# Research Papers — 2026-05 · bundle page 163 of 326

> Full-text markdown of papers #8101–8150 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/163
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/162.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/164.md)

### Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy

Authors: Youngmok Ha, Viktor Schlegel, Yidan Sun, Anil Anthony Bharath
Published: 2026-05-16
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2605.16812v4

While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent randomization requirements often lead to severe degradation in data representation utility. This degradation stems from the task-agnostic nature of conventional LDP mechanisms, which perturb all dimensions without accounting for their relative importance to the downstream objective. To address this issue, we propose a novel approach that mitigates noise in task-relevant subspaces of the data representation. Our method identifies task-critical subspaces via the Jacobian of a public downstream model, selectively attenuates noise along these directions, and reshapes the isotropic noise of standard LDP mechanisms into an anisotropic distribution. The resulting mechanism preserves the privacy guarantee of the underlying LDP randomizer while heterogeneously modulating the impact of noise across task directions, thereby substantially enhancing data utility. The approach is applicable to both linear and nonlinear models and can be seamlessly integrated with existing LDP mechanisms. Extensive experiments on CIFAR-10-C under brightness corruption at the highest severity level demonstrate that integrating our approach improves classification accuracy by approximately 8 percentage points for Laplace and 20 percentage points for PrivUnit variants at $ε=7.5$. The source code is available at https://github.com/ymha/jacobian-anr-ldp.

---

### Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy

Authors: Youngmok Ha, Viktor Schlegel, Yidan Sun, Anil Anthony Bharath
Published: 2026-05-16
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2605.16812v2

While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent noise injection requirement often leads to severe degradation in data utility. This degradation stems from the task-agnostic nature of conventional LDP mechanisms, which inject noise uniformly across all dimensions regardless of their relative importance to the downstream objective. To address this issue, we propose a novel approach that mitigates noise in task-relevant subspaces of the data representation. Our method identifies task-critical subspaces via the Jacobian matrix of the public downstream model, selectively attenuates noise along those dimensions, and reshapes the isotropic noise of standard LDP into an anisotropic distribution. This method preserves the uniform per-dimension privacy budget while heterogeneously modulating noise impact across dimensions, thereby substantially enhancing data utility. Furthermore, our approach generalizes to both linear and non-linear models and integrates seamlessly with existing mechanisms. Extensive experiments on CIFAR-10-C (Brightness corruption at the highest severity level 5) demonstrate that integrating our approach improves the utility of PrivUnit2 and PrivUnitG by approximately 20\% at $ε=7.5$. The source code is available at https://github.com/ymha/jacobian-anr-ldp.

---

### Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending

Authors: Jingqi Hou, Hongtian Wang
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16810v1

We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable typography and place an occluding object over the intended text region. This setting remains difficult for existing text-to-image generators: the occluder often drifts away from the text, while the text may be distorted or appear to float on top of the occluding object. To address this problem, we propose a restarted dual-stream inference framework that decouples text-layout preservation from occluder insertion. A Base Stream provides a clean typographic reference and same-step key/value (K/V) features, while the Edit Stream is conditioned on the occlusion prompt. We further adopt the spectral glyph-prior idea from FreeText and adapt it to stabilize the target text structure during early-to-mid denoising. In the reasoning pass, our method localizes the target text, estimates a text-band region from token-conditioned attention and glyph support, and derives an anchor-aware hard fusion mask for the occluder. In the final edit pass, generation restarts from the same initial noise and applies hard mask-guided image-token K/V replacement at selected attention sites, preserving the Base layout outside the mask while injecting the occluder appearance from the Edit Stream inside the mask. Experiments on representative occluded text scenarios demonstrate substantially improved text readability and competitive occlusion alignment, yielding more stable object-on-text compositions without any model fine-tuning.

---

### Informative Graph Structure Learning

Authors: Shen Han, Zhiyao Zhou, Jiawei Chen, Sheng Zhou, Canghong Jin, Hai Lin, Da Zhong Li, Bingde Hu, Can Wang
Published: 2026-05-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.16809v1

The quality of graph-structured data is fundamental to the success of modern graph analysis techniques such as Graph Neural Networks (GNNs). However, real-world graph data is often suboptimal, suffering from issues such as noise and incomplete connections. Graph Structure Learning (GSL) has emerged as a promising technique that adaptively optimizes node connections. However, we observe that the effectiveness of GSL often comes at the cost of a dramatic expansion in edge count, resulting in significant storage and computational overhead. In this work, we reveal that this limitation stems from the prevalent use of similarity-based edge construction, which predominantly connects highly similar neighbors based on their embeddings, introducing substantial structure redundancy. To address this, we propose a novel Informative Graph Structure Learning method (InGSL), which jointly considers both similarity and diversity in edge construction by incorporating a mutual-information-guided learning strategy. Notably, InGSL serves as a plug-in module that can be seamlessly integrated into existing GSL frameworks. Through extensive experiments on six representative GSL methods, we demonstrate that InGSL achieves significant performance improvements at a reduced number of edges.

---

### DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion

Authors: Yuhan Ping, Yuan Liu, Xiaoxiao Long, Peng Wang, Junhui Hou, Jianyi Zheng, Jia Pan, Xin Li, Cheng Lin
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16807v1

In this paper, we introduce \textit{DecoRec}, a novel system designed to elevate single-view 2D images to a decomposed 3D scene mesh. Current methods for single-view scene reconstruction typically rely on object retrieval or the regression of coarse 3D voxels or surfaces, leading to inaccuracies in capturing the appearance and geometry of the input image. The lack of high-quality large-scale scene-level datasets further complicates direct 3D scene generation from single-view images. To achieve high-quality 3D scene generation from a single-view image, DecoRec takes advantage of recent diffusion-based single-view object reconstruction methods to reconstruct individual objects separately. Subsequently, a refinement pipeline is proposed to effectively merge these reconstructed objects, enhancing appearance and geometry through a differentiable rendering technique and diffusion-guided refinement. Our results demonstrate that DecoRec facilitates high-quality single-view scene reconstruction in both geometry and novel synthesis, offering significant benefits for downstream applications like room interior design.

---

### Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning

Authors: Wen-Hsin Tsai, Chia-Ming Lee, Yuk-Ying Tung
Published: 2026-05-16
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.16806v1

Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student collaboration satisfaction remains challenging. A critical barrier is modality degradation: in educational deployments, individual modalities such as eye gaze exhibit inconsistent informativeness across student cohorts, causing implicit attention-based fusion to produce brittle multimodal representations. We propose the Affinity-Aligned Multimodal Learning Analytics (AAMLA) framework, whose core contribution is the Cross-modal Affinity-guided Modality Alignment (CAMA) module, which explicitly models inter-modal relationships via affinity matrices and enforces cross-modal consistency through contrastive learning, enabling adaptive suppression of uninformative modalities without discarding them. AAMLA further applies modality-specific projection layers to map heterogeneous features, including facial action units, head pose, eye gaze, and interaction trace logs, into a unified semantic space prior to alignment. Experiments on 50 middle school students in the EcoJourneys collaborative learning environment demonstrate consistent improvements over unimodal baselines and prior cross-attention approaches under standard and modality degradation conditions, with SHAP and t-SNE analyses confirming that CAMA produces robust, interpretable cross-modal representations for student collaboration modeling.

---

### NeuroLiDAR: Adaptive Frame Rate Depth Sensing via Neuromorphic Event-LiDAR Fusion

Authors: Darshana Rathnayake, Dulanga Weerakoon, Meera Radhakrishnan, Archan Misra
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16805v1

LiDARs are widely used for 3D depth reconstruction, but their performance is often limited by inherent hardware constraints that impose trade-offs between range, spatial resolution, and frame rate. Many LiDAR systems typically operate at low frame rates (e.g., 5-10 Hz), prioritizing long-range sensing over responsiveness to rapid scene changes. We present NeuroLiDAR, an adaptive depth sensing framework that achieves effective frame rates of up to $\approx$66 Hz by fusing temporally sparse LiDAR data with temporally dense inputs from neuromorphic event cameras. NeuroLiDAR integrates two components: event-based keyframe detection and event-guided depth extrapolation, to dynamically adjust the sensing rate in response to scene dynamics. To evaluate our approach, we introduce ELiDAR, a dataset spanning outdoor and indoor scenarios, and show that NeuroLiDAR reduces depth reconstruction error by $\approx$29\% in RMSE while achieving adaptive frame rates between 27.8-47.3 Hz. Our code and dataset are available at https://github.com/darshanakgr/neurolidar.

---

### FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation

Authors: Ramakrishnan Sathyavageeswaran
Published: 2026-05-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.16800v1

Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: different layers contribute unequally to task adaptation. We address this with a lightweight engineering solution: before fine-tuning begins, run eight calibration backward passes, compute the gradient variance of each LoRA-B matrix as a proxy for layer informativeness, and redistribute the rank budget proportionally. The resulting adapter is a standard LoRA with a per-layer rank pattern - no new parameters, no training overhead, no changes to serving infrastructure. We implement this via an efficient approximation of the empirical Fisher Information Matrix (eFIM) diagonal, restricted to LoRA adapter matrices only, which reduces memory cost by approximately 256x compared to full-model Fisher estimation. On GLUE with DeBERTa-v3-base, FIM-LoRA matches LoRA (88.6 vs. 88.7) at the same parameter budget, and on commonsense reasoning with LLaMA-3-8B reaches 68.5 vs. 68.7 for LoRA. The per-layer rank maps are interpretable: value projections and early-to-middle layers consistently receive higher rank, consistent with established findings on transformer layer roles.

---

### Cross-Domain Molecular Relational Learning: Leveraging Chemical Structure-Activity Analysis

Authors: Peiliang Zhang, Jingling Yuan, Shiqing Wu, Mengqing Hu, Chao Che, Yongjun Zhu, Lin Li
Published: 2026-05-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.16799v2

Recent advances in molecular representation integrates molecular topological and visual modalities, opening new avenues for precise Molecular Relational Learning (MRL). Existing MRL methods focus on intra-domain modeling, and their inherent domain-closed effect limits applicability to molecular science, particularly in elucidating cross-domain interaction mechanisms. Consequently, the imperative for Cross-Domain Molecular Relational Learning has become increasingly pressing. Benefiting from structure-activity analysis, we propose the Domain Adversarial Training Network with Structural-Semantic Transfer Discrepancy (DisTrans) to optimize cross-domain adaptive representation for molecular structures and visual images. 1) We employ the gradient reversal strategy based on substructure topological discrepancies between domains to learn the domain dependence of molecular structures. This strategy guides the model to adapt to the structural adjacency patterns in the target domain, generating domain-separable structural representations. 2) We apply the cross-domain representation guidance mechanism to align the functional-group semantic information between the source and target domains, learning cross-domain consistency information. The experimental results in two typical cross-domain strategies demonstrate that DisTrans outperforms 16 baseline methods, maintaining satisfactory performance even under pronounced inter-domain discrepancy.

---

### EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices

Authors: Liuchuan Yu, Erdem Murat, Beichen Wang, Yan Zeng, Tingting Luo, Huizhen Zhou, Shanghao Li, Huining Feng, Zhigen Zhao, Ning Yang, Ke Jing, Yunhao Liu et al.
Published: 2026-05-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2605.16797v1

Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone, iPhone, iPad, smart glasses, or extended reality (XR) headset, exposes a different SDK, a different policy on raw camera access, and different limitations on external USB cameras and on-device tracking. Synchronized ego-view and wrist-view capture is therefore typically obtained by either committing to a single proprietary platform or building one-off rigs that do not transfer across devices. To address this gap, we present EgoKit, a toolkit that exposes the same egocentric recording workflow across six heterogeneous host devices. Across all supported devices, EgoKit presents the same recording interaction and produces locally stored video with a uniform log format; on XR headsets, it additionally logs head pose and OpenXR-standard 26-joint hand tracking aligned to the video streams. The companion accessories, including two wrist cameras with mounts, a head strap, and a USB-C hub, add wrist-view capture to any supported host without custom hardware fabrication. EgoKit is available at \url{https://egokit.chuange.org/}.

---

### Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy

Authors: Maria Bulychev, Neil G. Marchant, Benjamin I. P. Rubinstein
Published: 2026-05-16
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2605.16796v1

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are clearly motivated to steal copyrighted material or circumvent legislated deepfake protections. In this work, we make a simple-yet-powerful observation: that such attacks on watermarking-like watermarks themselves-seek an imperceptible change to an input image (now already watermarked) that will trigger a detector. This analogy comparing watermark attacks to watermarking itself is highly suggestive: that watermarks could be used to attack watermarks. Our first contribution validates this hypothesis. In rigorous experiments spanning 96 combinations of dataset, victim, and attack watermarks, we show that simply re-watermarking an already watermarked image reliably suppresses the original signal, without requiring gradients, surrogate models, or detection keys. Our second contribution is a simple classifier for detecting the presence and identity of an existing watermark in a given image. Surprisingly, experimental findings demonstrate outstanding overall accuracies 0.878-0.953. This result is of independent interest as a security vulnerability: research shows that method-specific attacks achieve substantially stronger removal than black-box attacks. Taken together, watermark identification combined with re-watermarking successfully reduces bit accuracy by at least 25% and up to 48%. Our work constitutes a cheap, generic, and highly effective attack pipeline, calling into question the reliability of current watermarking schemes to such a simple attack, as well as the value of existing sophisticated attacks.

---

### 3DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulation

Authors: Hwidong Kim, Yunho Kim, Tae-Kyun Kim
Published: 2026-05-16
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2605.16795v1

Video generative models have made remarkable progress, yet they often yield visual artifacts that violate grounding in physical dynamics. Recent works such as PhysGen3D tackle single image-to-3D physics through mesh reconstruction and Physically-Based Rendering, but challenges remain in modeling fluid dynamics, multi-object interactions and photorealism. This work introduces 3DPhysVideo, a novel training-free pipeline that generates physically realistic videos from a single image. We repurpose an off-the-shelf video model for two stages. First, we use it as a novel view synthesizer to reconstruct complete 360-degree 3D scene geometry by guiding the image-to-video (I2V) flow model with rendered point clouds. Second, after applying physics solvers to this geometry, the physically simulated point cloud is used to guide the same I2V flow model to synthesize final, high-quality videos. Consistency-Guided Flow SDE, which decomposes the predicted velocity of the I2V flow model into denoising and consistency bias, enforces consistency to the conditional inputs, allowing us to effectively repurpose the model for both 3D reconstruction and simulation-guided video generation. In the diverse experiments including multi-objects, and fluid interaction scenes, our method successfully bridges the gap from single-images to physically plausible videos, while remaining efficient to run on a single consumer GPU. It outperforms state-of-the-art baselines on GPT-based scores, VideoPhy benchmark and human evaluation.

---

### PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting

Authors: Yangyou Liu, Zezhi Shao, Xinyu Chen, Hu Chen, Fei Wang, Yuankai Wu
Published: 2026-05-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.16793v2

Time series forecasting under non-stationarity faces a fundamental tension between capturing stable representations and adapting to distribution shifts. Existing methods implicitly rely on static historical assumptions, leading to a critical failure mode we term Phase Amnesia, where models become blind to the evolving global context. To resolve this, we formalize non-stationary dynamics through three physical hypotheses: wold decomposition, dynamical phase evolution, and heteroscedastic manifold generation. These principles inspire PULSE, a physics-informed, plug-and-play framework adopting a Disentangle--Evolve--Simulate design philosophy. Specifically, PULSE utilizes phase-anchored disentanglement to resolve optimization interference caused by dominant trends, employs a Phase Router to actively generate future trajectories, and introduces Statistic-Aware Mixup (SAM) to ensure robustness against out-of-distribution volatility. Empirically, PULSE enables a simple MLP backbone to achieve state-of-the-art or highly competitive performance across 12 real-world benchmarks. This validates that a correct physics-informed inductive bias is far more critical than raw architectural complexity for non-stationary forecasting. The code is available at: https://github.com/Gemost/PULSE.

---

### TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition

Authors: Anay Kulkarni, ChiaEn Lu, Dheeraj Mekala, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang
Published: 2026-05-16
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.16790v1

Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition settings. Outcome-based rewards provide only sparse feedback, while trajectory-supervised rewards depend on annotated reference solutions, penalizing valid alternatives and limiting scalability. We propose TIER: Trajectory-Invariant Execution Rewards, a reward framework that derives supervision directly from function schemas and runtime execution, rather than from reference trajectories. The reward decomposes into format validity, schema adherence, execution success, and answer correctness, providing dense, interpretable sequence-level feedback derived from fine-grained verification of individual steps of tool use. This design allows any valid execution path to receive credit, naturally supporting multiple solution strategies and adapting to evolving tool interfaces. On DepthBench, a compositional benchmark stratified by depth (1 to 6 steps), TIER achieves >90% accuracy across steps, where trajectory-supervised rewards collapse beyond step-4. We further demonstrate consistent gains on benchmarks like BFCL v3 and NestFUL. Ablation studies confirm that all reward components are necessary, highlighting the importance of multi-level supervision for compositional reasoning.

---

### Accelerating Rectified Flow Models via Trajectory-Aware Caching

Authors: Xiao Liu, Kai Liu, Naiyang Guan, Hongliang Lu, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16789v1

Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their coarse approximations introduce accumulated errors over long skip intervals and degrade quality under aggressive acceleration. We propose TACache (Trajectory-Aware Cache), a training-free acceleration framework following a skip-then-compensate paradigm. TACache performs an orthogonal decomposition of discrete velocity acceleration along the RF trajectory into a parallel component and an orthogonal residual, isolating the magnitude and directional sources of per-step approximation error. The framework operates in two stages: offline, cumulative variation thresholds on the magnitude and direction indicators yield the skip schedule and bound how far each skip interval may extend; online, at each skipped step the offline statistics are combined with the sample's historical orthogonal direction to reconstruct the skipped velocity without additional model evaluations. Experiments on BAGEL, FLUX.1-dev, and Wan2.1-1.3B show that TACache achieves up to 4.14 speedup on text-to-image generation and 2.11 speedup on text-to-video generation, with consistent improvements over prior cache-based methods on all reference-based fidelity metrics. Code will be released soon.

---

### The Unlearnability Phenomenon in RLVR for Language Models

Authors: Yulin Chen, He He, Chen Zhao
Published: 2026-05-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.16787v1

Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain underexplored. In this paper, we reveal a counterintuitive phenomenon: among hard examples that the model initially struggles with, a substantial subset remains unlearnable even when correct rollouts are present. To understand the phenomenon, we first demonstrate that existing optimization and sampling techniques fail to resolve unlearnability. With cross-example gradient analysis, we show that unlearnable examples have fundamental representation issue, characterized by low gradient similarity with the rest of the examples and ungeneralizable reasoning patterns. We further show that representation flaws are difficult to mitigate in RL, as data augmentation does not improve gradient similarity. Our study provides the first systematic characterization of unlearnable data in RLVR training and reveals fundamental limitations in current RL approaches for reasoning tasks. Code and data are available at \url{https://github.com/yulinchen99/unlearnability-rlvr}.

---

### Lever: Speculative LLM Inference on Smartphones

Authors: Tuowei Wang, Fengzu Li, Yanfan Sun, Wei Gao, Ju Ren
Published: 2026-05-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.16786v1

Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow because autoregressive decoding repeatedly invokes the target model and incurs costly I/O. We observe that speculative decoding is a natural fit for this setting: a small draft model can remain in DRAM, while a larger flash-resident target model verifies multiple candidate tokens per invocation. However, existing methods assume server-class accelerators and fail to account for prolonged I/O latency, limited computation parallelism, and irregular speculation execution. We present Lever, an end-to-end system for efficient flash-backed LLM inference on smartphones. Lever jointly optimizes the three stages of speculative decoding under mobile constraints. For drafting, it builds token trees using an I/O- and compute-aware gain-cost objective. For verification, it prunes low-value branches through early-exit prediction to reduce target-model computation. For execution, it maps speculation efficiently across mobile CPU-NPU hardware to improve utilization. Comprehensive evaluations show that Lever reduces inference latency by an average of 2.93x over baseline flash-offloaded inference and 1.50x over conventional speculative decoding, narrowing the latency gap between flash-backed and memory-resident LLM inference.

---

### Encoding Robust Topological Signatures for Hyperdimensional Computing

Authors: Arpan Kusari
Published: 2026-05-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.16785v1

Hyperdimensional (HD) computing offers an attractive alternative to deep networks for edge learning due to its simplicity, fast prototype-based inference, and compatibility with online updates. However, standard pixel-based HD encoders are brittle: small distribution shifts such as rotation, noise, or occlusion can drastically reduce accuracy. We extract discrete topological primitives-most notably holes-from binarized shapes and pair them with rotation/translation/scale (RTS)-invariant shape signatures. Our method constructs RTS-stable descriptors for (i) the outer shape using a spatial-pyramid variant of Zernike moments and (ii) each hole using an intrinsic Fourier descriptor of its radial signature together with RTS-canonical relative geometry. Each primitive is mapped to a bipolar hypervector via randomized projection and role binding, and variable-cardinality hole sets are aggregated by permutation-invariant bundling to form a single image hypervector. To avoid over-weighting any cue, we learn nonnegative reliability weights for the Zernike and hole channels on a validation set via late fusion of cosine similarities. Experiments on MNIST and EMNIST under controlled corruptions (rotation, Gaussian noise, salt-and-pepper, cutout, zoom) show that Topology-guided HD computing substantially improves robustness compared with a naive HD baseline, maintaining high accuracy across multiple corruption families and benefiting from lightweight online training. Compared with a compact CNN trained on clean data, our method achieves competitive clean accuracy while offering markedly stronger robustness to several pixel-level corruptions, demonstrating that explicit topological structure is a practical route to robust HD representations. The code is provided at https://github.com/arpan-kusari/Topological-HDC.

---

### A Holistic Method for Superquadric Fitting Using Unsupervised Clustering Analysis

Authors: Mingyang Zhao, Sipu Ruan, Xiaohong Jia
Published: 2026-05-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.16779v1

This work presents a novel method for fitting superquadrics to point clouds under the contamination of noise and outliers, which has many applications for shape modeling across diverse fields. Unlike prior approaches that either exclusively focus on fitting rigid or deformable superquadrics, or suffer from robustness and numerical instability issues, our method redefines the problem from a new unsupervised clustering perspective, enabling the holistic fitting of both rigid and deformable superquadrics within a unified framework. Central to our approach is a stable optimization function inspired by unsupervised clustering analysis, where we formulate the point cloud data and samples from the potential parametric surface as clustering members and centroids, respectively. Then, the clustering process with dynamic updates to centroid locations serves as a direct proxy for optimizing superquadric parameters, establishing a principled link between geometric fitting and clustering dynamics. We further derive the relationship between pairwise computations of clustering centroids and clustering members to orthogonal distances, effectively eliminating the need for the time-consuming surface sampling process. Moreover, our formulation provides closed-form analytical solutions for both the fuzzy membership degree vector and the covariance matrix, ensuring efficient iteration optimization and enabling more effective handling of geometric deformations. In addition, we provide a theoretical certificate of convergence analysis and demonstrate that the clustering-inspired fitting method can escape local minima by inherently increasing the convexity of the objective function. The implementation is publicly available at https://github.com/zikai1/SuperquadricFitting.

---

### Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning

Authors: Puning Yang, Junchi Yu, Qizhou Wang, Philip Torr, Bo Han, Xiuying Chen
Published: 2026-05-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.16776v1

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and Distinguishable Refusal (DR), which steers models away from using sensitive knowledge during inference. Despite rapid progress, KD-based unlearning struggles with biased deletion due to suppressing specific token sequences as a substitute for complete knowledge removal, whereas DR-based unlearning risks the re-emergence of harmful knowledge because the underlying knowledge remains intact. To address these issues, we propose Distinguishable Deletion ($\mathrm{D^2}$), a paradigm that restricts the response distribution in the latent representation rather than specific tokens to erase undesirable knowledge, while distinguishing it from retained knowledge, enabling a refusal mechanism to handle unlearned inputs safely and coherently. To implement $\mathrm{D^2}$, we introduce an energy index that quantifies the presence of knowledge and the separation between unlearned and retained content. Mathematical and empirical analyses show that energy is both accurate and efficient, enabling Energy-based Unlearning Alignment (EUA) to enforce energy-boundary unlearning during training and apply an energy-based refusal mechanism at inference. Extensive experiments demonstrate that EUA significantly outperforms previous methods, indicating the superiority of $\mathrm{D^2}$. Our code is available at https://github.com/Puning97/EUA-for-LLM-Unlearning.

---

### VolTA-3D: Self-Supervised Learning for Brain MRI using 3D Volumetric Token Alignment

Authors: Amy Makawana, Abhijeet Parida, Marius George Linguraru, Julia Ive, Syed Muhammad Anwar
Published: 2026-05-16
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.16775v1

Self-supervised learning (SSL) has advanced medical image analysis be enabling learning form large unlabelled data. However, in brain magnetic resonance imaging (MRI), most 3D models remain specialized for either segmentation of classification, limiting their ability to generalize across datasets, imaging protocols,, and downstream tasks. This lack of transferability constrains the clinical utility of 3D MRI models, despite the availability of unlabeled volumetric data. We present Volta-3D, a self-supervised 3D Vision Transformer framework designed to learn transferable volumetric representations. Volta-3D jointly aligns global class-style tokens and local patch tokens within a student-teacher paradigm and enforces fine-grained structural reconstruction. This combined global-local alignment addresses the limited semantic diversity and subtle anatomical characteristics of brain MRI, which challenges existing SSL approaches. We evaluate Volta-3D on multiple out-of-distribution downstream tasks, including hippocampal segmentation and classification of sex and Alzheimer's disease versus healthy controls. Across all tasks, representations learned by Volta-3D outperform randomly initialized baselines, demonstrating improved transferability and robustness under domain shift. Hence jointly enforcing global semantic consistency and local structural learning during pretraining enables broader concept learning from unlabeled brain MRI data. Overall VolTA-3D supports effective multi-task downstream performance with task-specific pertaining, a step towards generalizable and clinically viable 3D models.

---

### CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris

Authors: Zaid Aljundi, Zahra F. Rahmatullah, Mostafa Elemam, Abdullah Moosa
Published: 2026-05-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.16774v1

Surface-level marine debris remains a practical bottleneck for autonomous clean-up, where small, reflective targets (e.g., aluminum cans) must be detected at distance under glare, ripples, and partial submersion. This paper presents, an ASV vision system and a new surface-can dataset. The dataset comprises ~7.3k raw images extracted from videos and annotated with bounding boxes, expanded via ten augmentation types to ~57k training/validation images spanning diverse lighting and water states. A family of detector and detector-tracker pipelines tailored to surface operations were benchmarked. Training YOLOv11 on CANSURF boosts performance 12x over generic datasets, highlighting the dataset's value. Experiments show that YOLOv11+ByteTrack yields the most stable tracks (fewer identity switches) and stronger multi-object accuracy under, while YOLOv11+SAHI increases recall on far-field cans at the cost of lower precision in full-context inputs. Given the mission profile, single-can pickup with approach and grab, YOLOv11 + SAHI proves better for detecting the maximum number of cans. No prior open dataset targets aluminum cans on water from a surface-level viewpoint; this dataset fills this gap and supports reproducible evaluation.

---

### Exploring Lightweight Large Language Models for Court View Generation

Authors: Zhitian Hou, Tianyong Hao, Nanli Zeng, Zhixiong Chao, Kun Zeng
Published: 2026-05-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.16770v1

Criminal Court View Generation (CVG) is a critical task in Legal Artificial Intelligence (Legal AI), involving the generation of court view based on case facts. In this work, we systematically explore the capabilities of lightweight (smaller than 2B) large language models (LLMs) in CVG and their impact on charge prediction. Our study addresses four key questions: (1) how does different architecture of LLMs affect the CVG quality and charge prediction. (2) how does LLMs size contribute to the performance, (3) how do lightweight LLMs compare with Deep Neural Networks (DNNs) in these tasks, and (4) how does predicting charge by court view generation first compare with predicting it directly. Additionally, we also develop CVGEvalKit, an evaluation framework including three public available datasets for CVG tasks, as well as predicting their charges. Comprehensive experiments are conducted on this framework, where models are trained on a mixed training set and evaluated on each dataset's test set. Experimental results provide new insights into the trade-offs between model architecture, model size, and the influence between different tasks, highlighting the potential of lightweight LLMs in judicial AI applications. The source code is anonymously available at \url{https://github.com/ZhitianHou/CVGEvalKit}

---

### GLT-PEFT: Gated Lie-Tucker Parameter-Efficient Fine-Tuning for Alzheimer's Disease Diagnosis with Hippocampal Segmentation Pretraining

Authors: Guanghua He, Hancan Zhu, Gaohang Yu, An Zhang
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16769v1

Parameter-efficient fine-tuning (PEFT) has emerged as a promising paradigm for adapting pretrained models under limited data conditions. However, most existing PEFT methods are designed for matrix-structured parameters and are not well suited for high-dimensional convolutional kernels in medical imaging models. Moreover, they typically rely on additive updates and lack mechanisms to preserve the geometric structure of pretrained parameters, while multiplicative (geometry-aware) updates are difficult to integrate within a unified framework. To address this issue, this paper proposes GLT-PEFT, a gated Lie-Tucker parameter-efficient fine-tuning framework for Alzheimer's disease (AD) diagnosis. The proposed approach transfers a hippocampal segmentation pretrained model to a downstream classification task. Tucker decomposition enables tensor-aware low-rank adaptation of 3D convolutional kernels, while Lie group-based transformations provide structure-preserving multiplicative updates. A gating mechanism further reconciles additive and multiplicative update forms, resulting in a unified and more stable fine-tuning strategy. Extensive experiments demonstrate that GLT-PEFT achieves effective cross-task transfer while significantly reducing trainable parameters, highlighting its effectiveness for efficient and robust adaptation in medical imaging models.

---

### Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation

Authors: Feng Gao, Zhilin Jin, Yanhai Gan, Junyu Dong, Qian Du
Published: 2026-05-16
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2605.16768v1

Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependencies with linear computational complexity. Moreover, an Axial-Relation Guided Fusion Module is designed to explicitly model global cross-modal correlations along horizontal and vertical axes, enabling efficient feature fusion between optical and elevation modalities. Extensive experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate that our ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency. The code will be made publicly available at \url{https://github.com/oucailab/ARG-Mamba}.

---

### Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free

Authors: Li Zhang, Jaromir Savelka, Kevin Ashley
Published: 2026-05-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.16767v1

Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited supervision. Parametric encoders typically require task-specific training and retraining when the label set changes, while prompting generative large language models becomes costly and degrades as the label space grows. We cast legal annotation as retrieval: we embed documents and label descriptions with a frozen retrieval model and predict labels via k-nearest neighbors in the embedding space, enabling updates by re-embedding and re-indexing rather than gradient-based backpropagation. Across three legal datasets (ECtHR-A, ECtHR-B, and Eurlex with 100 labels), retrieval achieves competitive accuracy and strong data efficiency; on Eurlex, Qwen-8B retrieval improves Macro-F1 from 40.41 (GPT-5.2, zero-shot) to 49.12 while reducing estimated compute by 20-30 times compared to fine-tuning. With only (N=100) training samples, retrieval nearly doubles Micro-F1 over hierarchical Legal-BERT on ECtHR-A (48.29 vs. 27.87). We also quantify a reliability failure mode of generative inference: GPT-5.2 hallucinates labels outside the provided taxonomy in 0.12-0.9% of test samples under deterministic decoding. In contrast, retrieval strictly respects defined label sets, eliminating hallucination by design. These results suggest retrieval-model-based annotators are a practical, deployable alternative for high-cardinality and rapidly changing legal label spaces.

---

### Synthetic Aperture Radar Image Change Detection Based on Global Dynamic Context-Aware Network

Authors: Baogui Huan, Chuanzheng Gong, Dezhong Chen, Feng Gao, Junyu Dong, Qian Du
Published: 2026-05-16
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2605.16764v1

Convolutional neural networks (CNNs) have been extensively and successfully applied to the task of synthetic aperture radar (SAR) image change detection. However, conventional convolutional layers are inherently limited by their local receptive fields, which mainly capture spatially localized patterns while neglecting the global context that is often crucial for accurately distinguishing subtle or large-scale changes in SAR imagery. To address these limitations, we propose a novel Global Dynamic Context-Aware Network (GDNet) specifically tailored for SAR image change detection. At the core of our approach lies a novel global dynamic convolution module, which adaptively modulates convolution kernel weights according to the global semantic information extracted from the input features. By dynamically incorporating long-range dependencies, this mechanism enables the network to integrate both local detail and global context, thus improving its ability to detect diverse change patterns. In addition, we introduce a carefully designed two-stage Mixup strategy for model training. Unlike conventional single-stage Mixup, our two-stage design generates more diverse and informative training samples, effectively regularizing the model and yielding more stable and reliable classification results even under limited data scenarios. Extensive experiments on three SAR datasets demonstrate the superiority of the proposed GDNet compared to other state-of-the-art methods. These findings highlight the potential of global dynamic modeling and advanced data augmentation strategies for advancing SAR image interpretation. Source codes are available at \url{https://github.com/oucailab/GDNet}.

---

### Language Acquisition Device in Large Language Models

Authors: Masato Mita, Taiga Someya, Ryo Yoshida, Yohei Oseki
Published: 2026-05-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.16758v1

Large Language Models (LLMs) remain substantially less data-efficient than humans. Pre-pretraining (PPT) on synthetic languages has been proposed to close this gap, with prior work emphasizing highly expressive formal languages such as $k$-Shuffle Dyck. Inspired by the Language Acquisition Device (LAD) hypothesis, which posits that innate constraints preemptively restrict the learner's hypothesis space to natural-language-like structure, we propose LAD-inspired PPT: pre-pretraining on MP-STRUCT, a formal language whose strings encode hierarchical composition, feature-based dependencies, and long-distance displacement via MERGE, AGREE, and MOVE. A brief 500-step PPT with MP-STRUCT matches strong formal-language baselines in token efficiency while additionally imparting a human-like resistance to structurally implausible languages (e.g., REVERSE). Analyzing simplified variants, we find that MP-STRUCT CORE outperforms $k$-Shuffle Dyck despite not being definable in C-RASP (a formal bound on transformer expressivity), challenging the prior hypothesis that effective PPT languages must be both hierarchically expressive and circuit-theoretically learnable. We show that functional landmarks, which reduce dependency resolution ambiguity, are a key driver, suggesting that effective PPT design depends not only on expressivity but also on the accessibility of dependency resolution.

---

### NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

Authors: Haoran Lu, Luyang Fang, Wenxuan Zhong, Ping Ma
Published: 2026-05-16
Categories: cs.AI, cs.MA, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2605.16757v1

Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate. This formulation shifts multi-agent design from workflow engineering toward architecture design, where depth, width, connectivity, and growth protocol become scalable sources of capability. Further, we provide a theoretical perspective showing why such modular textual computation is more parameter-efficient when tasks admit hierarchical decompositions. Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems. These results suggest that learned neural multi-agent systems are a promising scaling axis for LLMs.

---

### Learning Unbiased Permutations via Flow Matching

Authors: Yimeng Min, Carla P. Gomes
Published: 2026-05-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.16755v1

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a conditional flow matching framework that operates directly on the affine subspace of matrices with unit row and column sums. A closed-form tangent-space projector preserves these constraints exactly along every trajectory, by construction rather than through iterative correction, and a nearest-target coupling routes distinct noisy initializations toward distinct valid permutations. The result is a model that captures multimodal permutation distributions rather than collapsing them to a single mode. On a visual sorting task with blended-digit ambiguity and a symmetric linear assignment problem, PermFlow achieves high accuracy on unambiguous inputs and recovers both valid permutations under ambiguity, where Sinkhorn-based baselines structurally fail.

---

### UniER: A Unified Benchmark for Item-level and Path-level Exercise Recommendation

Authors: Xinghe Cheng, Guiyong Zhuang, Yusheng Xie, Jiapu Wang, Yixin Liu, Quanlong Guan, Liangda Fang, Shirui Pan
Published: 2026-05-16
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2605.16750v1

Personalized exercise recommendation dynamically aligns pedagogical resources with individual knowledge mastery, which is crucial for satisfying students' dynamic learning needs in modern education. The field is currently driven by two dominant paradigms: Item-Level Exercise Recommendation (ILER) optimizes for immediate single-step state transitions, while Path-Level Exercise Recommendation (PLER) constructs coherent learning paths to maximize cumulative gains. Despite sharing the same ultimate objective, disparate evaluation setups have kept these two lines of research isolated, hindering unified benchmarking and fair comparison. To fill the gap, in this paper, we present a Unified Benchmark for Exercise Recommendation (UniER), a comprehensive evaluation framework that unifies ILER and PLER. Specifically, we introduce Weighted Cognitive Gain (WCG) as a unified metric to measure cross-paradigm algorithmic performance. Our benchmark encompasses 9 datasets spanning four generation methods, facilitating the comparison of 18 representative ILER/PLER methods. Through multi-dimensional analyses covering effectiveness, generalizability, robustness, and efficiency, our results reveal the systematic dominance of PLER and expose the pedagogical failure of ILER's fragmented recommendations under extreme sparsity and noise. Furthermore, we provide an open-source codebase of UniER to foster reproducible research and outline potential directions for future investigations.

---

### Genflow Ad Studio: A Compound AI Architecture for Brand-Aligned, Self-Correcting Video Generation

Authors: Debanshu Das, Lavi Nigam, Sunil Kumar Jang Bahadur, Gopala Dhar
Published: 2026-05-16
Categories: cs.GR, cs.AI, cs.CV, cs.LG, cs.MA, cs.MM
arXiv: https://arxiv.org/abs/2605.16748v1

Recent advancements in generative video models demonstrate high visual fidelity, yet their integration into enterprise environments is restricted by temporal inconsistencies and severe brand misalignment. Current monolithic architectures struggle to enforce rigid brand constraints, frequently hallucinating unapproved visual assets. We introduce Genflow, a Compound AI System designed to enforce brand consistency in generative media production. Our architecture integrates a retrieval-based 'Brand DNA' extraction module to parameterize generation according to established corporate identity guidelines. Furthermore, we implement an Adversarial Multi-Agent Quality Control (QC) loop. Instead of a single-pass generation, this pipeline employs evaluator agents to iteratively critique generated frames against the extracted parameters, prompting generator models to refine outputs until a deterministic consensus is reached. By transitioning to a multi-stage, self-correcting pipeline, Genflow improved the yield of brand-compliant video generations from 42% to 89%, establishing a robust framework for scalable, enterprise-grade generative systems.

---

### Propagation of Chaos in Contextual Flow Maps

Authors: Shi Chen, Zhengjiang Lin, Kaizhao Liu, Philippe Rigollet
Published: 2026-05-16
Categories: cs.LG, math.AP, math.OC, math.PR, math.ST
arXiv: https://arxiv.org/abs/2605.16747v1

We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dynamical systems that evolve a distinguished token in the presence of a contextual measure across a stack of attention blocks. Within this framework, the finite-context model approximates an idealized infinite-context system in which the contextual measure is replaced by its underlying population, so that the context length $n$ becomes a statistical resource. Exploiting the McKean--Vlasov structure of the dynamics and the classical machinery of propagation of chaos, we establish a forward bound controlling the deviation between the finite- and infinite-context CFMs uniformly along depth, and a backward bound controlling the deviation between the corresponding training trajectories uniformly across iterations of online gradient descent. Both bounds achieve the optimal Wasserstein rate $n^{-1/d}$ for general CFMs and parametric rate $n^{-1/2}$ for a restricted class of CFMs that includes transformers as a special case. The analysis rests on a new Eulerian adjoint formulation of the loss gradient and stability estimates for the resulting forward--adjoint system, both of which may be of independent interest.

---

### State Contamination in Memory-Augmented LLM Agents

Authors: Yian Wang, Agam Goyal, Yuen Chen, Hari Sundaram
Published: 2026-05-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.16746v1

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what an agent stores and later reuses. We study a failure mode we call memory laundering: toxic or adversarial context can be compressed into memory summaries that no longer appear toxic under standard detectors, while still preserving hostile framing or conflict structure that influences future generations. Using paired counterfactual multi-agent rollouts, we show that toxic-origin memory summaries can remain below common toxicity thresholds while nevertheless increasing downstream toxicity relative to matched neutral baselines. To measure this hidden influence, we introduce the sub-threshold propagation gap (SPG), which quantifies downstream behavioral differences conditioned on memory states that a deployed monitor would classify as safe. Our experiments show that toxicity propagates through distinct state channels: raw transcript reuse drives overt downstream toxicity, while compressed memory carries hidden sub-threshold influence. We further find that mitigation depends critically on intervention placement. Sanitizing toxic state before summarization substantially reduces the hidden propagation gap, whereas cleaning only the completed summary can leave laundered influence intact. These results suggest that safety in memory-augmented agents should be treated as a state-control problem over evolving context, with sanitization applied before unsafe information is compressed into persistent memory.

---

### EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers

Authors: Zongyuan Yang, Mingjing Yi, Wanli Ma, Chenzhuo Fan, Bocheng Li, Baolin Liu, Yuke Lou, Yingde Song, Yongping Xiong, Zhengdong Guo, Shimu Wang
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16745v1

This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large reconstruction models decouple semantic understanding from geometric reasoning, operating as stateless reconstructors conditioned on dense 2D pixel priors. Recent MLLM-based methods treat the 3D modality as an external output rather than a native component of the multimodal sequence, making incremental adaptations without a systematic analysis of how geometric manifolds align with MLLM feature spaces. We introduce EVA01, a unified framework that extends the modality boundary of MLLMs to natively incorporate 3D mesh understanding, generation, and context-aware editing. Built upon a Mixture-of-Transformers (MoT) architecture, EVA01 decouples the model into a pre-trained Understanding Expert ($E_{\mathrm{und}}$) and a structurally mirrored Generation Expert ($E_{\mathrm{gen}}$), coupled through shared global self-attention with hard modality routing. This design aligns the semantic latent space of the MLLM backbone with the geometric manifold, enabling direct transfer of multimodal priors without intermediate 2D representations. Results show that EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines. Our findings further offer architectural insights for integrating 2D foundation models with 3D tasks, informing the design of 3D-native multimodal systems. Project Page: https://www.seeles.ai/research/pages/EVA01

---

### ConSEAL: Connectivity-Informed Streamline Endpoint Alignment for Diffeomorphic Cortical Registration

Authors: Yang Xiang, Martin Cole, Zhengwu Zhang
Published: 2026-05-16
Categories: cs.CV, stat.ME
arXiv: https://arxiv.org/abs/2605.16742v3

Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geometric correspondence, it neglects the long-range wiring constraints imposed by white-matter anatomy. Diffusion MRI tractography offers these crucial constraints; however, prior connectivity-informed pipelines typically align precomputed connectivity matrices, making the optimization highly sensitive to connectivity estimation and its resolution. In this paper, we introduce ConSEAL (Connectivity-Informed Streamline Endpoint Alignment), a novel connectivity-based surface registration method that aligns cortical surfaces by operating directly on white-matter fiber-tract endpoints. We model tract endpoints as a point cloud on the product manifold $Ω\times Ω$, where $Ω$ represents the spherical domain of the inflated cortical hemispheres. Our alignment method iteratively (i) computes a small diffeomorphic warp for $Ω$ by minimizing connectivity mismatch, and (ii) updates the endpoints based on this warp. The method relies on a geometric framework that ensures output warps are diffeomorphisms and has a final goal that optimizes the matching of well-known fiber bundles. Experiments on Human Connectome Project (HCP) data demonstrate that ConSEAL improves tract-level correspondence, achieving higher connectivity-level overlap coefficients on major fiber bundles and stronger robustness across grid resolutions for $Ω$ compared to state-of-the-art methods such as ENCORE and MSMAll.

---

### Diffeomorphic Cortical Alignment via Direct Warping of Streamline Endpoints

Authors: Yang Xiang, Martin Cole, Zhengwu Zhang
Published: 2026-05-16
Categories: cs.CV, stat.ME
arXiv: https://arxiv.org/abs/2605.16742v1

Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geometric correspondence, it neglects the long-range wiring constraints imposed by white-matter anatomy. Diffusion MRI tractography offers these crucial constraints; however, prior connectivity-informed pipelines typically align precomputed connectivity matrices, making the optimization highly sensitive to connectivity estimation and its resolution. In this paper, we introduce a novel connectivity-based surface registration method that aligns cortical surfaces by operating directly on white-matter fiber-tract endpoints. We model tract endpoints as a point cloud on the product manifold $Ω\times Ω$, where $Ω$ represents the spherical domain of the inflated cortical hemispheres. Our alignment method iteratively (i) computes a small diffeomorphic warp for $Ω$ by minimizing connectivity mismatch, and (ii) updates the endpoints based on this warp. The method relies on a geometric framework that ensures output warps are diffeomorphisms and has a final goal that optimizes the matching of well-known fiber bundles. Experiments on Human Connectome Project (HCP) data demonstrate improved tract-level correspondence, achieving higher connectivity-level overlap coefficients on major fiber bundles and stronger robustness across grid resolutions for $Ω$ compared to state-of-the-art methods such as ENCORE and MSMAll.

---

### TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation

Authors: Pengyu Yan, Akhil Gorugantu, Mahesh Bhosale, Abdul Wasi, Vishvesh Trivedi, David Doermann
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16740v2

Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-language models (LVLMs) often underperform in this regime because they quickly exhaust their context budget and struggle to precisely localize evidentially important segments, frequently missing dense informational cues such as broadcast graphics, subtitles, and scoreboards. We introduce TRACE, an evidence grounding-guided framework that follows a ground-before-reasoning strategy for multi-video event reasoning. Our approach first builds a structured, text-searchable timeline for each video using OCR and object detection. A text-only LLM then conducts query-aware evidence localization, selecting relevant moments prior to any downstream visual reasoning. The retrieved frames and their grounding summaries are subsequently used to steer LVLM-based claim generation and cross-video citation consolidation. Experiments on MAGMaR 2026 and WikiVideo demonstrate that structured grounding markedly boosts factual completeness and attribution fidelity. On the MAGMaR validation split, TRACE raises macro-average MiRAGE F1 from 0.705 to 0.811 compared to an unguided Qwen3-VL-30B baseline, with especially strong improvements in citation recall from 0.440 to 0.628. The method also attains state-of-the-art results on the official MAGMaR 2026 leaderboard. Code is released at https://github.com/pengyu965/TRACE.

---

### EmoMind: Decoding Affective Captions from Human Brain fMRI

Authors: Bilal A. Mohammed, Lin Gu, Ruogu Fang
Published: 2026-05-16
Categories: cs.LG, cs.AI, cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2605.16739v3

Decoding visual experience from brain activity has advanced substantially, but current brain-to-text systems largely recover semantic content while discarding affect. Additionally, language models can generate emotional text when prompted with categorical labels, but such labels collapse rich inter-subject variability into coarse discrete bins. We present EmoMind, the first end-to-end pipeline for decoding affective captions directly from fMRI signals. EmoMind first retrieves a semantically grounded neutral scene description from brain-decoded visual features, then rewrites it using a continuous 34-dimensional emotion vector decoded from the same fMRI recording. To control the balance between content preservation and affective expression, we train the rewriter with classifier-free guidance against an identity-preserving null branch, enabling smooth interpolation between semantic fidelity and affective expressivity. We evaluate affective caption generation with a three-axis validation framework spanning subject-specificity, structural geometry, and causal control. We further augment this framework with a synthetic-brain substitution test that probes robustness to the measurement apparatus, and we benchmark each axis against GPT-4 prompted with brain-decoded top-5 emotion labels as a strong discrete baseline. Across two independent emotion fMRI datasets, EmoMind significantly outperforms label-prompted GPT-4 on all three axes, with the largest gains on metrics that require person-specific affective structure rather than population-level emotion aggregation. These results establish continuous brain-decoded affect as a viable control signal for individualized affective caption generation and open new directions for studying individual affective brain organisation.

---

### EmoMind: Decoding Affective Captions from Human Brain fMRI

Authors: Bilal A. Mohammed, Lin Gu, Ruogu Fang
Published: 2026-05-16
Categories: cs.LG, cs.AI, cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2605.16739v2

Decoding visual experience from brain activity has advanced substantially, but current brain-to-text systems largely recover semantic content while discarding affect. Additionally, language models can generate emotional text when prompted with categorical labels, but such labels collapse rich inter-subject variability into coarse discrete bins. We present EmoMind, the first end-to-end pipeline for decoding affective captions directly from fMRI signals. EmoMind first retrieves a semantically grounded neutral scene description from brain-decoded visual features, then rewrites it using a continuous 34-dimensional emotion vector decoded from the same fMRI recording. To control the balance between content preservation and affective expression, we train the rewriter with classifier-free guidance against an identity-preserving null branch, enabling smooth interpolation between semantic fidelity and affective expressivity. We evaluate affective caption generation with a three-axis validation framework spanning subject-specificity, structural geometry, and causal control. We further augment this framework with a synthetic-brain substitution test that probes robustness to the measurement apparatus, and we benchmark each axis against GPT-4 prompted with brain-decoded top-5 emotion labels as a strong discrete baseline. Across two independent emotion fMRI datasets, EmoMind significantly outperforms label-prompted GPT-4 on all three axes, with the largest gains on metrics that require person-specific affective structure rather than population-level emotion aggregation. These results establish continuous brain-decoded affect as a viable control signal for individualized affective caption generation and open new directions for studying individual affective brain organisation.

---

### DriveSafer: End-to-End Autonomous Driving with Safety Guidance

Authors: Shounak Sural, Raj Rajkumar
Published: 2026-05-16
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2605.16737v1

End-to-End (E2E) autonomous driving models have shown growing capability in recent years, with performance improving on increasingly challenging benchmarks. However, modern generative E2E planners still suffer from a substantial number of catastrophic failures in safety-critical scenarios. We find that many such failures arise from violations of physical constraints and safety requirements, leading to unsafe behavior. Motivated by this finding, in this paper, we focus on improving safety outcomes in generative end-to-end driving with a targeted reduction of catastrophic planning failures, instead of enhancing average planning quality. Towards this end, we propose DriveSafer, a failure-aware safety framework for end-to-end planners. DriveSafer explicitly steers generative planners towards safe behaviors leveraging both training-time safety constraints and inference-time safety guidance. Compared to the state-of-the-art DiffusionDrive model, on the NAVSIM benchmark, DriveSafer reduces the number of catastrophic failures (PDMS=0) by 48%, with over 65% reduction in drivable-area compliance failures.

---

### CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth

Authors: Anuska Roy, Pravin Nair
Published: 2026-05-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.16736v2

Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. Existing acceleration methods either require additional training through distillation or rely on training-free high-order solvers, and both can degrade sample quality at low NFE budgets. We propose CAB (Corrected Adams-Bashforth), a training-free sampler that accelerates both flow and diffusion models. CAB first transforms the sampling dynamics to a common rectified coordinate system, and then applies a multistep Adams-Bashforth predictor augmented with a simple correction term based on past velocity evaluations and therefore incurs no additional NFEs. The resulting method is simple, has the same algorithmic form across model classes, and has at least third-order local truncation error and second-order global error. Experiments on pretrained flow and diffusion models, including class-conditional and large-scale text-to-image benchmarks, show that CAB improves quality-NFE trade-offs in the low-step regime of 6-20 NFEs. It also remains competitive with strong training-free samplers at higher step counts across most tested models. The official implementation is available at https://github.com/Anuska-Roy/CAB.

---

### Transformer-Based MCS Prediction for 5G Multicast-Broadcast Services (MBS)

Authors: Kasidis Arunruangsirilert, Jiro Katto
Published: 2026-05-16
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2605.16735v1

The deployment of 5G Multicast-Broadcast Services (MBS) is emerging as a critical technology for spectral-efficient UHD content delivery and serving as a promising solution to modernize CATV deployment. However, unlike unicast networks that rely on RLC-AM with HARQ retransmissions, MBS broadcast operates in RLC Unacknowledged Mode (RLC-UM), where the absence of a feedback loop means packet loss is permanent and immediately impacts user QoE. Conventional link adaptation algorithms, designed for unicast, typically aggressively maximize throughput and fail in this risk-intolerant environment, resulting in severe video stalls and rebuffering. To address this, we propose a lightweight Transformer-based framework that predicts the success probability of all 28 MCS indices over an upcoming video segment horizon. Utilizing a unique commercial network dataset with 0.5 ms slot-level granularity, we train our model using a custom Asymmetric Safety Loss function that penalizes channel overestimation to prioritize link stability. Experimental results show that our approach achieves a reliability score of 86.89%, significantly outperforming standard AI baselines optimized for raw throughput (31.65%) while maintaining a safe conservative bias. Furthermore, the model is optimized for real-time applications, demonstrating an inference time of less than 0.07 ms on COTS 5G-era smartphones.

---

### DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers

Authors: Sayeh Sharify, Mahsa Salmani, Hesham Mostafa
Published: 2026-05-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.16732v1

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant efficiency gains, it typically results in severe quality degradation. Existing approaches, including smoothing-based methods, mixed-precision schemes, rotation techniques, and low-rank residual methods, partially mitigate this issue but still leave a noticeable gap to FP16/BF16 performance. In this work, we introduce DiRotQ, a W4A4 PTQ framework that mitigates this degradation through rotation-aware activation quantization. DiRotQ identifies a low-rank subspace capturing dominant activation variance via Principal Component Analysis (PCA), preserving coefficients in this subspace at higher precision while quantizing the remaining components to 4-bit. Activations are rotated into the PCA basis at inference time using calibration-derived orthogonal transformations, while the inverse rotation is fused into the layer weights offline. Combined with GPTQ-based weight quantization, DiRotQ achieves an FID (lower is better) of 15.9 and PSNR (higher is better) of 19.1 dB on PixArt-Σ over the MJHQ-30K dataset, outperforming the prior state-of-the-art SVDQuant (FID 18.9, PSNR 17.6) under the same INT W4A4 setting. Beyond standard metrics, we introduce a VLM-as-a-Judge evaluation protocol for diffusion model quantization, the first such evaluation in this setting, providing a more holistic assessment of perceptual quality and prompt alignment under aggressive compression. On the systems side, we implement a Triton-based custom kernel to enable efficient end-to-end inference, reducing memory usage of the 12B FLUX.1-dev model by 2.1x and delivering 2.3x speedup over the BF16 baseline, on a 24 GB RTX 4090 GPU.

---

### Body-Grounded Perspective Formation and Conative Attunement in Artificial Agents

Authors: Hongju Pae
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.16728v1

This paper proposes a minimal architecture for body-grounded perspective formation in artificial agents. Extending prior work, the model introduces an interoceptive viability signal, a Fisher-style metric over fused exteroceptive-interoceptive states, and a conative alignment mechanism linking bodily tendency to action readiness. In a reward-free gridworld, conation converts learned bodily tendency into stable body-directed behavior, while body-to-perspective routing allows bodily perturbations to leave a recoverable geometric residue in the perspective latent. This study shows how minimal structural conditions for artificial subjectivity can be operationalized in the phenomenological sense, through the embodied organization of how a world is given to an agent.

---

### PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

Authors: Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf, Maxwill Lin, Augustine N. Mavor-Parker, Matthew James Sargent
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.16727v1

We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs. Teachers and students are specialised LoRA adapters on a shared frozen base: teachers propose problems, matched students solve them under a programmatic verifier, and cross-evaluation between sub-populations replaces the self-calibration that limits single-agent self-play. A family of LoRA weight-space evolution operators (mutations and crossovers that produce same-rank population members in seconds) serves as the replacement step of a population-based training loop at 7B scale. We instantiate PopuLoRA on top of Absolute Zero Reasoner and compare it against a per-adapter compute-matched single-agent baseline. Where the single agent self-calibrates to generating easy problems it can reliably solve, the population enters a co-evolutionary arms race: teachers produce increasingly complex problems, student solve rates oscillate, and problem-space coverage keeps expanding throughout training. Despite lower training-time reward, the population mean outperforms the baseline on three code benchmarks (HumanEval+, MBPP+, LiveCodeBench) and seven math benchmarks (AIME 24/25, AMC 23, MATH-500, Minerva, GSM8K, OlympiadBench), and even the weakest member of the population beats the baseline on aggregate.

---

### A Global-Local Graph Attention Network for Traffic Forecasting

Authors: Tianchi Zhang
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.16726v1

Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them to allow vertices to have far different characters. To address this, we propose the Global-Local Graph Attention Network (GLGAT) with pairwise encoding and the event-based adjacency matrix. The GLGAT allows vertices to have a global attention matrix set for the whole graph and assigns local attention matrix sets to each vertex. Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.

---

### Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

Authors: SeungWon Seo, DongHeun Han, SeongRae Noh, HyeongYeop Kang
Published: 2026-05-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.16725v1

Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, without rule descriptions, reward signals, or trustworthy lexical priors. We introduce Alice, a closed-loop system that treats failed candidate updates as structural signal: when a candidate explains a new transition but loses previously explained ones, the preservation conflict reveals dynamics that the current program had conflated. Alice refines these conflicts into hypothesis classes that both provide compact, class-stratified preservation counterexamples for update and guide frontier exploration toward transitions that are novel and underrepresented with respect to the current program. We evaluate Alice on Baba in Wonderland, a prior-misaligned variant of Baba Is You that preserves simulator dynamics while replacing semantically meaningful rule-property labels with unrelated words. Experiments show that Alice substantially improves executable world-model learning under prior misalignment, and ablations show that both class refinement and class-aware exploration contribute.

---

### Compositional Adversarial Training for Robust Visual Watermarking

Authors: Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, Andrew Xu, Georgios Milis, Heng Huang, Zikui Cai, Furong Huang
Published: 2026-05-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.16720v1

Robust watermarking is typically trained with random post-processing augmentation, but random sampling under-covers the combinatorial space of realistic attack pipelines and rarely encounters the rare compositions that actually break detection. This leads to unstable training and poor sample efficiency. We instead formulate watermark robustness as a min-max problem over a structured space of compositional transformations. We propose Compositional Adversarial Training (CAT), a plug-in framework that learns a sequential differentiable adversary that observes the current watermarked image and selects an attack family at each step to maximally disrupt message recovery. CAT combines a straight-through Gumbel-Softmax attack selection with entropy regularization, allowing the backward pass to be end-to-end differentiable and aggregate gradient information across attack families, yielding faster, smoother convergence without collapsing to a single attack mode. We evaluate CAT on post-generation watermarks VideoSeal 0.0, VideoSeal 1.0, and PixelSeal and in-generation WMAR under both single-step and two-step attack suites, on in-distribution and multiple out-of-distribution image and video benchmarks. CAT consistently outperforms random-augmentation baselines trained with the same augmentation budget, with the largest gains on hard composed attacks and OOD evaluations; improving overall watermark capacity by up to $63.5\%$ in the single-step attack setting and $13.0\%$ in the compositional setting. In the autoregressive setting, CAT improves the TPR@FPR$=1\%$ by $12\%$ on average on difficult geometric transformations. These results show that robust visual watermarking benefits from training against adaptive compositional adversaries rather than independent random corruptions.

---

### Universal Dynamics of Punctuated Progress

Authors: Yian Yin, Dashun Wang
Published: 2026-05-16
Categories: physics.soc-ph, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2605.16719v1

Scientific and technological frontiers advance through punctuated dynamics, yet the principles governing these dynamics remain poorly understood. Here we collect and analyze datasets tracking the evolution of frontiers across 9 different domains, spanning materials discovery, structural biology, AI, computational biomedicine, data science, theoretical computer science, Formula-1 racing, and physical wheel building. Analyzing 6.8M solutions to 6.7K tasks, we uncover three universal patterns: (1) waiting times between new frontiers are heavy-tailed, with most attempts concentrated in long stasis; (2) frontier records accumulate at a sublinear rate, faster than logarithmic yet slower than linear growth; (3) record-breaking events are temporally correlated, generating short-term predictability yet long-term unpredictability. Despite the differences in the scale, scope, and definition of the settings, these patterns are remarkably consistent across all domains we study, and are not captured by models from complex systems, record statistics, economics of innovation, and cultural evolution. We trace the missing ingredient to the distinction between radical and incremental innovation, and develop a minimal, analytically solvable model incorporating both radical resets that restructure what is achievable and incremental refinements that exploit the current frontier. The simple model reproduces all three empirical regularities. Remarkably, the leading-order predictions are parameter-independent, identifying a new universality class governing punctuated progress and yielding testable predictions about how openness and access to frontier solutions shape the pace of advance. Overall, these results reveal universal dynamics governing punctuated progress and identify the interplay between radical resets and incremental refinements as the key driver of how scientific and technological frontiers advance.

---