Machine Learning
Screening Is Enough
Ken M. Nakanishi
We call query–key relevance absolute when its values lie on a fixed bounded scale, depend on neither competing keys nor sequence length, require no sequence-length-dependent calibration, and can all be zero. To realize this notion, we introduce screening, whose explicit threshold transforms bounded query–key similarities into relevance values, enabling exact rejection, empty selection, and direct inspection on a common scale. In a controlled comparison of 12
attention mechanisms on a matched
Transformer backbone, only screening maintains both low long-context perplexity and robust
retrieval beyond the training context; notably, it does so without inference-time scaling. Building on screening, we introduce Multiscreen, a
language-model architecture composed of parallel gated screening tiles. Multiscreen retains these long-context gains while achieving greater parameter efficiency, stronger general zero-shot downstream performance, lower training cost at larger scales, and lower model-side time to first
token than
Transformer baselines. We further develop a normalization design that keeps Multiscreen training stable even at a learning rate of $1$ and show that an adapted version likewise stabilizes
Transformer at the same learning rate.
Read the full abstract ▾
Machine Learning
NeuroDDAF: Neural Dynamic Diffusion-Advection Fields with Evidential Fusion for Air Quality Forecasting
Prasanjit Dey, Soumyabrata Dev, Angela Meyer et al. (+1 more)
Accurate air quality
forecasting is crucial for protecting public health and guiding environmental policy, yet it remains challenging due to nonlinear spatiotemporal dynamics, wind-driven transport, and distribution shifts across regions. Physics-based models are interpretable but computationally expensive and often rely on restrictive assumptions, whereas purely data-driven models can be accurate but may lack robustness and calibrated uncertainty. To address these limitations, we propose Neural Dynamic
Diffusion-Advection Fields (NeuroDDAF), a physics-informed
forecasting framework that unifies neural representation learning with open-system transport modeling. NeuroDDAF integrates (i) a GRU-Graph
Attention encoder to capture temporal dynamics and wind-aware spatial interactions, (ii) a
Fourier-domain
diffusion-advection module with learnable residuals, (iii) a wind-modulated latent Neural ODE to model continuous-time
evolution under time-varying connectivity, and (iv) an evidential fusion mechanism that adaptively combines physics-guided and neural forecasts while quantifying uncertainty. Experiments on four urban
datasets (Beijing, Shenzhen, Tianjin, and Ancona) across 1-3 day horizons show that NeuroDDAF consistently outperforms strong baselines, including AirPhyNet, achieving up to 9.7% reduction in RMSE and 9.4% reduction in MAE on long-term forecasts. On the Beijing
dataset, NeuroDDAF attains an RMSE of 41.63 $\mu$g/m$^3$ for 1-day prediction and 48.88 $\mu$g/m$^3$ for 3-day prediction, representing the best performance among all compared methods. In addition, NeuroDDAF improves cross-city generalization and yields well-calibrated uncertainty estimates, as confirmed by ensemble variance analysis and case studies under varying wind conditions.
Read the full abstract ▾
All authors Prasanjit Dey, Soumyabrata Dev, Angela Meyer, Bianca Schoen-Phelan
Machine Learning · Cross-listed from eess.SY
Safe learning-based control via function-based uncertainty quantification
Abdullah Tokmak, Toni Karvonen, Thomas B. Schön et al. (+1 more)
Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems. This is commonly realized by constructing uncertainty tubes that enclose the unknown function of interest, e.g., the reward and constraint functions or the underlying dynamics model, with high probability. However, existing approaches for uncertainty quantification typically rely on restrictive assumptions that encode smoothness properties of the unknown function, such as a known norm in a function space. Moreover, these methods usually struggle with discontinuities. In this paper, we model the unknown function as a random function from which independent and identically distributed realizations can be generated. We then construct uncertainty tubes via the scenario approach that hold with high probability. Our uncertainty tubes rely solely on sampled realizations and can therefore accommodate discontinuities represented by the sampling model. We integrate these uncertainty tubes into a safe
Bayesian optimization
algorithm with which we safely tune control parameters on a real Furuta pendulum.
Read the full abstract ▾
All authors Abdullah Tokmak, Toni Karvonen, Thomas B. Schön, Dominik Baumann
Machine Learning
Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
Cai Zhou, Zekai Wang, Menghua Wu et al. (+6 more)
While test-time scaling has enabled large
language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs. These inefficiencies can be attributed to the miscalibration of post-trained
language models, and the lack of calibration in popular sampling techniques. Here, we present Online
Reasoning Calibration (ORCA), a framework for calibrating the sampling process that draws upon conformal prediction and test-time training. Specifically, we introduce a meta-learning procedure that updates the calibration module for each input. This allows us to provide valid confidence estimates under distributional shift, e.g. in thought patterns that occur across different stages of
reasoning, or in
prompt distributions between model development and deployment. ORCA not only provides theoretical guarantees on conformal risks, but also empirically shows higher efficiency and generalization across different
reasoning tasks. At risk level $\delta=0.1$, ORCA improves Qwen2.5-32B efficiency on in-distribution tasks with savings up to 47.5% with supervised labels and 40.7% with self-consistency labels. Under zero-shot out-of-domain settings, it improves MATH-500 savings from 24.8% of the static calibration baseline to 67.0% while maintaining a low empirical error rate, and the same trend holds across model families and downstream
benchmarks. Our code is publicly available at https://github.com/wzekai99/ORCA.
Read the full abstract ▾
All authors Cai Zhou, Zekai Wang, Menghua Wu, Qianyu Julie Zhu, Flora C. Shi, Chenyu Wang, Ashia Wilson, Tommi Jaakkola, Stephen Bates
Machine Learning
Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment
Kai Nelson, Tobias Kreiman, Sergey Levine et al. (+1 more)
A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are commonly modeled using simulators, which impose computational approximations. Meanwhile, experimental measurements more faithfully represent the real world, but experimental data typically consists of observations that only partially reflect the system's full underlying state. We propose a data-driven distribution
alignment framework that bridges this simulation-to-experiment gap by pre-training a generative model on fully observed (but imperfect) simulation data, then aligning it with partial (but real) observations of experimental data. While our method is domain-agnostic, we ground our approach in the physical sciences by introducing
Adversarial Distribution
Alignment (ADA). This method aligns a generative model of atomic positions – initially trained on a simulated Boltzmann distribution – with the distribution of experimental observations. We prove that our method recovers the target observable distribution, even with multiple, potentially correlated observables. We also empirically validate our framework on synthetic, molecular, and experimental
protein data, demonstrating that it can align generative models with diverse observables. Our code is available at https://kaityrusnelson.com/ada/.
Read the full abstract ▾
All authors Kai Nelson, Tobias Kreiman, Sergey Levine, Aditi S. Krishnapriyan
Machine Learning · Cross-listed from cs.CL
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
Jack Young
Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state
matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval. The method, which we call S0 tuning, optimizes one state
matrix per recurrent layer while freezing all model weights. On Qwen3.5-4B (GatedDeltaNet hybrid), S0 tuning improves greedy pass@1 by +23.6 +/- 1.7 pp (10 seeds). On FalconH1-7B (Mamba-2 hybrid), S0 reaches 71.8% +/- 1.3 and LoRA reaches 71.4% +/- 2.4 (3 seeds), statistically indistinguishable at this sample size while requiring no weight merging. Cross-domain transfer is significant on MATH-500 (+4.8 pp, p = 0.00002, 8 seeds) and GSM8K (+2.8 pp, p = 0.0003, 10 seeds); a text-to-SQL
benchmark (Spider) shows no transfer, consistent with the trajectory-steering mechanism. A prefix-tuning control on a pure
Transformer (Qwen2.5-3B) degrades performance by -13.9 pp under all nine configurations tested. On Qwen3.5, a per-step state-offset variant reaches +27.1 pp, above both S0 and LoRA but with per-step inference cost. Taken together, the results show that recurrent state initialization is a strong zero-inference-overhead PEFT surface for hybrid
language models when verified supervision is scarce. The tuned state is a ~48 MB file; task switching requires no weight merging or model reload. Code and library: https://github.com/jackyoung27/s0-tuning.
Read the full abstract ▾
Machine Learning
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Gleb Rodionov, Roman Garipov and George Yakushev
Large
language models (LLMs) exhibiting test-time scaling behavior, such as extended
reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term
reasoning tasks. However, the robustness of these
reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple
reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon:
reasoning models tend to produce much shorter
reasoning traces (up to 74%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. Importantly, we show that even when additional self-checks are forced, their efficiency depends not only on the content of the
reasoning traces, but also on the presence of redundant context. We hope our findings draw additional
attention to both the robustness of
reasoning models and the problem of context management for LLMs.
Read the full abstract ▾
Machine Learning
Property-Level Flood Risk Assessment Using AI-Enabled Street-View Lowest Floor Elevation Extraction and ML Imputation Across Texas
Xiangpeng Li, Yu-Hsuan Ho, Sam D Brody et al. (+1 more)
This paper argues that AI-enabled analysis of street-view imagery, complemented by performance-gated machine-learning imputation, provides a viable pathway for generating building-specific elevation data at regional scale for flood risk assessment. We develop and apply a three-stage pipeline across 18 areas of interest (AOIs) in Texas that (1) extracts LFE and the height difference between street grade and the lowest floor (HDSL) from Google Street View imagery using the Elev-
Vision framework, (2) imputes missing HDSL values with Random Forest and Gradient Boosting models trained on 16 terrain, hydrologic, geographic, and flood-exposure features, and (3) integrates the resulting elevation
dataset with Fathom 1-in-100 year inundation surfaces and USACE depth-damage functions to estimate property-specific interior flood depth and expected loss. Across 12,241 residential structures, street-view imagery was available for 73.4% of parcels and direct LFE/HDSL extraction was successful for 49.0% (5,992 structures). Imputation was retained for 13 AOIs where cross-validated performance was defensible, with selected models achieving R suqre values from 0.159 to 0.974; five AOIs were explicitly excluded from prediction because performance was insufficient. The results show that street-view-based elevation mapping is not universally available for every property, but it is sufficiently scalable to materially improve regional flood-risk characterization by moving beyond hazard exposure to structure-level estimates of interior inundation and expected damage. Scientifically, the study advances LFE estimation from a pilot-scale proof of concept to a regional, end-to-end workflow. Practically, it offers a replicable framework for jurisdictions that lack comprehensive Elevation Certificates but need parcel-level information to support mitigation, planning, and flood-risk management.
Read the full abstract ▾
All authors Xiangpeng Li, Yu-Hsuan Ho, Sam D Brody, Ali Mostafavi
Machine Learning · Cross-listed from cs.AI
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
Aaron Rose, Carissa Cullen, Sahar Abdelnabi et al. (+3 more)
Non-verbalised or secret collusion may impose a ceiling on transcript-level monitoring in multi-
agent deployments. Internal model activations are known to provide an additional monitoring surface for single-
agent phenomena such as deception, but detecting collusion within an unknown subgroup is ultimately a joint inference task over multiple
agents. This paper derives collusion detection statistics based on the composite hypothesis testing literature and introduces HELIOS, a multi-
agent detection framework for collusion. Using per-
agent activation probes as sensors, we then evaluate these principled statistics alongside heuristics on NARCBench, a novel
benchmark for evaluating multi-
agent collusion detection under environment distribution shift. Across four open-weight models, both our group-level statistics and heuristics transfer zero-shot to NARCBenchs holdout environments. Notably, the best method on every model reaches 0.99 to 1.00 AUROC when transferred from committee deliberations to a steganographic collusion task that unprimed transcript monitors fail to separate. We find empirically that no single statistic or heuristic dominates across tasks, consistent with our analysis that there is no known universally most powerful test for this setting. We then evaluate detector transfer to third-party environments with emergent, rather than instructed, collusion. In one such environment, only 2 of 229 collusive episodes verbalise the coordination in the transcript. We find evidence of partial transfer from NARCBench to these environments, indicating that probes fitted to instructed collusion may not fully capture emergent collusion signals. Overall, we establish multi-
agent interpretability as a complementary monitoring technique, while highlighting the need to evaluate detector performance on both emergent and instructed collusion risks.
Read the full abstract ▾
All authors Aaron Rose, Carissa Cullen, Sahar Abdelnabi, Philip Torr, Brandon Gary Kaplowitz, Christian Schroeder de Witt
Machine Learning · Cross-listed from cs.RO
Planning for Change: Reinforcement Learning Combined with Bounded Extremum Seeking for Robotic Control under Distribution Shift
Shaifalee Saxena, Rafael Fierro and Alexander Scheinker
Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distribution. This limitation is especially important for reliable
robot planning and control in contact-rich tasks such as pushing and pick-and-place, where changes in goals, contact conditions, or
robot dynamics can drive the system out-of-distribution at inference time. In this paper, we investigate a hybrid controller that combines reinforcement learning with bounded extremum seeking (ES) to improve robustness under such conditions. In the proposed approach, deep deterministic policy gradient (DDPG) policies are trained under standard conditions on the robotic pushing and pick-and-place tasks, and are then combined with bounded ES during deployment. The RL policy provides fast manipulation behavior, while bounded ES ensures robustness of the overall controller to time variations when operating conditions depart from those seen during training. The resulting controller is evaluated under several out-of-distribution settings, including time-varying goals and spatially varying friction patches. Crucially, under reasonable assumptions, we prove finite time RL-based convergence of a robotic arm to an object after which bounded ES achieves finite-time convergence to a bounded velocity moving target. We provide analytic formulas for both convergence times, and an ability to tune the convergence times by our choice of gains.
Read the full abstract ▾
Machine Learning
Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling
Zhantao Chen, Dongyi He, Jin Fang et al. (+4 more)
As sports training becomes more data-driven, traditional dart coaching based mainly on experience and visual observation is increasingly inadequate for high-precision, goal-oriented movements. Although prior studies have highlighted the importance of release parameters, joint motion, and coordination in dart throwing, most quantitative methods still focus on local variables, single-release metrics, or static template matching. These approaches offer limited support for personalized training and often overlook useful movement variability. This paper presents a data-driven dart training assistance system. The system creates a closed-loop framework spanning motion capture, feature modeling, and personalized feedback. Dart-throwing data were collected in markerless conditions using a Kinect 2.0 depth sensor and an optical camera. Eighteen kinematic features were extracted from four biomechanical dimensions: three-link coordination, release velocity, multi-joint angular configuration, and postural stability. Two modules were developed: a personalized optimal throwing trajectory model that combines historical high-quality samples with the minimum jerk criterion, and a motion deviation diagnosis and recommendation model based on z-scores and hierarchical logic. A total of 2,396 throwing samples from professional and non-professional athletes were collected. Results show that the system generates smooth personalized reference trajectories consistent with natural human movement. Case studies indicate that it can detect poor trunk stability, abnormal elbow displacement, and imbalanced velocity control, then provide targeted recommendations. The framework shifts dart evaluation from deviation from a uniform standard to deviation from an individual's optimal control range, improving personalization and interpretability for darts training and other high-precision target sports.
Read the full abstract ▾
All authors Zhantao Chen, Dongyi He, Jin Fang, Xi Chen, Yishuo Liu, Xiaozhen Zhong, Xuejun Hu
Machine Learning · Cross-listed from cs.CL
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao et al. (+3 more)
This paper introduces the first systematic evaluation framework for quantifying the quality and risks of papers written by modern coding
agents. While AI-driven paper writing has become a growing concern, rigorous evaluation of the quality and potential risks of AI-written papers remains limited, and a unified understanding of their reliability is still lacking. We introduce Paper Reconstruction Evaluation (PaperRecon), an evaluation framework in which an overview (overview.md) is created from an existing paper, after which an
agent generates a full paper based on the overview and minimal additional resources, and the result is subsequently compared against the original paper. PaperRecon disentangles the evaluation of the AI-written papers into two orthogonal dimensions, Presentation and
Hallucination, where Presentation is evaluated using a rubric and
Hallucination is assessed via agentic evaluation grounded in the original paper source. For evaluation, we introduce PaperWrite-Bench, a
benchmark of 51 papers from top-tier venues across diverse domains published after 2025. Our experiments reveal a clear trade-off: while both ClaudeCode and Codex improve with model advances, ClaudeCode achieves higher presentation quality at the cost of more than 10
hallucinations per paper on average, whereas Codex produces fewer
hallucinations but lower presentation quality. This work takes a first step toward establishing evaluation frameworks for AI-driven paper writing and improving the understanding of its risks within the research community.
Read the full abstract ▾
All authors Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao, Kenta Watanabe, Toshihiko Yamasaki, Kiyoharu Aizawa
Machine Learning · Cross-listed from cs.CV
Lightweight Prompt-Guided CLIP Adaptation for Monocular Depth Estimation
Reyhaneh Ahani Manghotay and Jie Liang
Leveraging the rich semantic features of
vision-
language models (VLMs) like CLIP for
monocular depth estimation tasks is a promising direction, yet often requires extensive fine-tuning or lacks
geometric precision. We present a parameter-efficient framework, named MoA-DepthCLIP, that adapts pretrained CLIP representations for
monocular depth estimation with minimal supervision. Our method integrates a lightweight Mixture-of-Adapters (MoA) module into the pretrained
Vision Transformer (ViT-B/32) backbone combined with selective fine-tuning of the final layers. This design enables spatially-aware adaptation, guided by a global semantic context vector and a hybrid prediction architecture that synergizes depth bin classification with direct regression. To enhance structural accuracy, we employ a composite loss function that enforces
geometric constraints. On the NYU Depth V2
benchmark, MoA-DepthCLIP achieves competitive results, significantly outperforming the DepthCLIP baseline by improving the $\delta_1$ accuracy from 0.390 to 0.745 and reducing the RMSE from 1.176 to 0.520. These results are achieved while requiring substantially few trainable parameters, demonstrating that lightweight,
prompt-guided MoA is a highly effective strategy for transferring VLM knowledge to fine-grained
monocular depth estimation tasks.
Read the full abstract ▾
Machine Learning
Reconsidering Dependency Networks from an Information Geometry Perspective
Kazuya Takabatake and Shotaro Akaho
Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their computational advantages over
Bayesian and Markov networks, the theoretical foundations of dependency networks remain incomplete, primarily because their model distributions – defined as stationary distributions of pseudo-Gibbs sampling – lack closed-form expressions. This paper develops an information-
geometric analysis of pseudo-Gibbs sampling, interpreting each sampling step as an m-projection onto a full conditional
manifold. Building on this interpretation, we introduce the full conditional divergence and derive an upper bound that characterizes the location of the stationary distribution in the space of probability distributions. We then reformulate both structure and parameter learning as optimization problems that decompose into independent subproblems for each node, and prove that the learned model distribution converges to the true underlying distribution as the number of training samples grows to infinity. Experiments confirm that the proposed upper bound is tight in practice.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.optics
Inverse Design of Optical Multilayer Thin Films using Robust Masked Diffusion Models
Jonas Schaible, Asena Karolin Özdemir, Charlotte Debus et al. (+5 more)
Inverse design of optical multilayer stacks seeks to infer layer materials, thicknesses, and ordering from a desired target spectrum. It is a long-standing challenge due to the large design space and non-unique solutions. We introduce OptoLlama, a masked
diffusion language model for inverse thin-film design from optical spectra. Representing multilayer stacks as sequences of material-thickness
tokens, OptoLlama conditions generation on reflectance, absorptance, and transmittance spectra and learns a probabilistic mapping from optical response to structure. Evaluated on a representative test set of 3,000 targets, OptoLlama reduces the mean absolute spectral error by 2.9-fold relative to a nearest-neighbor template baseline and by 3.45-fold relative to the state-of-the-art data-driven baseline, called OptoGPT. Case studies on designed and expert-defined targets show that the model reproduces characteristic spectral features and recovers physically meaningful stack motifs, including distributed Bragg reflectors. These results establish
diffusion-based sequence modeling as a powerful framework for inverse photonic design.
Read the full abstract ▾
All authors Jonas Schaible, Asena Karolin Özdemir, Charlotte Debus, Sven Burger, Achim Streit, Christiane Becker, Klaus Jäger, Markus Götz
Machine Learning
Approximating Pareto Frontiers in Stochastic Multi-Objective Optimization via Hashing and Randomization
Jinzhao Li, Nan Jiang and Yexiang Xue
Stochastic Multi-Objective Optimization (SMOO) is critical for decision-making trading off multiple potentially conflicting objectives in uncertain environments. SMOO aims at identifying the Pareto frontier, which contains all mutually non-dominating decisions. The problem is highly intractable due to the embedded probabilistic inference, such as computing the marginal, posterior probabilities, or expectations. Existing methods, such as scalarization, sample average approximation, and evolutionary
algorithms, either offer arbitrarily loose approximations or may incur prohibitive computational costs. We propose XOR-SMOO, a novel
algorithm that with probability $1-\delta$, obtains $\gamma$-approximate Pareto frontiers ($\gamma>1$) for SMOO by querying an SAT oracle poly-log times in $\gamma$ and $\delta$. A $\gamma$-approximate Pareto frontier is only below the true frontier by a fixed, multiplicative factor $\gamma$. Thus, XOR-SMOO solves highly intractable SMOO problems (\#P-hard) with only queries to SAT oracles while obtaining tight, constant factor approximation guarantees. Experiments on real-world road network strengthening and supply chain design problems demonstrate that XOR-SMOO outperforms several baselines in identifying Pareto frontiers that have higher objective values, better coverage of the optimal solutions, and the solutions found are more evenly distributed. Overall, XOR-SMOO significantly enhanced the practicality and reliability of SMOO solvers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
Yuheng Zhang, Mengfei Duan, Kunyu Peng et al. (+5 more)
3D semantic occupancy prediction is central to autonomous driving, yet current methods are vulnerable to long-tailed class bias and out-of-distribution (OOD) inputs, often overconfidently assigning anomalies to rare classes. We present ProOOD, a lightweight, plug-and-play method that couples prototype-guided refinement with training-free OOD scoring. ProOOD comprises (i) prototype-guided semantic imputation that fills occluded regions with class-consistent features, (ii) prototype-guided tail mining that strengthens rare-class representations to curb OOD absorption, and (iii) EchoOOD, which fuses local logit coherence with local and global prototype matching to produce reliable voxel-level OOD scores. Extensive experiments on five
datasets demonstrate that ProOOD achieves state-of-the-art performance on both in-distribution 3D occupancy prediction and OOD detection. On SemanticKITTI, it surpasses baselines by +3.57% mIoU overall and +24.80% tail-class mIoU; on VAA-KITTI, it improves AuPRCr by +19.34 points, with consistent gains across
benchmarks. These improvements yield more calibrated occupancy estimates and more reliable OOD detection in safety-critical urban driving. The source code is publicly available at https://github.com/7uHeng/ProOOD.
Read the full abstract ▾
All authors Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Di Wen, Danda Pani Paudel, Luc Van Gool, Kailun Yang
Machine Learning
Fast and Accurate Probing of In-Training LLMs' Downstream Performances
Zhichen Liu, Tianle Lun, Yang Xu et al. (+7 more)
The paradigm of scaling Large
Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive, therefore making the latency of LLM's in-training downstream performance evaluation unbearable. However, simple metrics like training loss (perplexity) are not always correlated with downstream performance, as sometimes their trends diverge from the actual task outcomes. This dilemma calls for a method that is computationally efficient and sufficiently accurate in measuring model capabilities. To address this challenge, we introduce a new in-training evaluation paradigm that uses a lightweight probe for monitoring downstream performance. The probes take the internal representations of LLM checkpoints (during training) as input and directly predict the checkpoint's performance on downstream tasks measured by success probability (i.e., pass@1). We design several probe architectures, validating their effectiveness using the OLMo3-7B's, OLMo3-32B's, and Apertus-8B's checkpoints across a diverse set of downstream tasks. The probes can accurately predict a checkpoint's performance (with avg. AUROC$>$0.75), have decent generalizability across checkpoints (earlier predicts later), and reduce the computation latency from $\sim$1 hr (using conventional generative evaluation method) to $\sim$3 min. In sum, this work presents a practical and scalable in-training downstream evaluation paradigm, enabling a more agile, informed, and efficient LLM development process.
Read the full abstract ▾
All authors Zhichen Liu, Tianle Lun, Yang Xu, Zhibin Wen, Hao An, Yulin Ou, Jianhui Xu, Hao Zhang, Wenyi Fang, Yang Zheng
Machine Learning
Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs
Philip Jordan and Maryam Kamgarpour
We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using finite action-observation windows. This induces a finite-state Markov decision process (MDP) over histories, referred to as the superstate MDP. Once a model of this superstate MDP is available, standard MDP
algorithms can be used to compute optimal policies, motivating the need for sample-efficient model estimation. Estimating the superstate MDP model is challenging because trajectories are generated by interaction with the original POMDP, creating a mismatch between the sampling process and target model. We propose a model estimation procedure for tabular POMDPs and analyze its sample complexity. Our analysis exploits a connection between filter stability and concentration inequalities for weakly dependent random variables. As a result, we obtain tight sample complexity guarantees for estimating the superstate MDP model from a single trajectory. Combined with value iteration, this yields approximately optimal finite-window policies for the POMDP.
Read the full abstract ▾
Machine Learning
Transfer learning for nonparametric Bayesian networks
Rafael Sojo, Pedro Larrañaga and Concha Bielza
This paper introduces two transfer learning methodologies for estimating nonparametric
Bayesian networks under scarce data. We propose two
algorithms, a constraint-based structure learning method, called PC-stable-transfer learning (PCS-TL), and a score-based method, called hill climbing transfer learning (HC-TL). We also define particular metrics to tackle the negative transfer problem in each of them, a situation in which transfer learning has a negative impact on the model's performance. Then, for the parameters, we propose a log-linear pooling approach. For the evaluation, we learn kernel density estimation
Bayesian networks, a type of nonparametric
Bayesian network, and compare their transfer learning performance with the models alone. To do so, we sample data from small, medium and large-sized synthetic networks and
datasets from the UCI Machine Learning repository. Then, we add noise and modifications to these
datasets to test their ability to avoid negative transfer. To conclude, we perform a Friedman test with a Bergmann-Hommel post-hoc analysis to show statistical proof of the enhanced experimental behavior of our methods. Thus, PCS-TL and HC-TL demonstrate to be reliable
algorithms for improving the learning performance of a nonparametric
Bayesian network with scarce data, which in real industrial environments implies a reduction in the required time to deploy the network.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding
Yiheng Wang, Lichen Zhu, Yueqian Lin et al. (+4 more)
Multimodal Large
Language Models (MLLMs) have shown strong performance on
video question answering, but their application to long-form
videos is constrained by limited context length and computational cost, making keyframe sampling essential. Existing approaches typically rely on semantic relevance or reinforcement learning, which either fail to capture evidential clues or suffer from inefficient combinatorial optimization. In this work, we propose an evidence-driven keyframe sampling framework motivated by an information-theoretic perspective. We consider maximizing the conditional mutual information between the selected frames and the answer given the query as an idealized objective, and use a modular singleton-gain surrogate to motivate a tractable frame-wise selection criterion. Guided by this motivation, we train a query-conditioned evidence scoring network using annotated answer-supporting segments. A contrastive objective encourages greater aggregate score mass on frames from evidence regions than on background frames, providing a practical evidence-based criterion beyond semantic similarity. Experiments on long-form
video understanding
benchmarks show that our method consistently outperforms prior sampling strategies under comparable frame budgets. With Qwen2.5-VL-7B under the same 32-frame budget, our method improves over uniform sampling by 10.1 points on LVBench and 4.4 points on the long-
video subset of VideoMME.
Read the full abstract ▾
All authors Yiheng Wang, Lichen Zhu, Yueqian Lin, Yudong Liu, Jingyang Zhang, Hai "Helen" Li, Yiran Chen
Machine Learning
EmbedPart: Embedding-Driven Graph Partitioning for Scalable Graph Neural Network Training
Nikolai Merkel, Ruben Mayer, Volker Markl et al. (+1 more)
Graph Neural Networks (GNNs) are widely used for learning on graph-structured data, but scaling GNN training to massive graphs remains challenging. To enable scalable distributed training, graphs are divided into smaller partitions that are distributed across multiple machines such that inter-machine communication is minimized and computational load is balanced. In practice, existing partitioning approaches face a fundamental trade-off between partitioning overhead and partitioning quality. We propose EmbedPart, an
embedding-driven partitioning approach that achieves both speed and quality. Instead of operating directly on irregular graph structures, EmbedPart leverages node
embeddings produced during the actual GNN training workload and clusters these dense
embeddings to derive a partitioning. EmbedPart achieves more than 100x speedup over Metis while maintaining competitive partitioning quality and accelerating distributed GNN training. Moreover, EmbedPart naturally supports graph updates and fast repartitioning, and can be applied to graph reordering to improve data locality and accelerate single-machine GNN training. By shifting partitioning from irregular graph structures to dense
embeddings, EmbedPart enables scalable and high-quality graph data optimization.
Read the full abstract ▾
All authors Nikolai Merkel, Ruben Mayer, Volker Markl, Hans-Arno Jacobsen
Machine Learning · Cross-listed from astro-ph.IM
Focal plane wavefront control with model-based reinforcement learning
Jalo Nousiainen, Iremsu Taskin, Markus Kasper et al. (+2 more)
The direct imaging of potentially habitable
exoplanets is one
prime science case for high-contrast imaging instruments on extremely large
telescopes. Most such
exoplanets orbit close to their host
stars, where their observation is limited by fast-moving atmospheric speckles and quasi-static non-common-path aberrations (NCPA). Conventional NCPA correction methods often use mechanical mirror probes, which compromise performance during operation. This work presents machine-learning-based NCPA control methods that automatically detect and correct both dynamic and static NCPA errors by leveraging sequential phase diversity. We extend previous work in reinforcement learning for AO to focal plane control. A new model-based RL
algorithm, Policy Optimization for NCPAs (PO4NCPA), interprets the focal-plane image as input data and, through sequential phase diversity, determines phase corrections that optimize both non-coronagraphic and post-coronagraphic PSFs without prior system knowledge. Further, we demonstrate the effectiveness of this approach by numerically simulating static NCPA errors on a ground-based
telescope and an infrared imager affected by water-vapor-induced seeing (dynamic NCPAs). Simulations show that PO4NCPA robustly compensates static and dynamic NCPAs. In static cases, it achieves near-optimal focal-plane light suppression with a coronagraph and near-optimal Strehl without one. With dynamics NCPA, it matches the performance of the modal least-squares reconstruction combined with a 1-step delay integrator in these metrics. The method remains effective for the ELT pupil, vector
vortex coronagraph, and under
photon and background noise. PO4NCPA is model-free and can be directly applied to standard imaging as well as to any coronagraph. Its sub-millisecond inference times and performance also make it suitable for real-time low-order correction of atmospheric
turbulence beyond HCI.
Read the full abstract ▾
All authors Jalo Nousiainen, Iremsu Taskin, Markus Kasper, Gilles Orban De Xivry, Olivier Absil
Machine Learning · Cross-listed from stat.ML
Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
Yi Cao, Zexun Chen, Lin William Cong et al. (+1 more)
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable constraints within flexible neural function approximation. SKINNs jointly estimate neural network parameters and economically meaningful structural parameters in a single optimization problem, enforcing theoretical consistency not only on observed data but over a broader input domain through collocation, and therefore nesting approaches such as functional GMM,
Bayesian updating, transfer learning, PINNs, and surrogate modeling. SKINNs define a class of M-
estimators that are consistent and asymptotically normal with root-N convergence, sandwich covariance, and recovery of pseudo-true parameters under misspecification. We establish identification of structural parameters under joint flexibility, derive generalization and target-risk bounds under distributional shift in a convex proxy, and provide a restricted-optimal characterization of the weighting parameter that governs the bias-variance tradeoff. In an illustrative financial application to option pricing, SKINNs improve out-of-sample valuation and hedging performance, particularly at longer horizons and during high-
volatility regimes, while recovering economically interpretable structural parameters with improved stability relative to conventional calibration. More broadly, SKINNs provide a general econometric framework for combining model-based
reasoning with high-dimensional, data-driven estimation.
Read the full abstract ▾
All authors Yi Cao, Zexun Chen, Lin William Cong, Heqing Shi
Machine Learning · Cross-listed from cs.CR
Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang et al. (+19 more)
We study whether phone-use
agents respect
privacy while completing benign mobile tasks. This question has remained hard to answer because
privacy-compliant behavior is not operationalized for phone-use
agents, and ordinary apps do not reveal exactly what data
agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for
privacy behavior in mobile
agents. We operationalize
privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled
memory through a minimal
privacy contract, iMy, and pair it with instrumented mock apps plus rule-based
auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success,
privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and
privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization:
agents still fill optional personal entries that the task does not require. These results show that
privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use
agents. All code, mock apps, and
agent trajectories are publicly available at~ https://github.com/FreedomIntelligence/MyPhoneBench.
Read the full abstract ▾
All authors Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang, Yiduo Guo, Ziniu Li, Chenxin Li, Jingyuan Hu, Shunian Chen, Tongxu Luo, Jiaxi Bi, Zeyu Qin, Shaobo Wang, Xin Lai, Pengyuan Lyu, Junyi Li, Can Xu, Chengquan Zhang, Han Hu, Ming Yan, Benyou Wang
Machine Learning
Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization
Ruijie Hao, Longfei Zhang, Yang Dai et al. (+3 more)
Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL
algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which constrains the policy from capturing
multimodal distributions, making it difficult to cover the full range of optimal solutions in multi-solution problems, and the return is reduced to a mean value, losing its
multimodal nature and thus providing insufficient guidance for policy updates. In response to these problems, we propose a RL
algorithm termed flow-based policy with distributional RL (FP-DRL). This
algorithm models the policy using flow matching, which offers both computational efficiency and the capacity to fit complex distributions. Additionally, it employs a distributional RL approach to model and optimize the entire return distribution, thereby more effectively guiding
multimodal policy updates and improving
agent performance. Experimental trails on MuJoCo
benchmarks demonstrate that the FP-DRL
algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting superior representation capability of the flow policy.
Read the full abstract ▾
All authors Ruijie Hao, Longfei Zhang, Yang Dai, Yang Ma, Xingxing Liang, Guangquan Cheng
Machine Learning · Cross-listed from cs.DS
Rapid mixing in positively weighted restricted Boltzmann machines
Weiming Feng, Heng Guo and Minji Yang
We show polylogarithmic mixing time bounds for the alternating-scan sampler for positively weighted restricted Boltzmann machines. This is done via analysing the same chain and the Glauber dynamics for
ferromagnetic two-
spin systems, where we obtain new mixing time bounds up to the critical thresholds.
Read the full abstract ▾
Machine Learning
Differentially Private Manifold Denoising
Jiaqi Wu, Yiqing Sun and Zhigang Yao
We introduce a differentially private
manifold denoising framework that allows users to exploit sensitive reference
datasets to correct noisy, non-private query points without compromising
privacy. The method follows an iterative procedure that (i) privately estimates local means and tangent geometry using the reference data under calibrated sensitivity, (ii) projects query points along the privately estimated subspace toward the local mean via corrective steps at each iteration, and (iii) performs rigorous
privacy accounting across iterations and queries using $(\varepsilon,\delta)$-differential
privacy (DP). Conceptually, this framework brings differential
privacy to
manifold methods, retaining sufficient
geometric signal for downstream tasks such as
embedding, clustering, and visualization, while providing formal DP guarantees for the reference data. Practically, the procedure is modular and scalable, separating DP-protected local geometry (means and tangents) from budgeted query-point updates, with a simple scheduler allocating
privacy budget across iterations and queries. Under standard assumptions on
manifold regularity, sampling density, and measurement noise, we establish high-probability utility guarantees showing that corrected queries converge toward the
manifold at a non-asymptotic rate governed by sample size, noise level, bandwidth, and the
privacy budget. Simulations and case studies demonstrate accurate signal recovery under moderate
privacy budgets, illustrating clear utility-
privacy trade-offs and providing a deployable DP component for
manifold-based workflows in regulated environments without reengineering
privacy systems.
Read the full abstract ▾
Machine Learning
WARP: Guaranteed Inner-Layer Repair of NLP Transformers
Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen et al. (+3 more)
Transformer-based NLP models remain vulnerable to
adversarial perturbations, yet existing repair methods face a fundamental trade-off: gradient-based approaches offer flexibility but lack verifiability and often overfit; methods that do provide repair guarantees are restricted to the final layer or small networks, significantly limiting the parameter search space available for repair. We present WARP (Weight-Adjusted Repair with Provability), a constraint-based repair framework that extends repair beyond the last layer of
Transformer models. WARP formulates repair as a convex quadratic program derived from a first-order linearization of the logit gap, enabling tractable optimization over a high-dimensional parameter space. Under the condition that the first-order approximation holds, this formulation induces three per-sample guarantees: (i) a positive margin constraint ensuring correct classification on repaired inputs, (ii) preservation constraints over a designated remain set, and (iii) a certified robustness radius derived from Lipschitz continuity. To ensure feasibility across varying model architectures, we introduce a sensitivity-based preprocessing step that conditions the optimization landscape accordingly. We further show that the iterative optimization procedure converges to solutions satisfying all repair constraints under mild assumptions. Empirical evaluation on encoder-only
Transformers with varying layer architectures validates that these guarantees hold in practice while improving robustness to
adversarial inputs. Our results demonstrate that guaranteed, generalizable
Transformer repair is achievable through principled constraint-based optimization.
Read the full abstract ▾
All authors Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen, Yan-Ru Chen, Yi-Ling Chang, Fang Yu
Machine Learning · Cross-listed from quant-ph
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
Gilhan Kim and Daniel K. Park
Energy-based models provide a natural bridge between statistical physics and machine learning by representing data through structured energy landscapes. Boltzmann machines are a particularly compelling class of such models for capturing complex interactions among latent variables, but their use in modern generative learning has been limited by the classical intractability of sampling from general (non-restricted) Boltzmann distributions. Here we develop a
quantum-annealing-based framework that enables variational autoencoders with general Boltzmann priors. The framework employs three complementary annealing modes tailored to different stages of learning and deployment: diabatic
quantum annealing provides unbiased Boltzmann samples for efficient training, slower annealing concentrates samples near low-energy configurations of the learned prior for unconditional generation, and conditional annealing with external fields steers the learned energy landscape toward attribute-specific regions for conditional generation and semantic editing. Using up to 2000
qubits on a D-Wave Advantage2 processor, we demonstrate stable training and high-quality generation on MNIST, Fashion-MNIST, and CelebA, achieving faster convergence and lower reconstruction loss than a Gaussian-prior VAE with the same encoder-decoder architecture. Beyond generation, the learned energy function provides out-of-distribution detection signals that add discriminative power beyond reconstruction loss. We demonstrate that these scores separate in-distribution samples from held-out digit classes in one-class MNIST experiments and improve the detection of
market regime shifts in financial data. These results establish
quantum annealing as a practical and controllable physical mechanism for energy-based representation learning and generative modeling beyond the reach of tractable classical approaches.
Read the full abstract ▾