# Research Papers — 2026-03 · bundle page 216 of 243

> Full-text markdown of papers #10751–10800 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-03/page/216
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/215.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/217.md)

### Monitoring Emergent Reward Hacking During Generation via Internal Activations

Authors: Patrick Wilhelm, Thorsten Wittkopp, Odej Kao
Published: 2026-03-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04069v1

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses, it remains unclear whether such behavior can be identified during generation. We propose an activation-based monitoring approach that detects reward-hacking signals from internal representations as a model generates its response. Our method trains sparse autoencoders on residual stream activations and applies lightweight linear classifiers to produce token-level estimates of reward-hacking activity. Across multiple model families and fine-tuning mixtures, we find that internal activation patterns reliably distinguish reward-hacking from benign behavior, generalize to unseen mixed-policy adapters, and exhibit model-dependent temporal structure during chain-of-thought reasoning. Notably, reward-hacking signals often emerge early, persist throughout reasoning, and can be amplified by increased test-time compute in the form of chain-of-thought prompting under weakly specified reward objectives. These results suggest that internal activation monitoring provides a complementary and earlier signal of emergent misalignment than output-based evaluation, supporting more robust post-deployment safety monitoring for fine-tuned language models.

---

### Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models

Authors: Ziyuan Chen, Yujin Jeong, Tobias Braun, Anna Rohrbach
Published: 2026-03-04
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.04064v1

As text-to-image diffusion models become increasingly deployed in real-world applications, concerns about backdoor attacks have gained significant attention. Prior work on text-based backdoor attacks has largely focused on diffusion models conditioned on a single lightweight text encoder. However, more recent diffusion models that incorporate multiple large-scale text encoders remain underexplored in this context. Given the substantially increased number of trainable parameters introduced by multiple text encoders, an important question is whether backdoor attacks can remain both efficient and effective in such settings. In this work, we study Stable Diffusion 3, which uses three distinct text encoders and has not yet been systematically analyzed for text-encoder-based backdoor vulnerabilities. To understand the role of text encoders in backdoor attacks, we define four categories of attack targets and identify the minimal sets of encoders required to achieve effective performance for each attack objective. Based on this, we further propose Multi-Encoder Lightweight aTtacks (MELT), which trains only low-rank adapters while keeping the pretrained text encoder weight frozen. We demonstrate that tuning fewer than 0.2% of the total encoder parameters is sufficient for successful backdoor attacks on Stable Diffusion 3, revealing previously underexplored vulnerabilities in practical attack scenarios in multi-encoder settings.

---

### FedCova: Robust Federated Covariance Learning Against Noisy Labels

Authors: Xiangyu Zhong, Xiaojun Yuan, Ying-Jun Angela Zhang
Published: 2026-03-04
Categories: cs.LG, cs.IT, eess.SP
arXiv: https://arxiv.org/abs/2603.04062v1

Noisy labels in distributed datasets induce severe local overfitting and consequently compromise the global model in federated learning (FL). Most existing solutions rely on selecting clean devices or aligning with public clean datasets, rather than endowing the model itself with robustness. In this paper, we propose FedCova, a dependency-free federated covariance learning framework that eliminates such external reliances by enhancing the model's intrinsic robustness via a new perspective on feature covariances. Specifically, FedCova encodes data into a discriminative but resilient feature space to tolerate label noise. Built on mutual information maximization, we design a novel objective for federated lossy feature encoding that relies solely on class feature covariances with an error tolerance term. Leveraging feature subspaces characterized by covariances, we construct a subspace-augmented federated classifier. FedCova unifies three key processes through the covariance: (1) training the network for feature encoding, (2) constructing a classifier directly from the learned features, and (3) correcting noisy labels based on feature subspaces. We implement FedCova across both symmetric and asymmetric noisy settings under heterogeneous data distribution. Experimental results on CIFAR-10/100 and real-world noisy dataset Clothing1M demonstrate the superior robustness of FedCova compared with the state-of-the-art methods.

---

### Fermi-Dirac thermal measurements: A framework for quantum hypothesis testing and semidefinite optimization

Authors: Nana Liu, Mark M. Wilde
Published: 2026-03-04
Categories: quant-ph, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2603.04061v2

Quantum measurements are the means by which we recover messages encoded into quantum states. They are at the forefront of quantum hypothesis testing, wherein the goal is to perform an optimal measurement for arriving at a correct conclusion. Mathematically, a measurement operator is Hermitian with eigenvalues in (0,1). By noticing that this constraint on each eigenvalue is the same as that imposed on fermions by the Pauli exclusion principle, we interpret every eigenmode of a measurement operator as an independent effective fermionic mode. Under this perspective, various objective functions in quantum hypothesis testing can be viewed as the total expected energy associated with these fermionic occupation numbers. By instead fixing a temperature and minimizing the total expected fermionic free energy, we find that optimal measurements for these modified objective functions are Fermi-Dirac thermal measurements, wherein their eigenvalues are specified by Fermi-Dirac distributions. In the low-temperature limit, their performance closely approximates that of optimal measurements for quantum hypothesis testing, and we show that their parameters can be learned by classical or hybrid quantum-classical optimization algorithms. This leads to a new quantum machine-learning model, termed Fermi-Dirac machines, consisting of parameterized Fermi-Dirac thermal measurements-an alternative to quantum Boltzmann machines based on thermal states. Beyond hypothesis testing, we show how general semidefinite optimization problems can be solved using this approach, leading to a novel paradigm for semidefinite optimization on quantum computers, in which the goal is to implement thermal measurements rather than prepare thermal states. Finally, we propose quantum algorithms for implementing Fermi-Dirac thermal measurements, and we also propose second-order hybrid quantum-classical optimization algorithms.

---

### Fermi-Dirac thermal measurements: A framework for quantum hypothesis testing and semidefinite optimization

Authors: Nana Liu, Mark M. Wilde
Published: 2026-03-04
Categories: quant-ph, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2603.04061v1

Quantum measurements are the means by which we recover messages encoded into quantum states. They are at the forefront of quantum hypothesis testing, wherein the goal is to perform an optimal measurement for arriving at a correct conclusion. Mathematically, a measurement operator is Hermitian with eigenvalues in (0,1). By noticing that this constraint on each eigenvalue is the same as that imposed on fermions by the Pauli exclusion principle, we interpret every eigenmode of a measurement operator as an independent effective fermionic mode. Under this perspective, various objective functions in quantum hypothesis testing can be viewed as the total expected energy associated with these fermionic occupation numbers. By instead fixing a temperature and minimizing the total expected fermionic free energy, we find that optimal measurements for these modified objective functions are Fermi-Dirac thermal measurements, wherein their eigenvalues are specified by Fermi-Dirac distributions. In the low-temperature limit, their performance closely approximates that of optimal measurements for quantum hypothesis testing, and we show that their parameters can be learned by classical or hybrid quantum-classical optimization algorithms. This leads to a new quantum machine-learning model, termed Fermi-Dirac machines, consisting of parameterized Fermi-Dirac thermal measurements-an alternative to quantum Boltzmann machines based on thermal states. Beyond hypothesis testing, we show how general semidefinite optimization problems can be solved using this approach, leading to a novel paradigm for semidefinite optimization on quantum computers, in which the goal is to implement thermal measurements rather than prepare thermal states. Finally, we propose quantum algorithms for implementing Fermi-Dirac thermal measurements, and we also propose second-order hybrid quantum-classical optimization algorithms.

---

### TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth

Authors: Valentin Biller, Niklas Bubeck, Lucas Zimmer, Ayhan Can Erdur, Sandeep Nagar, Anke Meyer-Baese, Daniel Rückert, Benedikt Wiestler, Jonas Weidner
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04058v2

Glioblastoma exhibits diverse, infiltrative, and patient-specific growth patterns that are only partially visible on routine MRI, making it difficult to reliably assess true tumor extent and personalize treatment planning and follow-up. We present a biophysically-conditioned generative framework that synthesizes biologically realistic 3D brain MRI volumes from estimated, spatially continuous tumor-concentration fields. Our approach combines a generative model with tumor-infiltration maps that can be propagated through time using a biophysical growth model, enabling fine-grained control over tumor shape and growth while preserving patient anatomy. This enables us to synthesize consistent tumor growth trajectories directly in the space of real patients, providing interpretable, controllable estimation of tumor infiltration and progression beyond what is explicitly observed in imaging. We evaluate the framework on longitudinal glioblastoma cases and demonstrate that it can generate temporally coherent sequences with realistic changes in tumor appearance and surrounding tissue response. These results suggest that integrating mechanistic tumor growth priors with modern generative modeling can provide a practical tool for patient-specific progression visualization and for generating controlled synthetic data to support downstream neuro-oncology workflows. In longitudinal extrapolation, we achieve a consistent 75% Dice overlap with the biophysical model while maintaining a constant PSNR of 25 in the surrounding tissue. Our code is available at: https://github.com/valentin-biller/lgm.git

---

### Sim2Sea: Sim-to-Real Policy Transfer for Maritime Vessel Navigation in Congested Waters

Authors: Xinyu Cui, Xuanfa Jin, Xue Yan, Yongcheng Zeng, Luoyang Sun, Siying Wei, Ruizhi Zhang, Jian Zhao, Haifeng Zhang, Jun Wang
Published: 2026-03-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.04057v1

Autonomous navigation in congested maritime environments is a critical capability for a wide range of real-world applications. However, it remains an unresolved challenge due to complex vessel interactions and significant environmental uncertainties. Existing methods often fail in practical deployment due to a substantial sim-to-real gap, which stems from imprecise simulation, inadequate situational awareness, and unsafe exploration strategies. To address these, we propose \textbf{Sim2Sea}, a comprehensive framework designed to bridge simulation and real-world execution. Sim2Sea advances in three key aspects. First, we develop a GPU-accelerated parallel simulator for scalable and accurate maritime scenario simulation. Second, we design a dual-stream spatiotemporal policy that handles complex dynamics and multi-modal perception, augmented with a velocity-obstacle-guided action masking mechanism to ensure safe and efficient exploration. Finally, a targeted domain randomization scheme helps bridge the sim-to-real gap. Simulation results demonstrate that our method achieves faster convergence and safer trajectories than established baselines. In addition, our policy trained purely in simulation successfully transfers zero-shot to a 17-ton unmanned vessel operating in real-world congested waters. These results validate the effectiveness of Sim2Sea in achieving reliable sim-to-real transfer for practical autonomous maritime navigation.

---

### Long-Term Visual Localization in Dynamic Benthic Environments: A Dataset, Footprint-Based Ground Truth, and Visual Place Recognition Benchmark

Authors: Martin Kvisvik Larsen, Oscar Pizarro
Published: 2026-03-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.04056v1

Long-term visual localization has the potential to reduce cost and improve mapping quality in optical benthic monitoring with autonomous underwater vehicles (AUVs). Despite this potential, long-term visual localization in benthic environments remains understudied, primarily due to the lack of curated datasets for benchmarking. Moreover, limited georeferencing accuracy and image footprints necessitate precise geometric information for accurate ground-truthing. In this work, we address these gaps by presenting a curated dataset for long-term visual localization in benthic environments and a novel method to ground-truth visual localization results for near-nadir underwater imagery. Our dataset comprises georeferenced AUV imagery from five benthic reference sites, revisited over periods up to six years, and includes raw and color-corrected stereo imagery, camera calibrations, and sub-decimeter registered camera poses. To our knowledge, this is the first curated underwater dataset for long-term visual localization spanning multiple sites and photic-zone habitats. Our ground-truthing method estimates 3D seafloor image footprints and links camera views with overlapping footprints, ensuring that ground-truth links reflect shared visual content. Building on this dataset and ground truth, we benchmark eight state-of-the-art visual place recognition (VPR) methods and find that Recall@K is significantly lower on our dataset than on established terrestrial and underwater benchmarks. Finally, we compare our footprint-based ground truth to a traditional location-based ground truth and show that distance-threshold ground-truthing can overestimate VPR Recall@K at sites with rugged terrain and altitude variations. Together, the curated dataset, ground-truthing method, and VPR benchmark provide a stepping stone for advancing long-term visual localization in dynamic benthic environments.

---

### An Adaptive KKT-Based Indicator for Convergence Assessment in Multi-Objective Optimization

Authors: Thiago Santos, Sebastiao Xavier
Published: 2026-03-04
Categories: math.OC, cs.NE
arXiv: https://arxiv.org/abs/2603.04053v1

Performance indicators are essential tools for assessing the convergence behavior of multi-objective optimization algorithms, particularly when the true Pareto front is unknown or difficult to approximate. Classical reference-based metrics such as hypervolume and inverted generational distance are widely used, but may suffer from scalability limitations and sensitivity to parameter choices in many-objective scenarios. Indicators derived from Karush--Kuhn--Tucker (KKT) optimality conditions provide an intrinsic alternative by quantifying stationarity without relying on external reference sets. This paper revisits an entropy-inspired KKT-based convergence indicator and proposes a robust adaptive reformulation based on quantile normalization. The proposed indicator preserves the stationarity-based interpretation of the original formulation while improving robustness to heterogeneous distributions of stationarity residuals, a recurring issue in many-objective optimization.

---

### Inference-Time Toxicity Mitigation in Protein Language Models

Authors: Manuel Fernández Burda, Santiago Aranguri, Iván Arcuschin Moreno, Enzo Ferrante
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04045v1

Protein language models (PLMs) are becoming practical tools for de novo protein design, yet their dual-use potential raises safety concerns. We show that domain adaptation to specific taxonomic groups can elicit toxic protein generation, even when toxicity is not the training objective. To address this, we adapt Logit Diff Amplification (LDA) as an inference-time control mechanism for PLMs. LDA modifies token probabilities by amplifying the logit difference between a baseline model and a toxicity-finetuned model, requiring no retraining. Across four taxonomic groups, LDA consistently reduces predicted toxicity rate (measured via ToxDL2) below the taxon-finetuned baseline while preserving biological plausibility. We evaluate quality using Fréchet ESM Distance and predicted foldability (pLDDT), finding that LDA maintains distributional similarity to natural proteins and structural viability (unlike activation-based steering methods that tend to degrade sequence properties). Our results demonstrate that LDA provides a practical safety knob for protein generators that mitigates elicited toxicity while retaining generative quality.

---

### DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval

Authors: Geon Park, Ji-Hoon Park, Seong-Whan Lee
Published: 2026-03-04
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04037v1

Composed image retrieval (CIR) addresses the task of retrieving a target image by jointly interpreting a reference image and a modification text that specifies the intended change. Most existing methods are still built upon contrastive learning frameworks that treat the ground truth image as the only positive instance and all remaining images as negatives. This strategy inevitably introduces relevance suppression, where semantically related yet valid images are incorrectly pushed away, and semantic confusion, where different modification intents collapse into overlapping regions of the embedding space. As a result, the learned query representations often lack discriminativeness, particularly at fine-grained attribute modifications. To overcome these limitations, we propose distinctive query embeddings through learnable attribute weights and target relative negative sampling (DQE-CIR), a method designed to learn distinctive query embeddings by explicitly modeling target relative relevance during training. DQE-CIR incorporates learnable attribute weighting to emphasize distinctive visual features conditioned on the modification text, enabling more precise feature alignment between language and vision. Furthermore, we introduce target relative negative sampling, which constructs a target relative similarity distribution and selects informative negatives from a mid-zone region that excludes both easy negatives and ambiguous false negatives. This strategy enables more reliable retrieval for fine-grained attribute changes by improving query discriminativeness and reducing confusion caused by semantically similar but irrelevant candidates.

---

### mlx-vis: GPU-Native Dimensionality Reduction on Apple Silicon

Authors: Han Xiao
Published: 2026-03-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.04035v4

Dimensionality reduction is a foundational tool for visualizing high-dimensional data, yet its reference implementations span a fragmented stack of CPU-bound Python packages that leaves the Metal GPU on Apple Silicon entirely unused. We present mlx-vis, a library that reimplements seven widely used dimensionality reduction methods and k-nearest neighbor graph construction in pure MLX, with every stage -- from PCA preprocessing through embedding optimization to a circle-splatting renderer -- executing on GPU. On Fashion-MNIST 70K, all seven methods embed in 2.1--4.6 s on an M3 Ultra, achieving 3--13x speedups over CPU baselines while reducing the entire dependency stack to MLX and NumPy. The same pipeline scales to ten million points on a single workstation. Code at https://github.com/hanxiao/mlx-vis

---

### The Empty Quadrant: AI Teammates for Embodied Field Learning

Authors: Hyein Kim, Sung Park
Published: 2026-03-04
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.04034v1

For four decades, AIED research has rested on what we term the Sedentary Assumption: the unexamined design commitment to a stationary learner seated before a screen. Mobile learning and museum guides have moved learners into physical space, and context-aware systems have delivered location-triggered content -- yet these efforts predominantly cast AI in the role of information-de-livery tool rather than epistemic partner. We map this gap through a 2 x 2 matrix (AI Role x Learning Environment) and identify an undertheorized intersection: the configuration in which AI serves as an epistemic teammate during unstruc-tured, place-bound field inquiry and learning is assessed through trajectory rather than product. To fill it, we propose Field Atlas, a framework grounded in embod-ied, embedded, enactive, and extended (4E) cognition, active inference, and dual coding theory that shifts AIED's guiding metaphor from instruction to sensemak-ing. The architecture pairs volitional photography with immediate voice reflec-tion, constrains AI to Socratic provocation rather than answer delivery, and ap-plies Epistemic Trajectory Modeling (ETM) to represent field learning as a con-tinuous trajectory through conjoined physical-epistemic space. We demonstrate the framework through a museum scenario and argue that the resulting trajecto-ries -- bound to a specific body, place, and time -- constitute process-based evi-dence structurally resistant to AI fabrication, offering a new assessment paradigm and reorienting AIED toward embodied, dialogic human-AI sensemaking in the wild.

---

### Who Judges the Judge? Evaluating LLM-as-a-Judge for French Medical open-ended QA

Authors: Ikram Belmadani, Oumaima El Khettari, Pacôme Constant dit Beaufils, Richard Dufour, Benoit Favre
Published: 2026-03-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.04033v1

Automatic evaluation of medical open-ended question answering (OEQA) remains challenging due to the need for expert annotations. We evaluate whether large language models (LLMs) can act as judges of semantic equivalence in French medical OEQA, comparing closed-access, general-purpose, and biomedical domain-adapted models. Our results show that LLM-based judgments are strongly influenced by the model that generated the answer, with agreement varying substantially across generators. Domain-adapted and large general-purpose models achieve the highest alignment with expert annotations. We further show that lightweight adaptation of a compact model using supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) substantially improves performance and reduces generator sensitivity, even with limited data. Overall, our findings highlight the need for generator-aware evaluation and suggest that carefully adapted small models can support scalable evaluation in low-resource medical settings.

---

### Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN

Authors: Tobias Morocutti, Emmanouil Karystinaios, Jonathan Greif, Gerhard Widmer
Published: 2026-03-04
Categories: cs.SD, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2603.04032v1

Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts violate common linear-mixture assumptions. This technical report presents the CP-JKU team's system for the MSR ICASSP Challenge 2025. Our approach decomposes MSR into separation and restoration. First, a single BandSplit-RoFormer separator predicts eight stems plus an auxiliary other stem, and is trained with a three-stage curriculum that progresses from 4-stem warm-start fine-tuning (with LoRA) to 8-stem extension via head expansion. Second, we apply a HiFi++ GAN waveform restorer trained as a generalist and then specialized into eight instrument-specific experts.

---

### Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback

Authors: Fabian Domberg, Georg Schildbach
Published: 2026-03-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.04029v1

As learning-based robotic controllers are typically trained offline and deployed with fixed parameters, their ability to cope with unforeseen changes during operation is limited. Biologically inspired, this work presents a framework for online Continual Reinforcement Learning that enables automated adaptation during deployment. Building on DreamerV3, a model-based Reinforcement Learning algorithm, the proposed method leverages world model prediction residuals to detect out-of-distribution events and automatically trigger finetuning. Adaptation progress is monitored using both task-level performance signals and internal training metrics, allowing convergence to be assessed without external supervision and domain knowledge. The approach is validated on a variety of contemporary continuous control problems, including a quadruped robot in high-fidelity simulation, and a real-world model vehicle. Relevant metrics and their interpretation are presented and discussed, as well as resulting trade-offs described. The results sketch out how autonomous robotic agents could once move beyond static training regimes toward adaptive systems capable of self-reflection and -improvement during operation, just like their biological counterparts.

---

### A Multi-Dimensional Quality Scoring Framework for Decentralized LLM Inference with Proof of Quality

Authors: Arther Tian, Alex Ding, Frank Chen, Simon Wu, Aaron Chan
Published: 2026-03-04
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.04028v1

Decentralized large language model (LLM) inference networks can pool heterogeneous compute to scale serving, but they require lightweight and incentive-compatible mechanisms to assess output quality. Prior work introduced cost-aware Proof of Quality (PoQ) and adaptive robust PoQ to allocate rewards under evaluator heterogeneity and adversarial behavior. In this paper, we focus on the quality signal itself and propose a multi-dimensional quality scoring framework that decomposes output quality into modular dimensions, including model and cost priors, structure quality, semantic quality, query-output alignment, and agreement/uncertainty. Using logged outputs from QA and summarization tasks, we systematically audit dimension reliability and show that seemingly reasonable dimensions can be task-dependent and even negatively correlated with reference quality without calibration. While the default composite underperforms a strong single semantic evaluator, ablations reveal that removing unreliable dimensions and re-normalizing weights yields a calibrated composite that matches or exceeds the best single- evaluator and consensus baselines. Finally, we integrate the composite score as a drop-in quality signal in PoQ and demonstrate complementary benefits with robust aggregation and adaptive trust weighting under adversarial evaluator attacks.

---

### Volumetric Directional Diffusion: Anchoring Uncertainty Quantification in Anatomical Consensus for Ambiguous Medical Image Segmentation

Authors: Chao Wu, Mahesh Bhosale, Kangxian Xie, Pouya Karimian, David Doermann, Mingchen Gao
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.04024v2

Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deterministic models preserve coherent volumetric structures but collapse expert disagreement into a single mask, while stochastic generative models can produce diverse samples but may introduce disconnected components or slice-to-slice inconsistency when generating full 3D masks from unstructured noise. We propose Volumetric Directional Diffusion (VDD), a prior-anchored diffusion framework that shifts stochastic generation from full-mask synthesis to residual boundary exploration. VDD uses a coarse consensus prediction as an anatomical anchor and learns a directional diffusion process to generate plausible boundary variations around ambiguous regions while preserving stable volumetric topology. Experiments on three multi-rater datasets, including LIDC-IDRI, KiTS21, and ISBI 2015, show that VDD improves uncertainty distribution alignment while maintaining competitive segmentation accuracy and 3D structural consistency. These results suggest that prior-anchored residual diffusion can model clinically plausible expert disagreement without sacrificing anatomical fidelity.

---

### Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation

Authors: Zilin Lu, Ruifeng Yuan, Weiwei Cao, Wanxing Chang, Zhongyu Wei, Sinuo Wang, Yong Xia, Ling Zhang, Jianpeng Zhang
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.04022v1

Radiologists highly desire fully automated AI for radiology report generation (R2G), yet existing approaches fall short in clinical utility. Reinforcement learning (RL) holds potential to address these shortcomings, but its adoption in this task remains underexplored. In this paper, we revisit RL in terms of data efficiency and optimization effectiveness for R2G tasks. First, we explore the impact of data quantity and quality on the performance of RL in medical contexts, revealing that data quality plays a more critical role than quantity. To this end, we propose a diagnostic diversity-based data sampling strategy that enables comparable performance with fewer samples. Second, we observe that the majority of tokens in radiology reports are template-like and diagnostically uninformative, whereas the low frequency of clinically critical tokens heightens the risk of being overlooked during optimization. To tackle this, we introduce Diagnostic Token-weighted Policy Optimization (DiTPO), which directly optimizes for clinical accuracy by using a diagnostic F1 score as the reward signal. Unlike standard RL approaches that treat all tokens equally, DiTPO explicitly models the varying importance of different tokens through rule- or gradient-based mechanisms to prioritize clinically relevant content. Extensive experiments on the MIMIC-CXR, IU-Xray, and CheXpert Plus datasets demonstrate that our framework achieves state-of-the-art (SOTA) performance while requiring substantially fewer training samples in RL. Notably, on MIMIC-CXR, our framework attains an F1 score of 0.516 using only 20% of the RL training samples.

---

### Continuous Modal Logical Neural Networks: Modal Reasoning via Stochastic Accessibility

Authors: Antonin Sulc
Published: 2026-03-04
Categories: cs.LO, cs.LG
arXiv: https://arxiv.org/abs/2603.04019v1

We propose Fluid Logic, a paradigm in which modal logical reasoning, temporal, epistemic, doxastic, deontic, is lifted from discrete Kripke structures to continuous manifolds via Neural Stochastic Differential Equations (Neural SDEs). Each type of modal operator is backed by a dedicated Neural SDE, and nested formulas compose these SDEs in a single differentiable graph. A key instantiation is Logic-Informed Neural Networks (LINNs): analogous to Physics-Informed Neural Networks (PINNs), LINNs embed modal logical formulas such as ($\Box$ bounded) and ($\Diamond$ visits\_lobe) directly into the training loss, guiding neural networks to produce solutions that are structurally consistent with prescribed logical properties, without requiring knowledge of the governing equations. The resulting framework, Continuous Modal Logical Neural Networks (CMLNNs), yields several key properties: (i) stochastic diffusion prevents quantifier collapse ($\Box$ and $\Diamond$ differ), unlike deterministic ODEs; (ii) modal operators are entropic risk measures, sound with respect to risk-based semantics with explicit Monte Carlo concentration guarantees; (iii)SDE-induced accessibility provides structural correspondence with classical modal axioms; (iv) parameterizing accessibility through dynamics reduces memory from quadratic in world count to linear in parameters. Three case studies demonstrate that Fluid Logic and LINNs can guide neural networks to produce consistent solutions across diverse domains: epistemic/doxastic logic (multi-robot hallucination detection), temporal logic (recovering the Lorenz attractor geometry from logical constraints alone), and deontic logic (learning safe confinement dynamics from a logical specification).

---

### Fixed-Budget Constrained Best Arm Identification in Grouped Bandits

Authors: Raunak Mukherjee, Sharayu Moharir
Published: 2026-03-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.04007v1

We study fixed budget constrained best-arm identification in grouped bandits, where each arm consists of multiple independent attributes with stochastic rewards. An arm is considered feasible only if all its attributes' means are above a given threshold. The aim is to find the feasible arm with the largest overall mean. We first derive a lower bound on the error probability for any algorithm on this setting. We then propose Feasibility Constrained Successive Rejects (FCSR), a novel algorithm that identifies the best arm while ensuring feasibility. We show it attains optimal dependence on problem parameters up to constant factors in the exponent. Empirically, FCSR outperforms natural baselines while preserving feasibility guarantees.

---

### Training-Free Rate-Distortion-Perception Traversal With Diffusion

Authors: Yuhan Wang, Suzhi Bi, Ying-Jun Angela Zhang
Published: 2026-03-04
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2603.04005v2

The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, reconstruction fidelity, and perceptual quality. While recent neural compression methods have improved perceptual performance, they typically operate at fixed points on the RDP surface, requiring retraining to target different tradeoffs. In this work, we propose a training-free framework that leverages pre-trained diffusion models to traverse the entire RDP surface. Our approach integrates a reverse channel coding (RCC) module with a novel score-scaled probability flow ODE decoder. We theoretically prove that the proposed diffusion decoder is optimal for the distortion-perception tradeoff under AWGN observations and that the overall framework with the RCC module achieves the optimal RDP function in the Gaussian case. Empirical results across multiple datasets demonstrate the framework's flexibility and effectiveness in navigating the ternary RDP tradeoff using pre-trained diffusion models. Our results establish a practical and theoretically grounded approach to adaptive, perception-aware compression.

---

### Discriminative Perception via Anchored Description for Reasoning Segmentation

Authors: Tao Yang, Qing Zhou, Yanliang Li, Qi Wang
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.04002v1

Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization, they are incapable of discriminating whether the reasoning process remains anchored on the referred region or strays into irrelevant context. Lacking this discriminative guidance, the model's reasoning often devolves into unfocused and verbose chains that ultimately fail to disambiguate and perceive the target in complex scenes. This suggests a need to complement the RL objective with Discriminative Perception, an ability to actively distinguish a target from its context. To realize this, we propose DPAD to compel the model to generate a descriptive caption of the referred object, which is then used to explicitly discriminate by contrasting the caption's semantic relevance to the referred object against the wider context. By optimizing for this discriminative capability, the model is forced to focus on the unique attributes of the target, leading to a more converged and efficient reasoning chain. The descriptive caption also serves as an interpretability rationale that aligns with the segmentation. Experiments on the benchmarks confirm the validity of our approach, delivering substantial performance gains, with the cIoU on ReasonSeg increasing by 3.09% and the reasoning chain length decreasing by approximately 42%. Code is available at https://github.com/mrazhou/DPAD

---

### STEM Faculty Perspectives on Generative AI in Higher Education

Authors: Akila de Silva, Isabel Hyo Jung Song, Hui Yang, Shah Rukh Humayoun
Published: 2026-03-04
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.04001v1

Generative artificial intelligence (GenAI) tools are increasingly present in higher education, yet their adoption has been largely student-driven, requiring instructors to respond to technologies already embedded in classroom practices. While some faculty have embraced GenAI for pedagogical purposes such as content generation, assessment support, and curriculum design, others approach these tools with caution, citing concerns about student learning, assessment validity, and academic integrity. Understanding faculty perspectives is therefore essential for informing effective pedagogical strategies and institutional policies. In this paper, we present findings from a focus group study with 29 STEM faculty members at a large public university in the United States. We examine how faculty integrate GenAI into their courses, the benefits and challenges they perceive for student learning, and the institutional support they identify as necessary for effective and responsible adoption. Our findings highlight key patterns in how STEM faculty engage with GenAI, reflecting both active adoption and cautious use. Faculty described a range of pedagogical applications alongside concerns about student learning, assessment, and academic integrity. Overall, the results suggest that effective integration of GenAI in higher education requires rethinking assessment, pedagogy, and institutional governance in addition to technical adoption.

---

### On the Learnability of Offline Model-Based Optimization: A Ranking Perspective

Authors: Shen-Huan Lyu, Rong-Xi Tan, Ke Xue, Yi-Xiao He, Yu Huang, Qingfu Zhang, Chao Qian
Published: 2026-03-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.04000v1

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good predictive accuracy leads to good optimization performance. In this work, we challenge this assumption and study offline MBO from a learnability perspective. We argue that offline optimization is fundamentally a problem of ranking high-quality designs rather than accurate value prediction. Specifically, we introduce an optimization-oriented risk based on ranking between near-optimal and suboptimal designs, and develop a unified theoretical framework that connects surrogate learning to final optimization. We prove the theoretical advantages of ranking over regression, and identify distributional mismatch between the training data and near-optimal designs as the dominant error. Inspired by this, we design a distribution-aware ranking method to reduce this mismatch. Empirical results across various tasks show that our approach outperforms twenty existing methods, validating our theoretical findings. Additionally, both theoretical and empirical results reveal intrinsic limitations in offline MBO, showing a regime in which no offline method can avoid over-optimistic extrapolation.

---

### Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting

Authors: Zailong Tian, Yanzhe Chen, Zhuoheng Han, Lizi Liao
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.03995v1

Low-Rank Adaptation (LoRA) improves downstream performance by restricting task updates to a low-rank parameter subspace, yet how this limited capacity is allocated within a trained adapter remains unclear. Through a geometric and empirical study across multiple tasks and backbones, we find that trained LoRA updates often exhibit an inefficient spectrum: task effects concentrate in a small subset of singular directions, while many remaining components are neutral or detrimental, motivating post-hoc refinement within the learned subspace. We propose Spectral Surgery, a training-free refinement that decomposes a LoRA update with SVD, estimates per-component sensitivity using gradients on a small calibration set, and reweights singular values under a magnitude constraint while keeping the learned directions fixed. Across Llama-3.1-8B and Qwen3-8B on four benchmarks, Spectral Surgery yields consistent gains (up to +4.4 points on CommonsenseQA and +2.4 pass@1 on HumanEval) by adjusting only $\approx 1{,}000$ scalar coefficients. These results demonstrate that SVD-structured, low-cost parameter editing can serve as a practical route to improving trained LoRA adapters in a purely post-hoc manner.

---

### Specialization of softmax attention heads: insights from the high-dimensional single-location model

Authors: M. Sagitova, O. Duranthon, L. Zdeborová
Published: 2026-03-04
Categories: cs.LG, cond-mat.dis-nn
arXiv: https://arxiv.org/abs/2603.03993v2

Multi-head attention enables transformer models to represent multiple attention patterns simultaneously. Empirically, head specialization emerges in distinct stages during training, while many heads remain redundant and learn similar representations. We propose a theoretical model capturing this phenomenon, based on the multi-index and single-location regression frameworks. In the first part, we analyze the training dynamics of multi-head softmax attention under SGD, revealing an initial unspecialized phase followed by a multi-stage specialization phase in which different heads sequentially align with latent signal directions. In the second part, we study the impact of attention activation functions on performance. We introduce the Bayes-softmax attention, which achieves optimal prediction performance in this setting.

---

### Measuring AI R&D Automation

Authors: Alan Chan, Ranay Padarath, Joe Kwon, Hilary Greaves, Markus Anderljung
Published: 2026-03-04
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.03992v3

The automation of AI R&D (AIRDA) could have significant implications, but its extent and ultimate effects remain uncertain. We need empirical data to resolve these uncertainties, but existing data (primarily capability benchmarks) may not reflect real-world automation or capture its broader consequences, such as whether AIRDA accelerates capabilities more than safety progress or whether our ability to oversee AI R&D can keep pace with its acceleration. To address these gaps, this work proposes metrics to track the extent of AIRDA and its effects on AI progress and oversight. The metrics span dimensions such as capital share of AI R&D spending, researcher time allocation, and AI subversion incidents, and could help decision makers understand the potential consequences of AIRDA, implement appropriate safety measures, and maintain awareness of the pace of AI development. We recommend that companies and third parties (e.g. non-profit research organisations) start to track these metrics, and that governments support these efforts.

---

### Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy

Authors: Shramana Dey, Abhirup Banerjee, B. Uma Shankar, Ramachandran Rajalakshmi, Sushmita Mitra
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03991v1

Diabetic Retinopathy (DR) requires timely screening to prevent irreversible vision loss. However, its early detection remains a significant challenge since often the subtle pathological manifestations (lesions) get overlooked due to insufficient annotation. Existing literature primarily focuses on image-level supervision, weakly-supervised localization, and clustering-based representation learning, which fail to systematically annotate unlabeled lesion region(s) for refining the dataset. Expert-driven lesion annotation is labor-intensive and often incomplete, limiting the performance of deep learning models. We introduce Similarity-based Annotation via Feature-space Ensemble (SAFE), a two-stage framework that unifies weak supervision, contrastive learning, and patch-wise embedding inference, to systematically expand sparse annotations in the pathology. SAFE preserves fine-grained details of the lesion(s) under partial clinical supervision. In the first stage, a dual-arm Patch Embedding Network learns semantically structured, class-discriminative embeddings from expert annotated patches. Next, an ensemble of independent embedding spaces extrapolates labels to the unannotated regions based on spatial and semantic proximity. An abstention mechanism ensures trade-off between highly reliable annotation and noisy coverage. Experimental results demonstrate reliable separation of healthy and diseased patches, achieving upto 0.9886 accuracy. The annotation generated from SAFE substantially improves downstream tasks such as DR classification, demonstrating a substantial increase in F1-score of the diseased class and a performance gain as high as 0.545 in Area Under the Precision-Recall Curve (AUPRC). Qualitative analysis, with explainability, confirms that SAFE focuses on clinically relevant lesion patterns; and is further validated by ophthalmologists.

---

### When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models

Authors: Qianpu Chen, Derya Soydaner, Rob Saunders
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.03989v3

When visual evidence is ambiguous, vision models must decide how to interpret face-like patterns. Face pareidolia, the perception of faces in non-face objects, provides a controlled probe of such decisions. We introduce a diagnostic framework that analyzes detection, localization, uncertainty and bias across class, difficulty and emotion. We evaluate six models spanning four representational regimes: vision-language models (VLMs; CLIP-B/32, CLIP-L/14, LLaVA-1.5-7B), pure vision classification (ViT), object detection (YOLOv8), and face detection (RetinaFace). Our results reveal that uncertainty and bias are decoupled: low uncertainty can signal either safe suppression, as in detectors, or extreme over-interpretation, as in VLMs. VLMs exhibit semantic overactivation, systematically interpreting ambiguous non-human regions as Human, with LLaVA over-calling on 73% of non-human pareidolic images, especially for negative emotions. ViT instead follows an uncertainty-as-abstention strategy, remaining diffuse yet largely unbiased. Detection-based models achieve low bias through conservative priors that suppress pareidolia responses even when localization is controlled. Together, these results show that behavior under ambiguity is governed more by representation than thresholds, establishing face pareidolia as a diagnostic of semantic robustness and a source of ambiguity-aware hard negatives for vision models. Code will be released upon publication.

---

### RIVER: A Real-Time Interaction Benchmark for Video LLMs

Authors: Yansong Shi, Qingsong Zhao, Tianxiang Jiang, Xiangyu Zeng, Yi Wang, Limin Wang
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03985v1

The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online video comprehension. RIVER Bench introduces a novel framework comprising Retrospective Memory, Live-Perception, and Proactive Anticipation tasks, closely mimicking interactive dialogues rather than responding to entire videos at once. We conducted detailed annotations using videos from diverse sources and varying lengths, and precisely defined the real-time interactive format. Evaluations across various model categories reveal that while offline models perform well in single question-answering tasks, they struggle with real-time processing. Addressing the limitations of existing models in online video interaction, especially their deficiencies in long-term memory and future perception, we proposed a general improvement method that enables models to interact with users more flexibly in real time. We believe this work will significantly advance the development of real-time interactive video understanding models and inspire future research in this emerging field. Datasets and code are publicly available at https://github.com/OpenGVLab/RIVER.

---

### GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery

Authors: Lifan Jiang, Yuhang Pei, oxi Wu, Yan Zhao, Tianrun Wu, Shulong Yu, Lihui Zhang, Deng Cai
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.03983v1

Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable solution due to the prohibitive cost of reasoning-oriented data and domain-specific challenges like overhead viewpoints. We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation. GeoSeg couples MLLM reasoning with precise localization via: (i) bias-aware coordinate refinement to correct systematic grounding shifts and (ii) a dual-route prompting mechanism to fuse semantic intent with fine-grained spatial cues. We also introduce GeoSeg-Bench, a diagnostic benchmark of 810 image--query pairs with hierarchical difficulty levels. Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.

---

### Right in Time: Reactive Reasoning in Regulated Traffic Spaces

Authors: Simon Kohaut, Benedict Flade, Julian Eggert, Kristian Kersting, Devendra Singh Dhami
Published: 2026-03-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.03977v1

Exact inference in probabilistic First-Order Logic offers a promising yet computationally costly approach for regulating the behavior of autonomous agents in shared traffic spaces. While prior methods have combined logical and probabilistic data into decision-making frameworks, their application is often limited to pre-flight checks due to the complexity of reasoning across vast numbers of possible universes. In this work, we propose a reactive mission design framework that jointly considers uncertain environmental data and declarative, logical traffic regulations. By synthesizing Probabilistic Mission Design (ProMis) with reactive reasoning facilitated by Reactive Circuits (RC), we enable online, exact probabilistic inference over hybrid domains. Our approach leverages the Frequency of Change inherent in heterogeneous data streams to subdivide inference formulas into memoized, isolated tasks, ensuring that only the specific components affected by new sensor data are re-evaluated. In experiments involving both real-world vessel data and simulated drone traffic in dense urban scenarios, we demonstrate that our approach provides orders of magnitude in speedup over ProMis without reactive paradigms. This allows intelligent transportation systems, such as Unmanned Aircraft Systems (UAS), to actively assert safety and legal compliance during operations rather than relying solely on preparation procedures.

---

### Phi-4-reasoning-vision-15B Technical Report

Authors: Jyoti Aneja, Michael Harrison, Neel Joshi, Tyler LaBonte, John Langford, Eduardo Salinas
Published: 2026-03-04
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.03975v1

We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model, and share the motivations, design choices, experiments, and learnings that informed its development. Our goal is to contribute practical insight to the research community on building smaller, efficient multimodal reasoning models and to share the result of these learnings as an open-weight model that is good at common vision and language tasks and excels at scientific and mathematical reasoning and understanding user interfaces. Our contributions include demonstrating that careful architecture choices and rigorous data curation enable smaller, open-weight multimodal models to achieve competitive performance with significantly less training and inference-time compute and tokens. The most substantial improvements come from systematic filtering, error correction, and synthetic augmentation -- reinforcing that data quality remains the primary lever for model performance. Systematic ablations show that high-resolution, dynamic-resolution encoders yield consistent improvements, as accurate perception is a prerequisite for high-quality reasoning. Finally, a hybrid mix of reasoning and non-reasoning data with explicit mode tokens allows a single model to deliver fast direct answers for simpler tasks and chain-of-thought reasoning for complex problems.

---

### Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction

Authors: Soochul Park, Yeon Ju Lee
Published: 2026-03-04
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.03973v1

Diffusion models achieve state-of-the-art image quality. However, sampling is costly at inference time because it requires a large number of function evaluations (NFEs). To reduce NFEs, classical ODE numerical methods have been adopted. Yet, the choice of prediction type and integration domain leads to different sampling behaviors. To address these issues, we introduce Dual-Solver, which generalizes multistep samplers through learnable parameters that continuously (i) interpolate among prediction types, (ii) select the integration domain, and (iii) adjust the residual terms. It retains the standard predictor-corrector structure while preserving second-order local accuracy. These parameters are learned via a classification-based objective using a frozen pretrained classifier (e.g., MobileNet or CLIP). For ImageNet class-conditional generation (DiT, GM-DiT) and text-to-image generation (SANA, PixArt-$α$), Dual-Solver improves FID and CLIP scores in the low-NFE regime ($3 \le$ NFE $\le 9$) across backbones.

---

### No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason

Authors: Michael Jülich
Published: 2026-03-04
Categories: cs.CY, cs.AI, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2603.03971v4

Generative AI can convert uncertainty into authoritative-seeming verdicts, displacing the justificatory work on which democratic epistemic agency depends. As a corrective, I propose a Brouwer-inspired assertibility constraint for responsible AI: in high-stakes domains, systems may assert or deny claims only if they can provide a publicly inspectable and contestable certificate of entitlement; otherwise they must return Undetermined. This constraint yields a three-status interface semantics (Asserted, Denied, Undetermined) whose statuses mark entitlement to categorical speech rather than truth values of the underlying world-claim. The framework distinguishes internal entitlement from public standing while connecting them through the certificate as a boundary object. Philosophically, it develops a form of applied intuitionism: resistance to unwarranted completeness becomes a norm of public machine speech, under which categorical commitment requires exhibited and contestable entitlement. I operationalize the constraint through structured certificates, decision-layer gates for threshold and argmax predicates, and a reason-coded output contract. A design lemma shows that, under a refutation-soundness condition on the contractually specified negative side, certificate-sound binary totality presupposes witnessed decidability on the declared scope. Under the output contract, Undetermined is therefore not a tunable reject option but a mandatory status whenever the available certificates do not uniquely license assertion or denial. By making outputs answerable to contestable warrants rather than confidence alone, the paper aims to preserve epistemic agency where automated speech enters public justification.

---

### Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy

Authors: Sule Ozturk Birim, Fabrizio Marozzo, Yigit Kazancoglu
Published: 2026-03-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.03970v2

Generative artificial intelligence (GenAI) is increasingly being integrated into complex business workflows, fundamentally shifting the boundaries of managerial decision-making. However, the reliability of its strategic advice in ambiguous business contexts remains a critical knowledge gap. To address this gap, this study compares multiple GenAI models in their ability to detect ambiguity, examines whether a systematic ambiguity-resolution process improves response quality, and investigates their susceptibility to sycophantic behavior when confronted with flawed managerial directives. Using a novel four-dimensional business ambiguity taxonomy, we conducted a human-in-the-loop experiment across strategic, tactical, and operational scenarios. The resulting decisions were assessed through a human-validated automated evaluation framework based on agreement, actionability, justification quality, and constraint adherence. The results show that our approach not only distinguishes different types of ambiguity, but also reveals how ambiguity resolution systematically changes model behavior. In particular, resolving ambiguities improved decision quality across all managerial levels, with the strongest gains observed in constraint adherence. The analysis further showed that sycophantic behavior is not uniform across models: some models challenged flawed assumptions, whereas others tended to comply with them. This study contributes to the bounded rationality literature by positioning GenAI as a cognitive scaffold that can detect and resolve ambiguities managers might overlook, while demonstrating that its artificial limitations require human oversight to ensure its reliability as a strategic partner.

---

### Scaling Dense Event-Stream Pretraining from Visual Foundation Models

Authors: Zhiwen Chen, Junhui Hou, Zhiyu Zhu, Jinjian Wu, Guangming Shi
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03969v1

Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset size, semantic richness, and application scope. To mitigate this dilemma, we launch a novel self-supervised pretraining method that distills visual foundation models (VFMs) to push the boundaries of event representation at scale. Specifically, we curate an extensive synchronized image-event collection to amplify cross-modal alignment. Nevertheless, due to inherent mismatches in sparsity and granularity between image-event domains, existing distillation paradigms are prone to semantic collapse in event representations, particularly at high resolutions. To bridge this gap, we propose to extend the alignment objective to semantic structures provided off-the-shelf by VFMs, indicating a broader receptive field and stronger supervision. The key ingredient of our method is a structure-aware distillation loss that grounds higher-quality image-event correspondences for alignment, optimizing dense event representations. Extensive experiments demonstrate that our approach takes a great leap in downstream benchmarks, significantly surpassing traditional methods and existing pretraining techniques. This breakthrough manifests in enhanced generalization, superior data efficiency and elevated transferability.

---

### UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization

Authors: Qianfeng Yang, Qiyuan Guan, Xiang Chen, Jiyu Jin, Guiyue Jin, Jiangxin Dong
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03967v1

Despite significant progress has been made in image deraining, we note that most existing methods are often developed for only specific types of rain degradation and fail to generalize across diverse real-world rainy scenes. How to effectively model different rain degradations within a universal framework is important for real-world image deraining. In this paper, we propose UniRain, an effective unified image deraining framework capable of restoring images degraded by rain streak and raindrop under both daytime and nighttime conditions. To better enhance unified model generalization, we construct an intelligent retrieval augmented generation (RAG)-based dataset distillation pipeline that selects high-quality training samples from all public deraining datasets for better mixed training. Furthermore, we incorporate a simple yet effective multi-objective reweighted optimization strategy into the asymmetric mixture-of-experts (MoE) architecture to facilitate consistent performance and improve robustness across diverse scenes. Extensive experiments show that our framework performs favorably against the state-of-the-art models on our proposed benchmarks and multiple public datasets.

---

### BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft

Authors: Hengquan Guo
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.03964v2

We present \textbf{BLOCK}, an open-source bi-stage character-to-skin pipeline that generates pixel-perfect Minecraft skins from arbitrary character concepts. BLOCK decomposes the problem into (i) a \textbf{3D preview synthesis stage} driven by a large multimodal model (MLLM) with a carefully designed prompt-and-reference template, producing a consistent dual-panel (front/back) oblique-view Minecraft-style preview; and (ii) a \textbf{skin decoding stage} based on a fine-tuned FLUX.2 model that translates the preview into a skin atlas image. We further propose \textbf{EvolveLoRA}, a progressive LoRA curriculum (text-to-image $\rightarrow$ image-to-image $\rightarrow$ preview-to-skin) that initializes each phase from the previous adapter to improve stability and efficiency. BLOCK is released with all prompt templates and fine-tuned weights to support reproducible character-to-skin generation.

---

### TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction

Authors: Hantong Feng, Yonggang Wu, Duxin Chen, Wenwu Yu
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.03963v1

Dynamic link prediction plays a crucial role in diverse applications including social network analysis, communication forecasting, and financial modeling. While recent Transformer-based approaches have demonstrated promising results in temporal graph learning, their performance remains limited when capturing complex multi-scale temporal dynamics. In this paper, we propose TFWaveFormer, a novel Transformer architecture that integrates temporal-frequency analysis with multi-resolution wavelet decomposition to enhance dynamic link prediction. Our framework comprises three key components: (i) a temporal-frequency coordination mechanism that jointly models temporal and spectral representations, (ii) a learnable multi-resolution wavelet decomposition module that adaptively extracts multi-scale temporal patterns through parallel convolutions, replacing traditional iterative wavelet transforms, and (iii) a hybrid Transformer module that effectively fuses local wavelet features with global temporal dependencies. Extensive experiments on benchmark datasets demonstrate that TFWaveFormer achieves state-of-the-art performance, outperforming existing Transformer-based and hybrid models by significant margins across multiple metrics. The superior performance of TFWaveFormer validates the effectiveness of combining temporal-frequency analysis with wavelet decomposition in capturing complex temporal dynamics for dynamic link prediction tasks.

---

### ProFound: A moderate-sized vision foundation model for multi-task prostate imaging

Authors: Yipei Wang, Yinsong Xu, Weixi Yi, Shaheer Ullah Saeed, Natasha Thorley, Alexander Ng, Yukun Zhou, Wen Yan, Dean Barratt, Shonit Punwani, Veeru Kasivisvanathan, Mark Emberton et al.
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03961v1

Many diagnostic and therapeutic clinical tasks for prostate cancer increasingly rely on multi-parametric MRI. Automating these tasks is challenging because they necessitate expert interpretations, which are difficult to scale to capitalise on modern deep learning. Although modern automated systems achieve expert-level performance in isolated tasks, their general clinical utility remains limited by the requirement of large task-specific labelled datasets. In this paper, we present ProFound, a domain-specialised vision foundation model for volumetric prostate mpMRI. ProFound is pre-trained using several variants of self-supervised approaches on a diverse, multi-institutional collection of 5,000 patients, with a total of over 22,000 unique 3D MRI volumes (over 1,800,000 2D image slices). We conducted a systematic evaluation of ProFound across a broad spectrum of $11$ downstream clinical tasks on over 3,000 independent patients, including prostate cancer detection, Gleason grading, lesion localisation, gland volume estimation, zonal and surrounding structure segmentation. Experimental results demonstrate that finetuned ProFound consistently outperforms or remains competitive with state-of-the-art specialised models and existing medical vision foundation models trained/finetuned on the same data.

---

### Structural Action Transformer for 3D Dexterous Manipulation

Authors: Xiaohan Lei, Min Wang, Bohong Weng, Wengang Zhou, Houqiang Li
Published: 2026-03-04
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.03960v1

Achieving human-level dexterity in robots via imitation learning from heterogeneous datasets is hindered by the challenge of cross-embodiment skill transfer, particularly for high-DoF robotic hands. Existing methods, often relying on 2D observations and temporal-centric action representation, struggle to capture 3D spatial relations and fail to handle embodiment heterogeneity. This paper proposes the Structural Action Transformer (SAT), a new 3D dexterous manipulation policy that challenges this paradigm by introducing a structural-centric perspective. We reframe each action chunk not as a temporal sequence, but as a variable-length, unordered sequence of joint-wise trajectories. This structural formulation allows a Transformer to natively handle heterogeneous embodiments, treating the joint count as a variable sequence length. To encode structural priors and resolve ambiguity, we introduce an Embodied Joint Codebook that embeds each joint's functional role and kinematic properties. Our model learns to generate these trajectories from 3D point clouds via a continuous-time flow matching objective. We validate our approach by pre-training on large-scale heterogeneous datasets and fine-tuning on simulation and real-world dexterous manipulation tasks. Our method consistently outperforms all baselines, demonstrating superior sample efficiency and effective cross-embodiment skill transfer. This structural-centric representation offers a new path toward scaling policies for high-DoF, heterogeneous manipulators.

---

### LoRA-MME: Multi-Model Ensemble of LoRA-Tuned Encoders for Code Comment Classification

Authors: Md Akib Haider, Ahsan Bulbul, Nafis Fuad Shahid, Aimaan Ahmed, Mohammad Ishrak Abedin
Published: 2026-03-04
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2603.03959v4

Code comment classification is a critical task for automated software documentation and analysis. In the context of the NLBSE'26 Tool Competition, we present LoRA-MME, a Multi-Model Ensemble architecture utilizing Parameter-Efficient Fine-Tuning (PEFT). Our approach addresses the multi-label classification challenge across Java, Python, and Pharo by combining the strengths of four distinct transformer encoders: UniXcoder, CodeBERT, GraphCodeBERT, and CodeBERTa. By independently fine-tuning these models using Low-Rank Adaptation(LoRA) and aggregating their predictions via a learned weighted ensemble strategy, we maximize classification performance without the memory overhead of full model fine-tuning. Our tool achieved an F1 Weighted score of 0.7906 and a Macro F1 of 0.6867 on the test set. However, the computational cost of the ensemble resulted in a final submission score of 41.20%, highlighting the trade-off between semantic accuracy and inference efficiency.

---

### Towards Generalized Multimodal Homography Estimation

Authors: Jinkun You, Jiaxin Cheng, Jie Zhang, Yicong Zhou
Published: 2026-03-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.03956v1

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address this issue, we propose a training data synthesis method that generates unaligned image pairs with ground-truth offsets from a single input image. Our approach renders the image pairs with diverse textures and colors while preserving their structural information. These synthetic data empower the trained model to achieve greater robustness and improved generalization across various domains. Additionally, we design a network to fully leverage cross-scale information and decouple color information from feature representations, thus improving estimation accuracy. Extensive experiments show that our training data synthesis method improves generalization performance. The results also confirm the effectiveness of the proposed network.

---

### GIPO: Gaussian Importance Sampling Policy Optimization

Authors: Chengxuan Lu, Zhenquan Zhang, Shukuan Wang, Qunzhi Lin, Baigui Sun, Yang Liu
Published: 2026-03-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.03955v3

Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor data efficiency, particularly in settings where interaction data are scarce and quickly become outdated. To address this challenge, GIPO (Gaussian Importance sampling Policy Optimization) is proposed as a policy optimization objective based on truncated importance sampling, replacing hard clipping with a log-ratio-based Gaussian trust weight to softly damp extreme importance ratios while maintaining non-zero gradients. Theoretical analysis shows that GIPO introduces an implicit, tunable constraint on the update magnitude, while concentration bounds guarantee robustness and stability under finite-sample estimation. Experimental results show that GIPO achieves state-of-the-art performance among clipping-based baselines across a wide range of replay buffer sizes, from near on-policy to highly stale data, while exhibiting superior bias--variance trade-off, high training stability and improved sample efficiency. Code is available at https://github.com/distanceLu/GIPO.

---

### RVN-Bench: A Benchmark for Reactive Visual Navigation

Authors: Jaewon Lee, Jaeseok Heo, Gunmin Lee, Howoong Jun, Jeongwoo Oh, Songhwai Oh
Published: 2026-03-04
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.03953v2

Safe visual navigation is critical for indoor mobile robots operating in cluttered environments. Existing benchmarks, however, often neglect collisions or are designed for outdoor scenarios, making them unsuitable for indoor visual navigation. To address this limitation, we introduce the reactive visual navigation benchmark (RVN-Bench), a collision-aware benchmark for indoor mobile robots. In RVN-Bench, an agent must reach sequential goal positions in previously unseen environments using only visual observations and no prior map, while avoiding collisions. Built on the Habitat 2.0 simulator and leveraging high-fidelity HM3D scenes, RVN-Bench provides large-scale, diverse indoor environments, defines a collision-aware navigation task and evaluation metrics, and offers tools for standardized training and benchmarking. RVN-Bench supports both online and offline learning by offering an environment for online reinforcement learning, a trajectory image dataset generator, and tools for producing negative trajectory image datasets that capture collision events. Evaluations demonstrate that policies trained on RVN-Bench generalize effectively across unseen simulated environments. Furthermore, initial physical experiments using a Jackal UGV indicate promising sim-to-real transfer. Code and additional materials are available at: https://sequor-robotics-research.github.io/projects/RVN-Bench/.

---

### Lang2Str: Two-Stage Crystal Structure Generation with LLMs and Continuous Flow Models

Authors: Cong Liu, Chengyue Gong, Zhenyu Liu, Jiale Zhao, Yuxuan Zhang
Published: 2026-03-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.03946v1

Generative models hold great promise for accelerating material discovery but are often limited by their inflexible single-stage generative process in designing valid and diverse materials. To address this, we propose a two-stage generative framework, Lang2Str, that combines the strengths of large language models (LLMs) and flow-based models for flexible and precise material generation. Our method frames the generative process as a conditional generative task, where an LLM provides high-level conditions by generating descriptions of material unit cells' geometric layouts and properties. These descriptions, informed by the LLM's extensive background knowledge, ensure reasonable structure designs. A conditioned flow model then decodes these textual conditions into precise continuous coordinates and unit cell parameters. This staged approach combines the structured reasoning of LLMs and the distribution modeling capabilities of flow models. Experimental results show that our method achieves competitive performance on \textit{ab initio} material generation and crystal structure prediction tasks, with generated structures exhibiting closer alignment to ground truth in both geometry and energy levels, surpassing state-of-the-art models. The flexibility and modularity of our framework further enable fine-grained control over the generation process, potentially leading to more efficient and customizable material design.

---

### How Predicted Links Influence Network Evolution: Disentangling Choice and Algorithmic Feedback in Dynamic Graphs

Authors: Mathilde Perez, Raphaël Romero, Jefrey Lijffijt, Charlotte Laclau
Published: 2026-03-04
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2603.03945v1

Link prediction models are increasingly used to recommend interactions in evolving networks, yet their impact on network structure is typically assessed from static snapshots. In particular, observed homophily conflates intrinsic interaction tendencies with amplification effects induced by network dynamics and algorithmic feedback. We propose a temporal framework based on multivariate Hawkes processes that disentangles these two sources and introduce an instantaneous bias measure derived from interaction intensities, capturing current reinforcement dynamics beyond cumulative metrics. We provide a theoretical characterization of the stability and convergence of the induced dynamics, and experiments show that the proposed measure reliably reflects algorithmic feedback effects across different link prediction strategies.

---

### SCP: Spatial Causal Prediction in Video

Authors: Yanguang Zhao, Jie Yang, Shengqiong Wu, Shutong Hu, Hongbo Qiu, Yu Wang, Guijia Zhang, Tan Kai Ze, Hao Fei, Chia-Wen Lin, Mong-Li Lee, Wynne Hsu
Published: 2026-03-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.03944v2

Spatial reasoning, the ability to understand spatial relations, causality, and dynamic evolution, is central to human intelligence and essential for real-world applications such as autonomous driving and robotics. Existing studies, however, primarily assess models on visible spatio-temporal understanding, overlooking their ability to infer unseen past or future spatial states. In this work, we introduce Spatial Causal Prediction (SCP), a new task paradigm that challenges models to reason beyond observation and predict spatial causal outcomes. We further construct SCP-Bench, a benchmark comprising 2,500 QA pairs across 1,181 videos spanning diverse viewpoints, scenes, and causal directions, to support systematic evaluation. Through comprehensive experiments on {23} state-of-the-art models, we reveal substantial gaps between human and model performance, limited temporal extrapolation, and weak causal grounding. We further analyze key factors influencing performance and propose perception-enhancement and reasoning-guided strategies toward advancing spatial causal intelligence. The project page is https://guangstrip.github.io/SCP-Bench.

---