Machine Learning
Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow
Tinglan Wang, Haixu Liu, Shaobo Chen et al. (+4 more)
MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state update. We separate these two quantities at inference, fixing the model, update grid, and number of queries while varying the prediction horizon. Our central finding is that the horizon response depends on both query position and the states entering that query. Across seven independently trained CIFAR-10 checkpoints at classifier-free guidance (CFG) scale 2, a longer horizon worsens FID at early steps but improves it at the midpoint. To probe whether query time alone determines this response, we fix the midpoint query and current/subsequent guidance while changing only earlier CFG. In held-out factorial outcomes on five previously studied checkpoints, the mean midpoint horizon benefit increases from 0.109 to 1.308 FID, indicating sensitivity to the incoming-state distribution. A frozen four-query rule reduces mean CIFAR-10 FID by 2.023 without retraining or extra queries, including gains on five checkpoints trained after rule selection. A milder rule also improves mean FID by 1.041 on a stronger frozen grid, with fixed-rule FID gains on the evaluated public ImageNet-256 and AFHQ checkpoints. However, matched-budget calibration favors query-start shifting in historical CIFAR tests, and the tested Horizon allocation adds no FID benefit beyond Grid+Start on two public ImageNet models. Thus, prediction horizon is a distinct, position- and state-sensitive inference control, but not a universally preferred one.
Read the full abstract ▾
All authors Tinglan Wang, Haixu Liu, Shaobo Chen, Nuo Qian, Qi Gao, Kai Wen, Yu Yao
Machine Learning
Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks
Xiuyi Yang
What makes a deep network train, and what shape is its loss surface? We answer both with one construction at two scales: a
polynomial activation f (z) = z + {\lambda}z 3 , clamped and projected onto the unit sphere, plus an unnormalized identity path. As a deep stack it trains to one hundred layers on MNIST with no normalization machinery; as a small model its square loss is a
polynomial system we solve exactly. The small scale explains the large one: it prescribes how to design, initialize and train the stack.
Read the full abstract ▾
Machine Learning
GBTSVR: Twin Support Vector Regression via Granular Ball Computing
A. Quadir and M. Tanveer
Regression models used in real-world applications are often challenged by noise, outliers, data heterogeneity, and asymmetric error characteristics, which severely limit the effectiveness of conventional point-wise learning models. While twin support vector regression (TSVR) partially addresses these issues through the use of nonparallel regression bounds, it still relies on individual samples as basic learning units. As a result, TSVR remains highly sensitive to noisy and contaminated observations and fails to leverage the underlying structural and regional information inherent in complex
datasets, leading to suboptimal robustness and generalization performance. To address these limitations, we introduce granular ball twin support vector regression (GBTSVR) and its
quantile extension, granular ball twin support vector
quantile regression (GB-TSVQR). The proposed models integrate granular ball computing with TSVR, replacing individual data points with compact, structure-preserving granular balls as fundamental learning units. This region-level representation effectively suppresses noise and outliers while preserving intrinsic data geometry, thereby enhancing robustness, stability, and generalization. GBTSVR constructs nonparallel lower- and upper-bound regression functions over granular balls, significantly reducing sensitivity to sample-level perturbations. Building upon this framework, GB-TSVQR further incorporates
quantile regression principles to simultaneously capture heterogeneous trends and asymmetric error distributions across different
quantile levels. Extensive experiments on synthetic
datasets, time-series
benchmarks, and outlier-contaminated data demonstrate that the proposed GBTSVR and GB-TSVQR consistently outperform state-of-the-art regression models.
Read the full abstract ▾
Machine Learning
Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter
Samuela Rokocakau, Panagiotis Kakosimos, Giulia Tresca et al. (+1 more)
A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter from time-domain data. Gradients are released in the order of L to C to rL to rC, a sequence derived from sensitivity analysis. The five-stage schedule recovers L and C to within 5% and the series ESR to 10%, while a three-stage variant attains the same accuracy 11% faster. An 84 factorial sweep confirms that the trained PINN remains accurate for simultaneous 8% perturbations of all four components, achieving a waveform RMSE of 2.6 x 10-2 over 5 ms-an order-of-magnitude better than a simultaneous-training baseline.
Read the full abstract ▾
All authors Samuela Rokocakau, Panagiotis Kakosimos, Giulia Tresca, Pericle Zanchetta
Machine Learning · Cross-listed from stat.ML
Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost
Eliot Beyler and Francis Bach
We introduce Weighted Adjoint Matching, a method to finetune a pretrained
diffusion or flow matching model given a differentiable reward. We derive it from Adjoint Matching, which reformulates finetuning as a
stochastic optimal control problem with a quadratic control cost. Building on the observation that these models generate coarse features before fine details, we place a time-dependent weight on the control cost. A high cost early in the generative process preserves balance and diversity in the coarse features, which carry most of the semantics, while a low cost at the end lets the model increase the reward by refining details. We prove that our method is equivalent to maximizing the reward under time-varying Kullback–Leibler regularization on the generative paths. Experiments on Gaussian mixtures and on MNIST show a better tradeoff between reward and mode balance than Adjoint Matching.
Read the full abstract ▾
Machine Learning
On the Convergence of Semi-Gradient TD: A Mean Field Perspective
Haruki Settai, Tadashi Kozuno and Shinji Ito
Semi-gradient temporal-difference learning is a core algorithmic component of reinforcement learning, but bootstrapping with function approximation generally induces a non-conservative vector field and can lead to instability. We analyze this effect for two-layer neural networks in the mean-field regime and identify a simple stability mechanism in which
entropy-induced relaxation dominates the sensitivity of the moving bootstrap target. Under this condition, we prove exponential convergence to a unique fixed point and quantify its bias relative to the unregularized Bellman solution. We also show that the same mechanism extends to
entropy-regularized off-policy control through soft Q-learning.
Read the full abstract ▾
Machine Learning
ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark
Hanyao Guo, Mo Cui, Zihan Tan et al. (+21 more)
Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the
benchmarks that define the current frontier still score answer endpoints alone. Such scoring conflates memorized facts with stepwise derivation, treats visual and textual inputs as interchangeable, and confounds long-horizon planning with stepwise execution. These blind spots prevent any diagnosis of where the
reasoning chain breaks in a model. We present ChemArgus, a competition-level chemistry
benchmark drawn from chemistry competition material, textbooks, and research papers, whose scoring replaces the answer endpoint with three measurement properties. Fine-grained scoring grades every subquestion point by point with partial credit, so a score lands at the level of the step rather than the outcome.
Multimodal capability is priced on every problem containing a real image, paired with a controlled text description, so visual understanding is measured against text on identical tasks. Diagnostic attribution reads paired metrics that share one scoring unit and differ only in context construction, so a gap between two scores isolates a single cause, namely integration, propagation, or local
reasoning. GPT-5.6-Sol scores 23.2% on unassisted whole-problem solving against 28.8% and 30.4% under the two sequential metrics, a gap measuring the integration burden. Through rubric partial credit and these cause-isolating score gaps, ChemArgus shows not only whether a model answers chemistry correctly but where its
reasoning chain fails, so that every score it reports doubles as a diagnosis, a readout of the chain rather than a verdict, aiming to guide
language models step by step on their path toward chemistry expertise, one corrected step at a time, each step priced by the rubric, point by point.
Read the full abstract ▾
All authors Hanyao Guo, Mo Cui, Zihan Tan, Leixin Sun, Yichun Wang, Yinan Shen, Guojun Zhu, Jia Jiang, Erhao Chen, Zui Chen, Wenzhe Gao, Zhihao Yu, Qijun Wang, Yetian Zhu, Jiande Chen, Chuhang Pei, Yao Jiang, Yichen Fan, Pinhan Wang, Xiaorui Pan, Qianyi Zhu, Yang Liu, Mang Ye, Guancheng Wan
Machine Learning
Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL
Timo Klein, Thomas Lang, Andrii Shkabrii et al. (+3 more)
Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching performance, yet wall-clock time scales linearly with depth. We find that changing the geometry achieves stronger performance with far shallower networks. This matters in complex navigation environments, where walls can make route distance deviate substantially from Euclidean distance. In a U-shaped maze, we show that the longer the route, the more it deviates from Euclidean distance.
Hyperbolic CRL addresses this mismatch by replacing Euclidean distances in CRL's contrastive objective with geodesic distances in
hyperbolic space. On hard navigation tasks, inductive bias beats scale: depth 64
hyperbolic agents outperform 1024-layer-deep Euclidean networks while training more than $12 \times$ faster and using about $13 \times$ fewer parameters. We observe that
hyperbolic agents behave qualitatively better in hard humanoid mazes, where they follow corridors to reach goals, whereas Euclidean
agents try straight-line shortcuts over walls. Our results show that matching the representation geometry to the task can substitute for substantial network depth. Code is at https://github.com/Probabilistic-and-Interactive-ML/HypGCRL .
Read the full abstract ▾
All authors Timo Klein, Thomas Lang, Andrii Shkabrii, Lukas Miklautz, Yllka Velaj, Sebastian Tschiatschek
Machine Learning · Cross-listed from stat.ML
Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
Vahe Karagulyan, Mikołaj Kasprzak and Pierre Alquier
We study the minimax estimation of the pseudo-spectral gap $\gamma_{ps}$ of a Markov chain from the observation of a single trajectory. Extending earlier works on finite-state space chains by Wolfer and Kontorovich (2024), we provide an
estimator in the case of a compact, continuous state-space. Our
estimator appears to be minimax-optimal on the class of chains with a transition operator with Lipschitz density, up to logarithmic terms. Our
estimator, combined with Paulin's version of Bernstein inequality, allows to derive empirical concentration inequalities for Markov chains. This unlocks many applications, from confidence intervals, to active learning and generalization bounds. In particular, for rested bandits with Markov rewards, we provide a version of UCB with a regret bound similar to the one in the iid case, without assuming any knowledge on the pseudo-spectral gap of the chains.
Read the full abstract ▾
Machine Learning
Provable Transformer Context Compression for In-Context Reinforcement Learning
Yajie Zhao, Yingjun Mo, Zhiyong Wang et al. (+3 more)
Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context sizes that grow with the number of sampled transitions, leading to increasing
memory costs in large-scale problems. This raises a fundamental scalability question: how much context is intrinsically necessary to carry out such learning? We answer this question for fixed-policy TD evaluation. We show that, with a shared linear decoder, the minimum context dimension required to exactly reproduce the first $L$ TD iterates is the Krylov dimension induced by the sampled transitions. When the available context dimension $m$ falls below this threshold, exact reproduction is no longer possible. In this regime, we characterize the optimal approximation error and show that it decays as $\Theta(\gamma^m\max\{1,1/(m(1-\gamma))\})$ where $\gamma$ is the discounting factor. Moving from representation complexity to actual
memory cost, we characterize the optimal retained
memory for exact continuous representations as $\Theta(nk_L)$ and show experimentally that on a sampled task whose exact rank is full but whose numerical rank is small, a context accurate to $10^{-2}$ is $88.7\%$ smaller than the sparse sufficient statistics of TD. Finally, we establish the learnability of the shared executor through pretraining by proving global convergence of an auxiliary objective over effective
attention parameters under suitable task diversity. Experiments across diverse TD evaluation problems validate parameter recovery and the predicted context–accuracy tradeoff.
Read the full abstract ▾
All authors Yajie Zhao, Yingjun Mo, Zhiyong Wang, Bo Tang, Chao Xu, Fang Kong
Machine Learning
Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks
Mario Mallea, Angela Nebot and Franscisco Mugica
Efficient sequence modeling remains a fundamental challenge in machine learning. Despite the success of
Transformers, recurrent neural networks (RNNs) have recently re-emerged as efficient alternatives. Particularly, Echo State Networks (ESNs) offer a compelling framework of randomized RNNs that have been extensively studied for time-series forecasting and dynamical systems. This paper presents an empirical analysis of distributional, architectural, and optimization variants of ESNs evaluated on few-shot sequence-to-sequence (seq2seq) pattern tasks. These synthetic tasks utilize discrete symbol sequences, characterized by delays, inactive phases, and triggered markers to isolate and evaluate
memory and pattern recognition capabilities. The minimality of these tasks is crucial to understand the strengths and limitations of machine learning models. Furthermore, when the input signal utilizes a one-hot encoding, ESN dynamics are governed strictly by their weight distributions, offering an ideal lens through which to study reservoir computing. Our findings map the performance boundaries of ESNs relative to state-of-the-art (SOTA) models. We show that preserving a linear state regime is vital for
memory tasks, such as pattern completion or simple copy. We propose a data-dependent modulation mechanism for nonlinear input injection into the reservoir (G-ESN). G-ESN functions as a statistical filter capable of solving tasks that conventional ESNs cannot (the adding problem and bracket matching). Finally, for Deep ESNs, we evaluate a shared readout mechanism across layers that outperforms conventional concatenated readouts on structural tasks, including selective copy, sorting problem, and bracket matching.
Read the full abstract ▾
Machine Learning
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation
Zefeng He, Yunkai Chai, Xiaoyang Chen et al. (+5 more)
Looped Mixture-of-Experts (MoE) models combine parameter reuse with sparse computation to improve performance under matched budgets. Prior work demonstrates that different loop visits can play different roles even when they share parameters. To probe the contributions of different loop visits, we learn separate residual coefficients in a model that applies a shared block twice, observing a smaller scale in the first visit. Fixed coefficient experiments show that reducing the first visit's scale preserves or improves performance, whereas the same reductions to the second hurt it. This asymmetry motivates us to explore asymmetric compute allocation. We propose LatentLoop, which compresses the first visit's sequence, retains full resolution in the second, and reallocates saved computation to increase the hidden size. We further learn how strongly the first visit updates the full sequence, and share MoE weights across visits while using separate
attention parameters to accommodate their different sequence resolutions. Across 15 configurations spanning 1.3B–7B parameters, with the largest budget exceeding $10^{21}$ FLOPs, LatentLoop consistently lowers validation NLL. At a fitted NLL of 1.988, predicted compute savings are 19.0% and 7.9% relative to vanilla MoE and the looped baseline. It also improves average scores on nine
benchmarks at all sizes in 0-shot and 5-shot settings. These results suggest asymmetric compute allocation is a promising direction for looped MoE models.
Read the full abstract ▾
All authors Zefeng He, Yunkai Chai, Xiaoyang Chen, Tong Zhu, Zongliang Wu, Yun Luo, Yafu Li, Yu Cheng
Machine Learning
Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs
Shuaijie Ma, Yongkang Hu, Yu Cheng et al. (+4 more)
Federated fine-tuning enables large
language models (LLMs) to learn collaboratively from distributed client data, but malicious client updates can compromise global model safety. As
federated tasks evolve, changing malicious update patterns challenge the ability of existing defenses to maintain reliable risk detection over time. To address this challenge, we propose Safe-FCL, a framework integrating continual risk awareness with fine-grained safety aggregation for
federated continual learning of LLMs. Specifically, the Continual Risk Awareness (CRA) mechanism learns emerging risk patterns across sequential tasks and constrains detector updates using a protective subspace derived from historical features, mitigating forgetting of previously learned malicious patterns while adapting to new risks. To translate risk awareness into aggregation-level safety control, the Fine-Grained Safety Aggregation (FGSA) mechanism combines client-level risk assessments from CRA with module-level deviations from historical update behavior to adaptively regulate aggregation contributions, suppressing potentially malicious updates while minimizing unnecessary restrictions on benign updates. Extensive experiments demonstrate that Safe-FCL outperforms current SOTA methods, improving global-model Rule and MD-Judge scores in
federated continual learning by 0.41% and 0.64%, respectively, while increasing average risk recognition accuracy by 2.01%.
Read the full abstract ▾
All authors Shuaijie Ma, Yongkang Hu, Yu Cheng, Jiuan Zhou, Yi Xie, Yushuo Zhang, Zhaoxia Yin
Machine Learning · Cross-listed from cs.CL
Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study
Arjun Boya, Charan Sai Bandaru, Masthanaiah Pillimetla et al. (+1 more)
The number of
attention heads in a
transformer is usually set by convention or grid search. We test a simple heuristic for setting it in advance: estimate the intrinsic dimension of
token representations without labels, and use roughly that many heads. We estimate intrinsic dimension with a nested-dropout VAE trained on DistilBERT
embeddings of WikiText-2, choosing the KL weight at the knee of the VAE's rate-distortion curve rather than by hand. This gives $k^*=9.2$ (95% CI [8.6, 9.8]). In a small 4-layer
transformer trained from scratch, 10 heads and 32 heads are statistically equivalent on SST-2 and on MRPC (paired TOST over 10 seeds, $\pm1$ point margin), with 69% fewer
attention parameters for the 10-head model. Training 10 heads from the start also slightly outperforms training 32 heads and
pruning to 10 (0.6 points, $p=0.008$). The evidence is narrow: two classification tasks, one small architecture, no pretrained models, and no formal link between intrinsic dimension and head count. We present the result as a practical heuristic worth testing at larger scale, not as a general principle.
Read the full abstract ▾
All authors Arjun Boya, Charan Sai Bandaru, Masthanaiah Pillimetla, Kavana Chidanandappa
Machine Learning · Cross-listed from cs.CL
AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
Jia Tong, Senyou Deng, Min Peng et al. (+1 more)
Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judging each local edit only by its immediate score can discard useful intermediate states. We introduce AtomSearch, which keeps revision actions local while using subsequent skill states to guide search. Contrastive atomic editing links each primitive rule edit to failed and successful executions, a behavioral hypothesis, and an intended scope. Skill-State Tree Search (STS) evaluates short edit compositions and selectively retains them as executable states that can be revisited and extended. Outcome
memory supplies later proposals with observed repair and regression statistics. We evaluate AtomSearch across four tasks and five target models. With deepseek-v4-flash, it exceeds SkillOpt on three of four tasks, including a 9.68-percentage-point gain on LiveMathematicianBench, and SkillOpt's final skills contain 2.3-19.7 times as many characters. In 67% of completed searches, the best validation state passes through an ancestor that was not highest-scoring at its depth. These results show how local rule edits can support the exploration of useful revision paths and yield compact skills, with additional offline evaluations used to explore alternative states.
Read the full abstract ▾
All authors Jia Tong, Senyou Deng, Min Peng, Jianfeng Pan
Machine Learning
Learning Graph Energies for Finite-Time Generation
Amartya Banerjee, Xingyu Xu, Caroline Moosmüller et al. (+1 more)
Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at
equilibrium need not yield accurate samples when the sampler stops after a fixed number of steps. We introduce finite-horizon energy learning, which adapts the acceptance energy of a Metropolis–Hastings sampler to the distribution it returns after a prescribed number of steps, with initialization, proposals, and annealing schedule held fixed. For graph generation, a frozen pretrained model supplies initialization and proposals, and a learned energy governs acceptance. A training-only discriminator scores completed samples, and coupled continuations of the accepted and rejected branches of a proposal give an acceptance-gradient
estimator that is unbiased for a fixed discriminator under stated conditions, without equilibrated negative samples or differentiation through discrete states. Generation uses the learned energy in the original single-trajectory sampler, without discriminator evaluations or reranking. On twelve pairwise binary targets with exactly evaluated terminal laws, learned energies have lower median terminal total variation than the
equilibrium-correct energy in every tested short-horizon setting, and than its numerically tuned scalar multiple in most settings. On MOSES, a learned two-coefficient combination of pretrained Graph Energy Matching (GEM) potentials lowers FCD by 3.7–10.5% relative to scale-calibrated GEM at matched sampling steps, with validity gains at the shortest budget and a sub-point validity trade-off at higher budgets.
Read the full abstract ▾
All authors Amartya Banerjee, Xingyu Xu, Caroline Moosmüller, Harlin Lee
Machine Learning
MorphingNet: Symbolic Regression Where the Network Is the Formula
Jincheng Gao, Jiahe Yi and Shuo Sun
We introduce MorphingNet, a network for symbolic regression (SR) whose units change their function continuously. Instead of searching over expressions built from a fixed operator library, MorphingNet trains the form of each function as a parameter, so SR becomes one continuous optimization problem. Its units are either pole-free rational functions or complex exponential–logarithm functions, which move between exponentials, sinusoids, damped oscillations, power laws and logarithms as their parameters change. The network is a readable formula at every step of training, and no operator library is needed to train it; a structure-recovery step afterwards rewrites the trained formula into short elementary expressions. Training is dense linear
algebra, so it is GPU-friendly and scales to large data. MorphingNet achieves state-of-the-art accuracy on SRBench, recovers most generating formulas on synthetic
benchmarks, and on large data is up to two orders of magnitude faster than the strongest search method. By turning the search for a formula into the training of a network, MorphingNet offers a new paradigm for SR and for scientific discovery from data.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Tomáš Čížek, Matej Straka, Illia Volkov et al. (+5 more)
Segment Anything Model 3 (SAM 3) is a foundation model for image and
video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a
memory bank, managed by a simple First-In-First-Out rule, allowing temporal consistency in complex
videos. Several recent methods improve SAM 2 with hand-crafted
memory update rules, each targeting a specific failure mode, such as distractors, occlusions, or object motion. However, their gains transfer only partially to the stronger SAM 3 backbone. We instead present a more general, data-driven approach that frames
memory control as a sequential decision-making task. SAM3RL is an extension of the SAM 3 tracker with a lightweight
memory controller, trained by reinforcement learning, that decides which frames enter the
memory bank in order to maximize tracking performance. SAM3RL sets a new state of the art on 10 of 12 tracking and
video object segmentation
benchmarks, outperforming all hand-crafted rules without any runtime overhead. The same approach applied to SAM 2 gives SAM2RL, which outperforms hand-crafted rules on 9 of the 12
benchmarks, showing the generality of our method across model generations.
Read the full abstract ▾
All authors Tomáš Čížek, Matej Straka, Illia Volkov, Matěj Kripner, Ervin Macić, Jiri Matas, Klara Janouskova, Martin Schmid
Machine Learning · Cross-listed from stat.ML
Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization
Haowei Wang and Yilin Zheng
Efficient global optimization aims to identify a global optimum of an expensive black-box function within a limited evaluation budget $N$. We investigate the convergence rates of Gaussian process Thompson sampling (GP-TS) under noiseless observations, assuming a fixed objective function in a reproducing kernel
Hilbert space (RKHS). For Matérn kernels with smoothness parameter $\nu$ in dimension $d$, we establish a worst-case expected simple-regret upper bound of $O(N^{-\nu/d}\sqrt{\log N})$ for both discrete GP-TS on sufficiently fine grids and its continuous counterpart. For the continuous implementation, we develop a nested-grid argument to control posterior sample paths over the entire domain. We further establish matching lower bounds of $\Omega(N^{-5/2}\sqrt{\log N})$ for both implementations under a fixed one-dimensional Matérn-$5/2$ kernel, demonstrating that the logarithmic penalty is intrinsic to standard GP-TS in this setting. Motivated by this limitation, we propose Gaussian Process Capped Thompson Sampling (GP-CTS), which caps posterior sample paths using a valid RKHS norm upper bound while preserving optimism. This modification successfully eliminates the logarithmic penalty and achieves the minimax-optimal rate $\Theta(N^{-\nu/d})$ for both discrete and continuous implementations.
Read the full abstract ▾
Machine Learning
MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
Yanyi Su, Chenyan Wang, Yulei Gong et al. (+3 more)
Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of structurally distinct replacement molecules represent two fundamentally different search problems. LLM-based molecular design
agents typically perform the former, conducting local refinement within the neighborhood of existing structures to improve target properties through structural modifications. In contrast, the latter requires exploration of a broader chemical space to discover molecules with entirely different scaffolds while preserving the functional characteristics of reference molecules. We propose MolHop, an agentic framework for cross-scaffold molecular discovery that enables models to navigate and edit within a pre-organized chemical space. MolHop organizes approximately 1.6 million molecular scaffolds from commercial molecules into a coarse-to-fine hierarchical action space. The
agent selects new exploration regions through scaffold navigation actions and adjusts candidate properties through molecular editing. The framework maintains historical trajectory
memory to support long-horizon search processes. On drug molecule and commercial compound tasks, connecting Grok-4.6 and DeepSeek-Flash-V4.1 to the MolHop framework substantially improves their cross-scaffold joint success rates. We develop MolHop-9B through agentic reinforcement learning, and MolHop-9B outperforms generative baselines including GPT-5.6-sol, Claude-5-Opus, and Gemini-3.1-Pro, while generating candidate molecules with larger scaffold differences from the reference molecules. These results demonstrate that effective molecular discovery beyond the traditional optimization paradigm requires structured chemical and action spaces, enabling
agents to explore new structural regions rather than merely refine existing molecules.
Read the full abstract ▾
All authors Yanyi Su, Chenyan Wang, Yulei Gong, Yeyun Chen, Xiaohui Yang, Jun Cheng
Machine Learning
Beyond DFT electronic band structures via dual-space orbital learning
Minhyuk Kang, Beom Seok Kang, Nikolai Argatoff et al. (+4 more)
Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding. We introduce O-kRystal, a dual-space orbital-learning framework that uses a lower-cost Perdew-Burke-Ernzerhof (PBE) calculation as both an energy baseline and a source of structured orbital information. Combining PBE band energies with real- and reciprocal-space orbital
matrices, O-kRystal predicts higher-level corrections for individual electronic states as a function of
crystal momentum and
spin. For states within 5 eV of the band-edge midpoint, it predicts Heyd-Scuseria-Ernzerhof (HSE06) band energies with a mean absolute error of $0.171 \pm 0.009$ eV across nearly 6,000 three-dimensional materials spanning insulating, metallic,
magnetic, and nonmagnetic systems. On a separate
benchmark of six strongly correlated materials, it reduces the corresponding PBE band-energy MAE by 68.7% and resolves orbital-dependent changes in the relative placement of transition-metal d and ligand p states. Despite training only at high-
symmetry points, it maintains comparable accuracy at unseen points along band paths and reconstructs HSE06 densities of states from dense Brillouin-zone predictions. Finally, training O-kRystal on $G_0W_0$ quasiparticle energies for two-dimensional materials demonstrates its applicability across levels of theory and the potential of orbital learning for higher-fidelity, momentum-resolved electronic-structure prediction beyond density functional theory.
Read the full abstract ▾
All authors Minhyuk Kang, Beom Seok Kang, Nikolai Argatoff, Miguel Nouman, Danish Khan, William A. Goddard III, Anima Anandkumar
Machine Learning
CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation
Zhi Li, Haowei Liu, Hongchen Yang et al. (+5 more)
Adversarial robustness
distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner. This paradigm terminates teacher-student interaction once the student is distilled, thereby discarding potentially useful feedback from the distilled student. However, exploiting such feedback is nontrivial because indiscriminate weak-to-strong transfer may propagate student errors to the teacher. To address this issue, we propose Cyclic
Adversarial Robustness
Distillation (CARD), a closed-loop framework that turns the distilled student into a feedback source for refining the robust teacher and subsequently transfers the teacher gains back to the same student. CARD first performs strong-to-weak
adversarial distillation and then uses reliability-enhanced student feedback to refine the robust teacher. The refinement combines inverse
adversarial student feedback with teacher-student discrepancy maximization, after which the refined teacher is used to continue training the same student under the unchanged base
distillation objective. We further establish a sample-level sufficient condition for reliable weak-to-strong feedback transfer and derive a distribution-level upper bound on the refined teacher's risk. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet-10 across multiple teacher-student architectures and base
distillation methods show that CARD improves
adversarial robustness in most evaluated settings while generally preserving clean accuracy. These results show that the distilled student can provide useful feedback to the teacher, enabling robustness transfer to proceed beyond the conventional one-way teacher-to-student paradigm.
Read the full abstract ▾
All authors Zhi Li, Haowei Liu, Hongchen Yang, Xiaoxuan Wang, Song Gao, Zhenli He, Wei Zhou, Shaowen Yao
Machine Learning
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
Tao Yu, Zhongtian Luo, Yuchen Long et al. (+19 more)
Large
language model
agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-
evolution insufficiently understood. We introduce RSE-Bench, to our knowledge the first
benchmark for evaluating skill self-
evolution under ordinary, non-
adversarial noise. It spans four domains and six
benchmarks, with controlled perturbations to instructions, environmental evidence, execution records, and outcome–record pairings that preserve the underlying tasks and native scoring rules. The protocol separates noise during learning from input-side noise at evaluation, testing frozen skill stores on held-out tasks. We also introduce RSEClaw, a method-agnostic framework supporting consistent noise injection and process diagnostics of actual exposure and skill updates. Across three methods and two backbones, noisy learning retains only $25.5\%$–$42.1\%$ of the aggregate gain achieved by clean self-
evolution, depending on the noise type. Perturbations confined to execution records and outcome–record pairings cause average losses comparable to input-side noise, despite leaving the original executions and evaluations intact. Diagnostics further identify differences in candidate skill text that coexist with small changes in mean held-out performance.
Read the full abstract ▾
All authors Tao Yu, Zhongtian Luo, Yuchen Long, Yiheng Lu, Yuxuan Zhou, Yanpei Gong, Siyi Cao, Yuqing Wu, Haopeng Jin, Zhenghao Zhang, Yujia Yang, Jingmin Zhu, Yunyun Hou, Xinming Wang, Hongzhu Yi, Jiachen Liu, Sirui Wang, Nan Duan, Yan Huang, Liang Wang, Tianjin Huang, Yanyan Zou
Machine Learning · Cross-listed from cs.CV
Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Taha Sabir, Alberto Montero Molina, Thinh Quang Ly et al. (+3 more)
Adapting a single
vision-
language model to medical image parsing requires training choices that reflect the demands of each task. We study task-specific adaptation with Qwen3.5-9B for
FLARE 2026 Task 3, covering six task families and seven imaging modalities. Our system couples a shared, frozen 4-bit backbone with LoRA adapters selected from the input question. We customize adapter ranks and
prompts, rebalance rare classification targets, and supplement regression training with dermatology classification examples. On the fixed internal holdout, the task-specific adapters achieve a
dataset-macro balanced accuracy of 0.7791 for classification, a
dataset-macro micro-F1 of 0.6286 for multi-label classification, a counting mean absolute error (MAE) of 11.73, a
dataset-macro detection F1 of 0.8914, a
dataset-macro regression MAE of 9.78, and a report-generation CRIMSON score of 0.8204. On the organizer's 1,703-example hidden-validation set, the submitted system achieves 0.8496 classification balanced accuracy, 0.5338 sample-averaged multi-label F1, and 14.5950 regression MAE. The final 30.1 GB container averages 3.1 seconds per case, including model loading, and produces identical outputs across repeated verification runs. The benefits vary across tasks, supporting the use of task-specific adapter configurations and image budgets within a shared medical
vision-
language model. Code is available at https://github.com/TahaSabir0/
FLARE26-Hexapus.
Read the full abstract ▾
All authors Taha Sabir, Alberto Montero Molina, Thinh Quang Ly, Veronika Dmitrenko, Mohammad Yaqub, Tausifa Jan Saleem
Machine Learning
Universal Sample-Based Embeddings of Higher-Order Objects
Radovan Haluška, Christopher Solinas, Nathan R. Sturtevant et al. (+2 more)
Neural networks operate naturally on finite-dimensional vectors, yet many problems require
reasoning about higher-order objects such as distributions, functions, and graphs. Such objects capture relationships within a ground set and rarely admit an explicit compact representation. Moreover, we typically want a compact representation not of a single higher-order object but of an entire family of such objects, including members unseen during training. While a few approaches exist for particular object types, none is designed to work across object types. We propose a unified framework that represents any higher-order object as a fixed-size
embedding vector learned over a family of such objects. An encoder maps an object, seen only through a finite set of samples, to an
embedding, and a domain-specific decoder supplies the training signal by modeling the object conditioned on that
embedding. Since the encoder works only from samples, one architecture serves different object types. Because the decoder is a model already suited to single instances of the object type, the framework inherits that model's native operations and inductive biases. We instantiate the framework on distributions, functions, and graphs. In each case we show that a single trained model represents an entire family and generalizes to members unseen during training. Furthermore, we demonstrate the downstream utility of these
embeddings: interpolating distributions in
embedding space, solving differential equations in
embedding space, and predicting unseen edges from a graph's
embedding.
Read the full abstract ▾
All authors Radovan Haluška, Christopher Solinas, Nathan R. Sturtevant, Martin Schmid, Michael Bowling
Machine Learning · Cross-listed from cs.SD
Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate
Simone Lugani, Christof Pichler, Hannes Wegleiter et al. (+3 more)
Reliable fault detection is crucial for industrial machinery in large-scale facilities, where unexpected failures can cause costly downtime and production interruptions. Although acoustic monitoring provides a scalable solution for machine condition monitoring, its deployment is often constrained by high false-positive rates. We propose a two-step approach to automatic anomalous sound detection: first, when only normal operating audio samples are available, a regularized unsupervised model is deployed; then, after the first machine fault, a few-shot adaptation strategy exploits the anomalous samples acquired during the fault to improve the system. This adaptation increases the area under the precision-recall curve (AUPR) from 23.0 to 64.0 and improves detection in the low false-positive-rate region, with the partial area under the receiver operating characteristic curve (pAUROC) increasing from 39.6 to 72.8. We also show that covariance regularization improves both prediction accuracy and training stability in the unsupervised model. These results provide a practical strategy for acoustic anomaly detection systems, enabling improved accuracy and reduced false alarms.
Read the full abstract ▾
All authors Simone Lugani, Christof Pichler, Hannes Wegleiter, Christoph Feilmayr, Rodolfo Zunino, Edoardo Ragusa
Machine Learning
On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs
Mikołaj Piórczyński, Wojciech Masarczyk, Damian Sójka et al. (+2 more)
Vision-
language models suffer significant accuracy drops under common corruptions. While test-time adaptation (TTA) successfully mitigates these shifts in CLIP-like contrastive models, its application to generative
multimodal large
language models (MLLMs) remains underexplored and uniquely challenging due to their sequential
token generation. In this work, we demonstrate that representation-based TTA fails to recover performance in MLLMs. Our experiments reveal that even when violating standard TTA assumptions by leveraging target data offline, sample-blind feature
alignment recovers only marginal accuracy. We attribute this failure to the nature of corruption shifts: unlike CLIP-like architectures, which benefit from a shared domain-shift direction within a single pooled classification
embedding, MLLM visual
token sequence shifts are nearly orthogonal and span the full
embedding space.These findings bound what any sample-blind, position-shared correction at a single encoder site can achieve, establishing that representation-space interventions alone might be insufficient to ensure corruption robustness in MLLMs.
Read the full abstract ▾
All authors Mikołaj Piórczyński, Wojciech Masarczyk, Damian Sójka, Sebastian Cygert, Bartłomiej Twardowski
Machine Learning
Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction
Robin Uhrich, Marco Bagatella, Núria Armengol Urpí et al. (+2 more)
The growing interest in behavior foundation models, combined with recent advancements in generative modeling, has led to an appealing recipe for reinforcement learning from unlabeled data: pre-train a generative model to model occupancies, i.e., discounted state visitations, on reward-free trajectories, such that a policy can be easily extracted once a small reward-labeled
dataset becomes available. We decompose this recipe along three axes: (i) the degree to which the multi-modal structure of occupancies must be captured, (ii) the class of generative model, and (iii) the method used for policy extraction. Along each axis, we consider existing choices, propose simpler alternatives, and validate each decision experimentally. This analysis culminates in a novel, streamlined method that leverages drifting, a modern one-step generative sampler, to model the occupancy. We show that this enables policy extraction via direct differentiation through the occupancy model, and bypasses the need for critic
distillation. Overall, we observe that this nimble setup leads to improvements in performance on standard
benchmarks.
Read the full abstract ▾
All authors Robin Uhrich, Marco Bagatella, Núria Armengol Urpí, Pavel Kolev, Georg Martius
Machine Learning
Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference
Amartya Banerjee, Harlin Lee and Caroline Moosmüller
Population dynamics are often observed only as unpaired snapshots, which leave the
evolution between measurements underdetermined. Second-order regularization can constrain it, but a penalty on the accelerations of sampled particles is a prior on joint particle paths, and different particle representations of the same marginal curve can have different acceleration costs. We therefore introduce Neural Wasserstein Splines (NWSP), a sample-based method that learns a continuous population curve under a Wasserstein smoothness prior. A neural network maps latent variables to the control points of a cubic spline in time, so samples at any time come from the spline basis without numerical integration. We project the generator's velocity onto gradients of a finite dictionary of scalar potentials and differentiate this measure-dependent projection in time, obtaining a finite-dimensional surrogate for the intrinsic Wasserstein acceleration, trained jointly with distributional fit losses. For a fixed dictionary and ridge parameter, we prove that the population penalty depends only on the marginal curve and bound its sensitivity to moment-estimation errors. Learned potentials (NWSP-N) sharpen acceleration estimates. On various synthetic and single-
cell benchmarks, NWSP is highly competitive with transport and flow-based methods, ranking in the top two in 11 of 16 settings. The penalty improves on an unregularized spline in 13 of 16 settings and, while competitive with a particle-acceleration penalty, adds provable representation invariance.
Read the full abstract ▾
Machine Learning
SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning
Teif Aldaajani, Huda Hakami and Maha A. Thafar
Continual learning aims to acquire new knowledge while retaining previously learned knowledge. However, updating shared parameters when learning new tasks often overwrites existing knowledge, causing catastrophic forgetting.
Memory replay methods mitigate catastrophic forgetting but rely on previous samples, raising
privacy,
memory, and scalability concerns. On the other hand, parameter isolation-based methods preserve learned knowledge but may limit knowledge transfer, whereas regularization promotes adaptability but remains susceptible to interference between old and new tasks. To maintain the stability-plasticity trade-off, this paper proposes Stability-Plasticity-Aware Region Selection (SPARS), a replay-free hybrid framework combining global parameter isolation with localized parameter regularization. SPARS estimates parameter importance using either the Fisher Information
Matrix (FIM) or a novel Confidence Score (CS)
estimator that leverages logit sensitivity and achieves comparable performance to FIM without requiring labelled data. Based on parameter importance, SPARS partitions parameters into three importance-aware regions namely, winning, neighboring, and non-important parameter regions. Each region receives a different adaptation strategy: selective freezing, soft regularization, or unrestricted learning based on its role in the stability-plasticity trade-off. To mitigate classifier bias in class-incremental learning, we employ Quadratic Discriminant Analysis to improve performance on previously learned classes .Experiments on CIFAR-10 and TinyImageNet demonstrate consistent improvement in average incremental accuracy over existing isolation- and regularization-based methods across task- and class-incremental learning. On TinyImageNet, SPARS achieves the best performance with 6% improvement for class-incremental learning while retaining over 60% of parameters for future tasks.
Read the full abstract ▾