# Research Papers — 2026-02 · bundle page 180 of 210

> Full-text markdown of papers #8951–9000 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/180
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/179.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/181.md)

### Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure

Authors: Shuhui Qu
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03975v1

Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reasoning systems, a large fraction of verifier calls are spent on redundant or unpromising intermediate hypotheses. We study reasoning under a \emph{verification-cost-limited} setting and ask how verification effort should be allocated across intermediate states. We propose a state-level selective verification framework that combines (i) deterministic feasibility gating over a structured move interface, (ii) pre-verification ranking using a hybrid of learned state-distance and residual scoring, and (iii) adaptive allocation of verifier calls based on local uncertainty. Unlike solution-level best-of-$N$ or uniform intermediate verification, our method distributes verification where it is most informative. On the \textsc{MATH} benchmark, our approach achieves higher accuracy than best-of-$N$, majority voting, and beam search while using 44\% fewer verifier calls.

---

### Active Epistemic Control for Query-Efficient Verified Planning

Authors: Shuhui Qu
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03974v1

Planning in interactive environments is challenging under partial observability: task-critical preconditions (e.g., object locations or container states) may be unknown at decision time, yet grounding them through interaction is costly. Learned world models can cheaply predict missing facts, but prediction errors can silently induce infeasible commitments. We present \textbf{Active Epistemic Control (AEC)}, an epistemic-categorical planning layer that integrates model-based belief management with categorical feasibility checks. AEC maintains a strict separation between a \emph{grounded fact store} used for commitment and a \emph{belief store} used only for pruning candidate plans. At each step, it either queries the environment to ground an unresolved predicate when uncertainty is high or predictions are ambiguous, or simulates the predicate to filter hypotheses when confidence is sufficient. Final commitment is gated by grounded precondition coverage and an SQ-BCP pullback-style compatibility check, so simulated beliefs affect efficiency but cannot directly certify feasibility. Experiments on ALFWorld and ScienceWorld show that AEC achieves competitive success with fewer replanning rounds than strong LLM-agent baselines.

---

### VLS: Steering Pretrained Robot Policies via Vision-Language Models

Authors: Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu, Jiafei Duan, Ranjay Krishna
Published: 2026-02-03
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.03973v1

Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a limitation of imitation learning under train-test shifts, where action generation is tightly coupled to training-specific spatial configurations and task specifications. Retraining or fine-tuning to address these failures is costly and conceptually misaligned, as the required behaviors already exist but cannot be selectively adapted at test time. We propose Vision-Language Steering (VLS), a training-free framework for inference-time adaptation of frozen generative robot policies. VLS treats adaptation as an inference-time control problem, steering the sampling process of a pretrained diffusion or flow-matching policy in response to out-of-distribution observation-language inputs without modifying policy parameters. By leveraging vision-language models to synthesize trajectory-differentiable reward functions, VLS guides denoising toward action trajectories that satisfy test-time spatial and task requirements. Across simulation and real-world evaluations, VLS consistently outperforms prior steering methods, achieving a 31% improvement on CALVIN and a 13% gain on LIBERO-PRO. Real-world deployment on a Franka robot further demonstrates robust inference-time adaptation under test-time spatial and semantic shifts. Project page: https://vision-language-steering.github.io/webpage/

---

### Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Authors: Kapilan Balagopalan, Yinan Li, Yao Zhao, Tuan Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun
Published: 2026-02-03
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03972v3

The best-arm identification (BAI) problem is one of the most fundamental problems in interactive machine learning, which has two flavors: the fixed-budget setting (FB) and the fixed-confidence setting (FC). For $K$-armed bandits with a unique best arm, the optimal sample complexities for both settings have been settled down, and they match up to logarithmic factors. This prompts an interesting research question about the generic, potentially structured BAI problems: is FB harder than FC or the other way around? In this paper, we show that FB is no harder than FC up to logarithmic factors. We do this constructively: we propose a novel algorithm called FC2FB (fixed confidence to fixed budget), which is a meta algorithm that takes in an FC algorithm $\mathcal{A}$ and turn it into an FB algorithm. We prove that FC2FB enjoys a sample complexity that matches, up to logarithmic factors, that of the sample complexity of $\mathcal{A}$. This means that the optimal FC sample complexity is an upper bound of the optimal FB sample complexity up to logarithmic factors. Our result not only reveals a fundamental relationship between FB and FC, but also has a significant implication: FC2FB combined with existing state-of-the-art FC algorithms leads to improved sample complexity for a number of FB problems.

---

### Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits

Authors: Anastasis Kratsios, Giulia Livieri, A. Martina Neuman
Published: 2026-02-03
Categories: stat.ML, cs.LG, cs.NE, math.MG, math.ST
arXiv: https://arxiv.org/abs/2602.03970v3

We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by a looped Boolean circuit whose graph is a perfect $ν$-ary tree ($ν\ge 2$), with outputs recursively fed back as inputs across computation rounds. A probe observes a sampled subset of internal nodes and seeks to infer the latent operation at each node, represented as a probability distribution over a finite set of admissible Boolean gates. This partial observability induces a transductive generalization problem on a structured computation graph. We show that when the probe is parameterized by a graph convolutional network and queries $N$ nodes, the worst-case generalization error decays at the optimal rate $\mathcal{O}(\sqrt{\log(2/δ)}/\sqrt{N})$ with probability at least $1-δ$. Our analysis combines metric embedding techniques with tools from optimal transport. A key insight is that this rate is achievable independently of the size of the computation graph, enabled by a low-distortion one-dimensional snowflake embedding of the induced graph metric. These results highlight a geometric mechanism underlying statistical efficiency in probing structured, iterative computations.

---

### Structural shifts in institutional participation and collaboration within the AI arXiv preprint research ecosystem

Authors: Shama Maganur, Mayank Kejriwal
Published: 2026-02-03
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2602.03969v2

The emergence of large language models (LLMs) represents a significant technological shift within the scientific ecosystem, particularly within the field of artificial intelligence (AI). This paper examines structural changes in the AI research landscape using a dataset of arXiv preprints (cs.AI) from 2021 through 2025. Given the rapid pace of AI development, the preprint ecosystem has become a critical barometer for real-time scientific shifts, often preceding formal peer-reviewed publication by months or years. By employing a multi-stage data collection and enrichment pipeline in conjunction with LLM-based institution classification, we analyze the evolution of publication volumes, author team sizes, and academic--industry collaboration patterns. Our results reveal an unprecedented surge in publication output following the introduction of ChatGPT, with academic institutions continuing to provide the largest volume of research. However, we observe that academic--industry collaboration is still suppressed, as measured by a Normalized Collaboration Index (NCI) that remains significantly below the random-mixing baseline across all major subfields. These findings highlight a continuing institutional divide and suggest that the capital-intensive nature of generative AI research may be reshaping the boundaries of scientific collaboration.

---

### Non-linear PCA via Evolution Strategies: a Novel Objective Function

Authors: Thomas Uriot, Elise Chung
Published: 2026-02-03
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2602.03967v1

Principal Component Analysis (PCA) is a powerful and popular dimensionality reduction technique. However, due to its linear nature, it often fails to capture the complex underlying structure of real-world data. While Kernel PCA (kPCA) addresses non-linearity, it sacrifices interpretability and struggles with hyperparameter selection. In this paper, we propose a robust non-linear PCA framework that unifies the interpretability of PCA with the flexibility of neural networks. Our method parametrizes variable transformations via neural networks, optimized using Evolution Strategies (ES) to handle the non-differentiability of eigendecomposition. We introduce a novel, granular objective function that maximizes the individual variance contribution of each variable providing a stronger learning signal than global variance maximization. This approach natively handles categorical and ordinal variables without the dimensional explosion associated with one-hot encoding. We demonstrate that our method significantly outperforms both linear PCA and kPCA in explained variance across synthetic and real-world datasets. At the same time, it preserves PCA's interpretability, enabling visualization and analysis of feature contributions using standard tools such as biplots. The code can be found on GitHub.

---

### Automatic Classification of Pedagogical Materials against CS Curriculum Guidelines

Authors: Erik Saule, Kalpathi Subramanian, Razvan Bunescu
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.03962v1

Professional societies often publish curriculum guidelines to help programs align their content to international standards. In Computer Science, the primary standard is published by ACM and IEEE and provide detailed guidelines for what should be and could be included in a Computer Science program. While very helpful, it remains difficult for program administrators to assess how much of the guidelines is being covered by a CS program. This is in particular due to the extensiveness of the guidelines, containing thousands of individual items. As such, it is time consuming and cognitively demanding to audit every course to confidently mark everything that is actually being covered. Our preliminary work indicated that it takes about a day of work per course. In this work, we propose using Natural Language Processing techniques to accelerate the process. We explore two kinds of techniques, the first relying on traditional tools for parsing, tagging, and embeddings, while the second leverages the power of Large Language Models. We evaluate the application of these techniques to classify a corpus of pedagogical materials and show that we can meaningfully classify documents automatically.

---

### Temporal Validation Changes the Apparent Public-Health Utility of Under-Five Mortality Prediction in Bangladesh: A Four-Round DHS Machine-Learning Study

Authors: Md Muhtasim Munif Fahim, M. Monimul Huq, M. Sabiruzzaman, Md Rezaul Karim
Published: 2026-02-03
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2602.03957v2

Background: Under-five mortality in Bangladesh remains uneven despite national progress. DHS-based prediction models may guide targeted follow-up, but only if validation reflects future use. We examined how validation design changes apparent prediction performance. Methods: Four BDHS rounds (2011-2022; 33,962 children; 1,290 deaths) were analysed with a 26-feature pipeline and three model classes under four validation regimes, including cross-survey temporal validation (train 2011+2014, calibrate 2017, test 2022). A 32-unit ELU multilayer perceptron was selected via genetic-algorithm neural architecture search. AUROC used 2,000 bootstrap resamples; screening utility used sensitivity, PPV, and number needed to screen (NNS) at fixed capacity. Results: Validation regime altered public-health interpretation more than model class. NAS MLP AUROC ranged from 0.669 (2022-only random) to 0.775 (pooled random), with temporal AUROC 0.730. At the top-10% temporal threshold, NAS identified 152/355 deaths in 2022 (sensitivity 42.8%, PPV 13.2%, NNS 7.6). NNS across designs ranged from 5.6 to 11.0. Conclusions: Validation-regime choice changed screening workload and apparent policy value more than architecture. Temporal validation supports defensible estimates of follow-up and referral demand; DHS child-mortality studies should report sensitivity, PPV, and NNS before programmatic use.

---

### AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

Authors: Yinyi Luo, Yiqiao Jin, Weichen Yu, Mengqi Zhang, Srijan Kumar, Xiaoxiao Li, Weijie Xu, Xin Chen, Jindong Wang
Published: 2026-02-03
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.03955v3

While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a novel framework to distill multi-agent dynamics into the weights of a single model, effectively transforming explicit test-time interactions into implicit model capabilities. This equips a single agent with the intelligence of multi-agent systems while remaining computationally efficient. Specifically, we investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios: reasoning-enhanced fine-tuning; trajectory-based augmentation; and process-aware distillation. By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents. They further demonstrate enhanced robustness and generalization across diverse reasoning tasks. We hope this work can shed light on future research on efficient and robust multi-agent development. Our code is at https://github.com/AIFrontierLab/AgentArk.

---

### Learning Multi-type heterogeneous interacting particle systems

Authors: Quanjun Lang, Xiong Wang, Fei Lu, Mauro Maggioni
Published: 2026-02-03
Categories: stat.ML, cs.LG, stat.CO, stat.ME
arXiv: https://arxiv.org/abs/2602.03954v1

We propose a framework for the joint inference of network topology, multi-type interaction kernels, and latent type assignments in heterogeneous interacting particle systems from multi-trajectory data. This learning task is a challenging non-convex mixed-integer optimization problem, which we address through a novel three-stage approach. First, we leverage shared structure across agent interactions to recover a low-rank embedding of the system parameters via matrix sensing. Second, we identify discrete interaction types by clustering within the learned embedding. Third, we recover the network weight matrix and kernel coefficients through matrix factorization and a post-processing refinement. We provide theoretical guarantees with estimation error bounds under a Restricted Isometry Property (RIP) assumption and establish conditions for the exact recovery of interaction types based on cluster separability. Numerical experiments on synthetic datasets, including heterogeneous predator-prey systems, demonstrate that our method yields an accurate reconstruction of the underlying dynamics and is robust to noise.

---

### Representation Geometry as a Diagnostic for Out-of-Distribution Robustness

Authors: Ali Zia, Farid Hazratian
Published: 2026-02-03
Categories: cs.LG, cs.CV, math.DG, math.GN
arXiv: https://arxiv.org/abs/2602.03951v2

Robust generalization under distribution shift remains difficult to monitor and optimize in the absence of target-domain labels, as models with similar in-distribution accuracy can exhibit markedly different out-of-distribution (OOD) performance. While prior work has focused on training-time regularization and low-order representation statistics, little is known about whether the geometric structure of learned embeddings provides reliable post-hoc signals of robustness. We propose a geometry-based diagnostic framework that constructs class-conditional mutual k-nearest-neighbor graphs from in-distribution embeddings and extracts two complementary invariants: a global spectral complexity proxy based on the reduced log-determinant of the normalized Laplacian, and a local smoothness measure based on Ollivier--Ricci curvature. Across multiple architectures, training regimes, and corruption benchmarks, we find that lower spectral complexity and higher mean curvature consistently predict stronger OOD accuracy across checkpoints. Controlled perturbations and topological analyses further show that these signals reflect meaningful representation structure rather than superficial embedding statistics. Our results demonstrate that representation geometry enables interpretable, label-free robustness diagnosis and supports reliable unsupervised checkpoint selection under distribution shift.

---

### Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation

Authors: Aditya Basarkar, Benyamin Tabarsi, Tiffany Barnes, Dongkuan Xu
Published: 2026-02-03
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.03950v2

Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential. Although recent advances in multi-agent LLM-based systems have enhanced their mathematical reasoning capabilities, they still lack a reliably revisable representation of the reasoning process. Existing agents either operate in rigid sequential pipelines that cannot correct earlier steps or rely on heuristic self-evaluation that can fail to identify and fix errors. In addition, programmatic context can distract language models and degrade accuracy. To address these gaps, we introduce Iteratively Improved Program Construction (IIPC), a reasoning method that iteratively refines programmatic reasoning chains and combines execution feedback with the native Chain-of-thought abilities of the base LLM to maintain high-level contextual focus. IIPC surpasses competing approaches in the majority of reasoning benchmarks on multiple base LLMs. All code and implementations are released as open source.

---

### Semantic Rate Distortion and Posterior Design: Compute Constraints, Multimodality, and Strategic Inference

Authors: Emrah Akyol
Published: 2026-02-03
Categories: cs.IT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03949v1

We study strategic Gaussian semantic compression under rate and compute constraints, where an encoder and decoder optimize distinct quadratic objectives. A latent Gaussian state generates a task dependent semantic variable, and the decoder best responds via MMSE estimation, reducing the encoder's problem to posterior covariance design under an information rate constraint. We characterize the strategic rate distortion function in direct, remote, and full information regimes, derive semantic waterfilling and rate constrained Gaussian persuasion solutions, and establish Gaussian optimality under misaligned objectives. We further show that architectural compute limits act as implicit rate constraints, yielding exponential improvements in semantic accuracy with model depth and inference time compute, while multimodal observation eliminates the geometric mean penalty inherent to remote encoding. These results provide information theoretic foundations for data and energy efficient AI and offer a principled interpretation of modern multimodal language models as posterior design mechanisms under resource constraints.

---

### Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks

Authors: Bibhabasu Mandal, Sagnik Nandy
Published: 2026-02-03
Categories: stat.ML, cs.CR, cs.LG, cs.SI, math.ST
arXiv: https://arxiv.org/abs/2602.03948v1

In sensitive applications involving relational datasets, protecting information about individual links from adversarial queries is of paramount importance. In many such settings, the available data are summarized solely through the degrees of the nodes in the network. We adopt the $β$ model, which is the prototypical statistical model adopted for this form of aggregated relational information, and study the problem of minimax-optimal parameter estimation under both local and central differential privacy constraints. We establish finite sample minimax lower bounds that characterize the precise dependence of the estimation risk on the network size and the privacy parameters, and we propose simple estimators that achieve these bounds up to constants and logarithmic factors under both local and central differential privacy frameworks. Our results provide the first comprehensive finite sample characterization of privacy utility trade offs for parameter estimation in $β$ models, addressing the classical graph case and extending the analysis to higher order hypergraph models. We further demonstrate the effectiveness of our methods through experiments on synthetic data and a real world communication network.

---

### Grables: Tabular Learning Beyond Independent Rows

Authors: Tamara Cucumides, Floris Geerts
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03945v1

Tabular learning is still dominated by row-wise predictors that score each row independently, which fits i.i.d. benchmarks but fails on transactional, temporal, and relational tables where labels depend on other rows. We show that row-wise prediction rules out natural targets driven by global counts, overlaps, and relational patterns. To make "using structure" precise across architectures, we introduce grables: a modular interface that separates how a table is lifted to a graph (constructor) from how predictions are computed on that graph (node predictor), pinpointing where expressive power comes from. Experiments on synthetic tasks, transaction data, and a RelBench clinical-trials dataset confirm the predicted separations: message passing captures inter-row dependencies that row-local models miss, and hybrid approaches that explicitly extract inter-row structure and feed it to strong tabular learners yield consistent gains.

---

### Linguistic Blind Spots in Clinical Decision Extraction

Authors: Mohamed Elgaar, Hadi Amiri
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.03942v1

Extracting medical decisions from clinical notes is a key step for clinical decision support and patient-facing care summaries. We study how the linguistic characteristics of clinical decisions vary across decision categories and whether these differences explain extraction failures. Using MedDec discharge summaries annotated with decision categories from the Decision Identification and Classification Taxonomy for Use in Medicine (DICTUM), we compute seven linguistic indices for each decision span and analyze span-level extraction recall of a standard transformer model. We find clear category-specific signatures: drug-related and problem-defining decisions are entity-dense and telegraphic, whereas advice and precaution decisions contain more narrative, with higher stopword and pronoun proportions and more frequent hedging and negation cues. On the validation split, exact-match recall is 48%, with large gaps across linguistic strata: recall drops from 58% to 24% from the lowest to highest stopword-proportion bins, and spans containing hedging or negation cues are less likely to be recovered. Under a relaxed overlap-based match criterion, recall increases to 71%, indicating that many errors are span boundary disagreements rather than complete misses. Overall, narrative-style spans--common in advice and precaution decisions--are a consistent blind spot under exact matching, suggesting that downstream systems should incorporate boundary-tolerant evaluation and extraction strategies for clinical decisions.

---

### Autonomous AI Agents for Real-Time Affordable Housing Site Selection: Multi-Objective Reinforcement Learning Under Regulatory Constraints

Authors: Olaf Yunus Laitinen Imanov, Duygu Erisken, Derya Umut Kulali, Taner Yilmaz, Rana Irem Turhan
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03940v1

Affordable housing shortages affect billions, while land scarcity and regulations make site selection slow. We present AURA (Autonomous Urban Resource Allocator), a hierarchical multi-agent reinforcement learning system for real-time affordable housing site selection under hard regulatory constraints (QCT, DDA, LIHTC). We model the task as a constrained multi-objective Markov decision process optimizing accessibility, environmental impact, construction cost, and social equity while enforcing feasibility. AURA uses a regulatory-aware state encoding 127 federal and local constraints, Pareto-constrained policy gradients with feasibility guarantees, and reward decomposition separating immediate costs from long-term social outcomes. On datasets from 8 U.S. metros (47,392 candidate parcels), AURA attains 94.3% regulatory compliance and improves Pareto hypervolume by 37.2% over strong baselines. In a New York City 2026 case study, it reduces selection time from 18 months to 72 hours and identifies 23% more viable sites; chosen sites have 31% better transit access and 19% lower environmental impact than expert picks.

---

### C-IDS: Solving Contextual POMDP via Information-Directed Objective

Authors: Chongyang Shi, Michael Dorothy, Jie Fu
Published: 2026-02-03
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2602.03939v1

We study the policy synthesis problem in contextual partially observable Markov decision processes (CPOMDPs), where the environment is governed by an unknown latent context that induces distinct POMDP dynamics. Our goal is to design a policy that simultaneously maximizes cumulative return and actively reduces uncertainty about the underlying context. We introduce an information-directed objective that augments reward maximization with mutual information between the latent context and the agent's observations. We develop the C-IDS algorithm to synthesize policies that maximize the information-directed objective. We show that the objective can be interpreted as a Lagrangian relaxation of the linear information ratio and prove that the temperature parameter is an upper bound on the information ratio. Based on this characterization, we establish a sublinear Bayesian regret bound over K episodes. We evaluate our approach on a continuous Light-Dark environment and show that it consistently outperforms standard POMDP solvers that treat the unknown context as a latent state variable, achieving faster context identification and higher returns.

---

### First-Principles AI finds crystallization of fractional quantum Hall liquids

Authors: Ahmed Abouelkomsan, Liang Fu
Published: 2026-02-03
Categories: cond-mat.mes-hall, cond-mat.str-el, cs.AI
arXiv: https://arxiv.org/abs/2602.03927v2

When does a fractional quantum Hall (FQH) liquid crystallize? Addressing this question requires a framework that treats fractionalization and crystallization on equal footing, especially in strong Landau-level mixing regime. Here, we introduce MagNet, a self-attention neural-network variational wavefunction designed for quantum systems in magnetic fields on the torus geometry. We show that MagNet provides a unifying and expressive ansatz capable of describing both FQH states and electron crystals within the same architecture. Trained solely by energy minimization of the microscopic Hamiltonian, MagNet discovers topological liquid and electron crystal ground states across a broad range of Landau-level mixing. Our results highlight the power of first-principles AI for solving strongly interacting many-body problems and finding competing phases without external training data or physics pre-knowledge.

---

### First-Principles AI finds crystallization of fractional quantum Hall liquids

Authors: Ahmed Abouelkomsan, Liang Fu
Published: 2026-02-03
Categories: cond-mat.mes-hall, cond-mat.str-el, cs.AI
arXiv: https://arxiv.org/abs/2602.03927v1

When does a fractional quantum Hall (FQH) liquid crystallize? Addressing this question requires a framework that treats fractionalization and crystallization on equal footing, especially in strong Landau-level mixing regime. Here, we introduce MagNet, a self-attention neural-network variational wavefunction designed for quantum systems in magnetic fields on the torus geometry. We show that MagNet provides a unifying and expressive ansatz capable of describing both FQH states and electron crystals within the same architecture. Trained solely by energy minimization of the microscopic Hamiltonian, MagNet discovers topological liquid and electron crystal ground states across a broad range of Landau-level mixing. Our results highlight the power of first-principles AI for solving strongly interacting many-body problems and finding competing phases without external training data or physics pre-knowledge.

---

### WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling

Authors: Michael Aich, Andreas Fürst, Florian Sestak, Carlos Ruiz-Gonzalez, Niklas Boers, Johannes Brandstetter
Published: 2026-02-03
Categories: cs.LG, cs.AI, physics.ao-ph
arXiv: https://arxiv.org/abs/2602.03924v2

Deep learning has revolutionized weather forecasting, but many challenges remain, including climate modeling. Moreover, the current landscape remains fragmented: highly specialized models are typically trained individually for distinct tasks. To unify this landscape, we introduce WIND, a single pre-trained foundation model capable of replacing specialized baselines across a vast array of tasks. Crucially, in contrast to previous atmospheric foundation models, we achieve this without any task-specific fine-tuning. To learn a robust, task-agnostic prior of the atmosphere, we pre-train WIND with a self-supervised video reconstruction objective, utilizing an unconditional video diffusion model to iteratively reconstruct atmospheric dynamics from a noisy state. At inference, we frame diverse domain-specific problems strictly as inverse problems and solve them via posterior sampling. This unified approach allows us to tackle highly relevant weather and climate problems, including probabilistic forecasting, spatial and temporal downscaling, reconstruction of spatial fields from sparse observations and enforcing global dry air mass conservation. We further demonstrate how WIND can be applied to explore extreme weather events under prescribed out-of-distribution thermodynamic perturbations. By combining generative video modeling with inverse problem solving, WIND offers a computationally efficient alternative for AI-based atmospheric modeling.

---

### Online Vector Quantized Attention

Authors: Nick Alonso, Tomas Figliolia, Beren Millidge
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03922v3

Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context tasks but has expensive quadratic compute and linear memory costs, while linear attention and SSMs use only linear compute and constant memory but struggle with long context processing. In this paper, we develop a sequence mixing layer that aims to find a better compromise between memory-compute costs and long-context processing, which we call online vector-quantized (OVQ) attention. OVQ-attention requires linear compute costs and constant memory, but, unlike linear attention and SSMs, it uses a sparse memory update that allows it to greatly increase the size of its memory state and, consequently, memory capacity. We develop a theoretical basis for OVQ-attention based on Gaussian mixture regression, and we test it on a variety of synthetic long context tasks and on long context language modeling. OVQ-attention shows significant improvements over linear attention baselines and the original VQ-attention, on which OVQ-attention was inspired. It demonstrates competitive, and sometimes identical, performance to strong self-attention baselines up 64k sequence length, despite using a small fraction of the memory of full self-attention.

---

### SpecMD: A Comprehensive Study On Speculative Expert Prefetching

Authors: Duc Hoang, Ajay Jaiswal, Mohammad Samragh, Minsik Cho
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03921v1

Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model's parameters is used during each inference. However, to translate this sparsity into practical performance, an expert caching mechanism is required. Previous works have proposed hardware-centric caching policies, but how these various caching policies interact with each other and different hardware specification remains poorly understood. To address this gap, we develop \textbf{SpecMD}, a standardized framework for benchmarking ad-hoc cache policies on various hardware configurations. Using SpecMD, we perform an exhaustive benchmarking of several MoE caching strategies, reproducing and extending prior approaches in controlled settings with realistic constraints. Our experiments reveal that MoE expert access is not consistent with temporal locality assumptions (e.g LRU, LFU). Motivated by this observation, we propose \textbf{Least-Stale}, a novel eviction policy that exploits MoE's predictable expert access patterns to reduce collision misses by up to $85\times$ over LRU. With such gains, we achieve over $88\%$ hit rates with up to $34.7\%$ Time-to-first-token (TTFT) reduction on OLMoE at only $5\%$ or $0.6GB$ of VRAM cache capacity.

---

### Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers

Authors: Peihao Xiang, Kaida Wu, Ou Bai
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03918v1

Masked self-supervised vision transformers have become a dominant pretraining paradigm, yet their substantial model size poses significant challenges for resource-constrained deployment and efficient transfer learning. A fundamental question remains: are all transformer blocks equally important for downstream performance? In this paper, we show that block importance in masked self-supervised vision transformers can be accurately estimated without access to any data. Our key finding is that the information entropy of pretrained block weights strongly correlates with oracle sensitivity obtained via iterative block removal and finetuning. This observation enables Gardener, a data-free, one-shot, block-level pruning principle that identifies redundant blocks through simple information-theoretic measurements. We evaluate Gardener on VideoMAE-B across multiple pruning ratios and downstream video recognition benchmarks. Despite its negligible computational overhead, Gardener consistently matches or outperforms existing data-free pruning baselines and closely approaches sensitivity-based pruning. Remarkably, even after pruning up to 91.7\% of blocks, the pruned model retains competitive transfer performance. Our results reveal substantial block-level redundancy in masked self-supervised vision transformers and demonstrate that information-theoretic analysis offers a principled and efficient pathway for model compression and resource-efficient transfer learning.

---

### SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

Authors: Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman, Mahfuz Ahmed Anik, Munem Shahriar, Mohsin Mahmud Topu, Sadia Tasnim Meem, Rahatun Nesa Priti, Sabrina Afroz Mitu, Md. Iqramul Hoque, Shahriyar Zaman Ridoy, Mohammed Eunus Ali et al.
Published: 2026-02-03
Categories: cs.CV, cs.CE, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.03916v3

Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs). Prior work largely relied on synthetic or LLM-generated environments with limited task designs and puzzle-like setups, failing to capture the real-world complexity, visual noise, and diverse spatial relationships that VLMs encounter. To address this, we introduce SpatiaLab, a comprehensive benchmark for evaluating VLMs' spatial reasoning in realistic, unconstrained contexts. SpatiaLab comprises 1,400 visual question-answer pairs across six major categories: Relative Positioning, Depth & Occlusion, Orientation, Size & Scale, Spatial Navigation, and 3D Geometry, each with five subcategories, yielding 30 distinct task types. Each subcategory contains at least 25 questions, and each main category includes at least 200 questions, supporting both multiple-choice and open-ended evaluation. Experiments across diverse state-of-the-art VLMs, including open- and closed-source models, reasoning-focused, and specialized spatial reasoning models, reveal a substantial gap in spatial reasoning capabilities compared with humans. In the multiple-choice setup, InternVL3.5-72B achieves 54.93% accuracy versus 87.57% for humans. In the open-ended setting, all models show a performance drop of around 10-25%, with GPT-5-mini scoring highest at 40.93% versus 64.93% for humans. These results highlight key limitations in handling complex spatial relationships, depth perception, navigation, and 3D geometry. By providing a diverse, real-world evaluation framework, SpatiaLab exposes critical challenges and opportunities for advancing VLMs' spatial reasoning, offering a benchmark to guide future research toward robust, human-aligned spatial understanding. SpatiaLab is available at: https://spatialab-reasoning.github.io/.

---

### Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science

Authors: Levi Lingsch, Georgios Kissas, Johannes Jakubik, Siddhartha Mishra
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2602.03915v1

Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and generalized to new tasks. These have become foundational for image and video generation and, more recently, physical simulation. As existing tokenizers are designed for the explicit requirements of realistic visual perception of images, it is necessary to ask whether these approaches are optimal for scientific images, which exhibit a large dynamic range and require token embeddings to retain physical and spectral properties. In this work, we investigate the accuracy of a suite of image tokenizers across a range of metrics designed to measure the fidelity of PDE properties in both physical and spectral space. Based on the observation that these struggle to capture both fine details and precise magnitudes, we propose Phaedra, inspired by classical shape-gain quantization and proper orthogonal decomposition. We demonstrate that Phaedra consistently improves reconstruction across a range of PDE datasets. Additionally, our results show strong out-of-distribution generalization capabilities to three tasks of increasing complexity, namely known PDEs with different conditions, unknown PDEs, and real-world Earth observation and weather data.

---

### Causal Discovery for Cross-Sectional Data Based on Super-Structure and Divide-and-Conquer

Authors: Wenyu Wang, Yaping Wan
Published: 2026-02-03
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2602.03914v1

This paper tackles a critical bottleneck in Super-Structure-based divide-and-conquer causal discovery: the high computational cost of constructing accurate Super-Structures--particularly when conditional independence (CI) tests are expensive and domain knowledge is unavailable. We propose a novel, lightweight framework that relaxes the strict requirements on Super-Structure construction while preserving the algorithmic benefits of divide-and-conquer. By integrating weakly constrained Super-Structures with efficient graph partitioning and merging strategies, our approach substantially lowers CI test overhead without sacrificing accuracy. We instantiate the framework in a concrete causal discovery algorithm and rigorously evaluate its components on synthetic data. Comprehensive experiments on Gaussian Bayesian networks, including magic-NIAB, ECOLI70, and magic-IRRI, demonstrate that our method matches or closely approximates the structural accuracy of PC and FCI while drastically reducing the number of CI tests. Further validation on the real-world China Health and Retirement Longitudinal Study (CHARLS) dataset confirms its practical applicability. Our results establish that accurate, scalable causal discovery is achievable even under minimal assumptions about the initial Super-Structure, opening new avenues for applying divide-and-conquer methods to large-scale, knowledge-scarce domains such as biomedical and social science research.

---

### Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition

Authors: Qiuming Luo, Tao Zeng, Feng Li, Heming Liu, Rui Mao, Chang Kong
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03913v2

Zero-shot Handwritten Chinese Character Recognition (HCCR) aims to recognize unseen characters by leveraging radical-based semantic compositions. However, existing approaches often treat characters as flat radical sequences, neglecting the hierarchical topology and the uneven information density of different components. To address these limitations, we propose an Entropy-Aware Structural Alignment Network that bridges the visual-semantic gap through information-theoretic modeling. First, we introduce an Information Entropy Prior to dynamically modulate positional embeddings via multiplicative interaction, acting as a saliency detector that prioritizes discriminative roots over ubiquitous components. Second, we construct a Dual-View Radical Tree to extract multi-granularity structural features, which are integrated via an adaptive Sigmoid-based gating network to encode both global layout and local spatial roles. Finally, a Top-K Semantic Feature Fusion mechanism is devised to augment the decoding process by utilizing the centroid of semantic neighbors, effectively rectifying visual ambiguities through feature-level consensus. Extensive experiments demonstrate that our method establishes new state-of-the-art performance, achieving an accuracy of 55.04\% on the ICDAR 2013 dataset ($m=1500$), significantly outperforming existing CLIP-based baselines in the challenging zero-shot setting. Furthermore, the framework exhibits exceptional data efficiency, demonstrating rapid adaptability with minimal support samples, achieving 92.41\% accuracy with only one support sample per class.

---

### Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

Authors: Alexander Häußer
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03912v5

This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE), symmetric mean absolute percentage error (sMAPE), and the overall weighted average (OWA). The ESN is compared with simple benchmarks, statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS, as well as multilayer perceptron (MLP), recurrent neural network (RNN), and hybrid exponential smoothing-RNN (ES-RNN) benchmarks. The model-configuration analysis reveals frequency-specific patterns: monthly series tend to favor moderately persistent reservoirs, whereas quarterly series favor more contractive dynamics; across both frequencies, high leakage rates are generally preferred. In the final benchmark, the ESN performs on par with ARIMA and TBATS under mean MASE for monthly data and achieves the second-lowest mean MASE for quarterly data. ES-RNN provides the best aggregate accuracy for both frequencies. Overall, the results indicate that a simple autoregressive ESN can provide competitive forecast accuracy on the considered filtered M4 subsets, particularly under MASE, while requiring low training and forecasting time once the ESN configuration has been fixed.

---

### Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

Authors: Alexander Häußer
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03912v4

This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE) and symmetric mean absolute percentage error (sMAPE) and compared with simple benchmarks and statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS. The model-configuration analysis reveals frequency-specific patterns: monthly series tend to favor moderately persistent reservoirs, whereas quarterly series favor more contractive dynamics; across both frequencies, high leakage rates are generally preferred. In the final benchmark, the ESN performs on par with ARIMA and TBATS for monthly data and achieves the lowest mean MASE for quarterly data, although it is not uniformly best across all metrics. Overall, the results indicate that a simple autoregressive ESN can provide competitive forecast accuracy on the considered filtered M4 subsets, particularly under MASE, while requiring low training and forecasting time once the ESN configuration has been fixed.

---

### The Role of Target Update Frequencies in Q-Learning

Authors: Simon Weissmann, Tilman Aach, Benedikt Wille, Sebastian Kassing, Leif Döring
Published: 2026-02-03
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.03911v1

The target network update frequency (TUF) is a central stabilization mechanism in (deep) Q-learning. However, their selection remains poorly understood and is often treated merely as another tunable hyperparameter rather than as a principled design decision. This work provides a theoretical analysis of target fixing in tabular Q-learning through the lens of approximate dynamic programming. We formulate periodic target updates as a nested optimization scheme in which each outer iteration applies an inexact Bellman optimality operator, approximated by a generic inner loop optimizer. Rigorous theory yields a finite-time convergence analysis for the asynchronous sampling setting, specializing to stochastic gradient descent in the inner loop. Our results deliver an explicit characterization of the bias-variance trade-off induced by the target update period, showing how to optimally set this critical hyperparameter. We prove that constant target update schedules are suboptimal, incurring a logarithmic overhead in sample complexity that is entirely avoidable with adaptive schedules. Our analysis shows that the optimal target update frequency increases geometrically over the course of the learning process.

---

### Beyond the Vehicle: Cooperative Localization by Fusing Point Clouds for GPS-Challenged Urban Scenarios

Authors: Kuo-Yi Chao, Ralph Rasshofer, Alois Christian Knoll
Published: 2026-02-03
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.03908v1

Accurate vehicle localization is a critical challenge in urban environments where GPS signals are often unreliable. This paper presents a cooperative multi-sensor and multi-modal localization approach to address this issue by fusing data from vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) systems. Our approach integrates cooperative data with a point cloud registration-based simultaneous localization and mapping (SLAM) algorithm. The system processes point clouds generated from diverse sensor modalities, including vehicle-mounted LiDAR and stereo cameras, as well as sensors deployed at intersections. By leveraging shared data from infrastructure, our method significantly improves localization accuracy and robustness in complex, GPS-noisy urban scenarios.

---

### HY3D-Bench: Generation of 3D Assets

Authors: Team Hunyuan3D, :, Bowen Zhang, Chunchao Guo, Dongyuan Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jiaao Yu, Jiachen Xu, Jingwei Huang, Kunhong Li et al.
Published: 2026-02-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.03907v1

While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an open-source ecosystem designed to establish a unified, high-quality foundation for 3D generation. Our contributions are threefold: (1) We curate a library of 250k high-fidelity 3D objects distilled from large-scale repositories, employing a rigorous pipeline to deliver training-ready artifacts, including watertight meshes and multi-view renderings; (2) We introduce structured part-level decomposition, providing the granularity essential for fine-grained perception and controllable editing; and (3) We bridge real-world distribution gaps via a scalable AIGC synthesis pipeline, contributing 125k synthetic assets to enhance diversity in long-tail categories. Validated empirically through the training of Hunyuan3D-2.1-Small, HY3D-Bench democratizes access to robust data resources, aiming to catalyze innovation across 3D perception, robotics, and digital content creation.

---

### GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression

Authors: Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Shui Yu
Published: 2026-02-03
Categories: cs.LG, cs.AI, cs.IT, stat.ML
arXiv: https://arxiv.org/abs/2602.03906v1

Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI) estimators, rather than directly controlling the MI I(X;Z) itself. The looseness and estimator-dependent bias can make IB "compression" only indirectly controlled and optimization fragile. We revisit the IB problem through the lens of information geometry and propose a \textbf{Geo}metric \textbf{I}nformation \textbf{B}ottleneck (\textbf{GeoIB}) that dispenses with mutual information (MI) estimation. We show that I(X;Z) and I(Z;Y) admit exact projection forms as minimal Kullback-Leibler (KL) distances from the joint distributions to their respective independence manifolds. Guided by this view, GeoIB controls information compression with two complementary terms: (i) a distribution-level Fisher-Rao (FR) discrepancy, which matches KL to second order and is reparameterization-invariant; and (ii) a geometry-level Jacobian-Frobenius (JF) term that provides a local capacity-type upper bound on I(Z;X) by penalizing pullback volume expansion of the encoder. We further derive a natural-gradient optimizer consistent with the FR metric and prove that the standard additive natural-gradient step is first-order equivalent to the geodesic update. We conducted extensive experiments and observed that the GeoIB achieves a better trade-off between prediction accuracy and compression ratio in the information plane than the mainstream IB baselines on popular datasets. GeoIB improves invariance and optimization stability by unifying distributional and geometric regularization under a single bottleneck multiplier. The source code of GeoIB is released at "https://anonymous.4open.science/r/G-IB-0569".

---

### All-Atom GPCR-Ligand Dynamics Simulation via a Residual Latent Flow Mode

Authors: Jiying Zhang, Shuhao Zhang, Pierre Vandergheynst, Patrick Barth
Published: 2026-02-03
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03902v2

G-protein-coupled receptors (GPCRs), which are targeted by over one-third of approved drugs, undergo intricate conformational transitions to transduce signals. While Molecular Dynamics (MD) is essential for elucidating this transduction process, particularly within ligand-bound complexes, conventional all-atom MD simulation is computationally prohibitive. In this paper, we introduce GPCRLMD, a deep generative framework for efficient all-atom GPCR-ligand simulation. GPCRLMD employs an Atom-Anchored Thermal Variational Autoencoder (AAT-VAE) to first map the complex into a regularized dimension-preserving latent space, maintaining geometric topology via physics-informed constraints. Within this latent space, a Residual Latent Flow samples evolution trajectories, which are subsequently decoded back to atomic coordinates. By capturing temporal dynamics via relative displacements anchored to the initial structure, this residual mechanism effectively decouples static topology from dynamic fluctuations. Experimental results demonstrate that GPCRLMD achieves state-of-the-art performance in GPCR-ligand dynamics simulation, faithfully reproducing ensemble observables and critical ligand-receptor interactions.

---

### All-Atom GPCR-Ligand Simulation via Residual Isometric Latent Flow

Authors: Jiying Zhang, Shuhao Zhang, Pierre Vandergheynst, Patrick Barth
Published: 2026-02-03
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03902v1

G-protein-coupled receptors (GPCRs), primary targets for over one-third of approved therapeutics, rely on intricate conformational transitions to transduce signals. While Molecular Dynamics (MD) is essential for elucidating this transduction process, particularly within ligand-bound complexes, conventional all-atom MD simulation is computationally prohibitive. In this paper, we introduce GPCRLMD, a deep generative framework for efficient all-atom GPCR-ligand simulation.GPCRLMD employs a Harmonic-Prior Variational Autoencoder (HP-VAE) to first map the complex into a regularized isometric latent space, preserving geometric topology via physics-informed constraints. Within this latent space, a Residual Latent Flow samples evolution trajectories, which are subsequently decoded back to atomic coordinates. By capturing temporal dynamics via relative displacements anchored to the initial structure, this residual mechanism effectively decouples static topology from dynamic fluctuations. Experimental results demonstrate that GPCRLMD achieves state-of-the-art performance in GPCR-ligand dynamics simulation, faithfully reproducing thermodynamic observables and critical ligand-receptor interactions.

---

### NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces

Authors: Rong Fu, Chunlei Meng, Haoyu Zhao, Kun Liu, JiaBao Dou, Youjin Wang, Simon James Fong
Published: 2026-02-03
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2602.03901v6

The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.

---

### Knowledge Model Prompting Increases LLM Performance on Planning Tasks

Authors: Erik Goh, John Kos, Ashok Goel
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03900v1

Large Language Models (LLM) can struggle with reasoning ability and planning tasks. Many prompting techniques have been developed to assist with LLM reasoning, notably Chain-of-Thought (CoT); however, these techniques, too, have come under scrutiny as LLMs' ability to reason at all has come into question. Borrowing from the domain of cognitive and educational science, this paper investigates whether the Task-Method-Knowledge (TMK) framework can improve LLM reasoning capabilities beyond its previously demonstrated success in educational applications. The TMK framework's unique ability to capture causal, teleological, and hierarchical reasoning structures, combined with its explicit task decomposition mechanisms, makes it particularly well-suited for addressing language model reasoning deficiencies, and unlike other hierarchical frameworks such as HTN and BDI, TMK provides explicit representations of not just what to do and how to do it, but also why actions are taken. The study evaluates TMK by experimenting on the PlanBench benchmark, focusing on the Blocksworld domain to test for reasoning and planning capabilities, examining whether TMK-structured prompting can help language models better decompose complex planning problems into manageable sub-tasks. Results also highlight significant performance inversion in reasoning models. TMK prompting enables the reasoning model to achieve up to an accuracy of 97.3\% on opaque, symbolic tasks (Random versions of Blocksworld in PlanBench) where it previously failed (31.5\%), suggesting the potential to bridge the gap between semantic approximation and symbolic manipulation. Our findings suggest that TMK functions not merely as context, but also as a mechanism that steers reasoning models away from their default linguistic modes to engage formal, code-execution pathways in the context of the experiments.

---

### Byzantine Machine Learning: MultiKrum and an optimal notion of robustness

Authors: Gilles Bareilles, Wassim Bouaziz, Julien Fageot, El-Mahdi El-Mhamdi
Published: 2026-02-03
Categories: stat.ML, cs.AI, cs.LG, math.OC, math.ST
arXiv: https://arxiv.org/abs/2602.03899v1

Aggregation rules are the cornerstone of distributed (or federated) learning in the presence of adversaries, under the so-called Byzantine threat model. They are also interesting mathematical objects from the point of view of robust mean estimation. The Krum aggregation rule has been extensively studied, and endowed with formal robustness and convergence guarantees. Yet, MultiKrum, a natural extension of Krum, is often preferred in practice for its superior empirical performance, even though no theoretical guarantees were available until now. In this work, we provide the first proof that MultiKrum is a robust aggregation rule, and bound its robustness coefficient. To do so, we introduce $κ^\star$, the optimal *robustness coefficient* of an aggregation rule, which quantifies the accuracy of mean estimation in the presence of adversaries in a tighter manner compared with previously adopted notions of robustness. We then construct an upper and a lower bound on MultiKrum's robustness coefficient. As a by-product, we also improve on the best-known bounds on Krum's robustness coefficient. We show that MultiKrum's bounds are never worse than Krum's, and better in realistic regimes. We illustrate this analysis by an experimental investigation on the quality of the lower bound.

---

### A hitchhiker's guide to Poisson gradient estimation

Authors: Michael Ibrahim, Hanqi Zhao, Eli Sennesh, Zhi Li, Anqi Wu, Jacob L. Yates, Chengrui Li, Hadi Vafaii
Published: 2026-02-03
Categories: stat.ML, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2602.03896v2

Poisson-distributed latent variable models are widely used in computational neuroscience, but differentiating through discrete stochastic samples remains challenging. Two approaches address this: *Exponential Arrival Time* (EAT) simulation and *Gumbel-SoftMax* (GSM) relaxation. We provide the first systematic comparison of these methods, along with practical guidance for practitioners. Our main technical contribution is a modification to the EAT method that theoretically guarantees an unbiased first moment (exactly matching the firing rate), and reduces second-moment bias. We evaluate these methods on their distributional fidelity, gradient quality, and performance on two tasks: (1) variational autoencoders with Poisson latents, and (2) partially observable generalized linear models, where latent neural connectivity must be inferred from observed spike trains. Across all metrics, our modified EAT method exhibits better overall performance (often comparable to exact gradients), and substantially higher robustness to hyperparameter choices. These results extend to over-dispersed Negative Binomial latents, where modified EAT again performs best. However, only GSM generalizes to arbitrary non-Poisson distributions, including the under-dispersed regime. Together, our results clarify the trade-offs between these methods and offer concrete recommendations for practitioners working with Poisson latent variable models.

---

### Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs

Authors: Xuwei Tan, Ziyu Hu, Xueru Zhang
Published: 2026-02-03
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.03895v1

Machine learning models trained on real-world data often inherit and amplify biases against certain social groups, raising urgent concerns about their deployment at scale. While numerous bias mitigation methods have been proposed, comparing the effectiveness of bias mitigation methods remains difficult due to heterogeneous datasets, inconsistent fairness metrics, isolated evaluation of vision versus multi-modal models, and insufficient hyperparameter tuning that undermines fair comparisons. We introduce NH-Fair, a unified benchmark for fairness without harm that spans both vision models and large vision-language models (LVLMs) under standardized data, metrics, and training protocols, covering supervised and zero-shot regimes. Our key contributions are: (1) a systematic ERM tuning study that identifies training choices with large influence on both utility and disparities, yielding empirically grounded guidelines to help practitioners reduce expensive hyperparameter tuning space in achieving strong fairness and accuracy; (2) evidence that many debiasing methods do not reliably outperform a well-tuned ERM baseline, whereas a composite data-augmentation method consistently delivers parity gains without sacrificing utility, emerging as a promising practical strategy. (3) an analysis showing that while LVLMs achieve higher average accuracy, they still exhibit subgroup disparities, and gains from scaling are typically smaller than those from architectural or training-protocol choices. NH-Fair provides a reproducible, tuning-aware pipeline for rigorous, harm-aware fairness evaluation.

---

### Vision Transformers for Zero-Shot Clustering of Animal Images: A Comparative Benchmarking Study

Authors: Hugo Markoff, Stefan Hein Bengtson, Michael Ørsted
Published: 2026-02-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.03894v1

Manual labeling of animal images remains a significant bottleneck in ecological research, limiting the scale and efficiency of biodiversity monitoring efforts. This study investigates whether state-of-the-art Vision Transformer (ViT) foundation models can reduce thousands of unlabeled animal images directly to species-level clusters. We present a comprehensive benchmarking framework evaluating five ViT models combined with five dimensionality reduction techniques and four clustering algorithms, two supervised and two unsupervised, across 60 species (30 mammals and 30 birds), with each test using a random subset of 200 validated images per species. We investigate when clustering succeeds at species-level, where it fails, and whether clustering within the species-level reveals ecologically meaningful patterns such as sex, age, or phenotypic variation. Our results demonstrate near-perfect species-level clustering (V-measure: 0.958) using DINOv3 embeddings with t-SNE and supervised hierarchical clustering methods. Unsupervised approaches achieve competitive performance (0.943) while requiring no prior species knowledge, rejecting only 1.14% of images as outliers requiring expert review. We further demonstrate robustness to realistic long-tailed distributions of species and show that intentional over-clustering can reliably extract intra-specific variation including age classes, sexual dimorphism, and pelage differences. We introduce an open-source benchmarking toolkit and provide recommendations for ecologists to select appropriate methods for sorting their specific taxonomic groups and data.

---

### GPAIR: Gaussian-Kernel-Based Ultrafast 3D Photoacoustic Iterative Reconstruction

Authors: Yibing Wang, Shuang Li, Tingting Huang, Yu Zhang, Chulhong Kim, Seongwook Choi, Changhui Li
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03893v1

Although the iterative reconstruction (IR) algorithm can substantially correct reconstruction artifacts in photoacoustic (PA) computed tomography (PACT), it suffers from long reconstruction times, especially for large-scale three-dimensional (3D) imaging in which IR takes hundreds of seconds to hours. The computing burden severely limits the practical applicability of IR algorithms. In this work, we proposed an ultrafast IR method for 3D PACT, called Gaussian-kernel-based Ultrafast 3D Photoacoustic Iterative Reconstruction (GPAIR), which achieves orders-of-magnitude acceleration in computing. GPAIR transforms traditional spatial grids with continuous isotropic Gaussian kernels. By deriving analytical closed-form expression for pressure waves and implementing powerful GPU-accelerated differentiable Triton operators, GPAIR demonstrates extraordinary ultrafast sub-second reconstruction speed for 3D targets containing 8.4 million voxels in animal experiments. This revolutionary ultrafast image reconstruction enables near-real-time large-scale 3D PA reconstruction, significantly advancing 3D PACT toward clinical applications.

---

### Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation

Authors: Jinxing Zhou, Yanghao Zhou, Yaoting Wang, Zongyan Han, Jiaqi Ma, Henghui Ding, Rao Muhammad Anwer, Hisham Cholakkal
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.LG, cs.MM, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2602.03892v1

Language-referred audio-visual segmentation (Ref-AVS) aims to segment target objects described by natural language by jointly reasoning over video, audio, and text. Beyond generating segmentation masks, providing rich and interpretable diagnoses of mask quality remains largely underexplored. In this work, we introduce Mask Quality Assessment in the Ref-AVS context (MQA-RefAVS), a new task that evaluates the quality of candidate segmentation masks without relying on ground-truth annotations as references at inference time. Given audio-visual-language inputs and each provided segmentation mask, the task requires estimating its IoU with the unobserved ground truth, identifying the corresponding error type, and recommending an actionable quality-control decision. To support this task, we construct MQ-RAVSBench, a benchmark featuring diverse and representative mask error modes that span both geometric and semantic issues. We further propose MQ-Auditor, a multimodal large language model (MLLM)-based auditor that explicitly reasons over multimodal cues and mask information to produce quantitative and qualitative mask quality assessments. Extensive experiments demonstrate that MQ-Auditor outperforms strong open-source and commercial MLLMs and can be integrated with existing Ref-AVS systems to detect segmentation failures and support downstream segmentation improvement. Data and codes will be released at https://github.com/jasongief/MQA-RefAVS.

---

### Sounding Highlights: Dual-Pathway Audio Encoders for Audio-Visual Video Highlight Detection

Authors: Seohyun Joo, Yoori Oh
Published: 2026-02-03
Categories: eess.AS, cs.AI, cs.CV, cs.MM, cs.SD
arXiv: https://arxiv.org/abs/2602.03891v2

Audio-visual video highlight detection aims to automatically identify the most salient moments in videos by leveraging both visual and auditory cues. However, existing models often underutilize the audio modality, focusing on high-level semantic features while failing to fully leverage the rich, dynamic characteristics of sound. To address this limitation, we propose a novel framework, Dual-Pathway Audio Encoders for Video Highlight Detection (DAViHD). The dual-pathway audio encoder is composed of a semantic pathway for content understanding and a dynamic pathway that captures spectro-temporal dynamics. The semantic pathway extracts high-level information by identifying the content within the audio, such as speech, music, or specific sound events. The dynamic pathway employs a frequency-adaptive mechanism as time evolves to jointly model these dynamics, enabling it to identify transient acoustic events via salient spectral bands and rapid energy changes. We integrate the novel audio encoder into a full audio-visual framework and achieve new state-of-the-art performance on the large-scale MrHiSum benchmark. Our results demonstrate that a sophisticated, dual-faceted audio representation is key to advancing the field of highlight detection.

---

### 4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping

Authors: Xindan Zhang, Weilong Yan, Yufei Shi, Xuerui Qiu, Tao He, Ying Li, Ming Li, Hehe Fan
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03890v3

Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This limitation is mainly caused by the lack of large-scale cross-modal datasets and the difficulty of modeling motions in spatio-temporal contexts. To bridge this gap, we present 4DPC$^2$hat, the first MLLM tailored for dynamic point cloud understanding. To this end, we construct a large-scale cross-modal dataset 4DPC$^2$hat-200K via a meticulous two-stage pipeline consisting of topology-consistent 4D point construction and two-level captioning. The dataset contains over 44K dynamic object sequences, 700K point cloud frames, and 200K curated question-answer (QA) pairs, supporting inquiries about counting, temporal relationship, action, spatial relationship, and appearance. At the core of the framework, we introduce a Mamba-enhanced temporal reasoning MLLM to capture long-range dependencies and dynamic patterns among a point cloud sequence. Furthermore, we propose a failure-aware bootstrapping learning strategy that iteratively identifies model deficiencies and generates targeted QA supervision to continuously strengthen corresponding reasoning capabilities. Extensive experiments demonstrate that our 4DPC$^2$hat significantly improves action understanding and temporal reasoning compared with existing models, establishing a strong foundation for 4D dynamic point cloud understanding.

---

### Transcendental Regularization of Finite Mixtures:Theoretical Guarantees and Practical Limitations

Authors: Ernest Fokoué
Published: 2026-02-03
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.03889v1

Finite mixture models are widely used for unsupervised learning, but maximum likelihood estimation via EM suffers from degeneracy as components collapse. We introduce transcendental regularization, a penalized likelihood framework with analytic barrier functions that prevent degeneracy while maintaining asymptotic efficiency. The resulting Transcendental Algorithm for Mixtures of Distributions (TAMD) offers strong theoretical guarantees: identifiability, consistency, and robustness. Empirically, TAMD successfully stabilizes estimation and prevents collapse, yet achieves only modest improvements in classification accuracy-highlighting fundamental limits of mixture models for unsupervised learning in high dimensions. Our work provides both a novel theoretical framework and an honest assessment of practical limitations, implemented in an open-source R package.

---

### To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?

Authors: Weiming Chen, Xitong Ling, Xidong Wang, Zhenyang Cai, Yijia Guo, Mingxi Fu, Ziyi Zeng, Minxi Ouyang, Jiawen Li, Yizhi Wang, Tian Guan, Benyou Wang et al.
Published: 2026-02-03
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.03887v1

Pathology foundation models (PFMs) have rapidly advanced and are becoming a common backbone for downstream clinical tasks, offering strong transferability across tissues and institutions. However, for dense prediction (e.g., segmentation), practical deployment still lacks a clear, reproducible understanding of how different PFMs behave across datasets and how adaptation choices affect performance and stability. We present PFM-DenseBench, a large-scale benchmark for dense pathology prediction, evaluating 17 PFMs across 18 public segmentation datasets. Under a unified protocol, we systematically assess PFMs with multiple adaptation and fine-tuning strategies, and derive insightful, practice-oriented findings on when and why different PFMs and tuning choices succeed or fail across heterogeneous datasets. We release containers, configs, and dataset cards to enable reproducible evaluation and informed PFM selection for real-world dense pathology tasks. Project Website: https://m4a1tastegood.github.io/PFM-DenseBench

---

### Prenatal Stress Detection from Electrocardiography Using Self-Supervised Deep Learning: Development and External Validation

Authors: Martin G. Frasch, Marlene J. E. Mayer, Clara Becker, Peter Zimmermann, Camilla Zelgert, Marta C. Antonelli, Silvia M. Lobmaier
Published: 2026-02-03
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2602.03886v3

Prenatal psychological stress affects 15-25% of pregnancies and increases risks of preterm birth, low birth weight, and adverse neurodevelopmental outcomes. Current screening relies on subjective questionnaires (PSS-10), limiting continuous monitoring. We developed deep learning models for stress detection from electrocardiography (ECG) using the FELICITy 1 cohort (151 pregnant women, 32-38 weeks gestation). A ResNet-34 encoder was pretrained via SimCLR contrastive learning on 40,692 ECG segments per subject. Multi-layer feature extraction enabled binary classification and continuous PSS prediction across maternal (mECG), fetal (fECG), and abdominal ECG (aECG). External validation used the FELICITy 2 RCT (28 subjects, different ECG device, yoga intervention vs. control). On FELICITy 1 (5-fold CV): mECG 98.6% accuracy (R2=0.88, MAE=1.90), fECG 99.8% (R2=0.95, MAE=1.19), aECG 95.5% (R2=0.75, MAE=2.80). External validation on FELICITy 2: mECG 77.3% accuracy (R2=0.62, MAE=3.54, AUC=0.826), aECG 63.6% (R2=0.29, AUC=0.705). Signal quality-based channel selection outperformed all-channel averaging (+12% R2 improvement). Mixed-effects models detected a significant intervention response (p=0.041). Self-supervised deep learning on pregnancy ECG enables accurate, objective stress assessment, with multi-layer feature extraction substantially outperforming single embedding approaches.

---