# Research Papers — 2026-02 · bundle page 133 of 210

> Full-text markdown of papers #6601–6650 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/133
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/132.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/134.md)

### Discovering Interpretable Algorithms by Decompiling Transformers to RASP

Authors: Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra, William Merrill, Michael Hahn
Published: 2026-02-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.08857v2

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization abilities of Transformers. In particular, Transformers have been suggested to length-generalize exactly on problems that have simple RASP programs. However, it remains open whether trained models actually implement simple interpretable programs. In this paper, we present a general method to extract such programs from trained Transformers. The idea is to faithfully re-parameterize a Transformer as a RASP program and then apply causal interventions to discover a small sufficient sub-program. In experiments on small Transformers trained on algorithmic and formal language tasks, we show that our method often recovers simple and interpretable RASP programs from length-generalizing transformers. Our results provide the most direct evidence so far that Transformers internally implement simple RASP programs.

---

### Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization

Authors: Yang Qiu, Yixiong Zou, Jun Wang
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08855v1

Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a prevalent yet under-explored phenomenon in graph generalization, Minimal Shift Flip (MSF),where test samples that slightly deviate from the training distribution are abruptly misclassified. To interpret this phenomenon, we revisit MSF through the lens of Sharpness-Aware Minimization (SAM), which characterizes the local stability and sharpness of the loss landscape while providing a theoretical foundation for modeling generalization error. To quantify loss sharpness, we introduce the concept of Local Robust Radius, measuring the smallest perturbation required to flip a prediction and establishing a theoretical link between local stability and generalization. Building on this perspective, we further observe a continual decrease in the robust radius during training, indicating weakened local stability and an increasingly sharp loss landscape that gives rise to MSF. To jointly solve the MSF phenomenon and the intractability of radius, we develop an energy-based formulation that is theoretically proven to be monotonically correlated with the robust radius, offering a tractable and principled objective for modeling flatness and stability. Building on these insights, we propose an energy-driven generative augmentation framework (E2A) that leverages energy-guided latent perturbations to generate pseudo-OOD samples and enhance model generalization. Extensive experiments across multiple benchmarks demonstrate that E2A consistently improves graph OOD generalization, outperforming state-of-the-art baselines.

---

### Cutting Through the Noise: On-the-fly Outlier Detection for Robust Training of Machine Learning Interatomic Potentials

Authors: Terry C. W. Lam, Niamh O'Neill, Christoph Schran, Lars L. Schaaf
Published: 2026-02-09
Categories: stat.ML, cond-mat.mtrl-sci, cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2602.08849v1

The accuracy of machine learning interatomic potentials suffers from reference data that contains numerical noise. Often originating from unconverged or inconsistent electronic-structure calculations, this noise is challenging to identify. Existing mitigation strategies such as manual filtering or iterative refinement of outliers, require either substantial expert effort or multiple expensive retraining cycles, making them difficult to scale to large datasets. Here, we introduce an on-the-fly outlier detection scheme that automatically down-weights noisy samples, without requiring additional reference calculations. By tracking the loss distribution via an exponential moving average, this unsupervised method identifies outliers throughout a single training run. We show that this approach prevents overfitting and matches the performance of iterative refinement baselines with significantly reduced overhead. The method's effectiveness is demonstrated by recovering accurate physical observables for liquid water from unconverged reference data, including diffusion coefficients. Furthermore, we validate its scalability by training a foundation model for organic chemistry on the SPICE dataset, where it reduces energy errors by a factor of three. This framework provides a simple, automated solution for training robust models on imperfect datasets across dataset sizes.

---

### Deciding the Satisfiability of Combined Qualitative Constraint Networks

Authors: Quentin Cohen-Solal, Alexandre Niveau, Maroua Bouzid
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08848v1

Among the various forms of reasoning studied in the context of artificial intelligence, qualitative reasoning makes it possible to infer new knowledge in the context of imprecise, incomplete information without numerical values. In this paper, we propose a formal framework unifying several forms of extensions and combinations of qualitative formalisms, including multi-scale reasoning, temporal sequences, and loose integrations. This framework makes it possible to reason in the context of each of these combinations and extensions, but also to study in a unified way the satisfiability decision and its complexity. In particular, we establish two complementary theorems guaranteeing that the satisfiability decision is polynomial, and we use them to recover the known results of the size-topology combination. We also generalize the main definition of qualitative formalism to include qualitative formalisms excluded from the definitions of the literature, important in the context of combinations.

---

### Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems

Authors: Lang Feng, Longtao Zheng, Shuo He, Fuxiang Zhang, Bo An
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08847v2

Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for training instability when extending group-based RL to multi-agent LLM systems. We show that under GRPO-style optimization, a global normalization baseline may deviate from diverse agents' reward distributions, which ultimately leads to gradient-norm instability. Based on this finding, we propose Dr. MAS, a simple and stable RL training recipe for multi-agent LLM systems. Dr. MAS uses an agent-wise remedy: normalizing advantages per agent using each agent's own reward statistics, which calibrates gradient scales and dramatically stabilizes training, both theoretically and empirically. Beyond the algorithm, Dr. MAS provides an end-to-end RL training framework for multi-agent LLM systems, supporting scalable orchestration, flexible per-agent LLM serving and optimization configs, and shared resource scheduling of LLM actor backends. We evaluate Dr. MAS on multi-agent math reasoning and multi-turn search benchmarks using Qwen2.5 and Qwen3 series models. Dr. MAS achieves clear gains over vanilla GRPO (e.g., +5.6\% avg@16 and +4.6\% pass@16 on math, and +15.2\% avg@16 and +13.1\% pass@16 on search) while largely eliminating gradient spikes. Moreover, it remains highly effective under heterogeneous agent-model assignments while improving efficiency.

---

### Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems

Authors: Lang Feng, Longtao Zheng, Shuo He, Fuxiang Zhang, Bo An
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08847v1

Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for training instability when extending group-based RL to multi-agent LLM systems. We show that under GRPO-style optimization, a global normalization baseline may deviate from diverse agents' reward distributions, which ultimately leads to gradient-norm instability. Based on this finding, we propose Dr. MAS, a simple and stable RL training recipe for multi-agent LLM systems. Dr. MAS uses an agent-wise remedy: normalizing advantages per agent using each agent's own reward statistics, which calibrates gradient scales and dramatically stabilizes training, both theoretically and empirically. Beyond the algorithm, Dr. MAS provides an end-to-end RL training framework for multi-agent LLM systems, supporting scalable orchestration, flexible per-agent LLM serving and optimization configs, and shared resource scheduling of LLM actor backends. We evaluate Dr. MAS on multi-agent math reasoning and multi-turn search benchmarks using Qwen2.5 and Qwen3 series models. Dr. MAS achieves clear gains over vanilla GRPO (e.g., +5.6\% avg@16 and +4.6\% pass@16 on math, and +15.2\% avg@16 and +13.1\% pass@16 on search) while largely eliminating gradient spikes. Moreover, it remains highly effective under heterogeneous agent-model assignments while improving efficiency.

---

### AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders

Authors: Minh-Duc Nguyen, Hai-Dang Kieu, Dung D. Le
Published: 2026-02-09
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.08837v1

Agentic systems powered by Large Language Models (LLMs) have shown strong potential in recommender systems but remain hindered by several challenges. Fine-tuning LLMs is parameter-inefficient, and prompt-based agentic reasoning is limited by context length and hallucination risk. Moreover, existing agentic recommendation systems predominantly leverages semantic knowledge while neglecting the collaborative filtering (CF) signals essential for implicit preference modeling. To address these limitations, we propose AMEM4Rec, an agentic LLM-based recommender that learns collaborative signals in an end-to-end manner through cross-user memory evolution. AMEM4Rec stores abstract user behavior patterns from user histories in a global memory pool. Within this pool, memories are linked to similar existing ones and iteratively evolved to reinforce shared cross-user patterns, enabling the system to become aware of CF signals without relying on a pre-trained CF model. Extensive experiments on Amazon and MIND datasets show that AMEM4Rec consistently outperforms state-of-the-art LLM-based recommenders, demonstrating the effectiveness of evolving memory-guided collaborative filtering.

---

### Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning

Authors: Andrés Holgado-Sánchez, Peter Vamplew, Richard Dazeley, Sascha Ossowski, Holger Billhardt
Published: 2026-02-09
Categories: cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2602.08835v2

Value-aware AI should recognise human values and adapt to the value systems (value-based preferences) of different users. This requires operationalization of values, which can be prone to misspecification. The social nature of values demands their representation to adhere to multiple users while value systems are diverse, yet exhibit patterns among groups. In sequential decision making, efforts have been made towards personalization for different goals or values from demonstrations of diverse agents. However, these approaches demand manually designed features or lack value-based interpretability and/or adaptability to diverse user preferences. We propose algorithms for learning models of value alignment and value systems for a society of agents in Markov Decision Processes (MDPs), based on clustering and preference-based multi-objective reinforcement learning (PbMORL). We jointly learn socially-derived value alignment models (groundings) and a set of value systems that concisely represent different groups of users (clusters) in a society. Each cluster consists of a value system representing the value-based preferences of its members and an approximately Pareto-optimal policy that reflects behaviours aligned with this value system. We evaluate our method against a state-of-the-art PbMORL algorithm and baselines on two MDPs with human values.

---

### WildReward: Learning Reward Models from In-the-Wild Human Interactions

Authors: Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Lei Hou, Juanzi Li
Published: 2026-02-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.08829v1

Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deployment of LLMs, in-the-wild interactions have emerged as a rich source of implicit reward signals. This raises the question: Can we develop reward models directly from in-the-wild interactions? In this work, we explore this possibility by adopting WildChat as an interaction source and proposing a pipeline to extract reliable human feedback, yielding 186k high-quality instances for training WildReward via ordinal regression directly on user feedback without preference pairs. Extensive experiments demonstrate that WildReward achieves comparable or even superior performance compared to conventional reward models, with improved calibration and cross-sample consistency. We also observe that WildReward benefits directly from user diversity, where more users yield stronger reward models. Finally, we apply WildReward to online DPO training and observe significant improvements across various tasks. Code and data are released at https://github.com/THU-KEG/WildReward.

---

### VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning

Authors: Hao Tan, Jun Lan, Senyuan Shi, Zichang Tan, Zijian Yu, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08828v1

The growing capability of video generation poses escalating security risks, making reliable detection increasingly essential. In this paper, we introduce VideoVeritas, a framework that integrates fine-grained perception and fact-based reasoning. We observe that while current multi-modal large language models (MLLMs) exhibit strong reasoning capacity, their granular perception ability remains limited. To mitigate this, we introduce Joint Preference Alignment and Perception Pretext Reinforcement Learning (PPRL). Specifically, rather than directly optimizing for detection task, we adopt general spatiotemporal grounding and self-supervised object counting in the RL stage, enhancing detection performance with simple perception pretext tasks. To facilitate robust evaluation, we further introduce MintVid, a light yet high-quality dataset containing 3K videos from 9 state-of-the-art generators, along with a real-world collected subset that has factual errors in content. Experimental results demonstrate that existing methods tend to bias towards either superficial reasoning or mechanical analysis, while VideoVeritas achieves more balanced performance across diverse benchmarks.

---

### Affective Flow Language Model for Emotional Support Conversation

Authors: Chenghui Zou, Ning Wang, Tiesunlong Shen, Luwei Xiao, Chuan Ma, Xiangpeng Li, Rui Mao, Erik Cambria
Published: 2026-02-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.08826v3

Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level or outcomes at the dialogue level, providing limited supervision for sequential strategy decisions in multi-turn interactions. This raises a key question: how can detailed process signals be derived from overall dialogue outcomes to guide the gradual adaptation of support strategies? We propose the Affective Flow Language Model (AFlow), which models multi-turn emotional support as an affective utility flow evolving along dialogue trajectories. AFlow searches diverse support trajectories and estimates the utility of intermediate dialogue states and candidate strategies. It further introduces Affective Flow Preference Optimization (AFPO), which uses a flow-balance objective defined over dialogue subpaths to propagate downstream preference signals to intermediate states and learn strategy transitions consistent with support outcomes over the full dialogue. AFlow introduces flow-balance learning into multi-turn affective interaction, providing a process-based approach to dynamic affect modeling and continuous strategy optimization. Experiments on ExTES and ESConv show consistent improvements in strategy alignment, response diversity, and generation quality across different model environments and evaluation settings. Our code is available at https://github.com/chz2025/AffectiveFlow.

---

### Affective Flow Language Model for Emotional Support Conversation

Authors: Chenghui Zou, Ning Wang, Tiesunlong Shen, Luwei Xiao, Chuan Ma, Xiangpeng Li, Rui Mao, Erik Cambria
Published: 2026-02-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.08826v2

Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains challenging.This is because existing alignment schemes rely on sparse outcome-level signals, thus offering limited supervision for intermediate strategy decisions. To fill this gap, this paper proposes affective flow language model for emotional support conversation (AFlow), a framework that introduces fine-grained supervision on dialogue prefixes by modeling a continuous affective flow along multi-turn trajectories. AFlow can estimate intermediate utility over searched trajectories and learn preference-consistent strategy transitions. To improve strategy coherence and empathetic response quality, a subpath-level flow-balance objective is presented to propagate preference signals to intermediate states. Experiment results show consistent and significant improvements over competitive baselines in diverse emotional contexts. Remarkably, AFlow with a compact open-source backbone outperforms proprietary LMMs such as GPT-4o and Claude-3.5 on major ESC metrics. Our code is available at https://github.com/chz2025/AffectiveFlow.

---

### A Methodology for Effective Surrogate Learning in Complex Optimization

Authors: Tomohiro Harada, Enrique Alba, Gabriel Luque
Published: 2026-02-09
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.08825v1

Solving complex problems requires continuous effort in developing theory and practice to cope with larger, more difficult scenarios. Working with surrogates is normal for creating a proxy that realistically models the problem into the computer. Thus, the question of how to best define and characterize such a surrogate model is of the utmost importance. In this paper, we introduce the PTME methodology to study deep learning surrogates by analyzing their Precision, Time, Memory, and Energy consumption. We argue that only a combination of numerical and physical performance can lead to a surrogate that is both a trusted scientific substitute for the real problem and an efficient experimental artifact for scalable studies. Here, we propose different surrogates for a real problem in optimally organizing the network of traffic lights in European cities and perform a PTME study on the surrogates' sampling methods, dataset sizes, and resource consumption. We further use the built surrogates in new optimization metaheuristics for decision-making in real cities. We offer better techniques and conclude that the PTME methodology can be used as a guideline for other applications and solvers.

---

### Any-to-All MRI Synthesis: A Unified Foundation Model for Nasopharyngeal Carcinoma and Its Downstream Applications

Authors: Yao Pu, Yiming Shi, Zhenxi Zhang, Peixin Yu, Yitao Zhuang, Xiang Wang, Hongzhao Chen, Jing Cai, Ge Ren
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08822v1

Magnetic resonance imaging (MRI) is essential for nasopharyngeal carcinoma (NPC) radiotherapy (RT), but practical constraints, such as patient discomfort, long scan times, and high costs often lead to incomplete modalities in clinical practice, compromising RT planning accuracy. Traditional MRI synthesis methods are modality-specific, limited in anatomical adaptability, and lack clinical interpretability-failing to meet NPC's RT needs. Here, we developed a unified foundation model integrating contrastive visual representation learning and vision-language alignment (VLA) to enable any-to-all MRI synthesis. The model uses a contrastive encoder for modality-invariant representations and a CLIP-based text-informed decoder for semantically consistent synthesis, supporting any-to-all MRI synthesis via one unified foundation model. Trained on 40,825 images from 13 institutions, it achieves consistently high performance (average SSIM 0.90, PSNR 27) across 26 internal/external validation sites (15,748 images), with superior synthesis fidelity and robustness to noise and domain shifts. Meanwhile, its unified representation enhances downstream RT-relevant tasks (e.g., segmentation). This work advances digital medicine solutions for NPC care by leveraging foundation models to bridge technical synthesis and clinical utility.

---

### Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing

Authors: Hao Yang, Zhiyu Tan, Jia Gong, Luozheng Qin, Hesen Chen, Xiaomeng Yang, Yuqing Sun, Yuetan Lin, Mengping Yang, Hao Li
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08820v2

We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the understanding and reasoning capabilities of MLLMs to produce explicit target captions to interpret user instructions. In this way, the rich contextual representations from the understanding model are directly used to guide the generative process, thereby improving performance on complex and compositional editing. Moreover, a lightweight adapter is developed to inject multimodal conditional tokens into pretrained text-to-video diffusion models, allowing maximum reuse of their powerful generative priors in a parameter-efficient manner. Benefiting from these designs, we scale up Omni-Video 2 to a 14B video diffusion model on meticulously curated training data with quality, supporting high quality text-to-video generation and various video editing tasks such as object removal, addition, background change, complex motion editing, \emph{etc.} We evaluate the performance of Omni-Video 2 on the FiVE benchmark for fine-grained video editing and the VBench benchmark for text-to-video generation. The results demonstrate its superior ability to follow complex compositional instructions in video editing, while also achieving competitive or superior quality in video generation tasks.

---

### Bayesian Preference Learning for Test-Time Steerable Reward Models

Authors: Jiwoo Hong, Shao Tang, Zhipeng Wang
Published: 2026-02-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.08819v2

Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode more complex and multifaceted preference distributions. However, classifier RMs remain static once trained, limiting their adaptability at test time. We propose Variational In-Context Reward Modeling (ICRM), a novel Bayesian reward modeling objective that enables test-time steerability via in-context preference demonstrations. ICRM casts reward modeling as amortized variational inference over a latent preference probability under the Bradley-Terry model using a conjugate Beta prior. We show that ICRM adapts to unseen preference distributions at test time for both single and multi-objective settings. With more demonstrations, ICRM improves RM-Bench accuracy from 60.5 to 70.8, achieves lower calibration error than a generative judge on moral dilemma preferences, and expands the attainable Pareto frontier under conflicting preferences. We further study the practical applicability of ICRM for RL training, showing that it can effectively encode verifiable rewards by outperforming a conventional RM in math reasoning. Finally, we provide theoretical guarantees that the variational objective admits a global interior optimum with finite confidence, and we analyze how KL regularization mitigates reward over-optimization.

---

### FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models

Authors: Annemette Brok Pirchert, Jacob Nielsen, Mogens Henrik From, Lukas Galke Poech, Peter Schneider-Kamp
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08818v1

Recent advances in mixture-of-experts architectures have shown that individual experts models can be trained federatedly, i.e., in isolation from other experts by using a common base model to facilitate coordination. However, we hypothesize that full-sized experts may not be necessary for all domains and that instead low-rank adapters may be sufficient. Here, we introduce FlexMoRE, a Flexible Mixture of Rank-heterogenous Experts, which may be either full-sized experts or adapters of a suitable rank. We systematically investigate the trade-off between expert rank and downstream task performance by evaluating $6$ experts with ranks $2^0$ to $2^{14}$ resulting in experiments covering 150 mixtures (96 with 2 experts, 54 with 7 experts) that are evaluated across $120$ tasks. For our experiments, we build on FlexOlmo and turn its pre-trained experts into low-rank versions. Our regression analysis from expert rank to downstream task performance reveals that the best-performing rank is substantially higher for reasoning-heavy benchmarks than for knowledge-heavy benchmarks. These findings on rank sensitivity come with direct implications for memory efficiency: Using optimal ranks, FlexMoRE yields improved downstream task performance (average score $47.18$) compared to the baseline FlexOlmo-style mixture of full-sized experts (average score $45.46$) at less than one third the parameters ($10.75$B for FlexMoRE vs. $33.27$B for FlexOlmo). All code will be made available.

---

### Kirin: Improving ANN efficiency with SNN Hybridization

Authors: Chenyu Wang, Zhanglu Yan, Zhi Zhou, Xu Chen, Weng-Fai Wong
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08817v1

Artificial neural networks (ANNs), particularly large language models (LLMs), demonstrate powerful inference capabilities but consume substantial energy. Conversely, spiking neural networks (SNNs) exhibit exceptional energy efficiency due to their binary and event-driven characteristics, thus motivating the study of ANN-to-SNN conversion. In this process, quantization plays a pivotal role, mapping LLMs' floating-point parameters to discrete SNN parameters via the temporal dimension of the time window. However, several challenges remain in the conversion process: (i) converting high bit-width quantization values into binary spikes requires longer time windows, increasing system latency; and (ii) the inherent trade-off between the information loss of single-spike schemes and the energy costs of multi-spike ones in SNN. To address these challenges, we propose Kirin, a integer and spike hybrid based SNN to achieve accuracy lossless ANN-to-SNN conversion with time and energy efficiency. Specifically, we first propose a Spike Matrix Hybridization strategy that encoding low bit-width parameters that leading to small time window size into binary spikes while preserving the rest in integer format, thereby reducing the overall latency of SNN execution. Second, we introduce a silence threshold mechanism to regulate the timing of single-spike firing, ensuring the output is mathematically equivalent to the LLM's output and preserves accuracy. Experimental results demonstrate that Kirin, under a W4A4\&8 quantization setting, achieves near-FP16 accuracy while reducing energy consumption by up to 84.66\% and shortening time steps by 93.75\%.

---

### Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity

Authors: James Jewitt, Gopi Krishnan Rajbahadur, Hao Li, Bram Adams, Ahmed E. Hassan
Published: 2026-02-09
Categories: cs.LG, cs.AI, cs.CY, cs.SE
arXiv: https://arxiv.org/abs/2602.08816v1

Permissive licenses like MIT, Apache-2.0, and BSD-3-Clause dominate open-source AI, signaling that artifacts like models, datasets, and code can be freely used, modified, and redistributed. However, these licenses carry mandatory requirements: include the full license text, provide a copyright notice, and preserve upstream attribution, that remain unverified at scale. Failure to meet these conditions can place reuse outside the scope of the license, effectively leaving AI artifacts under default copyright for those uses and exposing downstream users to litigation. We call this phenomenon ``permissive washing'': labeling AI artifacts as free to use, while omitting the legal documentation required to make that label actionable. To assess how widespread permissive washing is in the AI supply chain, we empirically audit 124,278 dataset $\rightarrow$ model $\rightarrow$ application supply chains, spanning 3,338 datasets, 6,664 models, and 28,516 applications across Hugging Face and GitHub. We find that an astonishing 96.5\% of datasets and 95.8\% of models lack the required license text, only 2.3\% of datasets and 3.2\% of models satisfy both license text and copyright requirements, and even when upstream artifacts provide complete licensing evidence, attribution rarely propagates downstream: only 27.59\% of models preserve compliant dataset notices and only 5.75\% of applications preserve compliant model notices (with just 6.38\% preserving any linked upstream notice). Practitioners cannot assume permissive labels confer the rights they claim: license files and notices, not metadata, are the source of legal truth. To support future research, we release our full audit dataset and reproducible pipeline.

---

### Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation

Authors: Yanglei Gan, Peng He, Yuxiang Cai, Run Lin, Guanyu Zhou, Qiao Liu
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08815v1

Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.

---

### Robust Policy Optimization to Prevent Catastrophic Forgetting

Authors: Mahdi Sabbaghi, George Pappas, Adel Javanmard, Hamed Hassani
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08813v2

Large language models are commonly trained through multi-stage post-training: first via RLHF, then fine-tuned for other downstream objectives. Yet even small downstream updates can compromise earlier learned behaviors (e.g., safety), exposing a brittleness known as catastrophic forgetting. This suggests standard RLHF objectives do not guarantee robustness to future adaptation. To address it, most prior work designs downstream-time methods to preserve previously learned behaviors. We argue that preventing this requires pre-finetuning robustness: the base policy should avoid brittle high-reward solutions whose reward drops sharply under standard fine-tuning. We propose Fine-tuning Robust Policy Optimization (FRPO), a robust RLHF framework that optimizes reward not only at the current policy, but across a KL-bounded neighborhood of policies reachable by downstream adaptation. The key idea is to ensure reward stability under policy shifts via a max-min formulation. By modifying GRPO, we develop an algorithm with no extra computation, and empirically show it substantially reduces safety degradation across multiple base models and downstream fine-tuning regimes (SFT and RL) while preserving downstream task performance. We further study a math-focused RL setting, demonstrating that FRPO preserves accuracy under subsequent fine-tuning.

---

### $\texttt{lrnnx}$: A library for Linear RNNs

Authors: Karan Bania, Soham Kalburgi, Manit Tanwar, Dhruthi, Aditya Nagarsekar, Harshvardhan Mestha, Naman Chibber, Raj Deshmukh, Anish Sathyanarayanan, Aarush Rathore, Pratham Chheda
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08810v1

Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and trainability. In recent years, multiple LRNN-based architectures have been proposed, each introducing distinct parameterizations, discretization schemes, and implementation constraints. However, existing implementations are fragmented across different software frameworks, often rely on framework-specific optimizations, and in some cases require custom CUDA kernels or lack publicly available code altogether. As a result, using, comparing, or extending LRNNs requires substantial implementation effort. To address this, we introduce $\texttt{lrnnx}$, a unified software library that implements several modern LRNN architectures under a common interface. The library exposes multiple levels of control, allowing users to work directly with core components or higher-level model abstractions. $\texttt{lrnnx}$ aims to improve accessibility, reproducibility, and extensibility of LRNN research and applications. We make our code available under a permissive MIT license.

---

### Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI

Authors: Karim Haroun, Aya Zitouni, Aicha Zenakhri, Meriem Amel Guessoum, Larbi Boubchir
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08809v1

Recent advances in deep learning, whether on discriminative or generative tasks have been beneficial for various applications, among which security and defense. However, their increasing computational demands during training and deployment translates directly into high energy consumption. As a consequence, this induces a heavy carbon footprint which hinders their widespread use and scalability, but also a limitation when deployed on resource-constrained edge devices for real-time use. In this paper, we briefly survey efficient deep learning methods for biometric applications. Specifically, we tackle the challenges one might incur when training and deploying deep learning approaches, and provide a taxonomy of the various efficient deep learning families. Additionally, we discuss complementary metrics for evaluating the efficiency of these models such as memory, computation, latency, throughput, and advocate for universal and reproducible metrics for better comparison. Last, we give future research directions to consider.

---

### How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs

Authors: Yapei Chang, Kyle Lo, Mohit Iyyer, Luca Soldaini
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08808v1

Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over complex tasks. Yet, measuring and improving procedural validity at scale on real-world tasks remains challenging and understudied. To address this, we introduce How2Everything, a scalable framework to evaluate and improve goal-conditioned procedure generation. Our framework includes How2Mine, which mines 351K procedures from 980K web pages across 14 topics and readily scales to larger corpora. From this pool we build How2Bench, a 7K-example evaluation set balanced across topics. To reliably score model outputs, we develop How2Score, an evaluation protocol that uses an LLM judge to detect whether a generation contains any critical failure that would prevent achieving the goal. For low-cost, reproducible evaluation, we distill a frontier model into an open 8B model, achieving 80.5% agreement with human annotators. How2Bench reveals clear scaling trends across model sizes and training stages, providing signal early in pretraining. Finally, RL using How2Score as a reward improves performance on How2Bench by >10 points across three models without systematic regressions on standard benchmarks, with gains robust to superficial source-document memorization or format compliance. Taken together, How2Everything shows how pretraining web data can support a closed loop of capability evaluation and improvement at scale.

---

### Root Cause Analysis Method Based on Large Language Models with Residual Connection Structures

Authors: Liming Zhou, Ailing Liu, Hongwei Liu, Min He, Heng Zhang
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08804v1

Root cause localization remain challenging in complex and large-scale microservice architectures. The complex fault propagation among microservices and the high dimensionality of telemetry data, including metrics, logs, and traces, limit the effectiveness of existing root cause analysis (RCA) methods. In this paper, a residual-connection-based RCA method using large language model (LLM), named RC-LLM, is proposed. A residual-like hierarchical fusion structure is designed to integrate multi-source telemetry data, while the contextual reasoning capability of large language models is leveraged to model temporal and cross-microservice causal dependencies. Experimental results on CCF-AIOps microservice datasets demonstrate that RC-LLM achieves strong accuracy and efficiency in root cause analysis.

---

### Addressing data annotation scarcity in Brain Tumor Segmentation on 3D MRI scan Using a Semi-Supervised Teacher-Student Framework

Authors: Jiaming Liu, Cheng Ding, Daoqiang Zhang
Published: 2026-02-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.08797v1

Accurate brain tumor segmentation from MRI is limited by expensive annotations and data heterogeneity across scanners and sites. We propose a semi-supervised teacher-student framework that combines an uncertainty-aware pseudo-labeling teacher with a progressive, confidence-based curriculum for the student. The teacher produces probabilistic masks and per-pixel uncertainty; unlabeled scans are ranked by image-level confidence and introduced in stages, while a dual-loss objective trains the student to learn from high-confidence regions and unlearn low-confidence ones. Agreement-based refinement further improves pseudo-label quality. On BraTS 2021, validation DSC increased from 0.393 (10% data) to 0.872 (100%), with the largest gains in early stages, demonstrating data efficiency. The teacher reached a validation DSC of 0.922, and the student surpassed the teacher on tumor subregions (e.g., NCR/NET 0.797 and Edema 0.980); notably, the student recovered the Enhancing class (DSC 0.620) where the teacher failed. These results show that confidence-driven curricula and selective unlearning provide robust segmentation under limited supervision and noisy pseudo-labels.

---

### The Use of AI Tools to Develop and Validate Q-Matrices

Authors: Kevin Fan, Jacquelyn A. Bialo, Hongli Li
Published: 2026-02-09
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.08796v1

Constructing a Q-matrix is a critical but labor-intensive step in cognitive diagnostic modeling (CDM). This study investigates whether AI tools (i.e., general language models) can support Q-matrix development by comparing AI-generated Q-matrices with a validated Q-matrix from Li and Suen (2013) for a reading comprehension test. In May 2025, multiple AI models were provided with the same training materials as human experts. Agreement among AI-generated Q-matrices, the validated Q-matrix, and human raters' Q-matrices was assessed using Cohen's kappa. Results showed substantial variation across AI models, with Google Gemini 2.5 Pro achieving the highest agreement (Kappa = 0.63) with the validated Q-matrix, exceeding that of all human experts. A follow-up analysis in January 2026 using newer AI versions, however, revealed lower agreement with the validated Q-matrix. Implications and directions for future research are discussed.

---

### MOVA: Towards Scalable and Synchronized Video-Audio Generation

Authors: SII-OpenMOSS Team, :, Donghua Yu, Mingshu Chen, Qi Chen, Qi Luo, Qianyi Wu, Qinyuan Cheng, Ruixiao Li, Tianyi Liang, Wenbo Zhang, Wenming Tu et al.
Published: 2026-02-09
Categories: cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2602.08794v2

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

---

### LakeHopper: Knowledge-Aware Adaptation of Column Type Annotators across Data Lakes

Authors: Yushi Sun, Xujia Li, Nan Tang, Quanqing Xu, Chuanhui Yang, Lei Chen
Published: 2026-02-09
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2602.08793v2

Column Type Annotation (CTA), which assigns a semantic type to a table column, underpins data integration, cleaning, and search over data lakes. State-of-the-art annotators are pre-trained language models (PLMs) fine-tuned on one particular corpus of tables, i.e., a source data lake, and they degrade sharply once deployed on a new (i.e., target) lake, whose tables and semantic type set both differ. Retraining per lake is prohibitive because it demands large volumes of expert annotations. We recast cross-lake adaptation as a knowledge management problem and make the resulting decomposition explicit: relative to a target annotator, a source annotator holds knowledge that must be discarded (source-specific), realigned and reused (shared), or acquired (target-specific). This decomposition exposes which part of the gap a general-purpose LLM can close and which part only target supervision can. Guided by it, we present LakeHopper, which adapts a source annotator under a fixed annotation budget through three coupled mechanisms: label-set realignment that transplants the output layer for shared types, LLM-verified gap discovery that localizes columns the annotator handles unreliably, and cluster-based propagation plus rehearsal fine-tuning that generalizes each flagged column into a labeling batch without erasing shared knowledge. Casting the LLM as a verifier of the annotator's own predictions rather than an annotator keeps every output inside the target type set, so LakeHopper structurally emits no out-of-domain labels, whereas prompted LLMs hallucinate types on 2.7-47.6% of columns. Across three data lake transfers of differing difficulty, LakeHopperlifts three PLM backbones by up to 71.4% relative macro-F1, reaches near-full-data quality with under 6% of the target labels, and matches fine-tuned table LLMs while training 27-131 times faster.

---

### LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation

Authors: Yushi Sun, Xujia Li, Nan Tang, Quanqing Xu, Chuanhui Yang, Lei Chen
Published: 2026-02-09
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2602.08793v1

Column type annotation is vital for tasks like data cleaning, integration, and visualization. Recent solutions rely on resource-intensive language models fine-tuned on well-annotated columns from a particular set of tables, i.e., a source data lake. In this paper, we study whether we can adapt an existing pre-trained LM-based model to a new (i.e., target) data lake to minimize the annotations required on the new data lake. However, challenges include the source-target knowledge gap, selecting informative target data, and fine-tuning without losing shared knowledge exist. We propose LakeHopper, a framework that identifies and resolves the knowledge gap through LM interactions, employs a cluster-based data selection scheme for unannotated columns, and uses an incremental fine-tuning mechanism that gradually adapts the source model to the target data lake. Our experimental results validate the effectiveness of LakeHopper on two different data lake transfers under both low-resource and high-resource settings.

---

### Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems

Authors: Hao Dong, Eleni Chatzi, Olga Fink
Published: 2026-02-09
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.08792v2

The pantograph-catenary interface is essential for ensuring uninterrupted and reliable power delivery in electrified rail systems. However, electrical arcing at this interface poses serious risks, including accelerated wear of contact components, degraded system performance, and potential service disruptions. Detecting arcing events at the pantograph-catenary interface is challenging due to their transient nature, noisy operating environment, data scarcity, and the difficulty of distinguishing arcs from other similar transient phenomena. To address these challenges, we propose a novel multimodal framework that combines high-resolution image data with force measurements to more accurately and robustly detect arcing events. First, we construct two arcing detection datasets comprising synchronized visual and force measurements. One dataset is built from data provided by the Swiss Federal Railways (SBB), and the other is derived from publicly available videos of arcing events in different railway systems and synthetic force data that mimic the characteristics observed in the real dataset. Leveraging these datasets, we propose MultiDeepSAD, an extension of the DeepSAD algorithm for multiple modalities with a new loss formulation. Additionally, we introduce tailored pseudo-anomaly generation techniques specific to each data type, such as synthetic arc-like artifacts in images and simulated force irregularities, to augment training data and improve the discriminative ability of the model. Through extensive experiments and ablation studies, we demonstrate that our framework significantly outperforms baseline approaches, exhibiting enhanced sensitivity to real arcing events even under domain shifts and limited availability of real arcing observations.

---

### On the Meta-Design of Allocation Problems

Authors: Unai Fischer-Abaigar, Emily Aiken, Christoph Kern, Juan Carlos Perdomo
Published: 2026-02-09
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2602.08786v4

There is an extensive literature that studies how to find optimal policies in resource allocation problems, taking the underlying design parameters that define the allocation, such as what data is collected, how many people can be served, and quality of service as fixed constraints. Yet, from a planner's perspective, these design parameters are themselves optimization variables that are just as important in determining overall welfare as selecting the optimal targeting rule for a given set of constraints. This realization motivates a rich set of meta-design questions exploring how planners should make principled decisions about investments in prediction, capacity constraints, and treatment quality, all of which lie upstream of classical policy optimization. Building on initial theoretical work in this space, our paper has three main contributions. First, we formally define the broad meta-design space of resource allocation problems. Second, we develop empirical tools that enable practitioners to reliably navigate it. Third, we demonstrate the framework in two real-world case studies on German employment services and targeted cash transfer programs in Ethiopia.

---

### A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

Authors: Ofek Amran, Tom Gilat, Ron Levie
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08785v2

Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a space of input graphs under which MPNNs are equicontinuous. Such analyses are of two varieties: 1) when the metric space includes graphs of unbounded sizes, the theory is only appropriate for dense graphs, and, 2) when studying sparse graphs, the metric space only includes graphs of uniformly bounded size. In this work, we present a unified approach, defining a compact metric on the space of graphs of all sizes, both sparse and dense, under which MPNNs are equicontinuous. This leads to more powerful universal approximation theorems and generalization bounds than previous works. The theory is based on, and extends, a recent approach to graph limit theory called graphop analysis.

---

### Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure

Authors: Zirui Li, Xuefeng Bai, Kehai Chen, Yizhi Li, Jian Yang, Chenghua Lin, Min Zhang
Published: 2026-02-09
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.08783v3

Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate computations are difficult to evaluate beyond correlation-based probes. In this paper, we view latent chain-of-thought as a manipulable causal process in representation space by modeling latent steps as variables in a structural causal model (SCM) and analyzing their effects through step-wise do-interventions. We study two representative paradigms (i.e., Coconut and CODI) on both mathematical and general reasoning tasks to investigate three key questions: (1) which steps are causally necessary for correctness and when answers become decodable early; (2) how influence propagates across steps and how this structure compares to explicit CoT; and (3) whether intermediate trajectories retain competing answer modes and how output-level commitment differs from representational commitment across steps. We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing, and we identify a persistent gap between early output bias and late representational commitment. These results motivate mode-conditional and stability-aware analyses, together with corresponding training/decoding objectives, as more reliable tools for interpreting and improving latent reasoning systems. Code is available at https://github.com/J1mL1/causal-latent-cot.

---

### Amortising Inference and Meta-Learning Priors in Neural Networks

Authors: Tommy Rochussen, Vincent Fortuin
Published: 2026-02-09
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.08782v1

One of the core facets of Bayesianism is in the updating of prior beliefs in light of new evidence$\text{ -- }$so how can we maintain a Bayesian approach if we have no prior beliefs in the first place? This is one of the central challenges in the field of Bayesian deep learning, where it is not clear how to represent beliefs about a prediction task by prior distributions over model parameters. Bridging the fields of Bayesian deep learning and probabilistic meta-learning, we introduce a way to $\textit{learn}$ a weights prior from a collection of datasets by introducing a way to perform per-dataset amortised variational inference. The model we develop can be viewed as a neural process whose latent variable is the set of weights of a BNN and whose decoder is the neural network parameterised by a sample of the latent variable itself. This unique model allows us to study the behaviour of Bayesian neural networks under well-specified priors, use Bayesian neural networks as flexible generative models, and perform desirable but previously elusive feats in neural processes such as within-task minibatching or meta-learning under extreme data-starvation.

---

### VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars

Authors: Vineet Kumar Rakesh, Ahana Bhattacharjee, Soumya Mazumdar, Tapas Samanta, Hemendra Kumar Pandey, Amitabha Das, Sarbajit Pal
Published: 2026-02-09
Categories: cs.CV, cs.CG
arXiv: https://arxiv.org/abs/2602.08775v1

Talking-head avatars are increasingly adopted in educational technology to deliver content with social presence and improved engagement. However, many recent talking-head generation (THG) methods rely on GPU-centric neural rendering, large training sets, or high-capacity diffusion models, which limits deployment in offline or resource-constrained learning environments. A deterministic and CPU-oriented THG framework is described, termed Symbolic Vedic Computation, that converts speech to a time-aligned phoneme stream, maps phonemes to a compact viseme inventory, and produces smooth viseme trajectories through symbolic coarticulation inspired by Vedic sutra Urdhva Tiryakbhyam. A lightweight 2D renderer performs region-of-interest (ROI) warping and mouth compositing with stabilization to support real-time synthesis on commodity CPUs. Experiments report synchronization accuracy, temporal stability, and identity consistency under CPU-only execution, alongside benchmarking against representative CPU-feasible baselines. Results indicate that acceptable lip-sync quality can be achieved while substantially reducing computational load and latency, supporting practical educational avatars on low-end hardware. GitHub: https://vineetkumarrakesh.github.io/vedicthg

---

### Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization

Authors: Nicolás Villagrán Prieto, Eduardo C. Garrido-Merchán
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08774v1

Bayesian Optimization (BO) is a standard tool for hyperparameter tuning thanks to its sample efficiency on expensive black-box functions. While most BO pipelines begin with uniform random initialization, default hyperparameter values shipped with popular ML libraries such as scikit-learn encode implicit expert knowledge and could serve as informative starting points that accelerate convergence. This hypothesis, despite its intuitive appeal, has remained largely unexamined. We formalize the idea by initializing BO with points drawn from truncated Gaussian distributions centered at library defaults and compare the resulting trajectories against a uniform-random baseline. We conduct an extensive empirical evaluation spanning three BO back-ends (BoTorch, Optuna, Scikit-Optimize), three model families (Random Forests, Support Vector Machines, Multilayer Perceptrons), and five benchmark datasets covering classification and regression tasks. Performance is assessed through convergence speed and final predictive quality, and statistical significance is determined via one-sided binomial tests. Across all conditions, default-informed initialization yields no statistically significant advantage over purely random sampling, with p-values ranging from 0.141 to 0.908. A sensitivity analysis on the prior variance confirms that, while tighter concentration around the defaults improves early evaluations, this transient benefit vanishes as optimization progresses, leaving final performance unchanged. Our results provide no evidence that default hyperparameters encode useful directional information for optimization. We therefore recommend that practitioners treat hyperparameter tuning as an integral part of model development and favor principled, data-driven search strategies over heuristic reliance on library defaults.

---

### FreqLens: Interpretable Frequency Attribution for Time Series Forecasting

Authors: Chi-Sheng Chen, Xinyu Zhang, En-Jui Kuo, Guan-Ying Chen, Qiuzhe Xie, Fan Zhang
Published: 2026-02-09
Categories: cs.LG, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2602.08768v1

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.

---

### Taming Scylla: Understanding the multi-headed agentic daemon of the coding seas

Authors: Micah Villmow
Published: 2026-02-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.08765v1

LLM-based tools are automating more software development tasks at a rapid pace, but there is no rigorous way to evaluate how different architectural choices -- prompts, skills, tools, multi-agent setups -- materially affect both capability and cost. This paper introduces Scylla, an evaluation framework for benchmarking agentic coding tools through structured ablation studies that uses seven testing tiers (T0-T6) progressively adding complexity to isolate what directly influences results and how. The key metric is Cost-of-Pass (CoP): the expected dollar cost to get one correct solution, which directly quantifies the trade-off between complexity and efficiency. The framework is model-agnostic, designed to work with any CLI tool; this paper demonstrates it with Claude Sonnet 4.5, using multiple LLM judges (Opus 4.5, Sonnet 4.5, Haiku 4.5) from the same vendor for evaluation consensus, where judges score results using direct tests, human-designed LLM-evaluated rubrics, and qualitative assessment. The result is a reproducible framework that quantifies trade-offs between agent complexity and actual outcomes, suggesting that architectural complexity does not always improve quality.

---

### Efficient Brain Extraction of MRI Scans with Mild to Moderate Neuropathology

Authors: Hjalti Thrastarson, Lotta M. Ellingsen
Published: 2026-02-09
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.08764v1

Skull stripping magnetic resonance images (MRI) of the human brain is an important process in many image processing techniques, such as automatic segmentation of brain structures. Numerous methods have been developed to perform this task, however, they often fail in the presence of neuropathology and can be inconsistent in defining the boundary of the brain mask. Here, we propose a novel approach to skull strip T1-weighted images in a robust and efficient manner, aiming to consistently segment the outer surface of the brain, including the sulcal cerebrospinal fluid (CSF), while excluding the full extent of the subarachnoid space and meninges. We train a modified version of the U-net on silver-standard ground truth data using a novel loss function based on the signed-distance transform (SDT). We validate our model both qualitatively and quantitatively using held-out data from the training dataset, as well as an independent external dataset. The brain masks used for evaluation partially or fully include the subarachnoid space, which may introduce bias into the comparison; nonetheless, our model demonstrates strong performance on the held-out test data, achieving a consistent mean Dice similarity coefficient (DSC) of 0.964$\pm$0.006 and an average symmetric surface distance (ASSD) of 1.4mm$\pm$0.2mm. Performance on the external dataset is comparable, with a DSC of 0.958$\pm$0.006 and an ASSD of 1.7$\pm$0.2mm. Our method achieves performance comparable to or better than existing state-of-the-art methods for brain extraction, particularly in its highly consistent preservation of the brain's outer surface. The method is publicly available on GitHub.

---

### HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training

Authors: Wen Xu, Zhetao Li, Yong Xiao, Pengpeng Qiao, Mianxiong Dong, Kaoru Ota
Published: 2026-02-09
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2602.08762v1

Graph neural networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks by effectively modeling high-order interactions between nodes. However, training GNNs without protection may leak sensitive personal information in graph data, including links and node features. Local differential privacy (LDP) is an advanced technique for protecting data privacy in decentralized networks. Unfortunately, existing local differentially private GNNs either only preserve link privacy or suffer significant utility loss in the process of preserving link and node feature privacy. In this paper, we propose an effective LDP framework, called HoGS, which trains GNNs with link and feature protection by generating a synthetic graph. Concretely, HoGS first collects the link and feature information of the graph under LDP, and then utilizes the phenomenon of homophily in graph data to reconstruct the graph structure and node features separately, thereby effectively mitigating the negative impact of LDP on the downstream GNN training. We theoretically analyze the privacy guarantee of HoGS and conduct experiments using the generated synthetic graph as input to various state-of-the-art GNN architectures. Experimental results on three real-world datasets show that HoGS significantly outperforms baseline methods in the accuracy of training GNNs.

---

### Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations

Authors: Duc-Anh Nguyen, Nhien-An Le-Khac
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08755v3

Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views, and heterogeneous modalities. Focusing on the context of human activity recognition, we propose AliAd, a model that combines multiview contrastive learning with a mixture-of-experts module to support arbitrary view availability during both training and inference. Instead of trying to reconstruct missing views, an adjusted center contrastive loss is used for self-supervised representation learning and view alignment, mitigating the impact of missing views on multiview fusion. This loss formulation allows for the integration of view weights to account for view quality. Additionally, it reduces computational complexity from $O(V^2)$ to $O(V)$, where $V$ is the number of views. To address residual discrepancies not captured by contrastive learning, we employ a mixture-of-experts module with a specialized load balancing strategy, tasked with adapting to arbitrary view combinations. We highlight the geometric relationship among components in our model and how they combine well in the latent space. AliAd is validated on four datasets encompassing inertial and human pose modalities, with the number of views ranging from three to nine, demonstrating its performance and flexibility.

---

### Belief Offloading in Human-AI Interaction

Authors: Rose E. Guingrich, Dvija Mehta, Umang Bhatt
Published: 2026-02-09
Categories: cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2602.08754v1

What happens when people's beliefs are derived from information provided by an LLM? People's use of LLM chatbots as thought partners can contribute to cognitive offloading, which can have adverse effects on cognitive skills in cases of over-reliance. This paper defines and investigates a particular kind of cognitive offloading in human-AI interaction, "belief offloading," in which people's processes of forming and upholding beliefs are offloaded onto an AI system with downstream consequences on their behavior and the nature of their system of beliefs. Drawing on philosophy, psychology, and computer science research, we clarify the boundary conditions under which belief offloading occurs and provide a descriptive taxonomy of belief offloading and its normative implications. We close with directions for future work to assess the potential for and consequences of belief offloading in human-AI interaction.

---

### MVAnimate: Enhancing Character Animation with Multi-View Optimization

Authors: Tianyu Sun, Zhoujie Fu, Bang Zhang, Guosheng Lin
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08753v1

The demand for realistic and versatile character animation has surged, driven by its wide-ranging applications in various domains. However, the animation generation algorithms modeling human pose with 2D or 3D structures all face various problems, including low-quality output content and training data deficiency, preventing the related algorithms from generating high-quality animation videos. Therefore, we introduce MVAnimate, a novel framework that synthesizes both 2D and 3D information of dynamic figures based on multi-view prior information, to enhance the generated video quality. Our approach leverages multi-view prior information to produce temporally consistent and spatially coherent animation outputs, demonstrating improvements over existing animation methods. Our MVAnimate also optimizes the multi-view videos of the target character, enhancing the video quality from different views. Experimental results on diverse datasets highlight the robustness of our method in handling various motion patterns and appearances.

---

### Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms

Authors: Nobuyuki Ota
Published: 2026-02-09
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2602.08751v4

Motivation: Interpretability is not optional in biology: understanding gene regulation requires models whose learned structure can be directly interrogated, not merely accurate predictors whose internals resist mapping onto regulatory relationships. We ask whether an architecture mirroring the central dogma yields attention and gradient maps that recover known regulatory elements and networks in inspectable form. Results: Central Dogma Transformer II (CDT-II) mirrors the central dogma in its architecture -- DNA self-attention, RNA self-attention, and DNA-to-RNA cross-attention -- requiring only genomic embeddings and raw per-cell expression. On K562 CRISPR interference (CRISPRi) data with five genes held out entirely, CDT-II predicts perturbation effects (per-gene mean r = 0.84), recovers the GFI1B regulatory network (6.6-fold enrichment, P = 3.5 x 10^-17), and concentrates cross-attention on ENCODE regulatory elements including CTCF sites (mean 7.67x across 28 target genes, P < 0.001). Gradient attribution predicts consequences of perturbing therapeutic targets (mean r = 0.82). For TFRC, target of the anti-TfR1 antibody PPMX-T003, it identifies erythrocyte-structure, iron-dependent DNA-synthesis and oxidative-stress genes, matching anemia and ferroptosis reported clinically and preclinically -- without clinical data as input. CDT-II acts as an AI microscope, surfacing clinically relevant regulatory structure from perturbation experiments alone. Availability: Source code is available at https://github.com/nobusama/CDT2. Pre-computed embeddings, training data, and model weights are available at https://huggingface.co/datasets/nobusama17/CDT2-data.

---

### Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms

Authors: Nobuyuki Ota
Published: 2026-02-09
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2602.08751v3

Current biological AI models lack interpretability -- their internal representations do not correspond to biological relationships that researchers can examine. Understanding gene regulation requires models whose learned structure can be directly interrogated to generate experimentally testable hypotheses. CDT-II mirrors the central dogma in its architecture -- DNA self-attention, RNA self-attention, and cross-attention for transcriptional control -- requiring only genomic embeddings and raw per-cell expression. Applied to K562 CRISPRi data with five genes held out entirely, CDT-II predicts perturbation effects (per-gene mean r = 0.84), recovers the GFI1B regulatory network (6.6-fold enrichment, P = 3.5 x 10^{-17}), and shows that cross-attention focuses on ENCODE regulatory elements including CTCF sites (mean 7.67x across 28 targets, P < 0.001). Gradient-based attribution accurately predicts downstream consequences of perturbing therapeutic targets (mean r = 0.82). Applied to TFRC, the target of the anti-TfR1 antibody PPMX-T003, gradient analysis identifies genes involved in erythrocyte structure, iron-dependent DNA synthesis, and oxidative stress -- pathways that align with anemia and reticulocyte decrease reported in Phase 1 trials and ferroptosis demonstrated in preclinical studies, without any clinical data as input, establishing CDT-II as an AI microscope that reveals clinically relevant regulatory structure from perturbation experiments alone.

---

### Shifting the Breaking Point of Flow Matching for Multi-Instance Editing

Authors: Carmine Zaccagnino, Fabio Quattrini, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, Silvia Cascianelli
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08749v4

Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors predominantly support global or single-instruction edits and struggle with multi-instance scenarios, where multiple parts of a reference input must be edited independently without semantic interference. We identify this limitation as a consequence of globally conditioned velocity fields and joint attention mechanisms, which entangle concurrent edits. To address this issue, we introduce Instance-Disentangled Attention, a mechanism that partitions joint attention operations, enforcing binding between instance-specific textual instructions and spatial regions during velocity field estimation. We evaluate our approach on both natural image editing and a newly introduced benchmark of text-dense infographics with region-level editing instructions. Experimental results demonstrate that our approach promotes edit disentanglement and locality while preserving global output coherence, enabling single-pass, instance-level editing.

---

### On the Expressive Power of GNNs for Boolean Satisfiability

Authors: Saku Peltonen, Roger Wattenhofer
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08745v1

Machine learning approaches to solving Boolean Satisfiability (SAT) aim to replace handcrafted heuristics with learning-based models. Graph Neural Networks have emerged as the main architecture for SAT solving, due to the natural graph representation of Boolean formulas. We analyze the expressive power of GNNs for SAT solving through the lens of the Weisfeiler-Leman (WL) test. As our main result, we prove that the full WL hierarchy cannot, in general, distinguish between satisfiable and unsatisfiable instances. We show that indistinguishability under higher-order WL carries over to practical limitations for WL-bounded solvers that set variables sequentially. We further study the expressivity required for several important families of SAT instances, including regular, random and planar instances. To quantify expressivity needs in practice, we conduct experiments on random instances from the G4SAT benchmark and industrial instances from the International SAT Competition. Our results suggest that while random instances are largely distinguishable, industrial instances often require more expressivity to predict a satisfying assignment.

---

### Welfarist Formulations for Diverse Similarity Search

Authors: Siddharth Barman, Nirjhar Das, Shivam Gupta, Kirankumar Shiragur
Published: 2026-02-09
Categories: cs.DS, cs.CG, cs.GT, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.08742v1

Nearest Neighbor Search (NNS) is a fundamental problem in data structures with wide-ranging applications, such as web search, recommendation systems, and, more recently, retrieval-augmented generations (RAG). In such recent applications, in addition to the relevance (similarity) of the returned neighbors, diversity among the neighbors is a central requirement. In this paper, we develop principled welfare-based formulations in NNS for realizing diversity across attributes. Our formulations are based on welfare functions -- from mathematical economics -- that satisfy central diversity (fairness) and relevance (economic efficiency) axioms. With a particular focus on Nash social welfare, we note that our welfare-based formulations provide objective functions that adaptively balance relevance and diversity in a query-dependent manner. Notably, such a balance was not present in the prior constraint-based approach, which forced a fixed level of diversity and optimized for relevance. In addition, our formulation provides a parametric way to control the trade-off between relevance and diversity, providing practitioners with flexibility to tailor search results to task-specific requirements. We develop efficient nearest neighbor algorithms with provable guarantees for the welfare-based objectives. Notably, our algorithm can be applied on top of any standard ANN method (i.e., use standard ANN method as a subroutine) to efficiently find neighbors that approximately maximize our welfare-based objectives. Experimental results demonstrate that our approach is practical and substantially improves diversity while maintaining high relevance of the retrieved neighbors.

---

### Map of Encoders -- Mapping Sentence Encoders using Quantum Relative Entropy

Authors: Gaifan Zhang, Danushka Bollegala
Published: 2026-02-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.08740v1

We propose a method to compare and visualise sentence encoders at scale by creating a map of encoders where each sentence encoder is represented in relation to the other sentence encoders. Specifically, we first represent a sentence encoder using an embedding matrix of a sentence set, where each row corresponds to the embedding of a sentence. Next, we compute the Pairwise Inner Product (PIP) matrix for a sentence encoder using its embedding matrix. Finally, we create a feature vector for each sentence encoder reflecting its Quantum Relative Entropy (QRE) with respect to a unit base encoder. We construct a map of encoders covering 1101 publicly available sentence encoders, providing a new perspective of the landscape of the pre-trained sentence encoders. Our map accurately reflects various relationships between encoders, where encoders with similar attributes are proximally located on the map. Moreover, our encoder feature vectors can be used to accurately infer downstream task performance of the encoders, such as in retrieval and clustering tasks, demonstrating the faithfulness of our map.

---