Machine Learning · Cross-listed from cs.RO
TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
Matthew M. Hong, Jesse Zhang, Anusha Nagabandi et al. (+1 more)
Fine-tuning pre-trained
robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration. We present a unified framework that enables the exploration necessary to enable efficient
robot policy finetuning by bridging BC pre-training and RL fine-tuning. Our pre-training method, Context-Smoothed Pre-training (CSP), injects forward-
diffusion noise into policy inputs, creating a continuum between precise imitation and broad action coverage. We then fine-tune pre-trained policies via Timestep-Modulated Reinforcement Learning (TMRL), which trains the
agent to dynamically adjust this conditioning during fine-tuning by modulating the
diffusion timestep, granting explicit control over exploration. Integrating seamlessly with arbitrary policy inputs, e.g., states, 3D point clouds, or image-based VLA policies, we show that TMRL improves RL fine-tuning sample efficiency. Notably, TMRL enables successful real-world fine-tuning on complex manipulation tasks in under one hour.
Videos and code available at https://weirdlabuw.github.io/tmrl/.
Read the full abstract ▾
All authors Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta
Machine Learning · Cross-listed from stat.ML
Optimal Policy Learning under Budget and Coverage Constraints
Giovanni Cerulli
We study optimal policy learning under combined budget and minimum coverage constraints. We show that the problem admits a knapsack-type structure and that the optimal policy can be characterized by an affine threshold rule involving both budget and coverage shadow prices. We establish that the linear programming relaxation of the combinatorial solution has an O(1) integrality gap, implying asymptotic equivalence with the optimal discrete allocation. Building on this result, we analyze two implementable approaches: a Greedy-Lagrangian (GLC) and a rank-and-cut (RC)
algorithm. We show that the GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples. By contrast, RC is approximately optimal whenever the coverage constraint is slack or costs are homogeneous, while misallocation arises only when cost heterogeneity interacts with a binding coverage constraint. Monte Carlo evidence supports these findings.
Read the full abstract ▾
Machine Learning
No More, No Less: Task Alignment in Terminal Agents
Sina Mavali, David Pape, Jonathan Evertz et al. (+5 more)
Terminal
agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user
prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing
benchmarks do not capture this ability. An
agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task
Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier
agents reveals a systematic gap between task capability and task
alignment. The strongest Terminal-Bench
agent achieves high task completion but low task
alignment on TAB. Evaluating six
prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned
agents require selective use of environmental instructions rather than blanket acceptance or rejection.
Read the full abstract ▾
All authors Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini, Devansh Srivastav, Thorsten Eisenhofer, Sahar Abdelnabi, Lea Schönherr
Machine Learning
Intrinsic Vicarious Conditioning for Deep Reinforcement Learning
Rodney A Sanchez, Ferat Sahin, Alex Ororbia et al. (+1 more)
Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our
agents' capacity by restricting how they learn from the environment as well as from others. Off-policy or learn-by-example methods can learn from demonstrators' representations, but they require access to the demonstrating
agent's policies or their reward functions. Our work overcomes this direct sampling limitation by introducing vicarious conditioning as an intrinsic reward mechanism. We draw from psychological and biological literature to provide a foundation for vicarious conditioning and use
memory-based methods to implement its four steps:
attention, retention, reproduction, and reinforcement. Crucially, our vicarious conditioning paradigms support low-shot learning and do not require the demonstrator
agent's policy nor its reward functions. We evaluate our approach in the MiniWorld Sidewalk environment, one of the few public environments that features a non-descriptive terminal condition (no reward provided upon
agent death), and extend it to Box2D's CarRacing environment. Our results across both environments demonstrate that vicarious conditioning enables longer episode lengths by discouraging the
agent from non-descriptive terminal conditions and guiding the
agent toward desirable states. Overall, this work emulates a cognitively-plausible learning paradigm better suited to problems such as single-life learning or continual learning.
Read the full abstract ▾
All authors Rodney A Sanchez, Ferat Sahin, Alex Ororbia, Jamison Heard
Machine Learning · Cross-listed from cs.CV
TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion
Mohammad Khoshkdahan and Alexey Vinel
Safe autonomous
agents and mobile
robots need fast real time 3D perception, especially for vulnerable road users (VRUs) such as pedestrians. We introduce a new bird's eye view (BEV) encoding, which maps the full 3D
LiDAR point cloud into a light-weight 2D BEV tensor with three height bands. We explicitly reformulate 3D detection as a 2D detection problem and then reconstruct 3D boxes from the BEV outputs. A single network detects cars, pedestrians, and cyclists in one pass. The backbone uses area
attention at deep stages, a hierarchical bidirectional neck over P1 to P4 fuses context and detail, and the head predicts oriented boxes with distribution focal learning for side offsets and a rotated IoU loss. Training applies a small vertical re bin and a mild reflectance jitter in channel space to resist memorization. We use an interquartile range (IQR) filter to remove noisy and outlier
LiDAR points during 3D reconstruction. On KITTI
dataset, TriBand-BEV attains 58.7/52.6/47.2 pedestrian BEV AP(%) for easy, moderate, and hard at 49 FPS on a single consumer GPU, surpassing Complex-YOLO, with gains of +12.6%, +7.5%, and +3.1%. Qualitative scenes show stable detection under occlusion. The pipeline is compact and ready for real time robotic deployment. Our source code is publicly available on GitHub.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
Julian Rodemann, Alexander Marquard, Thomas Augustin et al. (+1 more)
Approximate
Bayesian inference typically revolves around computing the posterior parameter distribution. In practice, however, the main object of interest is often a model's predictions rather than its parameters. In this work, we propose to bypass the parameter posterior and focus directly on approximating the posterior predictive distribution. We achieve this by drawing inspiration from self-training within self-supervised and semi-supervised learning. Essentially, we quantify a
Bayesian model's predictive uncertainty by refitting on self-predicted data. The idea is strikingly simple: If a model assigns high likelihood to self-predicted data, these predictions are of low uncertainty, and vice versa. This yields a deterministic, sampling-free approximation of the posterior predictive. The modular structure of our Self-Supervised Laplace Approximation (SSLA) further allows us to plug in different prior specifications, enabling classical
Bayesian sensitivity (w.r.t. prior choice) analysis. In order to bypass expensive refitting, we further introduce an approximate version of SSLA, called ASSLA. We study (A)SSLA both theoretically and empirically in regression models ranging from
Bayesian linear models to
Bayesian neural networks. Across a wide array of regression tasks with simulated and real-world
datasets, our methods outperform classical Laplace approximations in predictive calibration while remaining computationally efficient.
Read the full abstract ▾
All authors Julian Rodemann, Alexander Marquard, Thomas Augustin, Michele Caprio
Machine Learning
Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
Arijit Sehanobish and Charles Lovering
We study the parameter placement problem: given a fixed budget of $k$ trainable entries within the B
matrix of a LoRA adapter (A frozen), does the choice of which $k$ matter? Under supervised fine-tuning, random and informed subsets achieve comparable performance. Under GRPO on base models, random placement fails to improve over the base model, while gradient-informed placement recovers standard LoRA accuracy. This regime dependence traces to gradient structure: SFT gradients are low-rank and directionally stable, so any subset accumulates coherent updates; GRPO gradients are high-rank and near-orthogonal across steps, so only elements with consistently signed gradients retain the learning signal. Our scoring procedure identifies these critical parameters in under 10 seconds at less than 0.5% of training cost. Selected parameters concentrate on residual-stream-writing projections (V, O, Down), stable across model families and scales (1.5B - 8B).
Read the full abstract ▾
Machine Learning
Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policies
Asad Bakija, Florent De Geeter, Julien Brandoit et al. (+2 more)
In partially observable reinforcement learning (RL), a decision often depends on a cue seen many steps earlier, and training at such horizons is costly. Ideally, a policy trained on short horizons would remain optimal at arbitrarily long ones, making the training horizon a matter of convenience. We formalize this property as delay-horizon independence (DHI): optimality at every horizon, at a
memory, computation and precision cost that is bounded in the horizon. We study
agents that carry the cue in a recurrent
memory of fixed size, whose cost does not grow with the delay. This paper characterizes DHI through the dynamics of that
memory, in theory and on
benchmarks. Although quantified over all horizons, DHI reduces to a property of a single map: a recurrent policy is DHI if and only if it admits a continuous readout of the
memory, invariant under the idle dynamics and separating the cues. Monostable
memory then precludes DHI at any parameter values, whereas multistable
memory enables it. Monostability covers all contracting affine recurrences, hence state space models and gated linear recurrent neural networks (RNNs). Under arbitrarily small perturbations of the idle dynamics, multistability is the only mechanism supporting DHI at bounded
memory. On the T-maze, the effective horizon of monostable models resists hyperparameter search: selected horizons fall short by up to $745\times$ when retrained. Multistable models trained on short horizons stay optimal up to $10^6$, on the T-maze and on MiniGrid. Current parallelizable RNNs thus trade horizon independence for scalability: parallelizable multistable architectures are the direction this points to.
Read the full abstract ▾
All authors Asad Bakija, Florent De Geeter, Julien Brandoit, Pierre Sacré, Guillaume Drion
Machine Learning
Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea et al. (+4 more)
Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings. Recent TSFM architectures, such as Chronos-2 and TabPFN-TS, aim to integrate
covariates. In this paper, we design controlled experiments based on simple target-
covariate relationships to assess this integration capability. Our results show that TabPFN-TS captures these relationships more effectively than Chronos-2, especially for short horizons, suggesting that the strong
benchmark performance of Chronos-2 does not automatically translate into optimal modeling of simple
covariate-target dependencies.
Read the full abstract ▾
All authors Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea, Etienne Le Naour, Adrien Petralia, Tahar Nabil, Themis Palpanas
Machine Learning
Overtrained, Not Misaligned
Joel Schreiber and Ariel Goldstein
Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date, reproducing the original GPT-4o finding and expanding to 12 open-source models across 4 families (Llama, Qwen, DeepSeek, GPT-OSS) ranging from 8B to 671B parameters, evaluating over one million model responses with multiple random seeds. We find that EM replicates in GPT-4o but is far from universal: only 2 of 12 open-source models (17%) exhibit consistent EM across seeds, with a significant correlation between model size and EM susceptibility. Through checkpoint-level analysis during fine-tuning, we demonstrate that EM emerges late in training, distinct from and subsequent to near convergence of the primary task, suggesting EM emerges from continued training past task convergence. This yields practical mitigations: early stopping eliminates EM while retaining an average of 93% of task performance, and careful learning rate selection further minimizes risk. Cross-domain validation on medical fine-tuning confirms these patterns generalize: the size-EM correlation strengthens (r = 0.90), and overgeneralization to untruthfulness remains avoidable via early stopping in 67% of cases, though semantically proximate training domains produce less separable misalignment. As LLMs become increasingly integrated into real-world systems, fine-tuning and reinforcement learning remain the primary methods for adapting model behavior. Our findings demonstrate that with proper training practices, EM can be avoided, reframing it from an unforeseen fine-tuning risk to an avoidable training artifact.
Read the full abstract ▾
Machine Learning
A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
Haibo Chen, Xin Wang, Jiaheng Chao et al. (+2 more)
Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large
Language Models (LLMs) through
alignment instruction tuning has become a mainstream paradigm for constructing Graph
Language Models (GLMs), combining the generalization ability of LLMs with the structural modeling capacity of GNNs. However, existing GLMs that adopt GNNs as graph encoders largely overlook the problem of aligning GNN-encoded representations across domains and tasks with the LLM
token space to obtain unified graph
tokens, thereby limiting their ability to generalize across diverse graph data. To bridge this gap, we aim to incorporate a multi-domain, multi-task GNN encoder into GLMs and align its representations with LLMs to enable multi-domain, multi-task graph
alignment instruction tuning. This
alignment problem remains underexplored and poses two key challenges: 1) learning GNN-encoded representations that are simultaneously generalizable across domains and tasks and well aligned with textual semantics is difficult, due to substantial variations in graph structures, feature distributions, and supervision signals, together with the lack of textual-semantic
alignment guidance in task-specific GNN training; 2) diverse graph data and task-specific instructions can exhibit different degrees of compatibility with the LLM
token space during instruction tuning, leading to varying
alignment difficulty and rendering a fixed
alignment strategy suboptimal. To tackle these challenges, we propose UniGraphLM, a Unified Graph
Language Model that incorporates a multi-domain, multi-task GNN encoder to learn generalizable graph representations aligned with textual semantics, and then adaptively aligns these representations with the LLM.
Read the full abstract ▾
All authors Haibo Chen, Xin Wang, Jiaheng Chao, Ling Feng, Wenwu Zhu
Machine Learning
ECTO: Exogenous-Conditioned Temporal Operator for Ultra-Short-Term Wind Power Forecasting
Cao Yuan and Junjun Wang
Accurate ultra-short-term wind power
forecasting is critical for grid dispatch and reserve management, yet remains challenging due to the non-stationary, condition-dependent nature of wind generation. Meteorological exogenous variables carry substantial predictive information, but the most informative variable combination varies across sites, operating conditions, and prediction horizons. Existing deep learning approaches either treat exogenous inputs as generic auxiliary channels through uniform mixing or soft gating, or rely on fixed preprocessing steps such as PCA, without exploiting the physical structure of meteorological variables. We propose ECTO (Exogenous-Conditioned Temporal Operator), a unified framework that decomposes exogenous variable modeling into two complementary modules. Physically-Grounded Variable Selection (PGVS) performs hierarchical, group-aware sparse selection over exogenous variables using a domain-informed physical prior and sparsemax activations, producing a compact, condition-adaptive exogenous context. Exogenous-Conditioned Regime Refinement (ECRR) routes the forecast through learned regime experts that apply gain–bias calibration and horizon-specific corrections via a mixture-of-experts paradigm. Experiments on three wind farms spanning different climates, capacities (66–200 MW), and exogenous dimensions (11–13 variables) demonstrate that ECTO achieves the lowest MSE across all sites, with relative improvements over the strongest baseline ranging from 2.2% to 5.2%, widening to 8.6% at the longer prediction horizon ($H=32$). Ablation analysis confirms that each exogenous-related component contributes positively (PGVS +1.84%, ECRR +2.86%), and interpretability analysis reveals that PGVS learns physically meaningful, site-specific variable selection patterns, while ECRR converges to well-separated calibration strategies consistent across sites.
Read the full abstract ▾
Machine Learning
Fair Conformal Classification via Learning Representation-Based Groups
Senrong Xu, Yanke Zhou, Yuhao Tan et al. (+5 more)
Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to account for algorithmic biases, thereby undermining
fairness and trust. This paper introduces a fair conformal inference framework for classification tasks. The proposed method constructs prediction sets that guarantee conditional coverage on adaptively identified subgroups, which can be implicitly defined through nonlinear feature combinations. By balancing effectiveness and efficiency in producing compact, informative prediction sets and ensuring adaptive equalized coverage across unfairly treated subgroups, our approach paves a practical pathway toward trustworthy machine learning. Extensive experiments on both synthetic and real-world
datasets demonstrate the effectiveness of the framework.
Read the full abstract ▾
All authors Senrong Xu, Yanke Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Taolue Chen, Feng Xu, Xiaoxing Ma
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Probing Non-Equilibrium Grain Boundary Dynamics with XPCS and Domain-Adaptive Machine Learning
Mouyang Cheng, Bowen Yu, Chu-Liang Fu et al. (+14 more)
Grain-boundary (GB) dynamics control the stability, mechanical, and functional response of nanocrystalline materials, but direct experimental access to their slow non-
equilibrium motion has been limited. Here we establish X-ray
photon correlation spectroscopy (XPCS), combined with domain-adaptive machine learning, as a quantitative probe of GB dynamics. Temperature- and grain-size-dependent two-time XPCS measurements in nanocrystalline silicon reveal pronounced departures from time-translation invariance, showing that GB relaxation can remain far from
equilibrium over experimental timescales. However, direct extraction of quantitative physical information from these high-dimensional, noisy fluctuation maps faces a significant challenge. To overcome this barrier, we develop a semi-supervised learning framework that transfers physical parameter labels from continuum simulations to unlabeled experimental XPCS maps through domain-adaptive representation
alignment. This AI-augmented approach enables the extraction of key kinetic parameters, including bulk diffusivity, GB stiffness, and effective GB concentration, directly from experimental XPCS measurements. Our results show how machine learning can transform indirect fluctuation signals into quantitative materials dynamics, providing a general route to study non-
equilibrium defect motion in solids.
Read the full abstract ▾
All authors Mouyang Cheng, Bowen Yu, Chu-Liang Fu, Nina Andrejevic, Matthias T. Agne, Riley Hanus, Qiwei Wan, Nathan C. Drucker, Thanh Nguyen, Andrei Fluerasu, Lutz Wiegart, Xiaoqian M Chen, Daniel Pajerowski, Yongqiang Cheng, Joshua J Turner, G. Jeffrey Snyder, Mingda Li
Machine Learning · Cross-listed from stat.ML
Information-Theoretic Generalization Bounds for Sequential Decision Making
Futoshi Futami and Masahiro Fujisawa
Information-theoretic generalization bounds based on the supersample construction are a central tool for
algorithm-dependent generalization analysis in the batch i.i.d. setting. However, existing supersample conditional mutual information (CMI) bounds do not directly apply to sequential decision-making problems such as online learning, streaming active learning, and bandits, where data are revealed adaptively and the learner evolves along a causal trajectory. To address this limitation, we develop a sequential supersample framework that separates the learner filtration from a proof-side enlargement used for ghost-coordinate comparisons. Under a row-wise exchangeability assumption, the sequential generalization gap is controlled by sequential CMI, a sum of roundwise selector–loss information terms. We also establish a Bernstein-type refinement that yields faster rates under suitable variance conditions. The resulting bounds specialize to online learning, streaming active learning with importance weighting, and
stochastic multi-armed bandits.
Read the full abstract ▾
Machine Learning
DriftXpress: Faster Drifting Models via Projected RKHS Fields
Ali Falahati, Elliot Creager, Gautam Kamath et al. (+1 more)
Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in
diffusion models with a single evaluation of a generator. However, this creates a different trade-off: drifting reduces inference cost by moving much of the computation into training. We introduce DriftXpress, an accelerated formulation of drifting models based on projected RKHS fields. DriftXpress approximates the drifting kernel in a low-rank feature space. This preserves the attraction-repulsion structure of the original drifting field while reducing the cost of field evaluation. Across image-generation
benchmarks, DriftXpress achieves comparable FID to standard drifting while reducing wall-clock training cost. These results show that the training-inference trade-off of drifting models can be pushed further without giving up their one-step inference advantage.
Read the full abstract ▾
All authors Ali Falahati, Elliot Creager, Gautam Kamath, Shubhankar Mohapatra
Machine Learning · Cross-listed from cs.AI
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary et al. (+14 more)
World models enable
agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dynamics are often defined by tenant-specific business logic that varies across deployments and evolves over time, making models trained on historical transitions brittle under deployment shift. We ask a question the world-models literature has not addressed: when the rules can be read at inference time, does an
agent still need to learn them? We argue, and demonstrate empirically, that in settings where transition dynamics are configurable and readable, runtime discovery complements offline training by grounding predictions in the active system instance. We propose enterprise discovery
agents, which recover relevant transition dynamics at runtime by reading the system's configuration rather than relying solely on internalized representations. We introduce CascadeBench, a
reasoning-focused
benchmark for enterprise cascade prediction that adopts the evaluation methodology of World of Workflows on diverse synthetic environments, and use it together with deployment-shift evaluation to show that offline-trained world models can perform well in-distribution but degrade as dynamics change, whereas discovery-based
agents are more robust under shift by grounding their predictions in the current instance. Our findings suggest that, in configurable enterprise environments,
agents should not rely solely on fixed internalized dynamics, but should incorporate mechanisms for discovering relevant transition logic at runtime.
Read the full abstract ▾
All authors Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary, Surajit Dasgupta, Sravan Ramachandran, Aakash Bhagat, Shruthan Radhakrishna, Pulkit Pattnaik, Johan Obando-Ceron, Shiva Krishna Reddy Malay, Sagar Davasam, Seganrasan Subramanian, Vipul Mittal, Sridhar Krishna Nemala, Christopher Pal, Srinivas Sunkara, Sai Rajeswar
Machine Learning
Multi-Task Representation Learning for Conservative Linear Bandits
Jiabin Lin and Shana Moothedath
This paper presents the Constrained Multi-Task Representation Learning (CMTRL) framework for linear bandits. We consider T linear bandit tasks in a d dimensional space, which share a common low-dimensional representation of dimension r, where r is much smaller than the minimum of d and T. Furthermore, tasks are constrained so that only actions meeting specific safety or performance requirements are allowed, referred to as conservative (safe) bandits. We introduce a novel
algorithm, Safe-Alternating projected Gradient Descent and minimization (Safe-AltGDmin), to recover a low-rank feature
matrix while satisfying the given constraints. Building on this
algorithm, we propose a multi-task representation learning framework for conservative linear bandits and establish theoretical guarantees for its regret and sample complexity bounds. We presented experiments and compared the performance of our
algorithm with
benchmark algorithms.
Read the full abstract ▾
Machine Learning
Expected Batch Optimal Transport Plans and Consequences for Flow Matching
Samuel Boïté, Julie Delon and Kimia Nadjahi
Solving optimal transport (OT) on random minibatches is a common surrogate for exact OT in large-scale learning. In flow matching (FM), this surrogate is used to obtain OT-like couplings that can straighten probability paths and reduce numerical integration cost. Yet, the population-level coupling induced by repeated minibatch OT remains only partially understood. We formalize this coupling as the expected batch OT plan $\overline{\pi}_{k}$, obtained by averaging empirical OT plans over independent minibatches of size $k$. We then establish its large-batch consistency and, in the semidiscrete case relevant to generative modeling, derive rates for both the transport-cost bias and the convergence of $\overline{\pi}_{k}$ to the OT plan. For FM, this yields a population coupling whose induced velocity field is regular enough to define a unique flow from the source to the discrete target. We finally quantify how OT batch size interacts with numerical integration in a tractable two-atom model and in synthetic and image experiments.
Read the full abstract ▾
Machine Learning
Lower bounds for one-layer transformers that compute parity
Daniel Hsu
This note shows that no self-
attention layer post-processed by a rational function can sign-represent the parity function unless the product of the number of heads and the degree of the post-processing function grows linearly with the input length. Combining this lower bound with rational approximation of ReLU networks yields a margin-dependent extension for self-
attention layers post-processed by ReLU networks.
Read the full abstract ▾
Machine Learning
On What We Can Learn from Low-Resolution Data
Theresa Dahl Frehr, Niels Henrik Pontoppidan, Hiba Nassar et al. (+1 more)
Artificial intelligence systems typically rely on large, centrally collected
datasets, a premise that does not hold in many real-world domains such as healthcare and public institutions. In these settings, data sharing is often constrained by storage,
privacy, or resource limitations. For example, small wearable devices may lack the bandwidth or energy capacity needed to store and transmit high-resolution data, leading to aggregation during data collection and thus a loss of information. As a result,
datasets collected from different sources may consist of a mixture of high- and low-resolution samples. Despite the prevalence of this setting, it remains unclear how informative low-resolution data is when models are ultimately evaluated on high-resolution inputs. We provide a theoretical analysis based on the Kullback-Leibler divergence that characterises how the influence of a datapoint changes with resolution, and derive bounds that relate the relative contribution of high- and low-resolution observations to the information lost under downsampling. To support this analysis, we empirically demonstrate, using both a
vision transformer and a convolutional neural network, that adding low-resolution data to the training set consistently improves performance when high-resolution data is scarce.
Read the full abstract ▾
All authors Theresa Dahl Frehr, Niels Henrik Pontoppidan, Hiba Nassar, Tommy Sonne Alstrøm
Machine Learning · Cross-listed from physics.ins-det
Machine Learning for neutron source distributions
Jose Ignacio Robledo, Norberto Schmidt, Klaus Lieutenant et al. (+3 more)
In light of the recent advancements in machine learning, we propose a novel approach to
neutron source distribution estimation through the utilisation of probabilistic generative models. The estimation is based on a Monte Carlo particle list, which is only required during the training stage of the machine learning model. Once the source distribution has been learned, the model is independent of the original particle list, allowing for further sampling in an efficient, rapid, and
memory-costless manner. The performance of various generative models is evaluated, including a variational autoencoder, a normalizing flow, a generative
adversarial network, and a denoising
diffusion model. These approaches are then compared to existing source distribution estimations, and the advantages and disadvantages of each approach are discussed. The results demonstrate that source distributions can be modeled through the use of probabilistic generative models, which paves the way for further advancements in this field.
Read the full abstract ▾
All authors Jose Ignacio Robledo, Norberto Schmidt, Klaus Lieutenant, Jingjing Li, Stefan Kesselheim, Paul Zakalek
Machine Learning
Fused Gromov-Wasserstein Distance with Feature Selection
Harlin Lee, Ying Yu, Mingxin Li et al. (+1 more)
Fused Gromov-Wasserstein (FGW) distances provide a principled framework for comparing objects by jointly aligning structure and node features. However, existing FGW formulations treat all features uniformly, which limits interpretability and robustness in high-dimensional settings where many features may be irrelevant or noisy. We introduce FGW distances with feature selection, which incorporate adaptive feature suppression weights into the FGW objective to selectively downweight or suppress differentiating features during
alignment. We propose two approaches: (1) regularized FGW with Lasso and Ridge penalties, and (2) FGW with simplex-constrained weights, including groupwise extensions. We analyze the resulting models and establish their key theoretical properties, including bounds relative to classical FGW and Gromov-Wasserstein distances, and metric behavior. An efficient alternating minimization
algorithm is developed. Experiments illustrate how feature suppression enhances interpretability and reveals task-relevant structure, with a special application to computational redistricting.
Read the full abstract ▾
All authors Harlin Lee, Ying Yu, Mingxin Li, Ranthony Clark
Machine Learning · Cross-listed from cs.CR
PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
James Flemings and Murali Annavaram
Large
language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate $individual$
privacy decisions is not well understood. In this paper, we address the problem of evaluating whether a core set of user persona attributes can drive LLMs to simulate individual-level
privacy behavior. We introduce PrivacySIM, an evaluation suite that
benchmarks LLM simulation of user
privacy behavior against the ground-truth responses of 1,000 users. These users are drawn from five published user studies on
privacy spanning LLM healthcare consultations, conversational
agents, and chatbots. Drawing on these user studies, we hypothesize three persona facets as plausible predictors of
privacy decision-making: demographics, previous experiences, and stated
privacy attitudes. We condition nine frontier LLMs on subsets of these three facets and measure how often each model's response to a data-sharing scenario matches the user's actual response. Our findings show that (1)
privacy persona conditioning consistently improves simulation quality over no-persona conditioning, but even the strongest model (40.4% accuracy) remains far from faithfully simulating individual
privacy decisions. (2) A user's stated
privacy attitudes alone may not be the best predictor because they often diverge from the user's actual
privacy behavior. (3) Users with high AI/chatbot experience but low stated
privacy attitudes are the most challenging to simulate. PrivacySIM is a first step toward understanding and improving the capabilities of LLMs to simulate user
privacy decisions. We release PrivacySIM to enable further evaluation of LLM
privacy simulation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
Joshua Opria
We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone Hero / YARG charts for drums, guitar, bass, vocals, and keys without any oracle metadata. STRUM is a multi-stage hybrid: a two-stage CRNN onset detector and a six-model ensemble classifier for drums; neural onset detectors with monophonic pitch tracking for guitar and bass; word-aligned ASR for vocals; and spectral keyboard detection for keys. We evaluate on a 30-song in-envelope
benchmark constructed by screening candidate songs on a single audio-quality criterion – the median 1-second drum-stem RMS after htdemucs_6s source separation. On this
benchmark STRUM achieves drums onset F1 = 0.838, bass F1 = 0.694, guitar F1 = 0.651, and vocals F1 = 0.539 at a +/- 100 ms tolerance with per-song global offset search. We report a complete ablation of seven drum-pipeline components with paired per-song Wilcoxon tests, an analysis of ground-truth-to-audio timing distributions in community Clone Hero charts, and a per-class confusion
matrix for the drum classifier. Code, model weights, and the full
benchmark manifest are released.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
Sonali Godavarthy, Matthias Neuwirth-Trapp, Tim-Felix Faasch et al. (+3 more)
Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There have been a number of recent works dealing with learning and composing multiple objects and patterns. However, current work focuses almost entirely on image content, overlooking imaging factors such as camera lens, sensor types, imaging viewpoints, and scenes' domain characteristics. We introduce this new challenge as Imaging Factor Disentanglement and show limitations of current approaches in the regime. We, therefore, propose the new method Multi-factor disentanglement through Textual Inversion (MULTI). It consists of two stages: in the first stage, we learn general factors, and in the second stage, we extract
dataset-specific ones. This setup enables the extension of existing
datasets and novel factor combinations, thereby reducing distribution gaps. It further supports modifications of specific factors and image-to-image generation via ControlNets. The evaluation on our new DF-RICO
benchmark demonstrates the effectiveness of MULTI and highlights the importance of Factor Disentanglement as a new direction of research.
Read the full abstract ▾
All authors Sonali Godavarthy, Matthias Neuwirth-Trapp, Tim-Felix Faasch, Maarten Bieshaar, Michael Moeller, Danda Pani Paudel
Machine Learning
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
Hyeonjin Kim, Hangyeol Jung, Heechan Yun et al. (+2 more)
Unlearning specific concepts in text-to-image
diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted
attention due to their ability to suppress target concepts through lightweight manipulation of latent features, without modifying model parameters. However, SAEs trained primarily for sparse reconstruction do not explicitly enforce concept-wise separation, allowing semantically related concepts to share latent features. To address this, we propose SAEParate, which explicitly separates semantically overlapping concepts in the SAE latent space through concept-aware contrastive learning, supported by cross-
attention-guided spatial aggregation that emphasizes concept-relevant regions. In addition, we enhance the encoder with a nonlinear transformation to increase its expressive capacity under this separation objective, enabling more concept-discriminative latent representations. Experiments on UnlearnCanvas demonstrate state-of-the-art performance, with particularly strong gains in joint style-object unlearning, a challenging setting where existing methods suffer from severe interference between target and non-target concepts.
Read the full abstract ▾
All authors Hyeonjin Kim, Hangyeol Jung, Heechan Yun, Sungjun Yun, Dong-Jun Han
Machine Learning · Cross-listed from stat.ML
Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation
Alexander Shen and Mikael Kuusela
Neural likelihood surrogates (e.g., Neural Ratio Estimation) for
stochastic process models are commonly trained via probabilistic classification on simulated data, which forces a tradeoff between surrogate quality and training costs. For structured models where the exact score $\nabla_\theta \log p(x \mid \theta)$ is available, this information can be incorporated into training by augmenting the cross-
entropy loss with a score-matching term. However, the optimal weighting of the two losses is not known a priori, and selecting it by hand requires expensive tuning that undercuts the computational savings. We propose an adaptive, tuning-free
algorithm that sets the score loss weights during training based on loss gradients, adding minimal overhead to standard classifier training. We evaluate our approach on case studies involving network dynamics and spatial processes, demonstrating that it improves surrogate quality at a drastically lower computational cost than generating more training data. Notably, in some cases, our approach achieves downstream inference performance equivalent to a 10x increase in training data with less than a 1.1x increase in training time.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration
Youwei Yu, Jionghao Wang, Zhengming Yu et al. (+2 more)
Designing learnable information-theoretic objectives for
robot exploration remains challenging. Such objectives aim to guide exploration toward data that reduces uncertainty in model parameters, yet it is often unclear what information the collected data can actually reveal. Although reinforcement learning (RL) can optimize a given objective, constructing objectives that reflect parametric learnability is difficult in high-dimensional robotic systems. Many parameter directions are weakly observable or unidentifiable, and even when identifiable directions are selected, omitted directions can still influence exploration and distort information measures. To address this challenge, we propose Quasi-Optimal Experimental Design (Q{\footnotesize OED}), an adaptive information objective grounded in optimal experimental design. Q{\footnotesize OED} (i) performs eigenspace analysis of the Fisher information
matrix to identify an observable subspace and select identifiable parameter directions, and (ii) modifies the exploration objective to emphasize these directions while suppressing nuisance effects from non-critical parameters. Under bounded nuisance influence and limited coupling between critical and nuisance directions, Q{\footnotesize OED} provides a constant-factor approximation to the ideal information objective that explores all parameters. We evaluate Q{\footnotesize OED} on simulated and real-world
navigation and manipulation tasks, where identifiable-direction selection and nuisance suppression yield performance improvements of \SI{35.23}{\percent} and \SI{21.98}{\percent}, respectively. When integrated as an exploration objective in model-based policy optimization, Q{\footnotesize OED} further improves policy performance over established RL baselines.
Read the full abstract ▾
All authors Youwei Yu, Jionghao Wang, Zhengming Yu, Wenping Wang, Lantao Liu
Machine Learning
Elicitation-Augmented Bayesian Optimization
Alvar Haltia, Ville Hyvönen and Samuel Kaski
Human-in-the-loop
Bayesian optimization (HITL BO) methods utilize human expertise to improve the sample-efficiency of BO. Most HITL BO methods assume that a domain expert can quantify their knowledge, for instance by pinpointing query locations or specifying their prior beliefs about the location of the maximum as a probability distribution. However, since human expertise is often tacit and cannot be explicitly quantified, we consider a setting where domain knowledge of an expert is elicited via pairwise comparisons of designs. We interpret the expert's pairwise judgements as noisy evidence about the values of the observable objective function and develop a principled method for combining the information obtained via direct observations and pairwise queries. Specifically, we derive a cost-aware value-of-information acquisition function that balances direct observations against pairwise queries. The proposed method approaches the convex hull of the trajectories of the individual information sources: when pairwise queries are cheap it substantially improves sample-efficiency over observation-only BO, and when pairwise queries are costly or noisy, it recovers the performance of standard BO by relying on direct observations alone.
Read the full abstract ▾