] = 0$ is given by a closed-form block-diagonal projection, and provide an unsupervised alternating optimization that learns $P$ from the graph's own Fiedler vector. Experiments on synthetic networks show the true-$P$ defect is $3.38\times$ more sensitive to structural degradation than an index-reversal baseline and more sensitive than modularity. On Zachary's Karate Club with edge noise, Prism achieves $94.5\%$ community detection accuracy at $5\%$ noise versus $76.6\%$ for the raw
Laplacian baseline. Applied to live S&P~500 data (2026-05-17), Prism detects rising structural stress (defect $0.43 \to 0.73$ over 90 days) while surface correlations remain low – a signal invisible to correlation-based methods. In a historical backtest spanning five major stress events (2011–2020), the duality defect exhibits a consistent pattern: it reaches elevated levels before the correlation spike that accompanies each crisis, and sustains high readings during periods of structural fragility that conventional metrics classify as calm. The duality defect is a first-principles structural admissibility condition, requiring no training data and computable in milliseconds.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.LO
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
Jialin Lu, Soonho Kong, Rodrigo Stehling et al. (+4 more)
We present Lean Refactor, a plug-and-play
retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across library versions, yet existing refactoring works overlook three practical challenges: 1) Lean refactoring is natively multi-objective (proof length, compilation cost, and version compatibility are often in tension); 2) Lean repositories have fragile compatibility, whereas LLM releases are unaware of Lean/Mathlib versions; 3) Training-based pipelines require repeated fine-tuning with each new LLM release, scaling neither with model churn nor with Lean's release cycle. Lean Refactor steers a frozen agentic LLM with
retrievals from a curated database of multi-objective refactoring strategies, each densely annotated with metadata such as supported Lean/Mathlib versions and expected compilation-cost reduction. Experiments show over $70\%$
token-level compression on competition
benchmarks, over $20\%$ on research repositories, and up to $60\%$ compilation-time reduction, outperforming prior work and Claude Code. Version-filtered
retrieval further improves compression on the target Lean version, and refactored miniF2F proofs exhibit stronger zero-shot version transfer to future Lean releases than their unrefactored counterparts.
Read the full abstract ▾
All authors Jialin Lu, Soonho Kong, Rodrigo Stehling, Kaiyu Yang, Zhangyang Wang, Weiran Sun, Wuyang Chen
Machine Learning
LEAP: A closed-loop framework for perovskite precursor additive discovery
Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao et al. (+3 more)
Efficient discovery of precursor additives is essential for improving the performance of perovskite
solar cells, yet the large chemical space makes conventional trial-and-error screening inefficient. We develop LEAP(LLM-driven Exploration via Active Learning for Perovskites), an expert-in-the-loop closed framework that couples a domain-specialized large
language model(LLM) with active learning for iterative additive prioritization. The LLM is trained to extract mechanism-relevant knowledge from the perovskite additive literature and to represent candidate molecules through interpretable descriptors, which are further integrated into a
Bayesian optimization workflow for uncertainty-aware prioritization under low-data conditions.
Benchmark results on unseen literature show that the domain-specialized model outperforms general-purpose models in mechanism-consistent
reasoning. Experimental validation in an expert-in-the-loop proof-of-concept study suggests improved additive prioritization across three screening rounds, leading to average device PCEs of 20.13% and 20.87% for the later-round 6-CDQ- and 2-CNA-treated devices, respectively, compared with 19.25% for the control, with a champion PCE of 21.32%. These results provide preliminary evidence that literature-grounded mechanistic descriptors, when coupled with
Bayesian optimization and expert feasibility review, can support mechanism-aware additive prioritization in perovskite photovoltaics.
Read the full abstract ▾
All authors Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao, Peng-Jie Guo, Cheng Mu, Zhong-Yi Lu
Machine Learning
Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
Woo Seob Sim and Yu Rang Park
Prompt-level safety probes for large
language models use hidden-state representations to separate safe from unsafe
prompts, but strong average detection performance does not explain the geometry of this separation. In particular, it remains unclear how safety evidence is formed across layers, which aspects of that layer-wise geometry support low-false-positive decisions, and which
geometric biases remain stable under
benchmark shift. We study this as an empirical decomposition problem and introduce Geometry-Lite, a compact
prompt-level probe that maps each layer's final
prompt-
token representation to signed margins under centroid, local-neighborhood, and supervised linear-boundary readouts, then summarizes the resulting margin profiles by boundary position, layer-to-layer change, and coarse shape. Across nine instruction-tuned backbones ($1.2$B–$70$B) and seven safety
benchmarks, Geometry-Lite improves over single-layer probes while remaining close to raw multi-layer score stacking, making it a useful instrument for analyzing the multi-layer safety signal. The decomposition shows that safety evidence is expressed primarily through persistent boundary-position geometry: final or extremal margins and unsafe-side layer occupancy dominate aggregate detection performance. In contrast, finite-difference drift and structural summaries add little to pooled AUROC, although drift can provide small recall-oriented corrections under shifted low-FPR thresholds. Under
benchmark shift, optimized linear boundaries are sharp on the training mixture, whereas class-conditional mean geometry retains separation more reliably on a predefined hard held-out subset. Overall,
prompt-level safety evidence is not primarily a layer-to-layer motion signal, but a persistent layer-wise margin geometry whose useful components and readout-level biases become visible in decision-critical regimes.
Read the full abstract ▾
Machine Learning
Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection
Andrea Morandi
Multi-
agent LLM debate improves factuality and
reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on hard ones. We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute governor for LLM debates. After each round, an LLM judge emits a [0,1] consensus score on the latest
agent positions; a Wald monitor accumulates the log-likelihood ratio of "useful convergence" vs "not yet useful" under a Beta likelihood family, and stops when either boundary is crossed or returns a capped best-effort outcome at R_max. Under i.i.d. assumptions the rule inherits SPRT type-I/type-II error guarantees; in deployment the calibration itself is the more important object, since it estimates whether the judge score actually separates useful from unhelpful convergence in a given domain. We evaluate two tracks: (i) a Monte-Carlo study under calibrated Beta models characterising working curves, error rates, capping behaviour, and sensitivity; and (ii) a real-LLM evaluation on 200 attempted MMLU and 200 attempted GSM8K items with three heterogeneous
agents (gpt-5, claude-opus-4-6, gemini-2.5-pro) and a claude-opus-4-6 judge, using disjoint 40-item calibration subsets. On GSM8K the rule stops in 1.01 average rounds (4.06 LLM calls) at 97.0% accuracy vs 99.0% for fixed-5 debate at 15 calls: a 3.7x call reduction at -2pp accuracy. On MMLU the calibrated KL collapses to about 0 and the rule caps on 99.5% of items at 2.1x cost. The takeaway is not that SPRT makes debate more accurate, but that a classical sequential test serves as a cheap compute-control and failure-detection layer for multi-
agent LLM systems.
Read the full abstract ▾
Machine Learning
Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
Shiheng Zhang
Sparse goal-conditioned planning with few cost-to-go labels can be viewed as a graph-PDE Dirichlet extension problem: extend sparse labels on a goal-dependent boundary to unlabelled graph vertices so that greedy rollouts reach the goal. We study which graph value extensions are planner-admissible under the operational argmin-Q planner. Our main result is a local action-gap certificate: if the surrogate value error along the rollout stays below half the true action gap, then the greedy rollout reaches the goal. Absolutely Minimal Lipschitz Extension (AMLE), the p=infinity endpoint of the graph p-
Laplacian family, instantiates this certificate through a comparison-principle fill-distance bound. Harmonic extension, by contrast, can mis-rank local actions because its values reflect boundary hitting probabilities rather than shortest-path greedy order. On 120 AntMaze layout-derived graph configurations, harmonic extension achieves 0.584 aggregate rollout success, while AMLE reaches 0.970. Finite high-p methods also enter a high-success regime, with success 0.903 for p=4, 0.973 for p=8, and 0.982 for a fixed-budget p=16 solver, though the p=16 row is not used as a converged endpoint ranking due to incomplete solver certification. Mechanism audits show that many rollout decisions occur in AMLE-compatible but harmonic-incompatible local geometry, and that AMLE corrects most harmonic inversions on the rollout-weighted decision scope.
Read the full abstract ▾
Machine Learning · Cross-listed from astro-ph.EP
A Cloud-Based Tool for Meteorite Recovery Using Drones and Machine Learning
Seamus L. Anderson, Hadrien A. R. Devillepoix, Lewis Lakerink et al. (+30 more)
We present a cloud-based tool that uses drones and machine learning to help recover instrumentally observed meteorite falls. We showcase a collection of improvements made upon previous iterations of our system, as well as detail the successes and limitations of this technique when applied to observed meteorite falls in South and Western Australia. This tool is available to the meteoritics research community upon request at https://find.gfo.rocks.
Read the full abstract ▾
All authors Seamus L. Anderson, Hadrien A. R. Devillepoix, Lewis Lakerink, Sawitchaya Tippaya, Dale P. Giancono, Martin C. Towner, Iona Clemente, Martin Cupák, Ashley F. Rogers, John H. Fairweather, Mia Walker, Daniel Burgin, Michael A. Frazer, Sophie E. Deam, Veronika Pazderová, Eleanor K. Sansom, Benjamin A. D. Hartig, Hely C. Branco, Thomas Stevenson, Isabella Hatty, Anna Zappatini, Anthony Lagain, Tom Lovelock, Auriane Egal, Lucy Forman, David Belton, Simon Windsor, Shibli Saleheen, Asher Leslie, Gregory B. Poole, Andrew Langendam, Rachel S. Kirby, Andrew G. Tomkins
Machine Learning · Cross-listed from cond-mat.dis-nn
Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines
Giovanni di Sarra and Yasser Roudi
The great success of neural networks primarily arises from the presence of the large number of weight parameters combined with nonlinearities in the input-output relationship of single
neurons. In this work, we study the relationship between the statistical properties of the weights and the nonlinearity of the hidden unit in Restricted Boltzmann Machines (RBMs) on the one side, and the distribution induced on binary visible units. We do this for four commonly used activation functions: Linear, Step, ReLU, and Exponential, and make qualitative predictions about the ability of these models to learn distributions with strong higher order interactions over the visible nodes. We show that in general, in an ensemble of RBMs with Gaussian weights, these distributions are rare and hard to learn, except when the hidden unit activation function is an Exponential.
Read the full abstract ▾
Machine Learning
Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand
Yihong Tang, Tong Nie, Junlin He et al. (+3 more)
Forecasting urban delivery demand becomes substantially more challenging when newly added service regions lack historical records. Existing spatiotemporal forecasters effectively model spatial dependence once sufficient node histories are available. Still, they remain parametric and therefore struggle to recover short-term operational dynamics in cold-start regions. Geospatial
embeddings help identify where a region is and what function it serves, yet they do not directly reveal how a similar region behaves under a comparable temporal context. We propose Bridge, a
retrieval-augmented spatiotemporal graph framework that combines an inductive contextual graph backbone with a time-aware
memory of region-time windows. For each target region, Bridge retrieves future demand patterns from the
memory using both regional context and recent dynamics, and refines the backbone forecast through a gated fusion mechanism. To align
retrieval with
forecasting utility, we further train the retriever with a future-aware objective that favors entries whose future trajectories best match the target. Experiments on four real-world delivery
datasets show that Bridge consistently improves over competitive spatiotemporal baselines in both within-city cold-start and cross-city transfer with partial observations. The results show that
retrieval augmentation provides a useful operational
memory for cold-start urban demand
forecasting when parametric graph generalization alone is insufficient.
Read the full abstract ▾
All authors Yihong Tang, Tong Nie, Junlin He, Qianjun Huang, Dingyi Zhuang, Lijun Sun
Machine Learning · Cross-listed from stat.ML
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Benjamin Sterling, Mónica F. Bugallo and Tom Tirer
Diffusion/score-based models have emerged as powerful generative models, capable of generating high-quality samples that mimic the training data distribution. However, it has been observed that they are prone to reproducing training samples-known as "memorization"-potentially violating copyright and
privacy. In this paper, we study the effect of Higher-Order Langevin Dynamics (HOLD) on this phenomenon. HOLD
diffusion processes introduce auxiliary variables; if the data variable is interpreted as "position," then the auxiliary variables can be interpreted as "velocity" and "acceleration," depending on the chosen order of the model. They were originally proposed based on the intuition that they regularize the trajectories of the data variable by implicitly imposing additional dynamical constraints. Our work provides, to our knowledge, the first theoretical characterization of the regularization effect of HOLD. Specifically, we show that in HOLD, the dynamics of the data variable are governed by a low-pass-filtered version of the learned score function, with smoothness increasing with the order of HOLD. We then analyze the optimal empirical score and the possibility of distribution collapse. Together, our results explain the mitigation of memorization as the model order increases. Finally, we present an empirical study on real-world data that supports our theory and highlights this distinct advantage of HOLD over standard
diffusion in practice.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions
Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy et al. (+1 more)
Reinforcement learning (RL)-based quadrotor control policies have achieved impressive performance in tasks such as fast
navigation in cluttered environments and drone racing, where the focus is on speed and agility. However, in several applications, such as infrastructure inspection, it is critical to achieve precise, controlled maneuvers with tunable performance. In this article, we present a novel heuristic approach to achieve tunable performance in RL-based Quadrotor control through reward design and termination conditions. We present a novel reward structure containing dual bandwidth exponentials that achieves a baseline critically damped response in setpoint tracking, with low steady-state errors. When trained with a Proximal Policy Optimization (PPO)
algorithm, in conjunction with episode truncation conditions, the desired performance is achieved in 6 million time steps in a sample-efficient manner. In order to tune the performance about the baseline behavior, we present intuitive heuristic rules to adjust the reward weights and exponential coefficients to achieve faster (acrobatic-like) and slower (inspection-like) settling time performance, while retaining the baseline critically damped response and approximately 2% steady-state error. We evaluate the three RL policies (baseline, acrobatic, and inspection) across 100 trials and show accurate and tunable performance in position and yaw tracking from random initial conditions, thereby demonstrating the effectiveness of the proposed heuristic approach.
Read the full abstract ▾
All authors Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy, George Nikolakopoulos
Machine Learning · Cross-listed from cs.AI
How Far Are We From True Auto-Research?
Zhengxin Zhang, Ning Wang, Sainyam Galhotra et al. (+1 more)
Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good
agent-generated papers actually are. We introduce ResearchArena, a minimal scaffold that lets off-the-shelf
agents (Claude Code using Opus 4.6, Codex using GPT-5.4, and Kimi Code using K2.5) carry out the full research loop themselves (ideation, experimentation, paper writing, self-refinement) under only lightweight guidance. Across 13 computer science seeds and 3 trials per
agent-domain pair, ResearchArena yields 117
agent-generated papers, each evaluated under three complementary lenses: a manuscript-only reviewer (SAR), an artifact-aware peer review (PR) in which
agents inspect the workspace alongside the manuscript, and an human conducted meta-review. Under SAR alone the picture is optimistic: Claude Code obtains the highest score, outperforms Analemma's FARS, and matches the weighted-average human ICLR 2025 submission, suggesting that minimally scaffolded
agents can produce papers that look competitive on manuscript-only review. Manual inspection, however, reveals this picture is overstated: SAR scores are poorly aligned with its actual acceptance decisions and reward plausible framing without verifying experimental substance. Under artifact-aware PR scores drop sharply, and manual
auditing identifies experimental rigor as the major bottleneck, decomposing into three failure modes (fabricated results, underpowered experiments, and plan/execution mismatch) that are highly
agent-dependent: Codex 5%/8% paper-vs-artifact mismatch / fabricated references versus Kimi Code 77%/72%, a $\sim$15$\times$ spread that tracks distinct research personas the
agents develop. None of the 117
agent-generated papers reaches the acceptance bar of a top-tier venue. This suggests that we are still gapped from the true auto-research.
Read the full abstract ▾
All authors Zhengxin Zhang, Ning Wang, Sainyam Galhotra, Claire Cardie
Machine Learning · Cross-listed from stat.ML
Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
Rahul Uma Ramachandran and Serge Massar
Physical computing systems provide a promising route toward hardware-native machine learning, but their computational capabilities remain difficult to characterize in a principled, task-independent, and data-efficient way. We extend the Information Processing Capacity (IPC) framework to stationary physical computing systems and establish several fundamental results: individual capacities are bounded between zero and one, their sum over a complete basis is bounded by the number of readouts, and noise strictly reduces this bound. We address the finite-sample estimation of IPC and derive the asymptotic form of the systematic positive bias affecting naive
estimators. Building on these results, we introduce data-efficient estimation methods based on Richardson extrapolation and Sobol quasi-random sampling. We validate the framework experimentally using a photonic computing system based on picosecond
laser pulses propagating through a nonlinear optical fibre. By varying the
laser power and fibre length, we observe systematic shifts of the IPC distribution toward higher-order nonlinear capacities induced by the Kerr effect. Finally, we demonstrate that the total IPC strongly correlates with performance on
benchmark machine-learning tasks and provides a reliable estimate of the effective dimensionality of the system. These results establish IPC as a practical bridge between the intrinsic dynamics of physical computing systems and their machine-learning performance.
Read the full abstract ▾
Machine Learning
Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
Aleksandar Terzić, Francesco Carzaniga, Nicolas Menet et al. (+4 more)
State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition
matrix. Unstructured transition
matrices enable maximal expressivity, as measured by their ability to model finite-state automaton (FSA) transitions, but come at a prohibitively high compute and
memory cost. In contrast, most structured transition
matrix forms are highly efficient both in runtime and
memory consumption, but suffer from limited expressivity. Building on recent work on structured sparse SSMs, we propose Flash PD-SSM, a novel SSM that achieves comparable throughput to widely-used structured SSMs with significantly better expressivity guarantees. Flash PD-SSM maintains a trainable set of structured sparse
matrices, a single one of which is discretely selected at each time-step, enabling FSA expressiveness at the level of unstructured
matrices while maintaining the efficiency required for training models at scale. First, we validate Flash PD-SSM against a suite of alternative models on synthetic mechanistic and state-tracking tasks, finding that its theoretical expressivity is achieved in practice. Second, on multivariate time-series tasks involving sequences of length over 17,000, we find that Flash PD-SSM defines a new state-of-the-art (SoTA) accuracy among competing SSM methods. Finally, we demonstrate that Flash PD-SSM is an effective drop-in replacement for hybrid LLMs, yielding improvements both in natural
language state-tracking and in common
language modeling scenarios. The model exhibits increased throughput and decreased
memory consumption compared to SSMs widely used in frontier
language models.
Read the full abstract ▾
All authors Aleksandar Terzić, Francesco Carzaniga, Nicolas Menet, Yannick Biehl, Michael Hersche, Thomas Hofmann, Abbas Rahimi
Machine Learning · Cross-listed from cs.CR
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
John T. Halloran and Noopur S. Bhatt
Large
language models (LLMs) are highly susceptible to
backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM rewriting as a proactive defense against data poisoning. First, we theoretically show that when LLM rewriting utilizes open-book benign samples–termed open-book benign rewriting (OBBR)–the probability of a rewritten output being benign is strictly greater than that of closed-book rewriting. Thus, OBBR neutralizes harmful content by projecting training samples to the space of benign
prompts. We then show that, in contrast to previous defenses, OBBR effectively mitigates a large number of existing BAs: across five known BAs and four widely used LLMs, OBBR increases safety performance by an average 51% compared to state-of-the-art BA defenses and 25.7% compared to closed-book rewriting methods. Finally, we show that OBBR is computationally efficient relative to other BA defenses, does not degrade model performance on natural
language tasks after fine-tuning, and is capable of defending against non-trigger based data poisoning attacks.
Read the full abstract ▾
Machine Learning
PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
Srijith Nair, Atilla Eryilmaz and Jia Liu
In the literature, many continual learning (CL)
algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all CL approaches use some form of
memory to retain information about past tasks, a grounded understanding of what information needs to be stored to minimize catastrophic forgetting remains elusive. Recently, it has been recognized that under the strong assumption of the existence of a common global minimizer over all tasks, catastrophic forgetting can be completely avoided. However, in practice, tasks rarely have a common global minimizer, and a certain amount of forgetting is inevitable. In this paper, we propose a foundational reframing of CL as balancing conflicting tasks in hindsight from a multi-task learning (MTL) perspective. The approach is based on finding Pareto-optimal solutions, i.e., the solutions which, by definition, minimally forget the previous tasks in the Pareto sense. We derive a Pareto-minimal-forgetting CL (PMF-CL)
algorithm for linear and basis-function regression. Our
algorithm naturally extends to loss functions with quadratic upper bounds around their minimizers, despite consuming only a static
memory footprint of $O(d^2)$ for $d$ model parameters, independent of the number of sequentially occurring tasks $T$. In the quadratic-loss setting, we obtain exact hindsight Pareto-optimal guarantees on forgetting. In the quadratic-upper-bound setting, forgetting is provably bounded, with the tightness of the forgetting bound being directly determined by the tightness of the quadratic bound on the loss function. Our numerical results validate our theoretical claims of convergence to the Pareto-optimal solution, and demonstrate that we consistently out-perform prior empirical methods while occupying lesser
memory.
Read the full abstract ▾
Machine Learning
GRASP: Deterministic argument ranking in interaction graphs
Diganta Misra, Antonio Orvieto, Rediet Abebe et al. (+1 more)
Large
language models are increasingly deployed as automated judges to evaluate the strength of arguments. As this role expands, their legitimacy depends on consistency, transparency, and the ability to separate argumentative structure from rhetorical appeal. However, we show that holistic judging - a common LLM-as-a-Judge practice where a model provides a global verdict on a debate - suffers from substantial inter-model disagreement. We argue that this instability arises from collapsing a debate's complex interaction structure into a single opaque score. To address this, we propose GRASP (Gradual Ranking with Attacks and Support Propagation), a deterministic framework that aggregates stable local interaction judgments into a global ranking via a convergent attack–defense propagation operator. We show that local interaction judgments are more reproducible than holistic rankings in LLM-as-a-Judge evaluations, allowing GRASP to produce more consistent global rankings. We further show that GRASP scores do not correlate with human "convincingness" labels, highlighting a vital sociotechnical distinction: GRASP does not measure persuasion, factuality, or rhetorical appeal, but structural sufficiency - a defense-aware notion of argument robustness over the explicit interaction graph. Overall, GRASP offers a transparent and auditable alternative to holistic LLM judging.
Read the full abstract ▾
All authors Diganta Misra, Antonio Orvieto, Rediet Abebe, Volkan Cevher
Machine Learning · Cross-listed from cs.RO
COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones
Ayush Agarwal, Ansh Gandhi, Jeremy A. Collins et al. (+6 more)
The scarcity of large-scale, high-quality demonstration data remains a bottleneck in scaling imitation learning for robotic manipulation. We present COBALT, a teleoperation platform designed to democratize
robot learning at scale both in simulation and in the real world. By leveraging vectorized environments, our scalable, load-balanced infrastructure supports concurrent teleoperation by multiple users on a single GPU, yielding a significant reduction in teleoperation cost. Operators can connect from nearly anywhere on Earth using commonly available devices, including single or dual smartphones, VR headsets, 3D mice, and keyboards. An inmemory data cache and efficient
video streaming keep control and rendering synchronous, sustaining dozens of concurrent users at 20 Hz with sub-100 ms end-to-end latency for up to 8 concurrent users per GPU. We also demonstrate stable operation supporting 256 simulated clients across 8 GPUs, underscoring the system's ability to scale across hardware and within individual servers. We perform a comprehensive user study showing that phone-based teleoperation performs comparably to or better than specialized hardware, enabling faster, more ergonomic data collection. To ensure data quality, COBALT logs a suite of real-time metrics to automatically filter suboptimal demonstrations. We further demonstrate that a structured user training curriculum significantly improves data collection quality. Guided by insights from our user study, we crowdsource the collection of a large-scale, high-quality pilot
dataset with 7500+ demonstrations (50+ hours) collected with smartphones across nine countries over five days. We validate the
dataset's quality by training state-of-the-art imitation learning
algorithms. Please visit https://cobalt-teleop.github.io/ for more details.
Read the full abstract ▾
All authors Ayush Agarwal, Ansh Gandhi, Jeremy A. Collins, Omar Rayyan, Aryan Sarswat, Ranjani Koushik, Masoud Moghani, Ajay Mandlekar, Animesh Garg
Machine Learning
Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
Manal Benhamza, Marianne Clausel and Myriam Tami
Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observational data. Although its significance, CRL identifiability remains a crucial property, as it ensures the recovery of the mechanisms behind the data generation process, and hence the interpretability and robustness of the representation. Proving identifiability in CRL is intrinsically difficult, and we address in this work an even more challenging setting: multimodality. We consider
multimodal observed data with a latent partially shared structure. Each modality is generated, through non linear mixing functions, from a specific subset of causal latent variables. Under flexible assumptions and without imposing any parametric distribution on the latent variables, we establish component-wise identifiability guarantees for the causal latent representation. Our identifiability results, furthermore, apply to the undercomplete scenario where we have, for each modality, more observed than latent variables. To instantiate our theoretical analysis, we introduce a Wasserstein-based module to recover the partially shared latent structure. Due to its differentiability, the latter can be easily integrated into all types of architecture, only requiring minimal changes. Extensive experiments on synthetic and realistic
datasets validate the superiority of our approach over SOTA methods.
Read the full abstract ▾
Machine Learning
CLIC: Contextual Language-Informed Cardiac Pathology Classification
Giovani D. Lucafo, Rafael da Costa Silva, João Lucas Luz Lima Sarcinelli et al. (+2 more)
The electrocardiogram (ECG) is the gold standard for non-invasive diagnosis of cardiac pathologies and is a fundamental pillar of cardiovascular medicine. Recent progress in deep learning has led to the development of robust automated classifiers that achieve high performance by processing raw physiological signals. However, in clinical practice, diagnosis is rarely based solely on the signal. Cardiologists commonly support their interpretation with the patient's characteristics and the specific data-acquisition context. Despite this, most current
algorithms remain restricted to signal-only analysis, failing to integrate technical metadata and demographic variables. This paper proposes Contextual
Language-Informed Cardiac pathology classification (CLIC), a
multimodal framework that significantly enhances diagnostic precision by encoding these variables through natural
language. We demonstrate that translating patient-level contextual data into descriptive text provides an informative anchor that helps the model disambiguate complex physiological patterns. We further investigate the use of Large
Language Models to synthesize richer clinical descriptions and observe that, while these generated texts remain competitive, controlled template-based contextual clinical text leads to consistent improvements in downstream classification performance.
Read the full abstract ▾
All authors Giovani D. Lucafo, Rafael da Costa Silva, João Lucas Luz Lima Sarcinelli, Andre Guarnier De Mitri, Diego Furtado Silva
Machine Learning
EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data
Dongyan Lin, Phillip Rust, Angel Villar Corrales et al. (+19 more)
Children acquire
language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large
multimodal models. Recent research suggests current
vision-
language models (VLMs) trained on curated web data fail to generalize to the sparse, weakly-aligned
egocentric streams produced by wearable devices,
embodied agents, and infant head-cams – and no fixed evaluation pipeline exists for measuring progress on this regime. We train VLMs on
datasets with varying degrees of semantic
alignment between visual and linguistic inputs, including naturalistic infant and adult
egocentric videos, and evaluate them with a comprehensive suite spanning
multimodal language grounding and unimodal
vision and
language tasks. At the core of this suite is Machine-DevBench, a corpus-grounded
benchmark of lexical and grammatical competence, automatically generated from the model's training vocabulary across logarithmic frequency bins to eliminate the train/eval mismatch and low statistical power of prior developmental
benchmarks. Our results show that current VLM paradigms hinge on the tight semantic
alignment of curated data and fail to exploit the weakly-aligned signal that dominates naturalistic
egocentric input – the very regime in which humans thrive. To motivate progress, we introduce the EgoBabyVLM Challenge to drive the development of models capable of grounded
language learning from the kind of naturalistic data that human infants experience.
Read the full abstract ▾
All authors Dongyan Lin, Phillip Rust, Angel Villar Corrales, Alvin W. M. Tan, Mahi Luthra, Charles-Éric Saint-James, Rashel Moritz, Sheila Krogh-Jespersen, Vanessa Stark, Surya Parimi, Jiayi Shen, Youssef Benchekroun, Yosuke Higuchi, Martin Gleize, Tom Fizycki, Nicolas Hamilakis, Manel Khentout, Sho Tsuji, Balázs Kégl, Juan Pino, Michael C. Frank, Emmanuel Dupoux