# Research Papers — 2026-02 · bundle page 152 of 210

> Full-text markdown of papers #7551–7600 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/152
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/151.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/153.md)

### RAIGen: Rare Attribute Identification in Text-to-Image Generative Models

Authors: Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie, Muhammad Awais, Anjan Dutta
Published: 2026-02-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.06806v3

Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultural, or stylistic) yet still encoded in model representations. We introduce RAIGen, the first framework, to our knowledge, for label-free rare-attribute discovery in diffusion models, requiring no predefined minority categories. RAIGen leverages Matryoshka Sparse Autoencoders and a novel minority metric combining neuron activation frequency with semantic distinctiveness to identify interpretable neurons whose top-activating images reveal underrepresented attributes. Experiments show RAIGen discovers attributes beyond fixed fairness categories in Stable Diffusion, scales to larger models such as SDXL, supports systematic auditing across architectures, and enables targeted amplification of rare attributes during generation. The project page is available at https://vssilpa.github.io/RAIGen_webpage/ .

---

### A Unified Formula for Affine Transformations between Calibrated Cameras

Authors: Levente Hajder
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06805v1

In this technical note, we derive a closed-form expression for the affine transformation mapping local image patches between two calibrated views. We show that the transformation is a function of the relative camera pose, the image coordinates, and the local surface normal.

---

### On the Non-Identifiability of Steering Vectors in Large Language Models

Authors: Sohan Venkatesh, Ashish Mahendran Kurapath
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06801v4

Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and uniquely recoverable from input-output behavior. We show that, under white-box single-layer access, steering vectors are fundamentally non-identifiable due to large equivalence classes of behaviorally indistinguishable interventions. Empirically, we find that orthogonal perturbations achieve near-equivalent efficacy with negligible effect sizes across multiple models and traits, with pre-trained semantic classifiers confirming equivalence at the output level. We estimate null-space dimensionality via SVD of activation covariance matrices and validate that equivalence holds robustly throughout the operationally relevant steering range. Critically, we show that non-identifiability is a robust geometric property that persists across diverse prompt distributions. These findings reveal fundamental interpretability limits and highlight the need for structural constraints beyond behavioral testing to enable reliable alignment interventions.

---

### FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matching

Authors: Ran Cheng, Lailai Zhu
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06800v1

Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine learning (ML)-based forecasting pipelines due to reliance on traditional variational methods. Recent generative ML-based DA methods offer a promising alternative but typically require many sampling steps and suffer from error accumulation under long-horizon auto-regressive rollouts with cycling assimilation. We propose FlowDA, a low-latency weather-scale generative DA framework based on flow matching. FlowDA conditions on observations through a SetConv-based embedding and fine-tunes the Aurora foundation model to deliver accurate, efficient, and robust analyses. Experiments across observation rates decreasing from $3.9\%$ to $0.1\%$ demonstrate superior performance of FlowDA over strong baselines with similar tunable-parameter size. FlowDA further shows robustness to observational noise and stable performance in long-horizon auto-regressive cycling DA. Overall, FlowDA points to an efficient and scalable direction for data-driven DA.

---

### Visual Word Sense Disambiguation with CLIP through Dual-Channel Text Prompting and Image Augmentations

Authors: Shamik Bhattacharya, Daniel Perkins, Yaren Dogan, Vineeth Konjeti, Sudarshan Srinivasan, Edmon Begoli
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06799v1

Ambiguity poses persistent challenges in natural language understanding for large language models (LLMs). To better understand how lexical ambiguity can be resolved through the visual domain, we develop an interpretable Visual Word Sense Disambiguation (VWSD) framework. The model leverages CLIP to project ambiguous language and candidate images into a shared multimodal space. We enrich textual embeddings using a dual-channel ensemble of semantic and photo-based prompts with WordNet synonyms, while image embeddings are refined through robust test-time augmentations. We then use cosine similarity to determine the image that best aligns with the ambiguous text. When evaluated on the SemEval-2023 VWSD dataset, enriching the embeddings raises the MRR from 0.7227 to 0.7590 and the Hit Rate from 0.5810 to 0.6220. Ablation studies reveal that dual-channel prompting provides strong, low-latency performance, whereas aggressive image augmentation yields only marginal gains. Additional experiments with WordNet definitions and multilingual prompt ensembles further suggest that noisy external signals tend to dilute semantic specificity, reinforcing the effectiveness of precise, CLIP-aligned prompts for visual word sense disambiguation.

---

### Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay

Authors: Binghui Li, Zilin Wang, Fengling Chen, Shiyang Zhao, Ruiheng Zheng, Lei Wu
Published: 2026-02-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06797v3

We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training dynamics into signal learning and noise forgetting. In power-law kernel regression, these two components are governed by a source exponent $s>0$ and a capacity exponent $q>1$, respectively, with smaller $s$ corresponding to harder tasks. For a fixed training horizon $N$, we characterize the schedules that minimize the final-step loss under a stability constraint and reveal a sharp phase transition. In the easy-task regime $s>1-1/q$, the optimal schedule follows power decay from the beginning of training; in the hard-task regime $s<1-1/q$, it becomes warmup-stable-decay (WSD)-like (Hu et al., 2024), staying at the largest admissible LR for most of training before a final decay. In both regimes, the decay exponent is $2q-1$: task difficulty determines when to decay, while model capacity determines how to decay. Beyond the exact optimum, we study fractional schedules, whose shape is defined over relative training progress. We show that precise tuning of the decay shape is often unnecessary: a broad class of profiles attains the optimal convergence rate, while overly slow terminal decay leads to schedule-induced capacity saturation. Finally, for one-pass SGD in kernel regression, FSL-motivated power-decay schedules achieve optimal last-iterate rates. Experiments support the theoretical predictions and the task-dependent transition between early and delayed decay.

---

### Optimal Learning-Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay

Authors: Binghui Li, Zilin Wang, Fengling Chen, Shiyang Zhao, Ruiheng Zheng, Lei Wu
Published: 2026-02-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06797v2

We study optimal learning-rate schedules (LRSs) under the functional scaling law (FSL) framework introduced in Li et al. (2025), which accurately models the loss dynamics of both linear regression and large language model (LLM) pre-training. Within FSL, loss dynamics are governed by two exponents: a source exponent $s>0$ controlling the rate of signal learning, and a capacity exponent $β>1$ determining the rate of noise forgetting. Focusing on a fixed training horizon $N$, we derive the optimal LRSs and reveal a sharp phase transition. In the easy-task regime $s \ge 1 - 1/β$, the optimal schedule follows a power decay to zero, $η^*(z) = η_{\mathrm{peak}}(1 - z/N)^{2β- 1}$, where the peak learning rate scales as $η_{\mathrm{peak}} \eqsim N^{-ν}$ for an explicit exponent $ν= ν(s,β)$. In contrast, in the hard-task regime $s < 1 - 1/β$, the optimal LRS exhibits a warmup-stable-decay (WSD) (Hu et al. (2024)) structure: it maintains the largest admissible learning rate for most of training and decays only near the end, with the decay phase occupying a vanishing fraction of the horizon. We further analyze optimal shape-fixed schedules, where only the peak learning rate is tuned -- a strategy widely adopted in practiceand characterize their strengths and intrinsic limitations. This yields a principled evaluation of commonly used schedules such as cosine and linear decay. Finally, we apply the power-decay LRS to one-pass stochastic gradient descent (SGD) for kernel regression and show the last iterate attains the exact minimax-optimal rate, eliminating the logarithmic suboptimality present in prior analyses. Numerical experiments corroborate our theoretical predictions.

---

### Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling

Authors: Kate Sanders, Nathaniel Weir, Sapana Chaudhary, Kaj Bostrom, Huzefa Rangwala
Published: 2026-02-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.06795v1

An impediment to using Large Language Models (LLMs) for reasoning output verification is that LLMs struggle to reliably identify errors in thinking traces, particularly in long outputs, domains requiring expert knowledge, and problems without verifiable rewards. We propose a data-driven approach to automatically construct highly granular reasoning error taxonomies to enhance LLM-driven error detection on unseen reasoning traces. Our findings indicate that classification approaches that leverage these error taxonomies, or "rubrics", demonstrate strong error identification compared to baseline methods in technical domains like coding, math, and chemical engineering. These rubrics can be used to build stronger LLM-as-judge reward functions for reasoning model training via reinforcement learning. Experimental results show that these rewards have the potential to improve models' task accuracy on difficult domains over models trained by general LLMs-as-judges by +45%, and approach performance of models trained by verifiable rewards while using as little as 20% as many gold labels. Through our approach, we extend the usage of reward rubrics from assessing qualitative model behavior to assessing quantitative model correctness on tasks typically learned via RLVR rewards. This extension opens the door for teaching models to solve complex technical problems without a full dataset of gold labels, which are often highly costly to procure.

---

### Rare Event Analysis of Large Language Models

Authors: Jake McAllister Dorman, Edward Gillman, Dominic C. Rose, Jamie F. Mair, Juan P. Garrahan
Published: 2026-02-06
Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech
arXiv: https://arxiv.org/abs/2602.06791v2

Being probabilistic models, during inference large language models (LLMs) display rare events: behaviour that is far from typical but highly significant. By definition all rare events are hard to see, but the enormous scale of LLM usage means that events completely unobserved during development are likely to become prominent in deployment. Here we present an end-to-end framework for the systematic analysis of rare events in LLMs. We provide a practical implementation spanning theory, efficient generation strategies, probability estimation and error analysis, which we illustrate with concrete examples. We outline extensions and applications to other models and contexts, highlighting the generality of the concepts and techniques presented here.

---

### Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences

Authors: Idan Pipano, Shoham Sabach, Kavosh Asadi, Mohammad Ghavamzadeh
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06788v1

DPO and related algorithms align language models by directly optimizing the RLHF objective: find a policy that maximizes the Bradley-Terry reward while staying close to a reference policy through a KL divergence penalty. Previous work showed that this approach could be further generalized: the original problem remains tractable even if the KL divergence is replaced by a family of $f$-divergence with a convex generating function $f$. Our first contribution is to show that convexity of $f$ is not essential. Instead, we identify a more general condition, referred to as DPO-inducing, that precisely characterizes when the RLHF problem remains tractable. Our next contribution is to establish a second condition on $f$ that is necessary to prevent probability displacement, a known empirical phenomenon in which the probabilities of the winner and the loser responses approach zero. We refer to any $f$ that satisfies this condition as displacement-resistant. We finally focus on a specific DPO-inducing and displacement-resistant $f$, leading to our novel SquaredPO loss. Compared to DPO, this new loss offers stronger theoretical guarantees while performing competitively in practice.

---

### Weisfeiler and Lehman Go Categorical

Authors: Seongjin Choi, Gahee Kim, Se-Young Yun
Published: 2026-02-06
Categories: cs.LG, math.CT
arXiv: https://arxiv.org/abs/2602.06787v1

While lifting map has significantly enhanced the expressivity of graph neural networks, extending this paradigm to hypergraphs remains fragmented. To address this, we introduce the categorical Weisfeiler-Lehman framework, which formalizes lifting as a functorial mapping from an arbitrary data category to the unifying category of graded posets. When applied to hypergraphs, this perspective allows us to systematically derive Hypergraph Isomorphism Networks, a family of neural architectures where the message passing topology is strictly determined by the choice of functor. We introduce two distinct functors from the category of hypergraphs: an incidence functor and a symmetric simplicial complex functor. While the incidence architecture structurally mirrors standard bipartite schemes, our functorial derivation enforces a richer information flow over the resulting poset, capturing complex intersection geometries often missed by existing methods. We theoretically characterize the expressivity of these models, proving that both the incidence-based and symmetric simplicial approaches subsume the expressive power of the standard Hypergraph Weisfeiler-Lehman test. Extensive experiments on real-world benchmarks validate these theoretical findings.

---

### Machine Learning for Detection and Severity Estimation of Sweetpotato Weevil Damage in Field and Lab Conditions

Authors: Doreen M. Chelangat, Sudi Murindanyi, Bruce Mugizi, Paul Musana, Benard Yada, Milton A. Otema, Florence Osaru, Andrew Katumba, Joyce Nakatumba-Nabende
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06786v1

Sweetpotato weevils (Cylas spp.) are considered among the most destructive pests impacting sweetpotato production, particularly in sub-Saharan Africa. Traditional methods for assessing weevil damage, predominantly relying on manual scoring, are labour-intensive, subjective, and often yield inconsistent results. These challenges significantly hinder breeding programs aimed at developing resilient sweetpotato varieties. This study introduces a computer vision-based approach for the automated evaluation of weevil damage in both field and laboratory contexts. In the field settings, we collected data to train classification models to predict root-damage severity levels, achieving a test accuracy of 71.43%. Additionally, we established a laboratory dataset and designed an object detection pipeline employing YOLO12, a leading real-time detection model. This methodology incorporated a two-stage laboratory pipeline that combined root segmentation with a tiling strategy to improve the detectability of small objects. The resulting model demonstrated a mean average precision of 77.7% in identifying minute weevil feeding holes. Our findings indicate that computer vision technologies can provide efficient, objective, and scalable assessment tools that align seamlessly with contemporary breeding workflows. These advancements represent a significant improvement in enhancing phenotyping efficiency within sweetpotato breeding programs and play a crucial role in mitigating the detrimental effects of weevils on food security.

---

### Revisiting Emotions Representation for Recognition in the Wild

Authors: Joao Baptista Cardia Neto, Claudio Ferrari, Stefano Berretti
Published: 2026-02-06
Categories: cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.06778v1

Facial emotion recognition has been typically cast as a single-label classification problem of one out of six prototypical emotions. However, that is an oversimplification that is unsuitable for representing the multifaceted spectrum of spontaneous emotional states, which are most often the result of a combination of multiple emotions contributing at different intensities. Building on this, a promising direction that was explored recently is to cast emotion recognition as a distribution learning problem. Still, such approaches are limited in that research datasets are typically annotated with a single emotion class. In this paper, we contribute a novel approach to describe complex emotional states as probability distributions over a set of emotion classes. To do so, we propose a solution to automatically re-label existing datasets by exploiting the result of a study in which a large set of both basic and compound emotions is mapped to probability distributions in the Valence-Arousal-Dominance (VAD) space. In this way, given a face image annotated with VAD values, we can estimate the likelihood of it belonging to each of the distributions, so that emotional states can be described as a mixture of emotions, enriching their description, while also accounting for the ambiguous nature of their perception. In a preliminary set of experiments, we illustrate the advantages of this solution and a new possible direction of investigation. Data annotations are available at https://github.com/jbcnrlz/affectnet-b-annotation.

---

### Next-generation cyberattack detection with large language models: anomaly analysis across heterogeneous logs

Authors: Yassine Chagna, Antal Goldschmidt
Published: 2026-02-06
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.06777v1

This project explores large language models (LLMs) for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are inherently sensitive, making clean datasets rare. We address these challenges through three contributions: (1) LogAtlas-Foundation-Sessions and LogAtlas-Defense-Set, balanced and heterogeneous log datasets with explicit attack annotations and privacy preservation; (2) empirical benchmarking revealing why standard metrics such as F1 and accuracy are misleading for security applications; and (3) a two phase training framework combining log understanding (Base-AMAN, 3B parameters) with real time detection (AMAN, 0.5B parameters via knowledge distillation). Results demonstrate practical feasibility, with inference times of 0.3-0.5 seconds per session and operational costs below 50 USD per day.

---

### Fair Transit Stop Placement: A Clustering Perspective and Beyond

Authors: Haris Aziz, Ling Gai, Yuhang Guo, Jeremy Vollen
Published: 2026-02-06
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2602.06776v2

We study the transit stop placement (TrSP) problem in general metric spaces, where agents travel between source-destination pairs and may either walk directly or utilize a shuttle service via selected transit stops. We investigate fairness in TrSP through the lens of justified representation (JR) and the core, and uncover a structural correspondence with fair clustering. Specifically, we show that a constant-factor approximation to proportional fairness in clustering can be used to guarantee a constant-factor biparameterized approximation to core. We establish a lower bound of 1.366 on the approximability of JR, and moreover show that no clustering algorithm can approximate JR within a factor better than 3. Going beyond clustering, we propose the Expanding Cost Algorithm, which achieves a tight 2.414-approximation for JR, but does not give any bounded core guarantee. In light of this, we introduce a parameterized algorithm that interpolates between these approaches, and enables a tunable trade-off between JR and core. Finally, we complement our results with an experimental analysis using small-market public carpooling data.

---

### Robust Online Learning

Authors: Sajad Ashkezari
Published: 2026-02-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.06775v2

We study the problem of learning robust classifiers where the classifier will receive a perturbed input. Unlike robust PAC learning studied in prior work, here the clean data and its label are also adversarially chosen. We formulate this setting as an online learning problem and consider both the realizable and agnostic learnability of hypothesis classes. We define a new dimension of classes and show it controls the mistake bounds in the realizable setting and the regret bounds in the agnostic setting. In contrast to the dimension that characterizes learnability in the PAC setting, our dimension is rather simple and resembles the Littlestone dimension. We generalize our dimension to multiclass hypothesis classes and prove similar results in the realizable case. Finally, we study the case where the learner does not know the set of allowed perturbations for each point and only has some prior on them.

---

### Towards Understanding What State Space Models Learn About Code

Authors: Jiali Wu, Abhinav Anand, Shweta Verma, Mira Mezini
Published: 2026-02-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.06774v2

State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture. Prior work shows that, when trained under comparable conditions, SSMs can match or surpass Transformers on code understanding tasks. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models learn along with the direct comparison between SSM and Transformer models in this domain. Our analysis shows that SSMs capture syntactic and semantic structure more effectively than Transformers during pretraining but forgets certain relations during fine-tuning on some tasks. To investigate this behavior, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model by upto +6 MRR on NLCodeSearch. This demonstrates that our analysis not only explains model behavior but also leads directly to better designs.

---

### On the Convergence of Multicalibration Gradient Boosting

Authors: Daniel Haimovich, Fridolin Linder, Lorenzo Perini, Niek Tax, Milan Vojnovic
Published: 2026-02-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.06773v2

Multicalibration gradient boosting has recently emerged as a scalable method that empirically produces approximately multicalibrated predictors and has been deployed at web scale. Despite this empirical success, its convergence properties are not well understood. In this paper, we provide computational guarantees for multicalibration gradient boosting algorithms. We show that the magnitude of successive prediction updates decays at $O(1/\sqrt{T})$, which implies the same convergence rate bound for the empirical multicalibration error over rounds. Under additional smoothness assumptions on the weak learners, this rate improves to linear convergence. We further establish convergence for adaptive variants. Experiments on real-world datasets support our theory and clarify the regimes in which the method achieves fast convergence.

---

### Calibrating Generative AI to Produce Realistic Essays for Data Augmentation

Authors: Edward W. Wolfe, Justin O. Barber
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06772v1

Data augmentation can mitigate limited training data in machine-learning automated scoring engines for constructed response items. This study seeks to determine how well three approaches to large language model prompting produce essays that preserve the writing quality of the original essays and produce realistic text for augmenting ASE training datasets. We created simulated versions of student essays, and human raters assigned scores to them and rated the realism of the generated text. The results of the study indicate that the predict next prompting strategy produces the highest level of agreement between human raters regarding simulated essay scores, predict next and sentence strategies best preserve the rated quality of the original essay in the simulated essays, and predict next and 25 examples strategies produce the most realistic text as judged by human raters.

---

### AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models

Authors: Fengpeng Li, Kemou Li, Qizhou Wang, Bo Han, Jiantao Zhou
Published: 2026-02-06
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.06771v2

Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased concepts, even under semantically related prompts. Retention means unrelated concepts are preserved so the model's overall utility stays intact. Both are critical for concept erasure in practice, yet addressing them simultaneously is challenging, as existing works typically improve one factor while sacrificing the other. Prior work typically strengthens one while degrading the other, e.g., mapping a single erased prompt to a fixed safe target leaves class level remnants exploitable by prompt attacks, whereas retention-oriented schemes underperform against adaptive adversaries. This paper introduces Adversarial Erasure with Gradient Informed Synergy (AEGIS), a retention-data-free framework that advances both robustness and retention.

---

### Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities

Authors: Marco Bagatella, Thomas Rupf, Georg Martius, Andreas Krause
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06769v1

Recent advancements in zero-shot reinforcement learning (RL) have facilitated the extraction of diverse behaviors from unlabeled, offline data sources. In particular, forward-backward algorithms (FB) can retrieve a family of policies that can approximately solve any standard RL problem (with additive rewards, linear in the occupancy measure), given sufficient capacity. While retaining zero-shot properties, we tackle the greater problem class of RL with general utilities, in which the objective is an arbitrary differentiable function of the occupancy measure. This setting is strictly more expressive, capturing tasks such as distribution matching or pure exploration, which may not be reduced to additive rewards. We show that this additional complexity can be captured by a novel, maximum entropy (soft) variant of the forward-backward algorithm, which recovers a family of stochastic policies from offline data. When coupled with zero-order search over compact policy embeddings, this algorithm can sidestep iterative optimization schemes, and optimizes general utilities directly at test-time. Across both didactic and high-dimensional experiments, we demonstrate that our method retains favorable properties of FB algorithms, while also extending their range to more general RL problems.

---

### Sparse Spike Encoding of Channel Responses for Energy Efficient Human Activity Recognition

Authors: Eleonora Cicciarella, Riccardo Mazzieri, Jacopo Pegoraro, Michele Rossi
Published: 2026-02-06
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.06766v1

ISAC enables pervasive monitoring, but modern sensing algorithms are often too complex for energy-constrained edge devices. This motivates the development of learning techniques that balance accuracy performance and energy efficiency. Spiking Neural Networks (SNNs) are a promising alternative, processing information as sparse binary spike trains and potentially reducing energy consumption by orders of magnitude. In this work, we propose a spiking convolutional autoencoder (SCAE) that learns tailored spike-encoded representations of channel impulse responses (CIR), jointly trained with an SNN for human activity recognition (HAR), thereby eliminating the need for Doppler domain preprocessing. The results show that our SCAE-SNN achieves F1 scores comparable to a hybrid approach (almost 96%), while producing substantially sparser spike encoding (81.1% sparsity). We also show that encoding CIR data prior to classification improves both HAR accuracy and efficiency. The code is available at https://github.com/ele-ciccia/SCAE-SNN-HAR.

---

### R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging

Authors: Yanlin Lai, Mitt Huang, Hangyu Guo, Xiangfeng Wang, Haodong Li, Shaoxiong Zhan, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, Chun Yuan, Zheng Ge et al.
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06763v1

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate rationales before predicting preferences. Yet in GenRM training and evaluation, practice remains outcome-label-only, leaving reasoning quality unchecked. We show that reasoning fidelity-the consistency between a GenRM's preference decision and reference decision rationales-is highly predictive of downstream RLHF outcomes, beyond standard label accuracy. Specifically, we repurpose existing reward-model benchmarks to compute Spurious Correctness (S-Corr)-the fraction of label-correct decisions with rationales misaligned with golden judgments. Our empirical evaluation reveals substantial S-Corr even for competitive GenRMs, and higher S-Corr is associated with policy degeneration under optimization. To improve fidelity, we propose Rationale-Centric Alignment, R-Align, which augments training with gold judgments and explicitly supervises rationale alignment. R-Align reduces S-Corr on RM benchmarks and yields consistent gains in actor performance across STEM, coding, instruction following, and general tasks.

---

### Orientation-Robust Latent Motion Trajectory Learning for Annotation-free Cardiac Phase Detection in Fetal Echocardiography

Authors: Yingyu Yang, Qianye Yang, Can Peng, Elena D'Alberti, Olga Patey, Aris T. Papageorghiou, J. Alison Noble
Published: 2026-02-06
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.06761v2

Fetal echocardiography is essential for detecting congenital heart disease (CHD), facilitating pregnancy management, optimized delivery planning, and timely postnatal interventions. Among standard imaging planes, the four-chamber view (4CV) provides important information for CHD diagnosis, where clinicians carefully inspect the end-diastolic (ED) and end-systolic (ES) phases to evaluate cardiac structure and motion. Automated detection of these cardiac phases is thus a critical component towards fully automated CHD analysis. However, existing approaches typically rely on manual annotation of ED/ES frames, which is labour-intensive and time-consuming. We present ORBIT (Orientation-Robust Beat Inference from Trajectories), a self-supervised framework that identifies cardiac phases without manual annotations under various fetal heart orientation. ORBIT employs registration as self-supervision task and learns a latent motion trajectory of cardiac deformation, whose turning points capture transitions between cardiac relaxation and contraction, enabling accurate and orientation-robust localization of ED and ES frames across diverse fetal positions. Trained exclusively on normal fetal echocardiography videos, ORBIT achieves consistent performance on both normal (mean absolute error 1.9 frames for ED and 1.6 for ES) and CHD cases (mean absolute error 2.4 frames for ED and 2.1 for ES), outperforming existing annotation-free approaches constrained by fixed orientation assumptions. These results highlight the potential of ORBIT to facilitate robust cardiac phase detection directly from 4CV fetal echocardiography.

---

### Orientation-Robust Latent Motion Trajectory Learning for Annotation-free Cardiac Phase Detection in Fetal Echocardiography

Authors: Yingyu Yang, Qianye Yang, Can Peng, Elena D'Alberti, Olga Patey, Aris T. Papageorghiou, J. Alison Noble
Published: 2026-02-06
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.06761v1

Fetal echocardiography is essential for detecting congenital heart disease (CHD), facilitating pregnancy management, optimized delivery planning, and timely postnatal interventions. Among standard imaging planes, the four-chamber (4CH) view provides comprehensive information for CHD diagnosis, where clinicians carefully inspect the end-diastolic (ED) and end-systolic (ES) phases to evaluate cardiac structure and motion. Automated detection of these cardiac phases is thus a critical component toward fully automated CHD analysis. Yet, in the absence of fetal electrocardiography (ECG), manual identification of ED and ES frames remains a labor-intensive bottleneck. We present ORBIT (Orientation-Robust Beat Inference from Trajectories), a self-supervised framework that identifies cardiac phases without manual annotations under various fetal heart orientation. ORBIT employs registration as self-supervision task and learns a latent motion trajectory of cardiac deformation, whose turning points capture transitions between cardiac relaxation and contraction, enabling accurate and orientation-robust localization of ED and ES frames across diverse fetal positions. Trained exclusively on normal fetal echocardiography videos, ORBIT achieves consistent performance on both normal (MAE = 1.9 frames for ED and 1.6 for ES) and CHD cases (MAE = 2.4 frames for ED and 2.1 for ES), outperforming existing annotation-free approaches constrained by fixed orientation assumptions. These results highlight the potential of ORBIT to facilitate robust cardiac phase detection directly from 4CH fetal echocardiography.

---

### A Unified Framework for LLM Watermarks

Authors: Thibaud Gloaguen, Robin Staab, Nikola Jovanović, Martin Vechev
Published: 2026-02-06
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06754v1

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up approach. Crucially, there is no general and principled formulation for LLM watermarking. In this work, we show that most existing and widely used watermarking schemes can in fact be derived from a principled constrained optimization problem. Our formulation unifies existing watermarking methods and explicitly reveals the constraints that each method optimizes. In particular, it highlights an understudied quality-diversity-power trade-off. At the same time, our framework also provides a principled approach for designing novel watermarking schemes tailored to specific requirements. For instance, it allows us to directly use perplexity as a proxy for quality, and derive new schemes that are optimal with respect to this constraint. Our experimental evaluation validates our framework: watermarking schemes derived from a given constraint consistently maximize detection power with respect to that constraint.

---

### Gold Exploration using Representations from a Multispectral Autoencoder

Authors: Argyro Tsandalidou, Konstantinos Dogeas, Eleftheria Tetoula Tsonga, Elisavet Parselia, Georgios Tsimiklis, George Arvanitakis
Published: 2026-02-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.06748v1

Satellite imagery is employed for large-scale prospectivity mapping due to the high cost and typically limited availability of on-site mineral exploration data. In this work, we present a proof-of-concept framework that leverages generative representations learned from multispectral Sentinel-2 imagery to identify gold-bearing regions from space. An autoencoder foundation model, called Isometric, which is pretrained on the large-scale FalconSpace-S2 v1.0 dataset, produces information-dense spectral-spatial representations that serve as inputs to a lightweight XGBoost classifier. We compare this representation-based approach with a raw spectral input baseline using a dataset of 63 Sentinel-2 images from known gold and non-gold locations. The proposed method improves patch-level accuracy from 0.51 to 0.68 and image-level accuracy from 0.55 to 0.73, demonstrating that generative embeddings capture transferable mineralogical patterns even with limited labeled data. These results highlight the potential of foundation-model representations to make mineral exploration more efficient, scalable, and globally applicable.

---

### Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions

Authors: Alessandro Abate, Giuseppe De Giacomo, Mathias Jackermeier, Jan Kretínský, Maximilian Prokop, Christoph Weinhuber
Published: 2026-02-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06746v2

We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks. We consider tasks specified as linear temporal logic (LTL) formulae, which are commonly used in formal methods to specify properties of systems, and have recently been successfully adopted in RL. In this setting, we present a novel task embedding technique leveraging a new generation of semantic LTL-to-automata translations, originally developed for temporal synthesis. The resulting semantically labelled automata contain rich, structured information in each state that allow us to (i) compute the automaton efficiently on-the-fly, (ii) extract expressive task embeddings used to condition the policy, and (iii) naturally support full LTL. Experimental results in a variety of domains demonstrate that our approach achieves state-of-the-art performance and is able to scale to complex specifications where existing methods fail.

---

### Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions

Authors: Alessandro Abate, Giuseppe De Giacomo, Mathias Jackermeier, Jan Kretínský, Maximilian Prokop, Christoph Weinhuber
Published: 2026-02-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06746v1

We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks. We consider tasks specified as linear temporal logic (LTL) formulae, which are commonly used in formal methods to specify properties of systems, and have recently been successfully adopted in RL. In this setting, we present a novel task embedding technique leveraging a new generation of semantic LTL-to-automata translations, originally developed for temporal synthesis. The resulting semantically labelled automata contain rich, structured information in each state that allow us to (i) compute the automaton efficiently on-the-fly, (ii) extract expressive task embeddings used to condition the policy, and (iii) naturally support full LTL. Experimental results in a variety of domains demonstrate that our approach achieves state-of-the-art performance and is able to scale to complex specifications where existing methods fail.

---

### Clinical-Prior Guided Multi-Modal Learning with Latent Attention Pooling for Gait-Based Scoliosis Screening

Authors: Dong Chen, Zizhuang Wei, Jialei Xu, Xinyang Sun, Zonglin He, Meiru An, Huili Peng, Yong Hu, Kenneth MC Cheung
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06743v1

Adolescent Idiopathic Scoliosis (AIS) is a prevalent spinal deformity whose progression can be mitigated through early detection. Conventional screening methods are often subjective, difficult to scale, and reliant on specialized clinical expertise. Video-based gait analysis offers a promising alternative, but current datasets and methods frequently suffer from data leakage, where performance is inflated by repeated clips from the same individual, or employ oversimplified models that lack clinical interpretability. To address these limitations, we introduce ScoliGait, a new benchmark dataset comprising 1,572 gait video clips for training and 300 fully independent clips for testing. Each clip is annotated with radiographic Cobb angles and descriptive text based on clinical kinematic priors. We propose a multi-modal framework that integrates a clinical-prior-guided kinematic knowledge map for interpretable feature representation, alongside a latent attention pooling mechanism to fuse video, text, and knowledge map modalities. Our method establishes a new state-of-the-art, demonstrating a significant performance gap on a realistic, non-repeating subject benchmark. Our approach establishes a new state of the art, showing a significant performance gain on a realistic, subject-independent benchmark. This work provides a robust, interpretable, and clinically grounded foundation for scalable, non-invasive AIS assessment.

---

### Structural bias in multi-objective optimisation

Authors: Jakub Kudela, Niki van Stein, Thomas Bäck, Anna V. Kononova
Published: 2026-02-06
Categories: cs.NE, math.OC
arXiv: https://arxiv.org/abs/2602.06742v1

Structural bias (SB) refers to systematic preferences of an optimisation algorithm for particular regions of the search space that arise independently of the objective function. While SB has been studied extensively in single-objective optimisation, its role in multi-objective optimisation remains largely unexplored. This is problematic, as dominance relations, diversity preservation and Pareto-based selection mechanisms may introduce or amplify structural effects. In this paper, we extend the concept of structural bias to the multi-objective setting and propose a methodology to study it in isolation from fitness-driven guidance. We introduce a suite of synthetic multi-objective test problems with analytically controlled Pareto fronts and deliberately uninformative objective values. These problems are designed to decouple algorithmic behaviour from problem structure, allowing bias induced purely by algorithmic operators and design choices to be observed. The test suite covers a range of Pareto front shapes, densities and noise levels, enabling systematic analysis of different manifestations of structural bias. We discuss methodological challenges specific to the multi-objective case and outline how existing SB detection approaches can be adapted. This work provides a first step towards behaviour-based benchmarking of multi-objective optimisers, complementing performance-based evaluation and informing more robust algorithm design.

---

### Disentanglement by means of action-induced representations

Authors: Gorka Muñoz-Gil, Hendrik Poulsen Nautrup, Arunava Majumder, Paulin de Schoulepnikoff, Florian Fürrutter, Marius Krumm, Hans J. Briegel
Published: 2026-02-06
Categories: cs.LG, physics.data-an, quant-ph
arXiv: https://arxiv.org/abs/2602.06741v1

Learning interpretable representations with variational autoencoders (VAEs) is a major goal of representation learning. The main challenge lies in obtaining disentangled representations, where each latent dimension corresponds to a distinct generative factor. This difficulty is fundamentally tied to the inability to perform nonlinear independent component analysis. Here, we introduce the framework of action-induced representations (AIRs) which models representations of physical systems given experiments (or actions) that can be performed on them. We show that, in this framework, we can provably disentangle degrees of freedom w.r.t. their action dependence. We further introduce a variational AIR architecture (VAIR) that can extract AIRs and therefore achieve provable disentanglement where standard VAEs fail. Beyond state representation, VAIR also captures the action dependence of the underlying generative factors, directly linking experiments to the degrees of freedom they influence.

---

### Optimized Piecewise Affine Abstractions of Neural Networks with Learnable Activation Functions

Authors: Noah Schwartz, Chandra Kanth Nagesh, Sriram Sankaranarayanan, Ramneet Kaur, Tuhin Sahai, Susmit Jha
Published: 2026-02-06
Categories: cs.LG, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2602.06737v2

We present a generalized framework for the range verification of neural networks featuring non-linear activation functions. Our approach first constructs an ``optimized piecewise affine abstraction" of the network that replaces each non-linear activation function by a piecewise affine (PWA) function plus a bounded error. Such PWA functions are readily amenable to existing neural network verification techniques using specializations of linear arithmetic SMT solvers and mixed-integer optimization approaches. However, there are infinitely many ways to abstract each node, with a natural tradeoff between the number of pieces used, the global error bound, and the complexity of the resulting verification problem. We propose a dynamic programming (DP) algorithm to systematically compute the optimized PWA abstraction for general activation functions, guaranteeing tighter output bounds. The algorithm combines a local DP approximation at each node with a global error bound, yielding a variant of the knapsack problem for deciding how to allocate a fixed budget on the total number of pieces across units so as to minimize the worst-case error bound between the network and its approximation. Although the knapsack problem is itself NP-hard, we can use pseudo-polynomial DP algorithms as well as approximation schemes to solve it efficiently. Crucially, our approach is broadly applicable to diverse networks consisting of non-linear activations, including standard Multi-Layer Perceptrons (MLPs) and recently proposed architectures such as Kolmogorov-Arnold Networks (KANs). Over a series of KAN benchmarks spanning 20 to 22,000 parameters, our approach yields output bounds that are consistently of smaller width than uniform PWA allocation. The overall time taken is roughly comparable while the overhead for computing the optimized abstraction is subsumed by the time taken to compute output bounds.

---

### Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding

Authors: Rishabh Jain, Keisuke Okumura, Michael Amir, Pietro Lio, Amanda Prorok
Published: 2026-02-06
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.06733v2

Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their respective goals without collisions. Solving MAPF optimally is known to be NP-hard, leading to the adoption of learning-based approaches to alleviate the online computational burden. Prevailing approaches, such as Graph Neural Networks (GNNs), are typically constrained to pairwise message passing between agents. However, this limitation leads to suboptimal behaviours and critical issues, such as attention dilution, particularly in dense environments where group (i.e. beyond just two agents) coordination is most critical. Despite the importance of such higher-order interactions, existing approaches have not been able to fully explore them. To address this representational bottleneck, we introduce HMAGAT (Hypergraph Multi-Agent Attention Network), a novel architecture that leverages attentional mechanisms over directed hypergraphs to explicitly capture group dynamics. Empirically, HMAGAT establishes a new state-of-the-art among learning-based MAPF solvers: e.g., despite having just 1M parameters and being trained on 100$\times$ less data, it outperforms the current SoTA 85M parameter model. Through detailed analysis of HMAGAT's attention values, we demonstrate how hypergraph representations mitigate the attention dilution inherent in GNNs and capture complex interactions where pairwise methods fail. Our results illustrate that appropriate inductive biases are often more critical than the training data size or sheer parameter count for multi-agent problems.

---

### Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion

Authors: Tian Lan, Felix Henry, Bin Zhu, Qianghuai Jia, Junyang Ren, Qihang Pu, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06724v1

Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states, including planning procedure and massive search results, within one plain-text context is inherently fragile. To address this, we introduce \textbf{Table-as-Search (TaS)}, a structured planning framework that reformulates the InfoSeeking task as a Table Completion task. TaS maps each query into a structured table schema maintained in an external database, where rows represent search candidates and columns denote constraints or required information. This table precisely manages the search states: filled cells strictly record the history and search results, while empty cells serve as an explicit search plan. Crucially, TaS unifies three distinct InfoSeeking tasks: Deep Search, Wide Search, and the challenging DeepWide Search. Extensive experiments demonstrate that TaS significantly outperforms numerous state-of-the-art baselines across three kinds of benchmarks, including multi-agent framework and commercial systems. Furthermore, our analysis validates the TaS's superior robustness in long-horizon InfoSeeking, alongside its efficiency, scalability and flexibility. Code and datasets are publicly released at https://github.com/AIDC-AI/Marco-Search-Agent.

---

### GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Authors: Zuyao Xu, Yuqi Qiu, Lu Sun, Fasheng Miao, Fubin Wu, Xiang Li, Xinyi Wang, Haozhe Lu, Zhengze Zhang, Yuxin Hu, Jialu Li, Luo Jin et al.
Published: 2026-02-06
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.06718v2

Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Large Language Models (LLMs), this risk has intensified: LLMs are increasingly used for academic writing, but their tendency to fabricate citations (``ghost citations'') poses a systemic threat to citation validity. To quantify this threat, we develop \citeb, an open-source framework for large-scale citation verification, and conduct a comprehensive study of citation validity in the LLM era through three complementary experiments. First, we benchmark 13 LLMs on citation generation task in various research domains, finding that all models hallucinate citations at rate from 14.23\% to 94.93\%. Second, we analyze 2.2 million citations from 56,381 papers at AI/ML and Security venues (2020--2025), finding that 1.07\% of papers contain invalid citations, with an 80.9\% increase in 2025. Third, we survey 97 researchers, finding that 87.2\% use AI-powered tools in their workflows, 76.7\% of reviewers do not thoroughly check references, and 74.5\% view peer review as ineffective at catching citation errors. Based on these findings, we argue that ghost citations represent a systemic threat to academic integrity, and call for coordinated efforts from community to address this challenge.

---

### F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Authors: Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daria Korotyshova, Daniil Gavrilov
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06717v3

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with finite rollout sets that can reinforce only the correct behavior they expose. At practical group sizes, updates can miss rare-correct trajectories while still containing mixed rewards, concentrating probability on more common sampled solutions. We derive the probability of such prompt-local tail-miss events as a function of group size, showing non-monotonic behavior, and in the categorical abstraction characterize how unsampled-correct mass can shrink even as total correct mass grows. Motivated by this analysis, we propose a difficulty-aware scaling coefficient, inspired by Focal loss, that down-weights updates on high-success sampled groups. Empirically, categorical simulation illustrates the same effect in the categorical setting, Maze provides a single-solution test, and LLM experiments include a representative GRPO group-size sweep together with fixed-$N$ transfer across GRPO, DAPO, and CISPO. On Qwen2.5-7B at $N{=}8$, our method improves average math pass@256 from 64.1 $\rightarrow$ 70.3 (GRPO), 69.3 $\rightarrow$ 72.5 (DAPO), and 73.2 $\rightarrow$ 76.8 (CISPO); OOD pass@256 also improves in all three cases, without increasing group size or computational cost.

---

### F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Authors: Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daria Korotyshova, Daniil Gavrilov
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06717v2

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with finite rollout sets that can reinforce only the correct behavior they expose. At practical group sizes, updates can miss rare-correct trajectories while still containing mixed rewards, concentrating probability on more common sampled solutions. We derive the probability of such prompt-local tail-miss events as a function of group size, showing non-monotonic behavior, and in the categorical abstraction characterize how unsampled-correct mass can shrink even as total correct mass grows. Motivated by this analysis, we propose a difficulty-aware scaling coefficient, inspired by Focal loss, that down-weights updates on high-success sampled groups. Empirically, categorical simulation illustrates the same effect in the categorical setting, Maze provides a single-solution test, and LLM experiments include a representative GRPO group-size sweep together with fixed-$N$ transfer across GRPO, DAPO, and CISPO. On Qwen2.5-7B at $N{=}8$, our method improves average math pass@256 from 64.1 $\rightarrow$ 70.3 (GRPO), 69.3 $\rightarrow$ 72.5 (DAPO), and 73.2 $\rightarrow$ 76.8 (CISPO); OOD pass@256 also improves in all three cases, without increasing group size or computational cost.

---

### Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR

Authors: Luke Shannon, Song Liu, Katarzyna Reluga
Published: 2026-02-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06713v2

Missing data imputation, where a model is trained on observed data to estimate unobserved values, is a fundamental problem in machine learning. In this paper, we rigorously formulate imputation model learning as a mean-squared error risk minimisation problem. We show that when the probability of missingness depends on the data, many state-of-the-art methods fail to account for the resulting distribution shift between the observed data used for training and the full data distribution used for evaluation. Consequently, these approaches do not minimise mean-squared error on the full data distribution. Instead, we propose a novel imputation algorithm designed to learn an imputation model from the observed data while explicitly accounting for this distribution shift. Simulation studies show consistent improvements over otherwise identical uncorrected baselines, with average reductions of 3% in RMSE and 7% in Wasserstein distance.

---

### Autoregressive Models for Knowledge Graph Generation

Authors: Thiviyan Thanapalasingam, Antonis Vozikis, Peter Bloem, Paul Groth
Published: 2026-02-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.06707v1

Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples while maintaining domain validity constraints. Unlike link prediction, which scores triples independently, generative models must capture interdependencies across entire subgraphs to produce semantically coherent structures. We present ARK (Auto-Regressive Knowledge Graph Generation), a family of autoregressive models that generate KGs by treating graphs as sequences of (head, relation, tail) triples. ARK learns implicit semantic constraints directly from data, including type consistency, temporal validity, and relational patterns, without explicit rule supervision. On the IntelliGraphs benchmark, our models achieve 89.2% to 100.0% semantic validity across diverse datasets while generating novel graphs not seen during training. We also introduce SAIL, a variational extension of ARK that enables controlled generation through learned latent representations, supporting both unconditional sampling and conditional completion from partial graphs. Our analysis reveals that model capacity (hidden dimensionality >= 64) is more critical than architectural depth for KG generation, with recurrent architectures achieving comparable validity to transformer-based alternatives while offering substantial computational efficiency. These results demonstrate that autoregressive models provide an effective framework for KG generation, with practical applications in knowledge base completion and query answering.

---

### SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers

Authors: Shentong Mo, Lanqing Li
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06706v1

Generative models for de novo protein backbone design have achieved remarkable success in creating novel protein structures. However, these diffusion-based approaches remain computationally intensive and slower than desired for large-scale structural exploration. While recent efforts like Proteina have introduced flow-matching to improve sampling efficiency, the potential of tokenization for structural compression and acceleration remains largely unexplored in the protein domain. In this work, we present SaDiT, a novel framework that accelerates protein backbone generation by integrating SaProt Tokenization with a Diffusion Transformer (DiT) architecture. SaDiT leverages a discrete latent space to represent protein geometry, significantly reducing the complexity of the generation process while maintaining theoretical SE(3) equivalence. To further enhance efficiency, we introduce an IPA Token Cache mechanism that optimizes the Invariant Point Attention (IPA) layers by reusing computed token states during iterative sampling. Experimental results demonstrate that SaDiT outperforms state-of-the-art models, including RFDiffusion and Proteina, in both computational speed and structural viability. We evaluate our model across unconditional backbone generation and fold-class conditional generation tasks, where SaDiT shows superior ability to capture complex topological features with high designability.

---

### Explaining Grokking in Transformers through the Lens of Inductive Bias

Authors: Jaisidh Singh, Diganta Misra, Antonio Orvieto
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06702v1

We investigate grokking in transformers through the lens of inductive bias: dispositions arising from architecture or optimization that let the network prefer one solution over another. We first show that architectural choices such as the position of Layer Normalization (LN) strongly modulates grokking speed. This modulation is explained by isolating how LN on specific pathways shapes shortcut-learning and attention entropy. Subsequently, we study how different optimization settings modulate grokking, inducing distinct interpretations of previously proposed controls such as readout scale. Particularly, we find that using readout scale as a control for lazy training can be confounded by learning rate and weight decay in our setting. Accordingly, we show that features evolve continuously throughout training, suggesting grokking in transformers can be more nuanced than a lazy-to-rich transition of the learning regime. Finally, we show how generalization predictably emerges with feature compressibility in grokking, across different modulators of inductive bias. Our code is released at https://tinyurl.com/y52u3cad.

---

### Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Publicly Released Graphs

Authors: Ying Song, Balaji Palanisamy
Published: 2026-02-06
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.06700v1

Graph-structured data underpin a wide spectrum of modern applications. However, complex graph topologies and homophilic patterns can facilitate attribute inference attacks (AIAs) by enabling sensitive information leakage to propagate across local neighborhoods. Existing AIAs predominantly assume that adversaries can probe sensitive attributes through repeated model queries. Such assumptions are often impractical in real-world settings due to stringent data protection regulations, prohibitive query budgets, and heightened detection risks, especially when inferring multiple sensitive attributes. More critically, this model-centric perspective obscures a pervasive blind spot: \textbf{intrinsic multiple sensitive information leakage arising solely from publicly released graphs.} To exploit this unexplored vulnerability, we introduce a new attack paradigm and propose \textbf{Taipan, the first query-free transfer-based attack framework for multiple sensitive attribute inference attacks on graphs (G-MSAIAs).} Taipan integrates \emph{Hierarchical Attack Knowledge Routing} to capture intricate inter-attribute correlations, and \emph{Prompt-guided Attack Prototype Refinement} to mitigate negative transfer and performance degradation. We further present a systematic evaluation framework tailored to G-MSAIAs. Extensive experiments on diverse real-world graph datasets demonstrate that Taipan consistently achieves strong attack performance across same-distribution settings and heterogeneous similar- and out-of-distribution settings with mismatched feature dimensionalities, and remains effective even under rigorous differential privacy guarantees. Our findings underscore the urgent need for more robust multi-attribute privacy-preserving graph publishing methods and data-sharing practices.

---

### Quantum Attention by Overlap Interference: Predicting Classical and Many-Body Quantum Sequences

Authors: Alessio Pecilli, Matteo Rosati
Published: 2026-02-06
Categories: quant-ph, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.06699v2

We propose a variational quantum implementation of self-attention (QSA)-the core operation in transformers and large language models-which predicts future elements of a sequence by forming overlap-weighted combinations of past data. At variance with previous approaches, our QSA realizes the required nonlinearity through interference of state overlaps and a degree-$k$ polynomial kernel, and estimates a loss based on Rényi-$1/2$ entropic functionals via two observables' expectation values, avoiding the decoding of amplitude-encoded predictions into classical probabilities. QSA also accommodates a constrained, trainable data-embedding tying state overlaps to data-level similarities. Its dominant end-to-end training complexity scales as $O\left(μ^{-1}k^2Td\right)$, versus $O\left(T d^{k+1}\right)$ of the fairest classical comparison, with $μ$ a training signal; we show numerically that this allows a complexity advantage in the regime where sequence length $T$ dominates the embedding size $d$. In simulations, our QSA-based quantum transformer learns sequence prediction on classical data and on many-body transverse-field Ising trajectories-establishing trainable attention as a practical primitive for quantum dynamical modeling.

---

### Quantum Attention by Overlap Interference: Predicting Sequences from Classical and Many-Body Quantum Data

Authors: Alessio Pecilli, Matteo Rosati
Published: 2026-02-06
Categories: quant-ph, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.06699v1

We propose a variational quantum implementation of self-attention (QSA), the core operation in transformers and large language models, which predicts future elements of a sequence by forming overlap-weighted combinations of past data. At variance with previous approaches, our QSA realizes the required nonlinearity through interference of state overlaps and returns a Renyi-1/2 cross-entropy loss directly as the expectation value of an observable, avoiding the need to decode amplitude-encoded predictions into classical logits. Furthermore, QSA naturally accommodates a constrained, trainable data-embedding that ties quantum state overlaps to data-level similarities. We find a gate complexity dominant scaling O(T d^2) for QSA, versus O(T^2 d) classically, suggesting an advantage in the practical regime where the sequence length T dominates the embedding size d. In simulations, we show that our QSA-based quantum transformer learns sequence prediction on classical data and on many-body transverse-field Ising quantum trajectories, establishing trainable attention as a practical primitive for quantum dynamical modeling.

---

### Diffeomorphism-Equivariant Neural Networks

Authors: Josephine Elisabeth Oettinger, Zakhar Shumaylov, Johannes Bostelmann, Jan Lellmann, Carola-Bibiane Schönlieb
Published: 2026-02-06
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.06695v1

Incorporating group symmetries via equivariance into neural networks has emerged as a robust approach for overcoming the efficiency and data demands of modern deep learning. While most existing approaches, such as group convolutions and averaging-based methods, focus on compact, finite, or low-dimensional groups with linear actions, this work explores how equivariance can be extended to infinite-dimensional groups. We propose a strategy designed to induce diffeomorphism equivariance in pre-trained neural networks via energy-based canonicalisation. Formulating equivariance as an optimisation problem allows us to access the rich toolbox of already established differentiable image registration methods. Empirical results on segmentation and classification tasks confirm that our approach achieves approximate equivariance and generalises to unseen transformations without relying on extensive data augmentation or retraining.

---

### NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Authors: Hyochan Chong, Dongkyu Kim, Changdong Kim, Minseop Choi
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06694v3

Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit) levels, as they either require large amounts of data and compute or incur additional storage. In this work, we propose NanoQuant, the first post-training quantization (PTQ) method to compress LLMs to both binary and sub-1-bit levels. NanoQuant formulates quantization as a low-rank binary factorization problem, and compresses full-precision weights to low-rank binary matrices and scales. Specifically, it utilizes an efficient alternating direction method of multipliers (ADMM) solver to precisely initialize latent binary matrices and scales, and then tunes the initialized parameters through a block and model reconstruction process. Consequently, NanoQuant establishes a new Pareto frontier in low-memory post-training quantization, and enables sub-1-bit compression. NanoQuant makes large-scale deployment feasible on consumer hardware. For example, it compresses Llama2-70B by 25.8$\times$ in just 13 hours on a single H100, enabling a 70B model to operate on a consumer 8 GB GPU. Code is available at https://github.com/SamsungLabs/NanoQuant.

---

### Makespan Minimization in Split Learning: From Theory to Practice

Authors: Robert Ganian, Fionn Mc Inerney, Dimitra Tsigkari
Published: 2026-02-06
Categories: cs.NI, cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2602.06693v1

Split learning recently emerged as a solution for distributed machine learning with heterogeneous IoT devices, where clients can offload part of their training to computationally-powerful helpers. The core challenge in split learning is to minimize the training time by jointly devising the client-helper assignment and the schedule of tasks at the helpers. We first study the model where each helper has a memory cardinality constraint on how many clients it may be assigned, which represents the case of homogeneous tasks. Through complexity theory, we rule out exact polynomial-time algorithms and approximation schemes even for highly restricted instances of this problem. We complement these negative results with a non-trivial polynomial-time 5-approximation algorithm. Building on this, we then focus on the more general heterogeneous task setting considered by Tirana et al. (INFOCOM 2024), where helpers have memory capacity constraints and clients have variable memory costs. In this case, we prove that, unless P=NP, the problem cannot admit a polynomial-time approximation algorithm for any approximation factor. However, by adapting our aforementioned 5-approximation algorithm, we develop a novel heuristic for the heterogeneous task setting and show that it outperforms heuristics from prior works through extensive experiments.

---

### Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts

Authors: Kerstin Sahler, Sophie Jentzsch
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06692v1

The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI). However, deliberately controlling the sentiment in these systems remains challenging. The present study investigates the potential of prompt engineering for controlling sentiment in LLM-generated text, providing a resource-sensitive and accessible alternative to existing methods. Using Ekman's six basic emotions (e.g., joy, disgust), we examine various prompting techniques, including Zero-Shot and Chain-of-Thought prompting using gpt-3.5-turbo, and compare it to fine-tuning. Our results indicate that prompt engineering effectively steers emotions in AI-generated texts, offering a practical and cost-effective alternative to fine-tuning, especially in data-constrained settings. In this regard, Few-Shot prompting with human-written examples was the most effective among other techniques, likely due to the additional task-specific guidance. The findings contribute valuable insights towards developing emotion-adaptive AI systems.

---

### Memory-Conditioned Flow-Matching for Stable Autoregressive PDE Rollouts

Authors: Victor Armegioiu
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06689v1

Autoregressive generative PDE solvers can be accurate one step ahead yet drift over long rollouts, especially in coarse-to-fine regimes where each step must regenerate unresolved fine scales. This is the regime of diffusion and flow-matching generators: although their internal dynamics are Markovian, rollout stability is governed by per-step \emph{conditional law} errors. Using the Mori--Zwanzig projection formalism, we show that eliminating unresolved variables yields an exact resolved evolution with a Markov term, a memory term, and an orthogonal forcing, exposing a structural limitation of memoryless closures. Motivated by this, we introduce memory-conditioned diffusion/flow-matching with a compact online state injected into denoising via latent features. Via disintegration, memory induces a structured conditional tail prior for unresolved scales and reduces the transport needed to populate missing frequencies. We prove Wasserstein stability of the resulting conditional kernel. We then derive discrete Grönwall rollout bounds that separate memory approximation from conditional generation error. Experiments on compressible flows with shocks and multiscale mixing show improved accuracy and markedly more stable long-horizon rollouts, with better fine-scale spectral and statistical fidelity.

---