Machine Learning
Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study
Ivan Donà, Hans H. Brunner, Álvaro Troyano Olivas et al. (+3 more)
Federated Learning (FL) enables collaborative training of models across institutions without centralizing sensitive data, making it well-suited for
privacy-concerned applications, such as medical imaging. To protect FL model updates during secure aggregation, additive masking is commonly employed. However, its underlying classical key establishment is only computationally secure. On the other hand, physics-based Information-Theoretically Secure (ITS) key exchange introduces practical constraints: finite key generation rates and time-limited storage severely limit throughput and sustained training of uncompressed models. In this work, we address this bottleneck by developing an FL framework that integrates frozen backbones, knowledge
distillation, and quantization. These techniques reduce communication payload and, consequently, key material consumption. Moving beyond simulation, we
benchmark this framework on a real physics-based key distribution testbed involving a chest X-ray classification application. Our results show that key usage can be reduced by $\sim$35$\times$ while maintaining predictive accuracy. This prevents buffer depletion and key expiration, enabling sustainable FL training under physical key generation constraints.
Read the full abstract ▾
All authors Ivan Donà, Hans H. Brunner, Álvaro Troyano Olivas, Chi-Hang Fred Fung, Momtchil Peev, Giovanni Iacca
Machine Learning
Training-Free Transformer Merging via Sequential Local Operator Alignment
Akansh Maurya, Ya-Wei Eileen Lin, Stefanie Jegelka et al. (+2 more)
Training-free model merging aims to combine multiple fine-tuned models into a single model without further optimization on labeled data. Yet, in
transformers, independently merging individual layers can affect a shared
attention computation because the query-key and value-output operators depend on composed
matrices, overlooking the functional structure. Moreover, when merging earlier components, downstream components receive different activations than they do in the original model, thus, the merged and original execution paths no longer match. In this paper, we introduce Sequential Local Operator
Alignment, a training-free method that merges
transformers along the execution path of the partially merged model. Our method uses calibration data to estimate the local behavior of each functional component, aligns operators sequentially under the intermediate activation of the partially merged model, and subsequently factorizes the merged operators back into valid
transformer parameters. We empirically show that this sequential step reduces error accumulation across layers. Furthermore, the proposed operator factorization step enables rank expansion, providing a principled mechanism for increasing multi-task capacity. We demonstrate that our approach generalizes across modalities, model scales, and varying numbers of tasks, from CLIP and RoBERTa to billion-parameter LLMs, and further extends naturally to the merging of LoRA-fine-tuned models. The results indicate improvements over strong merging baselines without requiring rank expansion, while optional expansion provides a further accuracy-inference-cost trade-off. Project link: https://akansh12.github.io/SLOA-Merge/
Read the full abstract ▾
All authors Akansh Maurya, Ya-Wei Eileen Lin, Stefanie Jegelka, Sebastian U Stich, Rotem Mulayoff
Machine Learning
FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials
Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov et al. (+4 more)
Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of equivariant architectures limits the local correlations they can represent in practice and therefore their achievable accuracy. Here we introduce FlashCart, which makes higher-order correlations affordable by combining generated GPU kernels with an architecture that recursively builds equivariant features and compresses them to a fixed width at each step. We express tensor products in independent Cartesian components and symbolically simplify them and their derivatives, producing fused kernels that often outperform optimized spherical counterparts. We then show that increasing correlation order improves accuracy more efficiently than increasing width, depth, or tensor rank. On SPICE-MACE-OFF, FlashCart models advance the measured accuracy-efficiency frontier: a model with $5.6$ million parameters achieves lower energy and force errors and $10\times$ faster inference than a
transformer with $189$ million parameters.
Read the full abstract ▾
All authors Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov, Davit Hovhannisyan, Roland Aydin, Martin H. Müser, Mathias Niepert
Machine Learning
Quantifying the Stability of Multi-Step Reasoning via Error Amplification
Dongyue Li, Ziniu Zhang, Minxuan Duan et al. (+1 more)
We consider the stability of multi-step
reasoning processes, which have extensive applications in
language models, including chain-of-thought and algorithmic
reasoning. While longer sequences of
reasoning can improve a model's generation capability at test time, the errors due to intermediate
reasoning steps can accumulate in autoregressive generation, and thus grow substantially at the end. In this paper, we ask: What are the key factors determining the stability of multi-step
reasoning? First, we show an inference error bound governed by the product of spectral norms of the Jacobians taken through the input space across generation steps. This product can be viewed as an error amplification factor, which could scale exponentially with the number of
reasoning steps, serving as a quantitative measure of
reasoning stability. Second, we analyze this measure in
transformer models trained to predict simple tasks like linear and quadratic functions. We theoretically prove that the
transformer model converges to a solution where the stability measure decays, thus yielding nearly zero inference loss over (arbitrarily) long steps. Finally, the stability analysis leads to several algorithmic implications for controlling the stability, through (i) chain-of-thought length compression that reduces the sensitivity of each step, and (ii) quantization-aware training that regularizes the input Jacobian norms. We validate the proposed
algorithms by fine-tuning
language models on graph-algorithmic
reasoning tasks and symbolic state-tracking tasks. Across seven evaluations, our
algorithms improve over baseline comparisons by 3.5% on average, and by 8.2% for longer-length inputs. Ablation analysis validates that the stability measure is drastically reduced by 3-8$\times$, confirming the regularization effect on the spectral norms of the (input space) Jacobians.
Read the full abstract ▾
All authors Dongyue Li, Ziniu Zhang, Minxuan Duan, Hongyang R. Zhang
Machine Learning · Cross-listed from cs.CR
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Mohamed Dhouib, Clement Elliker, Alexi Canesse et al. (+5 more)
Tool-using
language-model
agents are vulnerable to indirect
prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-
Distillation), a training framework that combines self-generation and self-
distillation. The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. Then, through self-
distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. RAISED substantially reduces the attack success rate of
prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose
benchmarks.
Read the full abstract ▾
All authors Mohamed Dhouib, Clement Elliker, Alexi Canesse, Maël Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein
Machine Learning
Learning Pareto Stationary Fronts via Single-Pass Backpropagation
Elina Rojin Celik, Marcos Medeiros Raimundo and Isabel Valera
We propose MOSEL (Multi-Objective Stackelberg Efficient Learning), a framework for a posteriori multi-objective optimization (MOO) in deep neural networks that recovers a full front of Pareto stationary solutions at the computational cost of standard single-objective training. MOSEL reformulates the problem as a bilevel optimization problem that leverages network modularity to decouple representation learning from objective-preference
alignment. Casting the bilevel optimization problem as a Stackelberg game enables solving the original a posteriori MOO problem in a single forward-backward pass. As a result, MOSEL matches the time and
memory efficiency of standard single-objective training while enabling scalable Pareto stationary front learning. Empirically, MOSEL uncovers diverse and optimal Pareto frontiers in strongly conflicting settings (e.g.,
fairness-accuracy). Remarkably, even in weakly conflicting regimes such as multi-task learning, it consistently converges to solutions closer to the utopia point, outperforming both standard single-objective training and specialized multi-task learning methods. These results highlight the broader potential of a posteriori MOO learning as a pathway to efficiently learn more diverse and robust representations, ultimately improving generalization.
Read the full abstract ▾
Machine Learning
Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models
Joe Dwyer
Large
language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. However, traditional scaling approaches produce diminishing returns, rising financial and environmental costs, and barriers to participation for researchers operating outside large industrial laboratories. This review examines the
evolution of LLM scaling theory from empirical scaling laws to compute-optimal training, with particular emphasis on parameter efficiency,
token utilization, data efficiency, and resource-constrained environments. Foundational work on scaling laws is synthesized alongside later research on compute-optimal training, data
pruning, efficient architectures, quantization, low-rank adaptation, and edge-oriented optimization. The literature indicates a shift from scale maximization toward more deliberate allocation of parameters,
tokens, compute, and hardware resources. At the same time, important empirical, theoretical, and methodological gaps remain regarding whether scaling principles established on enterprise-grade infrastructure generalize to smaller models and constrained computing environments. This review organizes these developments into a unified framework for resource-efficient LLM training and argues that future progress should evaluate efficiency not solely through model performance, but through the relationship among performance, parameter count, computational cost,
token allocation, and hardware constraints.
Read the full abstract ▾
Machine Learning
Steering by Influence: Curvature Aware Data Weighting for Activation Steering
James A. E. Dixon, Stephen J. Roberts and Francesco Quinzan
Inference-time steering offers cheap, fine-grained control over a
language model's outputs by estimating a concept's representation in activation space and shifting activations towards it. Existing methods build these representations from activation averages over contrastive
datasets. These averages incorporate unrelated concepts and noise, and are dominated by a few
tokens, meaning the activation transport encodes
token-level rather than thematic concepts. In this work, we steer towards examples that most express a concept thematically, rather than towards an expectation over all. We identify these examples using influence functions, which estimate how much each data point contributes to a model's representation of a concept. Unlike simple model activation similarity, they incorporate the
curvature of the model's loss landscape, allowing them to capture concept-relevant relationships beyond superficial
token-level similarity. We then propose influence-weighted activation transport, which uses optimal transport to steer activations of non-concept text towards those of concept text, weighting concept examples by their influence scores. We evaluate on toxicity suppression (Jigsaw), object-based concept induction (OneSec) and truthfulness induction (TruthfulQA), outperforming existing activation-transport baselines. We track capability after steering using perplexity and MMLU accuracy, finding that our method improves steering while largely preserving model quality. We further show that influence functions capture concept-relevant information that activation-based methods miss with the two approaches ranking data points significantly differently. Together, these results demonstrate the value of
curvature-aware influence information for activation steering.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Environmental sensor readings in two crop disease image datasets identify the session in which each image was taken
Sungwoo Kang
Integrating environmental sensor data with leaf imagery is widely reported to boost crop disease classification accuracy. In this work, we reveal that these reported gains are often artifacts of
dataset construction: because a single sensor reading is shared across many images collected in a single session (one farm on one date),
multimodal networks can predict disease simply by memorizing session identities. Analyzing two widely used Korean
datasets, the Crop Disease Diagnosis (CDD)
benchmark and an AI Hub pest/disease
dataset, we demonstrate that nearly all images share sensor values, with 91.9% of CDD test images having exact sensor duplicates in the training set. Remarkably, an image-free classifier given only timestamps matches or exceeds sensor-driven predictions across all seven evaluated crops, and matches the published macro-F1 of a state-of-the-art CDD fusion model. These results indicate that performance gains on standard random splits cannot be disentangled from session leakage. We propose that
multimodal crop studies must evaluate on session-held-out splits and report performance against sensor-free date-time baselines to ensure genuine generalization.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning
Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni et al. (+1 more)
Large
Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; practitioners need explanations to triage bugs and engineer patches. Standard practice relies on Chain-of-Thought (CoT) prompting, but free-form
reasoning allows models to obscure logical leaps, hallucinated execution steps, and internal inconsistencies behind plausible prose. Our manual audit reveals that approximately 60% of correct vulnerability verdicts are accompanied by fabricated or unverifiable claims, and free-form explanations allow
reasoning errors to evade LLM-as-a-judge evaluation. We present Vulnerability Explanation
Reasoning Auditor (VERA), an automated framework for auditing LLM vulnerability
reasoning. Rather than accepting free-form text, VERA asks models to output a Structured
Reasoning Record (SRR) encoding tracked pointers,
memory operations, and state transitions in machine-readable fields. A multi-stage judge audits each SRR against eight
reasoning failure modes using deterministic checks, with LLM calls reserved for semantic interpretation. The standardized SRR schema also enables automated mutation testing to
benchmark judges at scale without human annotation. Our evaluation shows
reasoning flaws occur in correct verdicts just as frequently as incorrect ones, and VERA exposes 87% of
reasoning errors that free-form LLM-as-judge systematically miss.
Read the full abstract ▾
All authors Boyue Caroline Hu, Kaivalya Ahir, Ronghao Ni, Limin Jia
Machine Learning
Multimodal Deep Survival Analysis for Sinkhole Susceptibility
Lucas Yuan, Minhee Kim, Zihan Li et al. (+4 more)
Sinkholes are a widespread geohazard in karst terrain. In Florida, soluble carbonate bedrock, shallow groundwater, and intense rainfall combine to make subsidence both common and spatially heterogeneous. Predicting where and when sinkholes will occur is difficult for two reasons. First, locations without reported sinkholes cannot be directly labeled or sampled as true negative locations. Second, the potential factors governing sinkhole risk span heterogeneous data modalities and therefore require careful integration within a unified modeling framework. We address both problems with our proposed model, a
multimodal Cox proportional hazards framework for sinkhole susceptibility. Our contributions are threefold. First, we extend the proportional-hazards formulation to heterogeneous
multimodal input through modality-specific encoders and a cross-modal fusion layer. Second, we treat unreported locations as right-censored rather than negative, avoiding hard-negative labeling and yielding continuous, time-aware susceptibility from the predicted survival function. Third, a statewide Florida case study with spatially blocked validation and ablation studies quantifies the benefit of
multimodal integration. A Florida case study demonstrates that the proposed method effectively ranks sinkhole risk and produces a statewide susceptibility map that captures spatial variations in sinkhole occurrence.
Read the full abstract ▾
All authors Lucas Yuan, Minhee Kim, Zihan Li, Chunli Dai, Sanduni S. Disanayaka Mudiyanselage, Ming Ye, Kani Fu
Machine Learning · Cross-listed from cs.CL
Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Aditya Tanna and Abhishek Jindal
Reinforcement learning post-training for
language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clinical question answering fits neither. Near-correct answers differ by a single substituted entity, and no executable check decides clinical correctness. We instantiate a soft verifier from a maintained controlled vocabulary: UMLS Concept Unique Identifier overlap (via scispaCy, set-level F1) gives a graded, externally specified reward computed without a model in the loop. We combine it inside GRPO with an
entropy-normalised LLM judge, which covers the safety and evidence axes overlap cannot see, and a small consistency penalty on padding and repetition that keeps early-training samples scorable. This three-term composite improves over SFT on Phi-3-mini (3.8B) over MedQA by 2.9% on EM (0.700 vs 0.680) and 39% on
Token-F1 (0.202 vs 0.145); on Llama-3.2-3B the corresponding gains are 14% on EM and 35% on
Token-F1. We report
Token-F1 as the primary metric because it credits partially-correct clinical content that EM discards at this open-generation scale. Main-table results are means over 3 seeds with standard deviations below 0.005. The method transfers to PubMedQA, where training on the PubMedQA train set with the same composite reward improves
Token-F1 over SFT by 22% on Phi-3-mini and 17% on Llama-3.2-3B without retuning. A reward ablation on Phi-3, varying the judge-ontology split at a fixed consistency weight, attributes 3 EM points to the ontology term, the contribution that catches entity substitutions the judge cannot. Three negative findings constrain the design: DPO under random negatives underperforms SFT for strong-prior models but helps the weakest-prior one; PPO under a sparse neural reward diverges; GRPO with KL-in-loss collapses at 7B.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support
Yaniv Yacoby, Weiwei Pan, Hope Neveux et al. (+4 more)
Forecasting suicide risk is difficult due to the high heterogeneity of patients and the low base rate of suicide-related events (SREs). We present Latent Similarity Gaussian Processes (LSGPs), which embed patients in a continuous latent space to jointly model similarity and forecast risk. By selectively drawing information from latent peers, LSGPs better capture individualized risk trajectories, generalizing nomothetic (pooled), idiographic (per-patient), and hierarchical frameworks. Our contributions are: (1) an identifiable two-channel Similarity Kernel; (2) proof that the standard model-fitting
algorithm, mean-field variational inference, collapses LSGPs to nomothetic models, along with a fix; and (3) empirical results on intensive longitudinal suicide data showing LSGPs outperform nomothetic, idiographic, and hierarchical models for next-week risk forecasting, with the largest gains in forecasting first-occurrence SREs.
Read the full abstract ▾
All authors Yaniv Yacoby, Weiwei Pan, Hope Neveux, Taylor C. McGuire, Franchesca Castro-Ramirez, Anushka R. Patel, Matthew K. Nock
Machine Learning · Cross-listed from math.NA
IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs
Sima Naraghi, Kourosh Parand, Amirhossein Sadr et al. (+1 more)
Isogeometric analysis (IGA) solves partial differential equations accurately on exact NURBS geometry, whereas neural solvers are mesh-free but often orders of magnitude less accurate and typically trained by non-convex optimization without error control. We propose IGA-KAN, which uses local Kolmogorov-Arnold networks, fitted in closed form, to improve the IGA solution instead of replacing it. An IGA Galerkin solve produces u_h; on every
knot-vertex patch a Kolmogorov-Arnold ridge model is fitted to the strong form of the equation, the exact boundary data and u_h, and the models are blended by IGA hat functions. With fixed inner functions the fit is one batched linear least-squares problem, without optimizer, learning rate or initialization. An a posteriori safeguard, motivated by a maximum-principle bound, decides where local models are used, keeping the IGA solution elsewhere. On eight
benchmarks with exact solutions, five from the literature and one also posed on a domain fitted to a
brain slice from MRI, the method reduces the error of IGA, at an unchanged number of Galerkin unknowns, by factors of 4.2 to 90 in L^2 and 4.1 to 220 in H^1 on the reference meshes, and its L^2 error is 6 to 6x10^4 times smaller than that of the best Kolmogorov-Arnold network trained from scratch on the same equations with a fixed budget. In an inverse problem it recovers an unknown constant source from one noise-free observation 167 times more accurately than IGA. The gain is attributed to the superconvergence of local averages of the Galerkin solution.
Read the full abstract ▾
All authors Sima Naraghi, Kourosh Parand, Amirhossein Sadr, Dara Rahmati
Machine Learning
Stability-Shaped Deep Graph Learning
Junyou Zhu, Langzhou He, Fenying Cai et al. (+7 more)
In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align. We develop a unified, mode-wise stability framework for deep GNN propagation that provides a principled characterization of over-smoothing. By interpreting layer depth as time and layer updates as graph-coupled dynamics, over-smoothing can be understood as an undesirable dynamical synchronization of features, for which the master stability curve provides a theoretical tool to assess the stability of synchrony. Guided by this theory, we further propose Stability-Shaped Deep Graph Learning (SDGL) to mitigate over-smoothing in deep GNNs. SDGL has two complementary instantiations: one induces controlled Turing instability to replace synchronization with spatial pattern formation, and the other maintains stable near-critical propagation. Experiments on diverse node- and graph-level
benchmarks demonstrate the improved depth scaling and consistent accuracy gains over strong baselines, including graphs exhibiting long-range dependencies.
Read the full abstract ▾
All authors Junyou Zhu, Langzhou He, Fenying Cai, Christian Nauck, Ping Xiong, Chao Gao, Philip S. Yu, Klaus-Robert Müller, Jürgen Kurths, Frank Hellmann
Machine Learning
Dynamic Minimax Regret Optimization for Robust LLM Post-Training
Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan et al. (+3 more)
Modern LLM training increasingly relies on heterogeneous data sources spanning different domains, tasks, preference distributions, and difficulty levels. We study dynamic minimax regret for group-distributionally robust LLM post-training under instantaneous mini-batch-only bandit feedback. The framework views the training as a two-player sampler-optimizer process: a sampler adaptively selects among data sources using bandit feedback, while an optimizer updates the model parameters using
stochastic gradients from the selected source. We focus on the practically restrictive setting where source losses evolve with model training but historical data are not re-evaluated, requiring the sampler to track instantaneous worst-sources from stale partial feedback. We propose DUCB-OGD, a simple and scalable
algorithm that couples a Discounted Upper-Confidence-Bound sampler with an Online Gradient Descent optimizer. The sampler maintains exponential moving average loss estimates and confidence radii based on discounted effective sample sizes, avoiding costly re-evaluation of past data or intrusive changes to standard training pipelines. For $K$ data sources and $T$ training steps, we prove that DUCB-OGD achieves a dynamic minimax regret of $\tilde{O}(K^{1/4}T^{3/4})$, which is optimal up to logarithmic factors for the undiscounted objective under our feedback model. Extensive experiments across supervised fine-tuning, preference optimization, and reinforcement learning show that DUCB-OGD integrates seamlessly into modern LLM training pipelines and improves worst-group robustness with negligible computational overhead compared with standard sampling baselines.
Read the full abstract ▾
All authors Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan, Gil Zussman, Zoran Kostic, Javad Ghaderi
Machine Learning · Cross-listed from cs.RO
Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation
Álvaro Díez and Fidel Aznar
Vision-based autonomous navigation for low-cost
robots remains a fundamental challenge, primarily due to the significant gap between simulated training environments and real-world operational conditions. Direct policy transfer from simulation is often ineffective, while training exclusively on real data is impractical. We propose a hybrid transfer learning framework that effectively bridges the sim-to-real gap by combining domain randomization with feature-level domain adaptation. Our method employs a dual convolutional variational autoencoder architecture with a shared decoder, trained on an extensive set of 45225 simulated images and a minimal set of only 4556 real-world samples. This architecture learns a compact, common latent representation space that aligns the distributions of both domains. The adaptation process is further enhanced by two complementary data augmentation techniques designed to expand the limited real-world data. Experimental evaluation demonstrates that our method achieves an average success rate of almost 91% on image classification tasks for real-world indoor navigation, significantly outperforming both simulation-only and real-world-only training. We validate these findings through a direct, real-world deployment, where the proposed policy successfully guides a low-cost
robot in a reactive exploration task. Furthermore, we validate the model's efficiency through a rigorous computational estimation, confirming its suitability for resource-constrained embedded platforms such as the Raspberry Pi 4 and NVIDIA Jetson Nano. This work presents a practical solution for developing effective and efficient navigation policies for low-cost robotic systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain
Guangyuan Li, Tianming Du, Yan Jiang et al. (+2 more)
CLIP-like
vision-
language models remain a cornerstone of
multimodal systems, yet their scores stay near chance on directed spatial relations, such as whether one object is left of another. We call this failure readout blindness and analyze, theoretically and empirically, why deployed scores miss the direction: when scoring rules treat the subject and object symmetrically, direction cancels regardless of encoder training. Guided by this analysis, we introduce Antisymmetric Displacement Readout (ADR), which aligns caption words with image patches in the frozen features and scores each relation by the signed displacement between matched object centroids. Notably, ADR succeeds without additional training or learned parameters, thereby demonstrating that directional information remains in the frozen encoder. However, text and world priors can inflate accuracy, so we further introduce prior deflation, which measures the benefit of the image-text pairing as the grounded gain over a null that pairs each item with an unrelated image. Extensive experiments across encoder families show that ADR substantially improves over deployed scores, which remain near chance on most direction-balanced sets even for fine-tuned encoders. Compared with more complex readouts, ADR outperforms the evaluated MLLM likelihood readouts and is competitive with their chat inference at a small fraction of the computation. These results support our claim that directional information can be recovered from frozen features by an appropriate readout. Our implementation and evaluation kit will be publicly available.
Read the full abstract ▾
All authors Guangyuan Li, Tianming Du, Yan Jiang, Bihan Wen, Jiancheng Yang
Machine Learning · Cross-listed from cs.CR
Watermarking: from Impossibility to Auditable Compliance
Fernando Delbianco, Fernando Tohmé and Hugo Acciarri
Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectable, while qualifying the effectiveness, interoperability, robustness, and reliability by technical feasibility, cost, content-specific limits, and the state of the art. For free-form text, one important implementation route is the implementation of a generative watermarking procedure, which poses a compliance problem that is hard to address. Strong watermarking is impossible against adaptive removal, while ordinary edits attenuate statistical evidence, and unmarked human text may overlap distributionally with machine output. This article develops an auditable alternative. First, it defines a description-length robustness profile. A finite-sample bound shows that detectable bias decays and that the required sample size grows with the inverse square of the decay rate. This replaces an unidentified Shannon-
entropy constant with collision
entropy. Second, it constructs label-conditional conformal prediction sets with separate false-attribution and false-exclusion levels, reporting “watermark supported,” “not supported,” or “inconclusive”. Coverage is obtained as a finite-sample result and is class-conditional under exchangeability. A small reproducible simulation of a tournament watermark confirms both claims and shows that the surviving-
token rule overstates the tolerable edit rate roughly twofold. The resulting premarket certificate, signed detector report, and postmarket recalibration protocol operationalize the Commission's 2026 Code of Practice without claiming universal robustness.
Read the full abstract ▾
Machine Learning
SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts
Shanglin Li, Shiwen Chu, Okan Koç et al. (+5 more)
Electroencephalography (
EEG) based
brain-computer interfaces enable direct
brain-to-device communication for applications such as rehabilitation and communication. However, their practical utility is often limited as the non-stationary nature of the
EEG data introduces distribution shifts across domains (e.g., sessions and subjects). Adapting machine learning models to be invariant to these shifts in an unsupervised way, without using costly labeled calibration data, would drastically improve the utility of
EEG data. In this work, we use a classic generative model of
EEG to study distribution shifts introduced by the domain-specific forward process, which is associated with factors such as head geometry. We theoretically show that such distribution shifts can be recovered solely through linear transformations on the Symmetric Positive Definite
manifold. Building on this insight, we propose SPDAlign, an interpretable framework for promoting domain-invariant
EEG learning. SPDAlign first aligns the domain-specific means and corrects global rotations across domains using a recent optimal transport technique called Wasserstein Procrustes. We systematically study the proposed approach through simulations and demonstrate its competitive performance on extensive public
EEG datasets. Additionally, SPDAlign is a globally linear framework and is intrinsically interpretable, so that the framework can identify frequency ranges of interest, determine the spatial patterns reflecting source-sensor relationships, and address cross-subject variability.
Read the full abstract ▾
All authors Shanglin Li, Shiwen Chu, Okan Koç, Chenyu Liu, Qibin Zhao, Motoaki Kawanabe, Mitsuo Kawato, Yi Ding
Machine Learning · Cross-listed from math.ST
Sharp dimensional analysis of midpoint methods for Langevin sampling
Fan Chen, Sinho Chewi, Jianfeng Lu et al. (+1 more)
We study deterministic and randomized midpoint discretizations of Langevin dynamics for a target $\pi \propto e^{-V}$, where $0 \prec \alpha I\preceq\nabla^2V\preceq\beta I$ and $\kappa=\beta/\alpha$. To achieve $\sqrt\alpha\,W_2\leqslant\varepsilon$, we show that deterministic Heun uses at most $\widetilde O(\kappa^{4/3}d^{1/3}\varepsilon^{-2/3})$ gradient queries, and underdamped exponential midpoint uses $\widetilde O(\kappa^{5/4}d^{1/4}\varepsilon^{-1/2})$. The proofs exploit cancellation at stationarity and smoothing using techniques from Malliavin calculus, outperforming previous upper bounds based on standard couplings. At bounded condition number, a lower bound matches the $d$ and $\varepsilon$ powers of both deterministic methods. To contrast, for the randomized midpoint methods and Poisson midpoint with at least two grid points (both overdamped and underdamped variants), a simple Gaussian calculation yields a lower bound $d^{1/3}\varepsilon^{-1/3}$ to get an $\varepsilon$-close sample despite starting at a benign initialization. This shows surprisingly that in high dimensions, deterministic discretizations can outperform their random counterparts.
Read the full abstract ▾
All authors Fan Chen, Sinho Chewi, Jianfeng Lu, Matthew S. Zhang
Machine Learning · Cross-listed from cs.RO
GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories
Rishabh Jain, Akmaral Moldagalieva, Lorenzo Magnino et al. (+5 more)
GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game. Analogously, in multi-
robot coordination, individual
robots may need to forgo locally reward-maximising behaviours to improve overall team performance. Such self-sacrificial behaviours are difficult to capture with manually designed heuristics, particularly in dense, interaction-rich environments. Focusing on double-integrator continuous dynamics, this work studies how to learn such coordinated heuristics over motion primitives for multi-
robot trajectory execution. Our framework, GAMBIT, first learns coordinated motion-primitive selection through imitation learning and subsequently fine-tunes the policy through reinforcement learning. We further introduce a safeguarded rollout mechanism with backup trajectories that guarantees collision-free execution at all times. Experiments demonstrate that GAMBIT substantially outperforms a range of baselines, including centralised motion planners and decentralised reactive planners, while exhibiting strong scalability. In particular, it coordinates over a thousand
robots with planning latency below a few hundred milliseconds in continuous domains.
Read the full abstract ▾
All authors Rishabh Jain, Akmaral Moldagalieva, Lorenzo Magnino, Michael Amir, Keisuke Okumura, Ajay Shankar, Wolfgang Hönig, Amanda Prorok
Machine Learning
Trajectory-Guided Tokenization of Complex CSI for Wi-Fi Sensing
Ziyi Wang, Kenuo Xu, Jichu Jiang et al. (+8 more)
Wi-Fi channel state information (CSI) enables contactless presence detection and gesture recognition. Its high-dimensional complex-valued time series require input representations that preserve informative temporal variations during compression. We propose Trajectory-Guided Tokenization (TGT), which combines complex trajectory decomposition with asymmetric
attention to construct compact continuous
tokens. For each
antenna link and subcarrier, an orthonormal Helmert transform decomposes short, ordered temporal patches into local-center and centered-trajectory coordinates. Keys are learned from the centered-trajectory coordinates, while values retain both components. Learnable queries aggregate subcarriers into frequency slots, which are fused into temporal
tokens. Trained jointly from scratch, TGT with TokenMLP achieves the highest mean accuracy of 92.83% among all evaluated frontend-backend combinations on the self-collected
dataset. Experiments on EHUNAM and Widar further support the applicability of TGT to cross-domain presence detection and gesture recognition.
Read the full abstract ▾
All authors Ziyi Wang, Kenuo Xu, Jichu Jiang, Yumeng Yang, Zheng Chen, Xiaofei Bai, Muge Chen, Xuyang Chen, Jinglei He, Jannik Hammel Nielsen, Stefan Schmid
Machine Learning · Cross-listed from cs.CL
From Abusive Language Classification to Sequence Labeling Identification
Nicolas Zampieri, Ignacio Lopez, Manon Girard et al. (+1 more)
Industrial content moderation must process massive message streams under tight latency constraints, yet most abusive
language (AL) detection systems rely on sentence-level classification (ALC), which neither localizes abusive spans nor identifies who is targeted. We define Abusive
Language Identification (ALI) as a sequence-labeling task that jointly extracts AL spans and target mentions, and assess whether this approach can be used for text moderation. On a pilot corpus drawn from a production moderation pipeline, we compare ALI with ALC on cross-domain generalization and implicit abuse, and we also evaluate AL and target span detection. ALI remains competitive with ALC while providing localized outputs for moderators, with a modest and configuration-sensitive advantage on implicit abuse. Exact AL boundaries and target spans remain difficult to recover. We complement this comparison with a qualitative analysis and discuss perspectives on complete target–span linking and on structured
benchmarks for ALI.
Read the full abstract ▾
All authors Nicolas Zampieri, Ignacio Lopez, Manon Girard, Jeremy Auguste
Machine Learning
When Are Concept Bottleneck Model Explanations Faithful and Compact?
Stefano Teso, Emanuele Marconato, Steve Azzolin et al. (+1 more)
Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. However, their explanations are often derived heuristically. Building on formal explainability, we argue they should also be faithful, i.e., not misreport which concepts actually matter. We show that, for widespread CBM architectures, including recent VLM-based variants, faithful explanations must include all concepts in the bottleneck, compromising interpretability when this is large. This result applies to both heuristic and faithful-by-construction formal explanations. To encourage the existence of compact faithful explanations, we suggest i) modeling concepts probabilistically as binary or categorical random variables (rather than logits), and ii) employing per-concept training-time sparsification via group lasso (rather than regular elastic net). We also extend
algorithms from formal explainability to CBMs, and show they outperform natural heuristics in terms of guarantees and explanation size. Overall, our work warns against naive interpretability claims and provides formal conditions and practical strategies for ensuring CBMs are as interpretable as advertised.
Read the full abstract ▾
All authors Stefano Teso, Emanuele Marconato, Steve Azzolin, Antonio Vergari
Machine Learning
dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
Alfred Nilsson, Joel Lapin, Samuel H. Payne et al. (+2 more)
We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de novo sequencing models on the diverse, multi-species Kingdoms corpus under the same greedy-decoding protocol. Without peptide labels, dIon learns strong native peptide-similarity geometry compared with other learned models; with limited peptide-supervised adaptation, it achieves the best
retrieval and pair-discrimination performance across all representation
benchmarks.
Read the full abstract ▾
All authors Alfred Nilsson, Joel Lapin, Samuel H. Payne, Mathias Wilhelm, Lukas Käll
Machine Learning
What May an Agent Change About Itself? A Containment Floor for Self-Configuring Agent Runtimes
Sajib Hossain and Moeen Uddin Mahmud
Many
agent runtimes give the
agent a tool for editing its own configuration. Some of that configuration grants abilities, such as enabling a tool. Other parts set the
agent's limits: which directories it may write to, who may send it messages, which network address it listens on, how callers authenticate, and the gate that blocks risky writes. If the
agent can edit those limits, a single ordinary request can widen them. We study this in a deployed, model-agnostic runtime. We propose a rule: the
agent may change fields that grant abilities, and may never change fields that set its limits. We enforce the rule as a containment floor inside the configuration tool and measure what happens with and without it. Without the floor, a frontier model wrote a protected value on 25 of 72 ordinary requests that gave it permission to change settings, often when the request never named the field. Prohibitions written in the system
prompt failed in a predictable way. A
prompt that listed the protected field names stopped every request that used those names (0 of 36 saved, against 17 of 36 with no
prompt) and did not stop the requests that only described the goal (10 of 36 saved, against 8 of 36). A
prompt that described the forbidden effects did the reverse. With the floor, 0 of 167 protected writes were saved, although the models attempted a protected write in 65 of those cases. A search for other routes through the tool found only one, a pinned shell, which the floor's scope statement already excludes. The study covers two models and a single
agent. We state what that does and does not support.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries
Chonghe Jiang, Ao Qu, Siyuan Liu et al. (+9 more)
Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining executable solutions from verifier feedback. Methods such as TTT-Discover use test-time training (TTT) to update the solution-generating LLM from verifier feedback, adapting its generation policy to improve subsequent proposals on the target problem. However, this becomes expensive when reliable execution requires a large model, since training must maintain gradients, optimizer states, and policy statistics while repeatedly generating long, structured outputs. It also complicates credit assignment: outcome-level verifier feedback must jointly evaluate the high-level strategy and its low-level implementation. In this work, we introduce Guidance-TTT, which separates these roles. A compact guidance model is trained at test time to propose high-level strategic changes, while a frozen execution model implements them as complete executable solutions. At each step, the system selects a promising previously discovered solution, proposes a change, executes and verifies it, and updates only the guidance model using an adaptive group-relative RL objective. This concentrates test-time learning on short strategic decisions while retaining the implementation capability of a substantially stronger model without adapting it. Without web access, Guidance-TTT produces strong solutions across four distinct domains: combinatorial optimization (Polyomino Packing), heuristic programming (AHC058), machine learning (Lasso), and GPU kernel optimization (TriMul). Across these tasks, it outperforms the best solutions reported in prior work while remaining competitive with state-of-the-art results on public online leaderboards. Code is available at https://github.com/Human-
Agent-Society/reef/tree/guidance-ttt-support.
Read the full abstract ▾
All authors Chonghe Jiang, Ao Qu, Siyuan Liu, Ruoyun Ma, Zijian Zhou, Dingyi Zhuang, Bo Liu, Han Zheng, Hanfei Yu, Baichuan Mo, Jinhua Zhao, Paul Pu Liang
Machine Learning
Ramp Metering Control via Hybrid State Deep Reinforcement Learning in Partially Observable Connected Vehicle Environments
Youcef Mehamlia, Nadir Farhi and Meriem Bouali
Freeway on-ramp merges are major sources of congestion, causing significant economic and environmental costs. While Deep Reinforcement Learning (DRL) offers a promising solution for ramp metering, existing approaches rely primarily on aggregated macroscopic data. Connected vehicles (CVs) provide vehicle-level observations that can complement aggregate traffic measurements, but their limited penetration produces incomplete microscopic information. This paper proposes a hybrid observation representation combining macroscopic traffic measurements with a two-channel grid encoding observed CV presence and speed. A Dueling Double Deep Q-Network processes these inputs to select ramp-metering green durations. The controller is trained under varying traffic demands and CV penetration rates and evaluated against ALINEA and macroscopic-only DRL variants in SUMO. Across 50 matched evaluation scenarios, the hybrid controller under partial CV visibility reduces the reported total travel time by 11.4 % and mean spillback duration by 84.9 % relative to ALINEA. Evaluating the same trained policy with full CV visibility yields a further travel-time reduction of approximately 1.6 %. Analysis across penetration rates suggests that the performance gap decreases as microscopic observations become more complete. These results support the use of complementary macroscopic and sparse microscopic observations for learning-based ramp metering. The source code implementation of the model is available at: https://github.com/youcefMehamlia/
Multimodal-DRL-RMC
Read the full abstract ▾
Machine Learning
OCL-PDE: A Generative Framework for PDE Inverse Problems with Observation-Complementary Latents
Ding Yang, Chuqi Chen, Chang Ma et al. (+1 more)
Partial differential equation (PDE) inverse problems are often ill-posed, making fine-scale details difficult to recover. We address this problem by introducing a learned observation-complementary latent representation that preserves reconstruction-relevant information and is combined with the observation to reconstruct the unknown field. Building on this representation, we propose OCL-PDE, a generative framework that encourages the observation to guide large-scale structure and the latent to supply complementary fine-scale details. OCL-PDE is built on a physics-aware autoencoder (AE) and conditional Flow Matching, supporting inverse reconstruction as well as forward PDE prediction. Experiments demonstrate improved reconstruction accuracy and fine-detail recovery compared with the evaluated baselines.
Read the full abstract ▾
All authors Ding Yang, Chuqi Chen, Chang Ma, Yang Xiang