# Research Papers — 2026-02 · bundle page 124 of 210

> Full-text markdown of papers #6151–6200 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/124
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/123.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/125.md)

### Step-Size Stability in Stochastic Optimization: A Theoretical Perspective

Authors: Fabian Schaipp, Robert M. Gower, Adrien Taylor
Published: 2026-02-10
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2602.09842v2

We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify a key quantity that, for each method, describes how the performance degrades as the step size becomes too large. For convex problems, we show that this quantity directly impacts the suboptimality bound of the method. Most importantly, our analysis provides direct theoretical evidence that adaptive step-size methods, such as SPS or NGN, are more robust than SGD. This allows us to quantify the advantage of these adaptive methods beyond empirical evaluation. Finally, we show through experiments that our theoretical bound qualitatively mirrors the actual performance as a function of the step size, even for non-convex problems.

---

### Hybrid Responsible AI-Stochastic Approach for SLA Compliance in Multivendor 6G Networks

Authors: Emanuel Figetakis, Ahmed Refaey Hussein
Published: 2026-02-10
Categories: cs.NI, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.09841v1

The convergence of AI and 6G network automation introduces new challenges in maintaining transparency, fairness, and accountability across multivendor management systems. Although closed-loop AI orchestration improves adaptability and self-optimization, it also creates a responsibility gap, where violations of SLAs cannot be causally attributed to specific agents or vendors. This paper presents a hybrid responsible AI-stochastic learning framework that embeds fairness, robustness, and auditability directly into the network control loop. The framework integrates RAI games with stochastic optimization, enabling dynamic adversarial reweighting and probabilistic exploration across heterogeneous vendor domains. An RAAP continuously records AI-driven decision trajectories and produces dual accountability reports: user-level SLA summaries and operator-level responsibility analytics. Experimental evaluations on synthetic two-class multigroup datasets demonstrate that the proposed hybrid model improves the accuracy of the worst group by up to 10.5\%. Specifically, hybrid RAI achieved a WGAcc of 60.5\% and an AvgAcc of 72.7\%, outperforming traditional RAI-GA (50.0\%) and ERM (21.5\%). The audit mechanism successfully traced 99\% simulated SLA violations to the AI entities responsible, producing both vendor and agent-level accountability indices. These results confirm that the proposed hybrid approach enhances fairness and robustness as well as establishes a concrete accountability framework for autonomous SLA assurance in multivendor 6G networks.

---

### ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge

Authors: Yijie Lin, Guofeng Ding, Haochen Zhou, Haobin Li, Mouxing Yang, Xi Peng
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09839v1

Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To address this gap, we introduce ARK, a benchmark designed to analyze multimodal retrieval from two complementary perspectives: (i) knowledge domains (five domains with 17 subtypes), which characterize the content and expertise retrieval relies on, and (ii) reasoning skills (six categories), which characterize the type of inference over multimodal evidence required to identify the correct candidate. Specifically, ARK evaluates retrieval with both unimodal and multimodal queries and candidates, covering 16 heterogeneous visual data types. To avoid shortcut matching during evaluation, most queries are paired with targeted hard negatives that require multi-step reasoning. We evaluate 23 representative text-based and multimodal retrievers on ARK and observe a pronounced gap between knowledge-intensive and reasoning-intensive retrieval, with fine-grained visual and spatial reasoning emerging as persistent bottlenecks. We further show that simple enhancements such as re-ranking and rewriting yield consistent improvements, but substantial headroom remains.

---

### How Do People Quantify Naturally: Evidence from Mandarin Picture Description

Authors: Yayun Zhang, Guanyi Chen, Fahime Same, Saad Mahamood, Tingting He
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09838v1

Quantification is a fundamental component of everyday language use, yet little is known about how speakers decide whether and how to quantify in naturalistic production. We investigate quantification in Mandarin Chinese using a picture-based elicited description task in which speakers freely described scenes containing multiple objects, without explicit instructions to count or quantify. Across both spoken and written modalities, we examine three aspects of quantification: whether speakers choose to quantify at all, how precise their quantification is, and which quantificational strategies they adopt. Results show that object numerosity, animacy, and production modality systematically shape quantificational behaviour. In particular, increasing numerosity reduces both the likelihood and the precision of quantification, while animate referents and modality selectively modulate strategy choice. This study demonstrates how quantification can be examined under unconstrained production conditions and provides a naturalistic dataset for further analyses of quantity expression in language production.

---

### LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse

Authors: Bakhtawar Ahtisham, Kirk Vanacore, Zhuqian Zhou, Jinsook Lee, Rene F. Kizilcec
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09832v1

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by LLMs can be used to predict the correctness of a model's own predictions. We analyze 30,300 teacher utterances from classroom dialogue, each labeled by multiple state-of-the-art LLMs with an instructional move construct and an accompanying reasoning. Using human-verified ground-truth labels, we frame the task as predicting whether a model's assigned label for a given utterance is correct. We encode LLM reasoning using Term Frequency-Inverse Document Frequency (TF-IDF) and evaluate five supervised classifiers. A Random Forest classifier achieves an F1 score of 0.83 (Recall = 0.854), successfully identifying most incorrect predictions and outperforming baselines. Training specialist detectors for specific instructional move constructs further improves performance on difficult constructs, indicating that error detection benefits from construct-specific linguistic cues. Using the Linguistic Inquiry and Word Count (LIWC) framework, we examine four linguistic markers of correctness: Causation, Differentiation, Tentativeness, and Insight. Correct predictions exhibit grounded causal language (e.g., because, therefore), while incorrect reasoning is substantially more likely to rely on epistemic hedging (e.g., might, could) and performative metacognition (e.g., think, realize). Syntactic complexity does not distinguish correct from incorrect reasoning, and longer reasoning is not more reliable. These findings demonstrate that reasoning-based error detection offers a practical and scalable approach to quality control in automated educational dialogue analysis.

---

### From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models

Authors: Abdulmuizz Khalak, Abderrahmane Issam, Gerasimos Spanakis
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09826v2

Arabic Language Models (LMs) are pretrained predominately on Modern Standard Arabic (MSA) and are expected to transfer to its dialects. While MSA as the standard written variety is commonly used in formal settings, people speak and write online in various dialects that are spread across the Arab region. This poses limitations for Arabic LMs, since its dialects vary in their similarity to MSA. In this work we study cross-lingual transfer of Arabic models using probing on 3 Natural Language Processing (NLP) Tasks, and representational similarity. Our results indicate that transfer is possible but disproportionate across dialects, which we find to be partially explained by their geographic proximity. Furthermore, we find evidence for negative interference in models trained to support all Arabic dialects. This questions their degree of similarity, and raises concerns for cross-lingual transfer in Arabic models.

---

### SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding

Authors: Zhaoxu Li, Chenqi Kong, Peijun Bao, Song Xia, Yi Tu, Yi Yu, Xinghao Jiang, Xudong Jiang
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09825v1

Hallucinations in Large Vision-Language Models (LVLMs) pose significant security and reliability risks in real-world applications. Inspired by the observation that humans are more error-prone when uncertain or hesitant, we investigate how instability in a model 's internal knowledge contributes to LVLM hallucinations. We conduct extensive empirical analyses from three perspectives, namely attention heads, model layers, and decoding tokens, and identify three key hallucination patterns: (i) visual activation drift across attention heads, (ii) pronounced knowledge fluctuations across layers, and (iii) visual focus distraction between neighboring output tokens. Building on these findings, we propose Stability-Aware Knowledge-Enhanced Decoding (SAKED), which introduces a layer-wise Knowledge Stability Score (KSS) to quantify knowledge stability throughout the model. By contrasting the most stability-aware and stability-agnostic layers, SAKED suppresses decoding noise and dynamically leverages the most reliable internal knowledge for faithful token generation. Moreover, SAKED is training-free and can be seamlessly integrated into different architectures. Extensive experiments demonstrate that SAKED achieves state-of-the-art performance for hallucination mitigation on various models, tasks, and benchmarks.

---

### PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation

Authors: Xuhang Wu, Zhuoxuan Liang, Wei Li, Xiaohua Jia, Sumi Helal
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.09824v1

With the rapid advancement of IoT and edge computing, sensor networks have become indispensable, driving the need for large-scale sensor deployment. However, the high deployment cost hinders their scalability. To tackle the issues, Spatial Interpolation (SI) introduces virtual sensors to infer readings from observed sensors, leveraging graph structure. However, current graph-based SI methods rely on pre-trained models, lack adaptation to larger and unseen graphs at test-time, and overlook test data utilization. To address these issues, we propose PlugSI, a plug-and-play framework that refines test-time graph through two key innovations. First, we design an Unknown Topology Adapter (UTA) that adapts to the new graph structure of each small-batch at test-time, enhancing the generalization of SI pre-trained models. Second, we introduce a Temporal Balance Adapter (TBA) that maintains a stable historical consensus to guide UTA adaptation and prevent drifting caused by noise in the current batch. Empirically, extensive experiments demonstrate PlugSI can be seamlessly integrated into existing graph-based SI methods and provide significant improvement (e.g., a 10.81% reduction in MAE).

---

### Covo-Audio Technical Report

Authors: Wenfu Wang, Chenxing Li, Liqiang Zhang, Yiyang Zhao, Yuxiang Zou, Hanzhao Li, Mingyu Cui, Hao Zhang, Kun Wei, Le Xu, Zikang Huang, Jiajun Xu et al.
Published: 2026-02-10
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2602.09823v2

In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.

---

### Text summarization via global structure awareness

Authors: Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Yibei Liu, Chenghao Li, Qigan Sun, Shuai Yuan, Fachrina Dewi Puspitasari, Dongshen Han, Guoqing Wang, Sung-Ho Bae, Yang Yang
Published: 2026-02-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.09821v2

Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summarization essential. Existing research mainly focuses on model improvements and sentence-level pruning, but often overlooks global structure, leading to disrupted coherence and weakened downstream performance. Some studies employ large language models (LLMs), which achieve higher accuracy but incur substantial resource and time costs. To address these issues, we introduce GloSA-sum, the first summarization approach that achieves global structure awareness via topological data analysis (TDA). GloSA-sum summarizes text efficiently while preserving semantic cores and logical dependencies. Specifically, we construct a semantic-weighted graph from sentence embeddings, where persistent homology identifies core semantics and logical structures, preserved in a ``protection pool'' as the backbone for summarization. We design a topology-guided iterative strategy, where lightweight proxy metrics approximate sentence importance to avoid repeated high-cost computations, thus preserving structural integrity while improving efficiency. To further enhance long-text processing, we propose a hierarchical strategy that integrates segment-level and global summarization. Experiments on multiple datasets demonstrate that GloSA-sum reduces redundancy while preserving semantic and logical integrity, striking a balance between accuracy and efficiency, and further benefits LLM downstream tasks by shortening contexts while retaining essential reasoning chains.

---

### AnalyticsGPT: An LLM Workflow for Scientometric Question Answering

Authors: Khang Ly, Georgios Cheirmpos, Adrian Raudaschl, Christopher James, Seyed Amin Tabatabaei
Published: 2026-02-10
Categories: cs.CL, cs.DL
arXiv: https://arxiv.org/abs/2602.09817v1

This paper introduces AnalyticsGPT, an intuitive and efficient large language model (LLM)-powered workflow for scientometric question answering. This underrepresented downstream task addresses the subcategory of meta-scientific questions concerning the "science of science." When compared to traditional scientific question answering based on papers, the task poses unique challenges in the planning phase. Namely, the need for named-entity recognition of academic entities within questions and multi-faceted data retrieval involving scientometric indices, e.g. impact factors. Beyond their exceptional capacity for treating traditional natural language processing tasks, LLMs have shown great potential in more complex applications, such as task decomposition and planning and reasoning. In this paper, we explore the application of LLMs to scientometric question answering, and describe an end-to-end system implementing a sequential workflow with retrieval-augmented generation and agentic concepts. We also address the secondary task of effectively synthesizing the data into presentable and well-structured high-level analyses. As a database for retrieval-augmented generation, we leverage a proprietary research performance assessment platform. For evaluation, we consult experienced subject matter experts and leverage LLMs-as-judges. In doing so, we provide valuable insights on the efficacy of LLMs towards a niche downstream task. Our (skeleton) code and prompts are available at: https://github.com/lyvykhang/llm-agents-scientometric-qa/tree/acl.

---

### CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video

Authors: Hojun Song, Heejung Choi, Aro Kim, Chae-yeong Song, Gahyeon Kim, Soo Ye Kim, Jaehyup Lee, Sang-hyo Park
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09816v1

High-quality novel view synthesis (NVS) from real-world videos is crucial for applications such as cultural heritage preservation, digital twins, and immersive media. However, real-world videos typically contain long sequences with irregular camera trajectories and unknown poses, leading to pose drift, feature misalignment, and geometric distortion during reconstruction. Moreover, lossy compression amplifies these issues by introducing inconsistencies that gradually degrade geometry and rendering quality. While recent studies have addressed either long-sequence NVS or unposed reconstruction, compression-aware approaches still focus on specific artifacts or limited scenarios, leaving diverse compression patterns in long videos insufficiently explored. In this paper, we propose CompSplat, a compression-aware training framework that explicitly models frame-wise compression characteristics to mitigate inter-frame inconsistency and accumulated geometric errors. CompSplat incorporates compression-aware frame weighting and an adaptive pruning strategy to enhance robustness and geometric consistency, particularly under heavy compression. Extensive experiments on challenging benchmarks, including Tanks and Temples, Free, and Hike, demonstrate that CompSplat achieves state-of-the-art rendering quality and pose accuracy, significantly surpassing most recent state-of-the-art NVS approaches under severe compression conditions.

---

### Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning

Authors: Dexun Li, Sidney Tio, Pradeep Varakantham
Published: 2026-02-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.09813v1

Unsupervised Environment Design (UED) has emerged as a promising approach to developing general-purpose agents through automated curriculum generation. Popular UED methods focus on Open-Endedness, where teacher algorithms rely on stochastic processes for infinite generation of useful environments. This assumption becomes impractical in resource-constrained scenarios where teacher-student interaction opportunities are limited. To address this challenge, we introduce a hierarchical Markov Decision Process (MDP) framework for environment design. Our framework features a teacher agent that leverages student policy representations derived from discovered evaluation environments, enabling it to generate training environments based on the student's capabilities. To improve efficiency, we incorporate a generative model that augments the teacher's training dataset with synthetic data, reducing the need for teacher-student interactions. In experiments across several domains, we show that our method outperforms baseline approaches while requiring fewer teacher-student interactions in a single episode. The results suggest the applicability of our approach in settings where training opportunities are limited.

---

### A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer

Authors: Azkaa Nasir, Fatima Dossa, Muhammad Ahmed Atif, Mohammad Shahid Shaikh
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.09810v2

Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also fail under substantial domain shift. This paper presents a controlled empirical study examining how architectural differences between Double Deep Q-Networks (DDQN) and Dueling DQN influence transfer behavior across environments. Using CartPole as a source task and LunarLander as a structurally distinct target task, we evaluate a fixed layer-wise representation transfer protocol under identical hyperparameters and training conditions, with baseline agents trained from scratch used to contextualize transfer effects. Empirical results show that DDQN consistently avoids negative transfer under the examined setup and maintains learning dynamics comparable to baseline performance in the target environment. In contrast, Dueling DQN consistently exhibits negative transfer under identical conditions, characterized by degraded rewards and unstable optimization behavior. Statistical analysis across multiple random seeds confirms a significant performance gap under transfer. These findings suggest that architectural inductive bias is strongly associated with robustness to cross-environment transfer in value-based deep reinforcement learning under the examined transfer protocol.

---

### SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

Authors: Tong Zhang, Honglin Lin, Zhou Liu, Chong Chen, Wentao Zhang
Published: 2026-02-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.09809v3

Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks either rely on image-centric or subjective metrics insensitive to structure, or evaluate intermediate symbolic representations rather than final rendered images, leaving pixel-based diagram generation underexplored. We introduce SciFlow-Bench, a structure-first benchmark for evaluating scientific diagram generation directly from pixel-level outputs. Built from real scientific PDFs, SciFlow-Bench pairs each source framework figure with a canonical ground-truth graph and evaluates models as black-box image generators under a closed-loop, round-trip protocol that inverse-parses generated diagram images back into structured graphs for comparison. This design enforces evaluation by structural recoverability rather than visual similarity alone, and is enabled by a hierarchical multi-agent system that coordinates planning, perception, and structural reasoning. Experiments show that preserving structural correctness remains a fundamental challenge, particularly for diagrams with complex topology, underscoring the need for structure-aware evaluation.

---

### Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs

Authors: Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya, Benjamin Ricaud
Published: 2026-02-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.09805v2

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary verbosity. We introduce a trace-optional evaluation protocol that exactly decomposes token efficiency using three observables available even for closed models: completion rate, conditional correctness given completion, and generated length. When instance-level workload metadata is available, we further normalize generated length by declared task-implied work and separate mean verbalization overhead from workload-dependent scaling. When such metadata is absent, we define an auditable solver-derived workload scale and evaluate its stability under leave-self-out, leave-top-k, and held-out-reference-pool perturbations. We evaluate 14 shared open-weight models on CogniLoad, GSM8K, ProofWriter, and ZebraLogic. We further evaluate 11 additional models on CogniLoad, enabling a fine-grained analysis of reasoning-task difficulty factors: task length, intrinsic difficulty, and distractor density. Efficiency and overhead rankings remain stable across all benchmark pairs, more robustly than accuracy rankings, while the decomposition separates logic-limited, context-limited (truncation-driven), and verbosity-limited failure modes that look identical under accuracy-per-token. We release an evaluation artifact and reporting template, which elaborates on why an LLM is inefficient at reasoning.

---

### Would a Large Language Model Pay Extra for a View? Inferring Willingness to Pay from Subjective Choices

Authors: Manon Reusens, Sofie Goethals, Toon Calders, David Martens
Published: 2026-02-10
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.09802v2

As Large Language Models (LLMs) are increasingly deployed in applications such as travel assistance and purchasing support, they are often required to make subjective choices on behalf of users in settings where no objectively correct answer exists. We study LLM decision-making in a travel-assistant context by presenting models with choice dilemmas and analyzing their responses using multinomial logit models to derive implied willingness to pay (WTP) estimates. These WTP values are subsequently compared to human benchmark values from the economics literature. In addition to a baseline setting, we examine how model behavior changes under more realistic conditions, including the provision of information about users' past choices and persona-based prompting. Our results show that while meaningful WTP values can be derived for larger LLMs, they also display systematic deviations at the attribute level. Additionally, they tend to overestimate human WTP overall, particularly when expensive options or business-oriented personas are introduced. Conditioning models on prior preferences for cheaper options yields valuations that are closer to human benchmarks. Overall, our findings highlight both the potential and the limitations of using LLMs for subjective decision support and underscore the importance of careful model selection, prompt design, and user representation when deploying such systems in practice.

---

### Symbolic Pattern Temporal Numeric Planning with Intermediate Conditions and Effects

Authors: Matteo Cardellini, Enrico Giunchiglia
Published: 2026-02-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.09798v1

Recently, a Symbolic Pattern Planning (SPP) approach was proposed for numeric planning where a pattern (i.e., a finite sequence of actions) suggests a causal order between actions. The pattern is then encoded in a SMT formula whose models correspond to valid plans. If the suggestion by the pattern is inaccurate and no valid plan can be found, the pattern is extended until it contains the causal order of actions in a valid plan, making the approach complete. In this paper, we extend the SPP approach to the temporal planning with Intermediate Conditions and Effects (ICEs) fragment, where $(i)$ actions are durative (and thus can overlap over time) and have conditions/effects which can be checked/applied at any time during an action's execution, and $(ii)$ one can specify plan's conditions/effects that must be checked/applied at specific times during the plan execution. Experimental results show that our SPP planner Patty $(i)$ outperforms all other planners in the literature in the majority of temporal domains without ICEs, $(ii)$ obtains comparable results with the SoTA search planner for ICS in literature domains with ICEs, and $(iii)$ outperforms the same planner in a novel domain based on a real-world application.

---

### Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain

Authors: Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Xudong Wang, Zhenzhen Huang, Pengcheng Zheng, Shuai Yuan, Sheng Zheng, Qigan Sun, Jie Zou, Lik-Hang Lee, Yang Yang
Published: 2026-02-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.09794v2

Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However, due to the autoregressive, step-by-step generation paradigm, existing CoT methods suffer from two fundamental limitations. First, the reasoning process is highly sensitive to early decisions: once an initial error is introduced, it tends to propagate and amplify through subsequent steps, while the lack of a global coordination and revision mechanism makes such errors difficult to correct, ultimately leading to distorted reasoning chains. Second, current CoT approaches lack structured analysis techniques for filtering redundant reasoning and extracting key reasoning features, resulting in unstable reasoning processes and limited interpretability. To address these issues, we propose GHS-TDA. GHS-TDA first constructs a semantically enriched global hypothesis graph to aggregate, align, and coordinate multiple candidate reasoning paths, thereby providing alternative global correction routes when local reasoning fails. It then applies topological data analysis based on persistent homology to capture stable multi-scale structures, remove redundancy and inconsistencies, and extract a more reliable reasoning skeleton. By jointly leveraging reasoning diversity and topological stability, GHS-TDA achieves self-adaptive convergence, produces high-confidence and interpretable reasoning paths, and consistently outperforms strong baselines in terms of both accuracy and robustness across multiple reasoning benchmarks.

---

### Fully-automated sleep staging: multicenter validation of a generalizable deep neural network for Parkinson's disease and isolated REM sleep behavior disorder

Authors: Jesper Strøm, Casper Skjærbæk, Natasha Becker Bertelsen, Steffen Torpe Simonsen, Niels Okkels, David Bertram, Sinah Röttgen, Konstantin Kufer, Kaare B. Mikkelsen, Marit Otto, Poul Jørgen Jennum, Per Borghammer et al.
Published: 2026-02-10
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2602.09793v2

Isolated REM sleep behavior disorder (iRBD) is a key prodromal marker of Parkinson's disease (PD), and video-polysomnography (vPSG) remains the diagnostic gold standard. However, manual sleep staging is particularly challenging in neurodegenerative diseases due to EEG abnormalities and fragmented sleep, making PSG assessments a bottleneck for deploying new RBD screening technologies at scale. We adapted U-Sleep, a deep neural network, for generalizable sleep staging in PD and iRBD. A pretrained U-Sleep model, based on a large, multisite non-neurodegenerative dataset (PUB; 19,236 PSGs across 12 sites), was fine-tuned on research datasets from two centers (Lundbeck Foundation Parkinson's Disease Research Center (PACE) and the Cologne-Bonn Cohort (CBC); 112 PD, 138 iRBD, 89 age-matched controls. The resulting model was evaluated on an independent dataset from the Danish Center for Sleep Medicine (DCSM; 81 PD, 36 iRBD, 87 sleep-clinic controls). A subset of PSGs with low agreement between the human rater and the model (Cohen's $κ$ < 0.6) was re-scored by a second blinded human rater to identify sources of disagreement. Finally, we applied confidence-based thresholds to optimize REM sleep staging. The pretrained model achieved mean $κ$ = 0.81 in PUB, but $κ$ = 0.66 when applied directly to PACE/CBC. By fine-tuning the model, we developed a generalized model with $κ$ = 0.74 on PACE/CBC (p < 0.001 vs. the pretrained model). In DCSM, mean and median $κ$ increased from 0.60 to 0.64 (p < 0.001) and 0.64 to 0.69 (p < 0.001), respectively. In the interrater study, PSGs with low agreement between the model and the initial scorer showed similarly low agreement between human scorers. Applying a confidence threshold increased the proportion of correctly identified REM sleep epochs from 85% to 95.5%, while preserving sufficient (> 5 min) REM sleep for 95% of subjects.

---

### Toeplitz Based Spectral Methods for Data-driven Dynamical Systems

Authors: Vladimir R. Kostic, Karim Lounici, Massimiliano Pontil
Published: 2026-02-10
Categories: math.DS, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.09791v1

We introduce a Toeplitz-based framework for data-driven spectral estimation of linear evolution operators in dynamical systems. Focusing on transfer and Koopman operators from equilibrium trajectories without access to the underlying equations of motion, our method applies Toeplitz filters to the infinitesimal generator to extract eigenvalues, eigenfunctions, and spectral measures. Structural prior knowledge, such as self-adjointness or skew-symmetry, can be incorporated by design. The approach is statistically consistent and computationally efficient, leveraging both primal and dual algorithms commonly used in statistical learning. Numerical experiments on deterministic and chaotic systems demonstrate that the framework can recover spectral properties beyond the reach of standard data-driven methods.

---

### When Less is More: The LLM Scaling Paradox in Context Compression

Authors: Ruishan Guo, Yibing Liu, Guoxin Ma, Yan Wang, Yueyang Zhang, Long Xia, Kecheng Chen, Zhiyuan Sun, Daiting Shi
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.09789v3

Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabilities. However, under lossy context compression in a compressor--decoder setup, we find a \textbf{\textit{Size-Fidelity Paradox}}: increasing compressor size can lessen the faithfulness of reconstructed contexts though reconstruction error decreases. Across 27 compressor setups spanning model families, scales, and compression rates, we coin this paradox arising from two dominant factors: 1) \textit{knowledge overwriting}: larger models increasingly replace source facts with their own prior beliefs, \textit{e.g.}, ``the white strawberry`` $\to$ ``the red strawberry``; and 2) \textit{semantic drift}: larger models tend to paraphrase or restructure content instead of reproducing it verbatim, \textit{e.g.}, ``Alice hit Bob`` $\to$ ``Bob hit Alice``. Interestingly, this paradox persists across varied settings, with mid-sized compressors often outperforming larger ones in faithful recovery. By analyzing the compressed memory via embedding geometry and reconstruction determinacy, we further reveal that compressors tend to organize memory across broader semantic subspaces, yielding more ambiguous representations prone to overwriting, drift, and weakened recovery. These findings complement existing evaluations of context compression and expose a breakdown of scaling laws when the objective shifts from plausible generation to faithful preservation.

---

### Where Are We At with Automatic Speech Recognition for the Bambara Language?

Authors: Seydou Diallo, Yacouba Diarra, Mamadou K. Keita, Panga Azazia Kamaté, Adam Bouno Kampo, Aboubacar Ouattara
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09785v1

This paper introduces the first standardized benchmark for evaluating Automatic Speech Recognition (ASR) in the Bambara language, utilizing one hour of professionally recorded Malian constitutional text. Designed as a controlled reference set under near-optimal acoustic and linguistic conditions, the benchmark was used to evaluate 37 models, ranging from Bambara-trained systems to large-scale commercial models. Our findings reveal that current ASR performance remains significantly below deployment standards in a narrow formal domain; the top-performing system in terms of Word Error Rate (WER) achieved 46.76\% and the best Character Error Rate (CER) of 13.00\% was set by another model, while several prominent multilingual models exceeded 100\% WER. These results suggest that multilingual pre-training and model scaling alone are insufficient for underrepresented languages. Furthermore, because this dataset represents a best-case scenario of the most simplified and formal form of spoken Bambara, these figures are yet to be tested against practical, real-world settings. We provide the benchmark and an accompanying public leaderboard to facilitate transparent evaluation and future research in Bambara speech technology.

---

### Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path

Authors: Andres Saurez, Neha Sengar, Dongsoo Har
Published: 2026-02-10
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.09784v1

Circuit discovery and activation steering in transformers have developed as separate research threads, yet both operate on the same representational space. Are they two views of the same underlying structure? We show they follow a single geometric principle: answer tokens, processed in isolation, encode the directions that would produce them. This Circuit Fingerprint hypothesis enables circuit discovery without gradients or causal intervention -- recovering comparable structure to gradient-based methods through geometric alignment alone. We validate this on standard benchmarks (IOI, SVA, MCQA) across four model families, achieving circuit discovery performance comparable to gradient-based methods. The same directions that identify circuit components also enable controlled steering -- achieving 69.8\% emotion classification accuracy versus 53.1\% for instruction prompting while preserving factual accuracy. Beyond method development, this read-write duality reveals that transformer circuits are fundamentally geometric structures: interpretability and controllability are two facets of the same object.

---

### Why Linear Interpretability Works: Invariant Subspaces as a Result of Architectural Constraints

Authors: Andres Saurez, Yousung Lee, Dongsoo Har
Published: 2026-02-10
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.09783v1

Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity but a consequence of architectural necessity: transformers communicate information through linear interfaces (attention OV circuits, unembedding matrices), and any semantic feature decoded through such an interface must occupy a context-invariant linear subspace. We formalize this as the \emph{Invariant Subspace Necessity} theorem and derive the \emph{Self-Reference Property}: tokens directly provide the geometric direction for their associated features, enabling zero-shot identification of semantic structure without labeled data or learned probes. Empirical validation in eight classification tasks and four model families confirms the alignment between class tokens and semantically related instances. Our framework provides \textbf{a principled architectural explanation} for why linear interpretability methods work, unifying linear probes and sparse autoencoders.

---

### Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective

Authors: Kun Chen, Peng Shi, Fanfan Liu, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao
Published: 2026-02-10
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.09782v2

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Language Models (LLMs). However, continuous training often leads to policy entropy collapse, characterized by a rapid decay in entropy that results in premature overconfidence, reduced output diversity, and vanishing gradient norms that inhibit learning. Gradient-Preserving Clipping is a primary factor influencing these dynamics, but existing mitigation strategies are largely static and lack a framework connecting clipping mechanisms to precise entropy control. This paper proposes reshaping entropy control in RL from the perspective of Gradient-Preserving Clipping. We first theoretically and empirically verify the contributions of specific importance sampling ratio regions to entropy growth and reduction. Leveraging these findings, we introduce a novel regulation mechanism using dynamic clipping thresholds to precisely manage entropy. Furthermore, we design and evaluate dynamic entropy control strategies, including increase-then-decrease, decrease-increase-decrease, and oscillatory decay. Experimental results demonstrate that these strategies effectively mitigate entropy collapse and achieve superior performance across multiple benchmarks.

---

### Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis

Authors: Surjo Dey, Pallabi Saikia
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.09781v2

This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance imaging (MRI) synthesis. Although diffusion models have shown strong performance in generating realistic medical images, their internal decision making process remains largely opaque. We present a faithfulness-based explainability framework that analyzes how prototype-based explainability methods like ProtoPNet (PPNet), Enhanced ProtoPNet (EPPNet), and ProtoPool can link the relationship between generated and training features. Our study focuses on understanding the reasoning behind image formation through denoising trajectory of diffusion model and subsequently prototype explainability with faithfulness analysis. Experimental analysis shows that EPPNet achieves the highest faithfulness (with score 0.1534), offering more reliable insights, and explainability into the generative process. The results highlight that diffusion models can be made more transparent and trustworthy through faithfulness-based explanations, contributing to safer and more interpretable applications of generative AI in healthcare.

---

### Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets

Authors: Abhipsa Basu, Yugam Bahl, Kirti Bhagat, Preethi Seshadri, R. Venkatesh Babu, Danish Pruthi
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09775v1

Recent studies show that text-to-image models often fail to generate geographically representative images, raising concerns about the representativeness of their training data and motivating the question: which parts of the world do these training examples come from? We geographically profile large-scale multimodal datasets by mapping image-caption pairs to countries based on location information extracted from captions using LLMs. Studying English captions from three widely used datasets (Re-LAION, DataComp1B, and Conceptual Captions) across $20$ common entities (e.g., house, flag), we find that the United States, the United Kingdom, and Canada account for $48.0\%$ of samples, while South American and African countries are severely under-represented with only $1.8\%$ and $3.8\%$ of images, respectively. We observe a strong correlation between a country's GDP and its representation in the data ($ρ= 0.82$). Examining non-English subsets for $4$ languages from the Re-LAION dataset, we find that representation skews heavily toward countries where these languages are predominantly spoken. Additionally, we find that higher representation does not necessarily translate to greater visual or semantic diversity. Finally, analyzing country-specific images generated by Stable Diffusion v1.3 trained on Re-LAION, we show that while generations appear realistic, they are severely limited in their coverage compared to real-world images.

---

### Self-Supervised Learning as Discrete Communication

Authors: Kawtar Zaher, Ilyass Moummad, Olivier Buisson, Alexis Joly
Published: 2026-02-10
Categories: cs.CV, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.09764v2

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work, we frame visual self-supervised learning as a discrete communication process between a teacher and a student network, where semantic information is transmitted through a fixed-capacity binary channel. Rather than aligning continuous features, the student predicts multi-label binary messages produced by the teacher. Discrete agreement is enforced through an element-wise binary cross-entropy objective, while a coding-rate regularization term encourages effective utilization of the constrained channel, promoting structured representations. We further show that periodically reinitializing the projection head strengthens this effect by encouraging embeddings that remain predictive across multiple discrete encodings. Extensive experiments demonstrate consistent improvements over continuous agreement baselines on image classification, retrieval, and dense visual prediction tasks, as well as under domain shift through self-supervised adaptation. Beyond backbone representations, we analyze the learned binary codes and show that they form a compact and informative discrete language, capturing semantic factors reusable across classes.

---

### Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization

Authors: Matteo Pannacci, Andrea Fanti, Elena Umili, Roberto Capobianco
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.09761v2

In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms the only other previous method for multi-task learning that does not assume knowledge of the true symbol grounding.

---

### Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization

Authors: Matteo Pannacci, Andrea Fanti, Elena Umili, Roberto Capobianco
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.09761v1

In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms state-of-the-art methods for sub-symbolic environments.

---

### Improving Interpretability of Lexical Semantic Change with Neurobiological Features

Authors: Kohei Oda, Hiroya Takamura, Kiyoaki Shirai, Natthawut Kertkeidkachorn
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09760v1

Lexical Semantic Change (LSC) is the phenomenon in which the meaning of a word change over time. Most studies on LSC focus on improving the performance of estimating the degree of LSC, however, it is often difficult to interpret how the meaning of a word change. Enhancing the interpretability of LSC is a significant challenge as it could lead to novel insights in this field. To tackle this challenge, we propose a method to map the semantic space of contextualized embeddings of words obtained by a pre-trained language model to a neurobiological feature space. In the neurobiological feature space, each dimension corresponds to a primitive feature of words, and its value represents the intensity of that feature. This enables humans to interpret LSC systematically. When employed for the estimation of the degree of LSC, our method demonstrates superior performance in comparison to the majority of the previous methods. In addition, given the high interpretability of the proposed method, several analyses on LSC are carried out. The results demonstrate that our method not only discovers interesting types of LSC that have been overlooked in previous studies but also effectively searches for words with specific types of LSC.

---

### Towards Poisoning Robustness Certification for Natural Language Generation

Authors: Mihnea Ghitu, Matthew Wicker
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.09757v1

Understanding the reliability of natural language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide provable robustness bounds for classification tasks, they are fundamentally ill-equipped for autoregressive generation: they cannot handle sequential predictions or the exponentially large output space of language models. To establish a framework for certified natural language generation, we formalize two security properties: stability (robustness to any change in generation) and validity (robustness to targeted, harmful changes in generation). We introduce Targeted Partition Aggregation (TPA), the first algorithm to certify validity/targeted attacks by computing the minimum poisoning budget needed to induce a specific harmful class, token, or phrase. Further, we extend TPA to provide tighter guarantees for multi-turn generations using mixed integer linear programming (MILP). Empirically, we demonstrate TPA's effectiveness across diverse settings including: certifying validity of agent tool-calling when adversaries modify up to 0.5% of the dataset and certifying 8-token stability horizons in preference-based alignment. Though inference-time latency remains an open challenge, our contributions enable certified deployment of language models in security-critical applications.

---

### Linear Model Extraction via Factual and Counterfactual Queries

Authors: Daan Otto, Jannis Kurtz, Dick den Hertog, Ilker Birbil
Published: 2026-02-10
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2602.09748v2

In model extraction attacks, the goal is to reveal the parameters of a black-box machine learning model by querying the model for a selected set of data points. Due to an increasing demand for explanations, this may involve counterfactual queries besides the typically considered factual queries. In this work, we consider linear models and three types of queries: factual, counterfactual, and robust counterfactual. First, for an arbitrary set of queries, we derive novel mathematical formulations for the classification regions for which the decision of the unknown model is known, without recovering any of the model parameters. Second, we derive bounds on the number of queries needed to extract the model's parameters for (robust) counterfactual queries under arbitrary norm-based distances. We show that the full model can be recovered using just a single counterfactual query when differentiable distance measures are employed. In contrast, when using polyhedral distances for instance, the number of required queries grows linearly with the dimension of the data space. For robust counterfactuals, the latter number of queries doubles. Consequently, the applied distance function and robustness of counterfactuals have a significant impact on the model's security.

---

### Sparse Axonal and Dendritic Delays Enable Competitive SNNs for Keyword Classification

Authors: Younes Bouhadjar, Emre Neftci
Published: 2026-02-10
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.09746v1

Training transmission delays in spiking neural networks (SNNs) has been shown to substantially improve their performance on complex temporal tasks. In this work, we show that learning either axonal or dendritic delays enables deep feedforward SNNs composed of leaky integrate-and-fire (LIF) neurons to reach accuracy comparable to existing synaptic delay learning approaches, while significantly reducing memory and computational overhead. SNN models with either axonal or dendritic delays achieve up to $95.58\%$ on the Google Speech Command (GSC) and $80.97\%$ on the Spiking Speech Command (SSC) datasets, matching or exceeding prior methods based on synaptic delays or more complex neuron models. By adjusting the delay parameters, we obtain improved performance for synaptic delay learning baselines, strengthening the comparison. We find that axonal delays offer the most favorable trade-off, combining lower buffering requirements with slightly higher accuracy than dendritic delays. We further show that the performance of axonal and dendritic delay models is largely preserved under strong delay sparsity, with as few as $20\%$ of delays remaining active, further reducing buffering requirements. Overall, our results indicate that learnable axonal and dendritic delays provide a resource-efficient and effective mechanism for temporal representation in SNNs. Code will be made available publicly upon acceptance. Code is available at https://github.com/YounesBouhadjar/AxDenSynDelaySNN

---

### Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectors

Authors: Sandeep Gupta, Roberto Passerone
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09740v3

Connected and Autonomous Vehicles (CAVs), which is critical for achieving Level-5 autonomous driving. Safe and reliable CAV navigation depends on robust vision systems that enable accurate detection of objects, lane markings, and traffic signs. This survey presents a reference architecture for CAV vision systems (CAVVS) and uses it to derive a system-level threat model that maps assets, vulnerabilities, and attack points to three concrete attack surfaces (data, model, input) across the perception lifecycle. We examine attack vectors targeting each surface, rigorously evaluating their implications for confidentiality, integrity, and availability (CIA) and comparing them by adversary capability and practical exposure. We further outline atomic road events that can impact CAVVS robustness and propose a benchmark-oriented framework of datasets, metrics, and evaluation protocols for standardized future assessment. Together, these contributions provide a structured basis for vulnerability assessment, principled defense design, and reproducible robustness evaluation in real-world CAV vision systems.

---

### Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectors

Authors: Sandeep Gupta, Roberto Passerone
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09740v2

This article investigates the robustness of vision systems in Connected and Autonomous Vehicles (CAVs), which is critical for developing Level-5 autonomous driving capabilities. Safe and reliable CAV navigation undeniably depends on robust vision systems that enable accurate detection of objects, lane markings, and traffic signage. We analyze the key sensors and vision components essential for CAV navigation to derive a reference architecture for CAV vision system (CAVVS). This reference architecture provides a basis for identifying potential attack surfaces of CAVVS. Subsequently, we elaborate on identified attack vectors targeting each attack surface, rigorously evaluating their implications for confidentiality, integrity, and availability (CIA). Our study provides a comprehensive understanding of attack vector dynamics in vision systems, which is crucial for formulating robust security measures that can uphold the principles of the CIA triad.

---

### Toward Fine-Grained Facial Control in 3D Talking Head Generation

Authors: Shaoyang Xie, Xiaofeng Cong, Baosheng Yu, Zhipeng Gui, Jie Gui, Yuan Yan Tang, James Tin-Yau Kwok
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09736v1

Audio-driven talking head generation is a core component of digital avatars, and 3D Gaussian Splatting has shown strong performance in real-time rendering of high-fidelity talking heads. However, achieving precise control over fine-grained facial movements remains a significant challenge, particularly due to lip-synchronization inaccuracies and facial jitter, both of which can contribute to the uncanny valley effect. To address these challenges, we propose Fine-Grained 3D Gaussian Splatting (FG-3DGS), a novel framework that enables temporally consistent and high-fidelity talking head generation. Our method introduces a frequency-aware disentanglement strategy to explicitly model facial regions based on their motion characteristics. Low-frequency regions, such as the cheeks, nose, and forehead, are jointly modeled using a standard MLP, while high-frequency regions, including the eyes and mouth, are captured separately using a dedicated network guided by facial area masks. The predicted motion dynamics, represented as Gaussian deltas, are applied to the static Gaussians to generate the final head frames, which are rendered via a rasterizer using frame-specific camera parameters. Additionally, a high-frequency-refined post-rendering alignment mechanism, learned from large-scale audio-video pairs by a pretrained model, is incorporated to enhance per-frame generation and achieve more accurate lip synchronization. Extensive experiments on widely used datasets for talking head generation demonstrate that our method outperforms recent state-of-the-art approaches in producing high-fidelity, lip-synced talking head videos.

---

### Allure of Craquelure: A Variational-Generative Approach to Crack Detection in Paintings

Authors: Laura Paul, Holger Rauhut, Martin Burger, Samira Kabri, Tim Roith
Published: 2026-02-10
Categories: cs.CV, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.09730v3

Recent advances in imaging technologies, deep learning and numerical performance have enabled non-invasive detailed analysis of artworks, supporting their documentation and conservation. In particular, automated detection of craquelure in digitized paintings is crucial for assessing degradation and guiding restoration, yet remains challenging due to the possibly complex scenery and the visual similarity between cracks and crack-like artistic features such as brush strokes or hair. We propose a hybrid approach that models crack detection as an inverse problem, decomposing an observed image into a crack-free painting and a crack component. A deep generative model is employed as powerful prior for the underlying artwork, while crack structures are captured using a Mumford--Shah-type variational functional together with a crack prior. Joint optimization yields a pixel-level map of crack localizations in the painting.

---

### ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm

Authors: Hanyong Wang, Menglong Yang
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.09726v1

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most successful deep reinforcement-learning algorithm, the Proximal Policy Optimization algorithm (PPO) clips the policy gradient within a conservative on-policy updates, which ensures reliable and stable policy improvement. However, this training pattern may sacrifice sample efficiency. On the other hand, off-policy methods make more adequate use of data through sample reuse, though at the cost of increased the estimation variance and bias. To leverage the advantages of both, in this paper, we propose a new PPO variant based on the stability guarantee from conservative on-policy iteration with a more efficient off-policy data utilization. Specifically, we first derive an extended off-policy improvement from an expectation form of generalized policy improvement lower bound. Then, we extend the clipping mechanism with segmented exponential functions for a suitable surrogate objective function. Third, the trajectories generated by the past $M$ policies are organized in the replay buffer for off-policy training. We refer to this method as Extended Off-policy Proximal Policy Optimization (ExO-PPO). Compared with PPO and some other state-of-the-art variants, we demonstrate an improved performance of ExO-PPO with balanced sample efficiency and stability on varied tasks in the empirical experiments.

---

### Efficient Remote KV Cache Reuse with GPU-native Video Codec

Authors: Liang Mi, Weijun Wang, Jinghan Chen, Ting Cao, Haipeng Dai, Yunxin Liu
Published: 2026-02-10
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2602.09725v3

Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While it excels in high-speed networks, its performance degrades significantly in bandwidth-limited scenarios. Recent studies address this by transmitting KV caches in compressed form, but the associated heavyweight decompression counteracts the KV reuse benefits. In this paper, we propose an efficient and widely deployable remote KV cache reuse solution that leverages GPU-native video codecs. Our system, KVCodec, enables effective KV cache coding with two techniques. The codec-friendly tensor layout compresses the KV cache in a highly compact video format, enabling fast transmission. The efficient KV fetcher orchestrates the transmission, decoding, and restoration of compressed KV caches in an efficient pipelined manner, eliminating resource contention, masking network fluctuations, and achieving minimum time-to-first-token (TTFT). We prototype KVCodec on diverse GPUs from high- to low-end. Experiments reveal that it reduces TTFT by up to 3.51 times while maintaining lossless accuracy, compared to SOTA methods.

---

### Targum -- A Multilingual New Testament Translation Corpus

Authors: Maciej Rapacz, Aleksander Smywiński-Pohl
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09724v3

Many European languages possess rich biblical translation histories, yet existing corpora - in prioritizing linguistic breadth - often fail to capture this depth. To address this gap, we introduce a multilingual corpus of 651 New Testament translations, of which 334 are unique, spanning five languages with 2.4-5.0x more translations per language than any prior corpus: English (194 unique versions from 390 total), French (41 from 78), Italian (17 from 33), Polish (29 from 48), and Spanish (53 from 102). Aggregated from 12 online biblical libraries and one preexisting corpus, each translation is annotated with metadata that maps the text to a standardized identifier for the work, its specific edition, and its year of revision. This canonicalization allows researchers to define "uniqueness" for their own needs: they can perform micro-level analyses on translation families, such as the KJV lineage, or conduct macro-level studies by deduplicating closely related texts. By providing the first multilingual resource with sufficient depth per language for flexible, multilevel analysis, the corpus fills a gap in the quantitative study of translation history.

---

### AI-Assisted Scientific Assessment: A Case Study on Climate Change

Authors: Christian Buck, Levke Caesar, Michelle Chen Huebscher, Massimiliano Ciaramita, Erich M. Fischer, Zeke Hausfather, Özge Kart Tokmak, Reto Knutti, Markus Leippold, Joseph Ludescher, Katharine J. Mach, Sofia Palazzo Corner et al.
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09723v2

The emerging paradigm of AI co-scientists focuses on tasks characterized by repeatable verification, where agents explore search spaces in 'guess and check' loops. This paradigm does not extend to problems where repeated evaluation is impossible and ground truth is established by the consensus synthesis of theory and existing evidence. We evaluate a Gemini-based AI environment designed to support collaborative scientific assessment, integrated into a standard scientific workflow. In collaboration with a diverse group of 13 scientists working in the field of climate science, we tested the system on a complex topic: the stability of the Atlantic Meridional Overturning Circulation (AMOC). Our results show that AI can accelerate the scientific workflow. The group produced a comprehensive synthesis of 79 papers through 104 revision cycles in just over 46 person-hours. AI contribution was significant: most AI-generated content was retained in the report. AI also helped maintain logical consistency and presentation quality. However, expert additions were crucial to ensure its acceptability: less than half of the report was produced by AI. Furthermore, substantial oversight was required to expand and elevate the content to rigorous scientific standards.

---

### Continual Learning for non-stationary regression via Memory-Efficient Replay

Authors: Pablo García-Santaclara, Bruno Fernández-Castro, RebecaP. Díaz-Redondo, Martín Alonso-Gamarra
Published: 2026-02-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.09720v1

Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by continual learning (CL), which allows systems to gradually acquire knowledge without incurring the prohibitive costs of retraining them from scratch. Most research on continual learning focuses on classification problems, while very few studies address regression tasks. We propose the first prototype-based generative replay framework designed for online task-free continual regression. Our approach defines an adaptive output-space discretization model, enabling prototype-based generative replay for continual regression without storing raw data. Evidence obtained from several benchmark datasets shows that our framework reduces forgetting and provides more stable performance than other state-of-the-art solutions.

---

### Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs

Authors: Longhuan Xu, Cunjian Chen, Feng Yin
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.09719v1

Test-time adaptation (TTA) for large language models (LLMs) updates model parameters at inference time using signals available at deployment. This paper focuses on a common yet under-explored regime: unsupervised, sample-specific TTA, where the model adapts independently for each prompt using only the prompt itself, without gold answers or external supervision. Although appealing, naive unsupervised TTA with a fixed, handcrafted learning rate can be unstable: updates may overfit to prompt-specific statistics, drift from the desired answer distribution, and ultimately degrade generation quality. This failure mode is not surprising, as in this case TTA must adapt to a single prompt within only a few gradient steps, unlike standard training that averages updates over large datasets and long optimization horizons. Therefore, we propose layer-wise dynamic test-time adaptation, a framework which explicitly modulates TTA strength as a function of prompt representation, LLM structure and adaptation step. In our setting, TTA updates only LoRA parameters, and a lightweight hypernetwork predicts per-layer, per-step learning-rate multipliers, enabling fine-grained control. Experiments across various datasets and LLMs consistently show that our method substantially strengthens TTA by learning effective scaling patterns over adaptation steps and transformer layer projections, improving stability while delivering better performance.

---

### SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator

Authors: Jialiang Tang, Jialin Zhang, Xiaoming Sun
Published: 2026-02-10
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.09718v1

Quantum machine learning (QML), as an interdisciplinary field bridging quantum computing and machine learning, has garnered significant attention in recent years. Currently, the field as a whole faces challenges due to incomplete theoretical foundations for the expressivity of quantum neural networks (QNNs). In this paper we propose a constructive QNN model and demonstrate that it possesses the universal approximation property (UAP), which means it can approximate any square-integrable function up to arbitrary accuracy. Furthermore, it supports switching function bases, thus adaptable to various scenarios in numerical approximation and machine learning. Our model has asymptotic advantages over the best classical feed-forward neural networks in terms of circuit size and achieves optimal parameter complexity when approximating Sobolev functions under $L_2$ norm.

---

### From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

Authors: Radib Bin Kabir, Tawsif Tashwar Dipto, Mehedi Ahamed, Sabbir Ahmed, Md Hasanul Kabir
Published: 2026-02-10
Categories: cs.CV, cs.AI, cs.ET, cs.NE
arXiv: https://arxiv.org/abs/2602.09717v1

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant modules, yielding a pruned architecture, SNN-SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN-SqueezeNet. Crucially, it narrows the gap with CNN-SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge.

---

### Degree-Mass Message Passing for Betweenness Ranking in Directed and Undirected Networks

Authors: Justin Dachille, Aurora Rossi, Sunil Kumar Maurya, Frederik Mallmann-Trenn, Xin Liu, Frédéric Giroire, Tsuyoshi Murata, Emanuele Natale
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.09716v2

Computing the importance of nodes in networks is a long-standing fundamental problem that has driven extensive study of various centrality measures. A particularly well-known centrality measure is betweenness centrality, whose exact computation becomes prohibitive on large-scale networks. Graph Neural Network (GNN) models have thus been proposed to predict the ranking of nodes by betweenness centrality. However, existing GNN-based methods either have graph-size-dependent parameter counts or are limited to undirected graphs. We propose a lightweight GNN architecture that exploits the empirically observed relationship between betweenness centrality and multi-hop degree mass. This motivates the use of degree masses as size-invariant node features. To improve generalization, we train on synthetic graphs whose degree distributions more closely match those of real-world networks, including directed and undirected scale-free graphs and uniformly directed hyperbolic random graphs. We evaluate our model on 14 real-world networks spanning eight domains, including social, email, and citation networks, across both directed and undirected regimes. The experiments show that our model improves the Kendall $τ_b$ correlation by up to 24.6\% on undirected and 10.9\% on directed graphs, while using 56$\times$ fewer parameters than the lightest competing GNN baseline and achieving competitive inference time, with up to a 24.5$\times$ speedup on selected directed graphs.

---

### BRAVA-GNN: Betweenness Ranking Approximation Via Degree MAss Inspired Graph Neural Network

Authors: Justin Dachille, Aurora Rossi, Sunil Kumar Maurya, Frederik Mallmann-Trenn, Xin Liu, Frédéric Giroire, Tsuyoshi Murata, Emanuele Natale
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.09716v1

Computing node importance in networks is a long-standing fundamental problem that has driven extensive study of various centrality measures. A particularly well-known centrality measure is betweenness centrality, which becomes computationally prohibitive on large-scale networks. Graph Neural Network (GNN) models have thus been proposed to predict node rankings according to their relative betweenness centrality. However, state-of-the-art methods fail to generalize to high-diameter graphs such as road networks. We propose BRAVA-GNN, a lightweight GNN architecture that leverages the empirically observed correlation linking betweenness centrality to degree-based quantities, in particular multi-hop degree mass. This correlation motivates the use of degree masses as size-invariant node features and synthetic training graphs that closely match the degree distributions of real networks. Furthermore, while previous work relies on scale-free synthetic graphs, we leverage the hyperbolic random graph model, which reproduces power-law exponents outside the scale-free regime, better capturing the structure of real-world graphs like road networks. This design enables BRAVA-GNN to generalize across diverse graph families while using 54x fewer parameters than the most lightweight existing GNN baseline. Extensive experiments on 19 real-world networks, spanning social, web, email, and road graphs, show that BRAVA-GNN achieves up to 214% improvement in Kendall-Tau correlation and up to 70x speedup in inference time over state-of-the-art GNN-based approaches, particularly on challenging road networks.

---

### Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

Authors: Ruisi Zhao, Haoren Zheng, Zongxin Yang, Hehe Fan, Yi Yang
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.09713v2

Rigged 3D assets are fundamental to 3D deformation and animation. However, existing 3D generation methods face challenges in generating animatable geometry, while rigging techniques lack fine-grained structural control over skeleton creation. To address these limitations, we introduce Stroke3D, a novel framework that directly generates rigged meshes from user inputs: 2D drawn strokes and a descriptive text prompt. Our approach pioneers a two-stage pipeline that separates the generation into: 1) Controllable Skeleton Generation, we employ the Skeletal Graph VAE (Sk-VAE) to encode the skeleton's graph structure into a latent space, where the Skeletal Graph DiT (Sk-DiT) generates a skeletal embedding. The generation process is conditioned on both the text for semantics and the 2D strokes for explicit structural control, with the VAE's decoder reconstructing the final high-quality 3D skeleton; and 2) Enhanced Mesh Synthesis via TextuRig and SKA-DPO, where we then synthesize a textured mesh conditioned on the generated skeleton. For this stage, we first enhance an existing skeleton-to-mesh model by augmenting its training data with TextuRig: a dataset of textured and rigged meshes with captions, curated from Objaverse-XL. Additionally, we employ a preference optimization strategy, SKA-DPO, guided by a skeleton-mesh alignment score, to further improve geometric fidelity. Together, our framework enables a more intuitive workflow for creating ready to animate 3D content. To the best of our knowledge, our work is the first to generate rigged 3D meshes conditioned on user-drawn 2D strokes. Extensive experiments demonstrate that Stroke3D produces plausible skeletons and high-quality meshes.

---