# Research Papers — 2026-05 · bundle page 170 of 326

> Full-text markdown of papers #8451–8500 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/170
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/169.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/171.md)

### Unlocking Dense Metric Depth Estimation in VLMs

Authors: Hanxun Yu, Xuan Qu, Yuxin Wang, Jianke Zhu, Lei Ke
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15876v3

Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability. By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm with a two-stage schedule, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass. We further introduce a unified indoor-outdoor metric depth benchmark in a VLM-compatible format. Experiments show that DepthVLM significantly outperforms existing VLMs with higher inference efficiency, surpasses leading pure vision models, and improves complex 3D spatial reasoning, moving toward a truly unified multimodal foundation model. The project page is available at https://depthvlm.github.io/

---

### Ti-iLSTM: A TinyDL Approach for Logic-Level Anomaly Detection in Industrial Water Treatment Systems

Authors: Mandar Joshi, Farzana Zahid, Judy Bowen, Matthew M. Y. Kuo, Valeriy Vyatkin, Emil Karlsson
Published: 2026-05-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.15874v1

Industrial Water Treatment Systems (IWTS) are safety critical cyber-physical infrastructures and due to increased connectivity, these systems are exposed to cyber threats that can manipulate process behaviour without creating obvious devices outliers. In particular, logic-layer deception anomalies can preserve numerically plausible measurements while breaking expected cause-and-effect relationships in the control process. These attacks are difficult to detect using threshold-based monitoring or require heavy server-oriented anomaly detection models. This paper explores the potential of Tiny Deep Learning (TinyDL) to provide lightweight on-device logic-level anomaly detection for resource constrained Programmable Logic Controllers (PLCs). We propose a novel framework, TinyDL-based incremental LSTM (Ti-iLSTM) which optimises the memory and space foot print of Long Short-Term Memory (LSTM), to detect logic-layer inconsistencies in Programmable Logic Controller (PLC) based Industrial Water Treatment Systems (IWTS). Experiments on the publicly available SWaT dataset show that the optimised model achieves high detection performance (F1-score=0.983 and ROC-AUC=0.998). A deployment-style validation on the WADI dataset confirms that the proposed light-weight framework remains applicable beyond a single dataset. The research demonstrates that combining logic-aware supervision with Tiny Deep Learning (TinyDL) sequence learning creates an efficient and accurate anomaly detection suitable for resource constrained Programmable Logic Controllers (PLCs) in industrial environments.

---

### Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design

Authors: Alberto Pepe, Chien-Yu Lin, Despoina Magka, Bilge Acun, Yannan Nellie Wu, Anton Protopopov, Carole-Jean Wu, Yoram Bachrach
Published: 2026-05-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.15871v1

Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Compose for high-level architecture search, and AIRA-Design for low-level mechanistic implementation. AIRA-Compose uses 11 agents to explore fundamental computational primitives under a 24-hour budget. Agents evaluate million-parameter candidates, extrapolating top designs to 350M, 1B, and 3B scales. This yields 14 architectures across two families: AIRAformers (Transformer-based) and AIRAhybrids (Transformer-Mamba). Pre-trained at 1B scale, these consistently outperform Llama 3.2 and Composer-found baselines. On downstream tasks, AIRAformer-D and AIRAhybrid-D improve accuracy by 2.4% and 3.8% over Llama 3.2. Furthermore, AIRA-Compose finds models with highly efficient scaling frontiers: AIRAformer-C scales 54% and 71% faster than Llama 3.2 and Composer's best Transformer, while AIRAhybrid-C outscales Nemotron-2 by 23% and Composer's best hybrid by 37%. AIRA-Design tasks 20 agents with writing novel attention mechanisms for long-range dependencies and high-performing training scripts. On the Long Range Arena benchmark, agent-designed architectures reach within 2.3% and 2.6% of human state-of-the-art on document matching and text classification. On the Autoresearch benchmark, Greedy Opus 4.5 achieves 0.968 validation bits-per-byte under a fixed time budget, surpassing the published minimum. Together, these frameworks show AI agents can autonomously discover architectures and algorithmic optimizations matching or surpassing hand-designed baselines. This establishes a powerful paradigm for discovering next-generation foundation models, marking a clear step toward recursive self-improvement.

---

### SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval

Authors: Wenjie Yang, Hang Yu, Yuyu Guo, Peng Di
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15868v2

In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing universal multimodal retrieval works struggle with this task, as they are constrained by the labeled asymmetric datasets used. We produce SOLAR (Self-supervised jOint LeArning for symmetric multimodal Retrieval), a novel two-stage self-supervised framework that leverages readily available unlabeled web-scale image-text pairs. Based on the observation that both semantic alignment and discrepancies exist between two modalities, in the first stage, we learn the intersection mask of image-text pair, allowing us to align intersection while preserving semantic of difference. In the second stage, the learned mask is further utilized to construct positive and hardnegative samples via masking different parts of image/text, which enable us to conduct self-supervised multimodal embedding learning. Complementing this framework, we present a new benchmark featuring high-quality human-verified positive and hard-negative pairs to evaluate symmetric MM2MM retrieval under realistic conditions, as well as the corresponding pipeline. Extensive experiments against ten SOTA methods show SOLAR surpasses the strongest supervised VLM by 7.08 points on this benchmark, with over 50x fewer model parameters and a 5x smaller embedding dimension. Code, model and benchmark are available at https://github.com/codefuse-ai/SOLAR.

---

### Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination

Authors: Chufan Shi, Cheng Yang, Yaokang Wu, Linghao Jin, Bo Shui, Taylor Berg-Kirkpatrick, Xuezhe Ma
Published: 2026-05-15
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2605.15864v2

Vision-Language Models (VLMs) often produce self-reflective statements like "let me check the figure again" during reasoning. Do such statements trigger genuine visual re-examination, or are they merely learned textual patterns? We investigate this via VisualSwap, an image-swap probing framework: after a model reasons over an image, we replace it with a visually similar but semantically different one and test whether the model notices. We introduce VS-Bench, 800 image pairs curated from MathVista, MathVerse, MathVision, and MMMU-Pro. Experiments on Qwen3-VL, Kimi-VL, and ERNIE-VL reveal a striking failure: models overwhelmingly miss the swap, with accuracy dropping by up to 60%. Counterintuitively, thinking models are nearly 3x more vulnerable than their instructed counterparts, and scaling offers no mitigation. Multi-turn user instructions restore visual grounding, but self-generated reflective statements during continuous generation do not. Attention analysis explains why: user instructions substantially elevate attention to visual tokens, whereas self-reflection does not. Current VLMs tend to say rather than actually see when claiming to perform visual re-examination. Our code and dataset are available at the project page: https://visualswap.github.io

---

### From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint

Authors: Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
Published: 2026-05-15
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2605.15862v2

Understanding adaptive biomechanical systems requires distinguishing observable performance, static multivariate representation, longitudinal displacement, and internal approximation of observed change. This study introduces Level 5, which examines whether the M1-M2 transformation observed in a single-subject gait dataset can be approximated within a selected PCA representation. Gait was recorded with instrumented insoles in a participant with Parkinson's disease under six occlusal observational probes during two sessions eleven weeks apart. A simplified feed-forward neural network was trained to approximate M2 PC1-PC2 coordinates from M1 coordinates, occlusal-probe descriptors, and the longitudinal-transition indicator. In the core analysis aligned with Level 4, the model preserved the Euclidean centroid-displacement hierarchy dOC3 < dONL < dOC2.5. In the extended six-probe analysis, it preserved the broad structure of the exploratory ordering. Held-out M2 and leave-condition-out analyses provided internal tests beyond the full-dataset fit, while a within-session analysis described probe positions relative to ONL. The term predictive is used only in a restricted methodological sense. The model does not provide prospective clinical prediction, patient-level forecasting, or generalization to unseen individuals. Occlusal conditions are treated as observational probes applied during measurement, not as continuous causal drivers of longitudinal evolution. The findings are exploratory, retrospective, representation dependent, and non causal. They do not establish causal occlusal effects, validated viability thresholds, therapeutic superiority, distinct physiological states, or generalizable predictive validity.

---

### On RGB-TIR Stereo Calibration under Extreme Resolution Asymmetry

Authors: Michał Król, Michał Salamonowicz, Władysław Skarbek, Michał Tomaszewski
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15860v1

Accurate geometric calibration of RGB-thermal infrared (TIR) stereo camera systems is essential for multimodal building envelope analysis, yet remains challenging when low-cost thermal sensors with very low spatial resolution are employed. This paper presents a practical stereo calibration framework for an RGB camera (2028 x 1520 px) paired with a TIR camera operating at only 80 x 62 px - a pixel-count ratio of approximately 1:625. An active OLED screen dynamically switches modality-specific patterns (checkerboard for TIR, ChArUco for RGB) on a single physical surface, providing controlled and repeatable thermal contrast. A dedicated corner detection algorithm combining perspective rectification, Hessian saddle-point analysis, and Mean Shift localisation achieves reliable checkerboard detection at 80 x 62 px without per-frame parameter tuning. A baseline-constrained bundle adjustment enforces physically consistent rig geometry under the planar-calibration-object degeneracy, yielding a stereo baseline of 32.7 mm (nominal 30 mm) with an overall reprojection error of 0.382 px. The system is validated on a thermally active building mock-up using constant-depth and per-pixel depth estimation, demonstrating consistent TIR-to-RGB projection suitable for building energy performance assessment.

---

### Complexity of Non-Log-Concave Sampling in Fisher Information

Authors: Sinho Chewi, Andre Wibisono
Published: 2026-05-15
Categories: cs.DS, cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2605.15859v1

We study the query complexity of obtaining a relative Fisher information guarantee for sampling from a log-smooth non-log-concave distribution; this is a sampling analog of finding an approximate stationary point in optimization. Our algorithm is based on the proximal sampler, which is an implicit discretization of the Langevin diffusion, and requires an implementation of the backward step known as the restricted Gaussian oracle (RGO). We show that by leveraging the recent results for log-concave sampling with high-accuracy guarantees in Rényi divergence, we can obtain an approximate RGO implementation that -- when used with the proximal sampler -- yields a complexity guarantee in relative Fisher information that inherits the same dimension dependence as log-concave sampling, and improves upon prior work for non-log-concave sampling. We also show a converse reduction that any improvement in the dimension dependence in relative Fisher information for non-log-concave sampling will yield an improved dimension dependence for high-accuracy log-concave sampling.

---

### Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

Authors: Renye Yan, Jikang Cheng, Shikun Sun, Yi Sun, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Junliang Xing, Yimao Cai
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15855v1

Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards. However, most studies apply RL to the full denoising trajectory, making it computationally costly and weakening preference alignment, i.e., doing more but achieving less. We observe that the impact of RL fine-tuning varies significantly across denoising stages. In the early stage, image structures are unstable and distant from the final reward signal. Applying RL at this stage leads to delayed rewards and action-reward mismatching, resulting in high variance and inefficient updates. Conversely, in the later stage, reward gains saturate, and continued training tends to overfit local details, intensifying reward hacking. To tackle these challenges, we propose AdaScope, an RL-enhanced plug-in that improves generation quality while reducing computational cost. Specifically, AdaScope adaptively identifies the optimal intervention timing for RL by perceiving the structural evolution and semantic consistency during denoising, and dynamically terminates training once the denoising converges and reward gains saturate. As a result, it achieves a rare 'dual benefit': a reduction in computational costs alongside a significant performance improvement. We offer theoretical grounds for the design of AdaScope. Compared with state-of-the-art methods, AdaScope improves performance by 66% while cutting computational cost by 59%.

---

### GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction

Authors: Leyang Chen, Junyi Wu, Zhiteng Li, Yulun Zhang
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15852v2

Streaming 3D reconstruction from long monocular video sequences requires maintaining a key-value (KV) cache that grows linearly with sequence length, creating a severe memory bottleneck. Existing approaches either truncate the cache to a fixed set of anchor frames, leading to reconstruction quality degradation, or rely on attention-score heuristics that are agnostic to 3D scene structure, failing to preserve geometrically valuable tokens. To address these problems, we present GHOST (Geometry-Hierarchical Online Streaming Token Eviction), a training-free KV cache management framework that exploits the model's own 3D geometry outputs to evict redundant tokens online. GHOST introduces three mutually reinforcing innovations: a hierarchical dual-level importance scoring scheme, a privilege mechanism that protects special tokens from eviction, and a cosine-similarity-guided layer-wise budget allocation. Experiments on various benchmarks show that GHOST preserves excellent reconstruction quality while cutting the KV cache by nearly half and delivering 1.75x faster inference compared to state-of-the-art methods. Our code is available at https://github.com/lokiniuniu/GHOST.

---

### Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education

Authors: Janne Rotter, Pau Benazet i Montobbio, Davinia Hernández-Leo
Published: 2026-05-15
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2605.15850v3

In recent years, generative AI (GenAI) in educational settings has become ubiquitous in university students' daily lives, despite its potential to induce over-reliance, metacognitive disengagement, and diminished learning when used unrestrictedly. While most prior research has focused on how to pedagogically scaffold its usage, the question of when to allow off-the-shelf GenAI remains understudied and lacks pedagogically grounded empirical investigation. We treat access timing itself as a form of implicit scaffolding and operationalize it through a reinforcement learning (RL) agent that decides when students should access GenAI, with a reward function grounded in metacognitive theory, cognitive load theory, and productive failure. In a mixed-methods controlled lab study with N=105 higher education students, we compared the agent's effect on learning gains and metacognitive engagement to unrestricted and fully restricted use. Results show that strategically timed GenAI access under the reinforcement learning condition improved objective post-test performance and metacognitive accuracy compared with unrestricted access, without requiring explicit metacognitive prompts or structured scaffolding. Exploratory comparisons with the fully restricted condition further suggest that timed access may reduce task errors and time on task relative to complete withholding. Overall, timing of GenAI access therefore is a tractable, theoretically grounded, and scalable pedagogical strategy that improves over completely unrestricted and withheld access, compatible with off-the-shelf tools and potentially low adoption barrier. This opens up a new research area that explores how access timing can be facilitated by educators and implemented in human-AI learning system design.

---

### Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education

Authors: Janne Rotter, Pau Benazet i Montobbio, Davinia Hernández-Leo
Published: 2026-05-15
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2605.15850v2

In recent years, generative AI (GenAI) in educational settings has become ubiquitous in university students' daily lives, despite its potential to induce over-reliance, metacognitive disengagement, and diminished learning when used unrestrictedly. While most prior research has focused on how to pedagogically scaffold its usage, the question of when to allow off-the-shelf GenAI remains understudied and lacks pedagogically grounded empirical investigation. We treat access timing itself as a form of implicit scaffolding and operationalize it through a reinforcement learning (RL) agent that decides when students should access GenAI, with a reward function grounded in metacognitive theory, cognitive load theory, and productive failure. In a mixed-methods controlled lab study with N=105 higher education students, we compared the agent's effect on learning gains and metacognitive engagement to unrestricted and fully restricted use. Results show that strategically timed GenAI access under the reinforcement learning condition improved objective post-test performance and metacognitive accuracy compared with unrestricted access, while reducing task errors and time on task relative to complete withholding, thus outperforming both approaches without the need for explicit metacognitive prompts or structured scaffolding. However, no between-condition differences emerged on self-reported metacognitive awareness. Overall, timing of GenAI access therefore is a tractable, theoretically grounded, and scalable pedagogical strategy that improves over completely unrestricted and withheld access, compatible with off-the-shelf tools and potentially low adoption barrier. This opens up a new research area that explores how access timing can be facilitated by educators and implemented in human-AI learning system design.

---

### Conversations in Space: Non-Linear LLM Interaction in Everyday Use

Authors: Rifat Mehreen Amin, Alperen Adatepe, Daniela Fernandes, Daniel Buschek, Andreas Butz
Published: 2026-05-15
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2605.15848v2

As LLM conversations grow, their histories capture alternative directions, decisions, and evolving lines of thought that can be difficult to navigate through chat alone. We investigate an interaction concept that represents the same conversation through two synchronized views: a familiar linear chat for ongoing dialogue and a spatial canvas for navigating its emerging structure. To investigate this interaction concept, we developed CanvasConvo, which allows conversations to branch into alternative paths that remain accessible across both views. In a five-day field deployment with 24 participants, we examined how people appropriated this parallel representation in self-directed knowledge work. Participants selectively moved between the two views rather than replacing chat with the canvas. Chat remained central to conversational interaction, while the canvas supported overview, revisitation, and exploration of alternatives. Adoption was uneven, revealing challenges around established chat habits, transitions between representations, and understanding branch context. Our findings inform the design of user interfaces for LLMs that combine linear and non-linear conversation representations.

---

### Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas

Authors: Rifat Mehreen Amin, Alperen Adatepe, Daniela Fernandes, Daniel Buschek, Andreas Butz
Published: 2026-05-15
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2605.15848v1

Conversational interfaces powered by large language models (LLMs) are widely used for ideation and analysis, yet their linear structure limits exploration of alternatives and management of long-running interactions. We present CanvasConvo, a conversational interface concept that transforms linear chat into a branching conversation tree embedded in a spatial canvas. CanvasConvo enables users to explore what-if scenarios by branching directly from conversational content, supporting parallel development of alternative directions. These branches are visualized on a canvas while remaining integrated with a familiar chat interface, allowing users to switch between linear and non-linear interaction. Features such as timeline-based navigation, automatic tagging and summarization, and context-aware controls (e.g., goals, reusable prompts) support structured interaction and continuity. We evaluated CanvasConvo in a 5-7 day field study with 24 participants. Our findings highlight how non-linear conversational structures support exploratory workflows and different interactions in LLM-based work.

---

### RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades

Authors: Xinbo Xu, Ruihan Yang, Haiyang Shen, Wendong Xu, Bofei Gao, Ruoyu Wu, Kean Shi, Weichu Xie, Xuanzhong Chen, Ming Wu, Jason Zeng, Michael Heinrich et al.
Published: 2026-05-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.15846v2

Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes from Python repositories, with coarse pass/fail evaluation outcomes, and thus fail to capture long-horizon, multi-target development at real engineering scale. To address this gap, we present RoadmapBench, a benchmark of 115 long-horizon coding tasks grounded in real open-source version upgrades across 17 repositories and 5 programming languages. Each task places the agent on a source-version code snapshot and provides a multi-target roadmap instruction requiring it to implement the functionality introduced in the target version, with a median modification of 3,700 lines across 51 files. We conduct a systematic evaluation on thirteen frontier models and find that even the strongest, Claude-Opus-4.7, resolves only 39.1% of tasks, while the weakest achieves merely 5.2%, in stark contrast to existing bug-fix benchmarks, suggesting that long-horizon software development remains a largely unsolved problem.

---

### WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes

Authors: Jichen Hu, Jiawei Guo, Jiazhong Cen, Chen Yang, Sikuang Li, Wei Shen
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15843v1

Recent 3D world modeling systems based on generative scene synthesis, such as Marble, can create coherent and explorable 3D environments, yet their outputs are typically static monolithic assets with limited editability and physical interaction. This restricts their use in immersive content creation and embodied simulation, where generated worlds must be actively modified and manipulated. To tackle this challenge, we present WorldAct, a framework that converts static generated 3D worlds into editable and interaction-ready scenes. WorldAct uses a multimodal agent to guide scene decomposition, identify actionable objects, reconstruct geometrically aligned object-level meshes for interaction, and restore the residual background via 3D inpainting. The resulting scenes support object-level editing, collision-aware manipulation, and embodied task execution while preserving global scene coherence. Experiments show that WorldAct enables richer interaction scenarios than the original generated scenes, suggesting a practical path toward editable and interactive 3D world models.

---

### GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

Authors: Davide Buoso, Andrea Protopapa, Stefano Di Carlo, Francesca Pistilli, Giuseppe Averta
Published: 2026-05-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.15836v1

Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling high-dimensional RGB representations into control-relevant geometry without overfitting. While using frozen pre-trained Vision Foundation Models (VFMs) improves data efficiency, it also shifts most task adaptation onto a small spatial pooling module, which can latch onto task-irrelevant shortcuts and lose geometric grounding when finetuned with few data samples. More broadly, pre-trained visual representations used for policy learning have been observed to struggle under even minor scene perturbations, highlighting the need for robustness-oriented inductive biases. We propose Geometric Anchor Pre-training (GAP), a simple, action-free warm-up stage that regularizes the spatial adapter before downstream imitation learning. GAP pre-trains the pooling layer on a lightweight simulated proxy task where object masks are available at no cost, encouraging the adapter to produce keypoints that lie on the object, cover its spatial extent, and remain sharp and repeatable over time. This yields stable geometric anchors that provide a reliable coordinate interface for few-shot policy learning, while keeping the VFM frozen. We evaluate GAP on RoboMimic and ManiSkill under severe data scarcity (15-50 demonstrations) and domain shift. A simple adapter regularized with GAP consistently outperforms stronger attention-based poolers and end-to-end fine-tuning, achieving 62% success on RoboMimic Can with 15 demonstrations (+16% over AFA), 63% on the long-horizon high-precision Tool Hang task with 50 demonstrations, and 61% on ManiSkill StackCube with 30 demonstrations (+11% over full fine-tuning). The proxy stage is lightweight and fully decoupled from downstream tasks, making it practical to reuse across environments and manipulation skills.

---

### Community-aware evaluation and threshold calibration for open-set plankton image recognition

Authors: Xi Chen, Eryuan Huang, Yingjun Xiao, Gang Fang
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15835v1

Automated plankton image recognition is increasingly used in aquatic ecosystem monitoring, but deployed classifiers inevitably encounter unseen taxa and non-target particles. Open-set recognition methods are usually evaluated with sample-level metrics such as AUROC, AUPR, and FPR@95% unknown-recall operating points, whereas ecological monitoring depends on community-level estimates of taxon abundance and diversity. This study examines the mismatch between these objectives using controlled pseudo-communities and three datasets spanning marine zooplankton imaged by ZooScan, marine phytoplankton imaged by IFCB, and freshwater plankton imaged by an in-situ camera. We define Open-Set Community Distortion (OSCD), a Bray-Curtis-style error over known taxa plus an unknown bin, with directional components distinguishing known-taxon overestimation from underestimation. Closed-set classifiers achieved high known-class accuracy, but unknown samples were often absorbed with high confidence and in structured ways. Sample-level OOD metrics were not sufficient to select ecological operating points: for MSP, FPR@95% unknown-recall thresholds produced large test-community OSCD on all three datasets mainly because true known taxa were over-rejected into the unknown bin. Community-aware threshold calibration reduced MSP OSCD relative to fixed 95% known recall on SYKE-ZooScan 2024 and SYKE-IFCB 2022; on ZooLake the fixed-recall baseline was already close to the community-aware threshold, and the best community-level method was a prototype-distance variant rather than MSP. The benefit of community-aware calibration therefore depends on validation-community representativeness and the gap between fixed recall and the community optimum. These results show that open-set plankton recognition should be evaluated as an ecological measurement problem, not only as a sample-level detection task.

---

### Heuristic-Based Merging of HPC Traces to Extend Hardware Counter Coverage

Authors: Júlia Orteu Aubach, Fabio Banchelli, Marc Clascà Ramírez, Marta Garcia-Gasulla
Published: 2026-05-15
Categories: cs.PF, cs.LG
arXiv: https://arxiv.org/abs/2605.15832v1

This work extends a framework for predicting the performance of High-Performance Computing (HPC) workloads using Machine Learning (ML). A common limitation in performance modeling is the restricted number of hardware counters that can be collected simultaneously. To address this, we propose a heuristic-based methodology to merge execution traces from multiple runs, each instrumented with a different set of hardware counters. Our approach matches computation bursts across executions by analyzing MPI structure, timing, and communication patterns. This process enables the construction of a unified dataset that includes a wider set of hardware features without relying on multiplexing. The output is a new synthetic trace with all merged counters, which can be used both for HPC performance prediction and for conventional performance analysis. The methodology has been validated on MareNostrum5 machine with a range of kernels and real applications. Results show that the merged counters maintain acceptable accuracy depending on the application, and can be directly used to train ML models on a richer feature space without prior counter selection.

---

### Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation

Authors: Yuqing Cheng, Xingyu Ma, Guochen Yu, Xiaotao Gu
Published: 2026-05-15
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2605.15831v1

Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization, which preserves reconstruction quality but complicates language modeling after sequence flattening, as the residual hierarchy imposes strong sequential dependencies and can amplify error accumulation. We propose BandTok, a generation-oriented 2D Mel-spectrogram tokenizer that represents each frame with Mel-frequency band tokens from a single shared codebook. This design yields a physically interpretable time-frequency token grid with a more independent token structure, making it better suited for autoregressive modeling. BandTok improves reconstruction with a multi-scale PatchGAN objective and EMA codebook updates. We further introduce an autoregressive language model with 2D Rotary Position Embedding (2D RoPE) to preserve temporal and frequency-band structure during generation. Experiments show that BandTok improves over residual-codebook tokenizers and achieves strong results in a data-limited setting. The source code and generation demos for this work are publicly available.

---

### Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

Authors: Yipu Zhang, Jintao Cheng, Weilun Feng, Jiehao Luo, Chuanguang Yang, Zhulin An, Yongjun Xu, Wei Zhang
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15828v3

Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera pose prediction, and point cloud reconstruction in a single forward pass. They have been widely adopted in 3D vision applications, but their billion-scale parameters bring substantial memory and computation overhead, posing challenges for on-device deployment. Post-Training Quantization (PTQ) is an effective technique to reduce this overhead. Existing PTQ methods for feed-forward 3D models mainly focus on handling heavy-tailed activation distributions and constructing diverse calibration datasets. However, we observe that feed-forward 3D models predict multiple geometric attributes through a shared backbone, where different transformer blocks and hidden channels contribute distinctly to each task, resulting in substantially different sensitivities to quantization errors across tasks, blocks, and channels. Consequently, treating all tasks equally over-emphasizes insensitive tasks and causes significant accuracy loss on the sensitive ones. To address this issue, we propose Fisher-Guided Quantization (FGQ) for feed-forward 3D reconstruction models. Specifically, FGQ uses the diagonal Fisher information matrix to quantify the different sensitivities across tasks, blocks, and channels, and incorporates these sensitivities into the Learnable Affine Transformation during calibration to better preserve the channels and blocks most critical to each task. Extensive experiments across camera pose estimation, point map reconstruction, and depth estimation show that FGQ consistently outperforms state-of-the-art quantization baselines on VGGT, achieving up to 39% relative improvement under the 4-bit quantization. Code is available at https://github.com/ypzhng/FGQ.

---

### Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

Authors: Yipu Zhang, Jintao Cheng, Weilun Feng, Jiehao Luo, Chuanguang Yang, Zhulin An, Yongjun Xu, Wei Zhang
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15828v2

Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera pose prediction, and point cloud reconstruction in a single forward pass. They have been widely adopted in 3D vision applications, but their billion-scale parameters bring substantial memory and computation overhead, posing challenges for on-device deployment. Post-Training Quantization (PTQ) is an effective technique to reduce this overhead. Existing PTQ methods for feed-forward 3D models mainly focus on handling heavy-tailed activation distributions and constructing diverse calibration datasets. However, we observe that feed-forward 3D models predict multiple geometric attributes through a shared backbone, where different transformer blocks and hidden channels contribute distinctly to each task, resulting in substantially different sensitivities to quantization errors across tasks, blocks, and channels. Consequently, treating all tasks equally over-emphasizes insensitive tasks and causes significant accuracy loss on the sensitive ones. To address this issue, we propose Fisher-Guided Quantization (FGQ) for feed-forward 3D reconstruction models. Specifically, FGQ uses the diagonal Fisher information matrix to quantify the different sensitivities across tasks, blocks, and channels, and incorporates these sensitivities into the Learnable Affine Transformation during calibration to better preserve the channels and blocks most critical to each task. Extensive experiments across camera pose estimation, point map reconstruction, and depth estimation show that FGQ consistently outperforms state-of-the-art quantization baselines on VGGT, achieving up to 39% relative improvement under the 4-bit quantization. Code is available at https://github.com/ypzhng/FGQ.

---

### FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Authors: Quanjian Song, Yefeng Shen, Mengting Chen, Hao Sun, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Liujuan Cao
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15824v2

Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference-garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and consistent long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180$\times$ faster than existing baselines.

---

### Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds

Authors: Guoji Fu, Taiji Suzuki, Wee Sun Lee, Atsushi Nitanda
Published: 2026-05-15
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.15822v1

Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear structures. We prove that, for compact $d$-dimensional smooth manifolds $\mathcal{M} \subset (0,1)^D$ with $d > 2$ and $β$-Hölder densities strictly positive on $\mathcal{M}$, a variance-preserving SGM estimator attains the intrinsic Wasserstein--1 sample exponent $\tilde{\mathcal{O}}(D^{\mathcal{O}_β(d)}n^{-(β+1)/(d+2β)})$, up to logarithmic factors and explicit geometry and density factors. The full nonasymptotic bound explicitly isolates the finite-order geometry envelope, Hölder radius, density lower bound, ambient dependence, and finite-order correction terms. The analysis separates score approximation into a large-noise tangent-cell regime and a small-noise projection-centered, de-Gaussianized Laplace regime. The key technical ingredient is a ReLU implementation of nearest-projection coordinates via finite intrinsic anchors and Gauss--Newton iterations, rather than approximating the manifold projection as a black-box high-dimensional smooth map. Consequently, for families with polynomially controlled geometry and density lower bounds, the constructed score-network parameters have polynomial ambient dependence.

---

### StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion

Authors: Ofir Gilad, Aleksander Plocharski, Przemyslaw Musialski, Andrei Sharf
Published: 2026-05-15
Categories: cs.GR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.15816v1

Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iterative optimizers, which are slow, non-differentiable, and must be re-run from scratch for each new target. Learned alternatives have so far addressed only unconditional point generation; capacity-constrained, image-conditioned stippling has remained out of reach. We present the first diffusion-based sampler that simultaneously satisfies a learned local point-distribution prior and a continuous, image-defined capacity constraint at inference. The method is a ControlNet branch built on top of an optimal-transport-grid point-set diffusion baseline, conditioned on the target density map and a high-resolution image. Two design choices make the combination tractable: training and inference are restricted to the late-stage denoising regime, initialized from a density-weighted rejection sample, and the standard zero-convolution injection is replaced with a sigmoid-gated 1x1 projection that preserves the base model's blue-noise structure under hard density signals. A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end.

---

### BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge

Authors: Sihan Fu, Oucheng Liu, Shiyuan Wang, Jin Shi, Chengkun Wei
Published: 2026-05-15
Categories: cs.SE, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2605.15815v1

Code agents increasingly help developers work with unfamiliar repositories, but every such task depends on a costly prerequisite: bootstrapping the repository into a usable development state. This process requires substantial trial-and-error exploration, yet the resulting knowledge--resolved dependencies, repair strategies--stays trapped in a single conversation, unavailable to future agents. We therefore formulate repository bootstrapping as a reusable startup knowledge problem and introduce BootstrapAgent, a multi-agent framework that distills the heuristics discovered during bootstrap exploration into a persistent, verifiable, agent-consumable .bootstrap contract. Through evidence extraction, structured planning, deterministic Docker-based verification, and trace-driven repair, BootstrapAgent generates a contract covering environment setup, diagnostic checks, minimal verification, and accumulated repair knowledge. We further propose warm repair with clean replay to accelerate iterative debugging without sacrificing cold-start reproducibility, and a delta repair with sanity check to prevent reward hacking. Experiments on three benchmarks show that BootstrapAgent achieves a 92.9% success rate, outperforming the baseline by over 10% while reducing downstream agent token usage by 25.9% and build time by 22.3%. Our code is available at https://github.com/Vossera/BootstrapAgent.

---

### Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

Authors: Feier Qin, Xiao Li, Yi Zheng, Haibin Huang, Hanyao Wang, Xiaoyu Wang, Yan Lu, Yuan Zhang
Published: 2026-05-15
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2605.15812v1

Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents' social behaviors and internal emotions: generated behaviors rarely influence an agent's emotional state, and emotional states seldom shape subsequent behaviors. We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression. CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions; and user feedback continually revises both memory and emotional state, enabling reflection and anticipation. We instantiate CTEM as Auri, a companion agent on an instant-messaging platform, and report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.

---

### Diversified Residual Symbolic Regression

Authors: Koki Ikeda, Masahiro Nomura, Ryoki Hamano
Published: 2026-05-15
Categories: cs.NE
arXiv: https://arxiv.org/abs/2605.15809v1

Symbolic regression (SR) aims to discover explicit mathematical expressions that explain observed data and is widely used in domains where interpretability is essential. Because interpretability requires expressions to reflect meaningful regularities, SR is sensitive to observations that deviate from the dominant relationship. Such irregular observations, or outliers, are common in real-world data and can hinder SR from identifying underlying regularities. Robust regression mitigates this by downweighting observations with large residuals. However, deciding which observations should be treated as outliers is often ambiguous and depends on user interpretation and domain knowledge, a perspective largely overlooked in existing SR studies. This motivates approaches that present multiple candidate expressions, allowing users to examine different residual patterns and choose expressions consistent with their expertise. We propose diversified residual symbolic regression (DRSR), which achieves high predictive accuracy while promoting diversity with respect to residual patterns based on the Quality-Diversity paradigm. DRSR collects multiple expressions that fit the data well but differ in how residuals are distributed, enabling post-search selection aligned with domain knowledge. On a synthetic mixture dataset, DRSR produces more diverse expressions than conventional SR while capturing multiple underlying relationships. On a real-world astronomical dataset, DRSR discovers multiple expressions consistent with known physical relationships.

---

### Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization

Authors: Kai Hidajat
Published: 2026-05-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.15806v2

Neural operators excel as deterministic surrogates, but inevitably collapse to the conditional mean when applied to stochastic PDEs, discarding the variance and tail structure upon which uncertainty quantification depends. Recovering this structure typically requires Monte Carlo rollouts or grafted generative models, both of which surrender the one-shot efficiency and resolution invariance that define the operator paradigm. To resolve this, we draw on the Doob-Meyer theorem, which establishes that any semimartingale fundamentally decomposes into a predictable drift and an unpredictable, zero-mean martingale. Translating this theorem into an architectural prior, we introduce the Martingale Neural Operator (MNO). MNO maps an initial condition directly to the conditional mean and covariance of the terminal law, parameterized by a drift-like mean and a low-rank factor $B_φ$ with $B_φ^\top B_φ$ positive semi-definite by construction. For our experiments, we use a Gaussian residual instantiation. Across 1D SPDEs, rough volatility, and 2D operator tasks, MNO reduces Wasserstein distance by up to $120\times$ on $φ^4$ field theory and $68\times$ on stochastic Burgers, evaluating $\sim 3\times$ faster than a conditional diffusion baseline at matched wall-clock training budgets. On 2D tasks, MNO is comparable to FNO on zero-shot resolution transfer and turbulent flow, while quasi-deterministic systems such as Gray-Scott remain a failure mode.

---

### Embedding-perturbed Exploration Preference Optimization for Flow Models

Authors: Sujie Hu, Chubin Chen, Jiashu Zhu, Jiahong Wu, Xiangxiang Chu, Xiu Li
Published: 2026-05-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.15803v1

Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization frameworks (e.g., GRPO) face a critical limitation: the rapid decay of intra-group variance. As the distinctiveness among samples within a group diminishes, the variance approaches zero. This eliminates the very learning signal required for optimization, rendering the process unstable and forcing the policy into premature stagnation or reward hacking. Existing strategies, such as varying the initial noise or increasing group sizes, often fail to address this fundamental issue, resulting in training instability or diminishing returns. To overcome these challenges, we propose $\textbf{Embedding-perturbed Exploration Preference Optimization (}E^2\textbf{PO)}$, a novel framework that sustains optimization through embedding-level perturbation. Our method introduces structured, embedding-level perturbations within sample groups, guaranteeing a robust variance that preserves the discriminative signal throughout the training process. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving a more faithful alignment with human preference.

---

### Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion

Authors: Xiongjun Guan, Jianjiang Feng, Jie Zhou
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15796v2

Three-dimensional (3D) fingerprints preserve global finger geometry and local ridge structure while avoiding contact-induced deformation, but they remain difficult to integrate with legacy two-dimensional (2D) fingerprint systems. This paper addresses the intermediate stage between 3D acquisition and cross-modal matching, and presents a unified framework for 3D fingerprint preprocessing and registration across contactless and contact-based 2D modalities. The framework combines four components: 1) a nonparametric visualization and unwrapping method that converts a 3D fingerprint point cloud into a rolled-equivalent 2D representation without relying on a global finger-shape model; 2) a point-cloud fusion pipeline that registers and mosaics multiple partial 3D captures into a more complete fingerprint model; 3) an ellipse-based pose normalization method for canonical finger alignment; and 4) a pose-aware cross-modal registration strategy that improves compatibility between 3D fingerprints and both contactless and contact-based 2D fingerprints. Experiments on a self-collected multimodal fingerprint database containing 150 fingers show that the proposed framework achieves ridge-level 3D registration accuracy, robust pose estimation, and consistent gains in 2D compatibility. In particular, the 3D fusion error is concentrated around 0.09 mm, contactless 2D--3D registration reaches ridge-scale projection accuracy, and pose-aware unwrapping improves genuine matching scores relative to generic 3D unwrapping. These results support the use of 3D fingerprints as an effective geometric bridge across heterogeneous fingerprint modalities. The baseline implementation has been publicly released at https://github.com/XiongjunGuan/3DFpVisual.

---

### ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation

Authors: Michał Ciesiółka, Dawid Wiśniewski, Adrian Charkiewicz, Kamil Guttmann
Published: 2026-05-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.15794v1

We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across 15 language pairs that preserves original layout metadata proposed for multimodal machine translation. To ensure structural diversity in the dataset, we employ K-Medoids sampling over 45 geometric features, capturing complex elements like nested tables and formulas to focus only on visually diverse PDF documents. Our evaluation reveals that current MT systems struggle with spatial grounding and geometric synchronization, often losing the link between text and its visual context. ForMaT provides a benchmark for developing layout-aware translation models that integrate visual and textual context for high-fidelity document reconstruction.

---

### AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training

Authors: Qitan Lv, Hong Wang, Zhongkai Hao, Wen Wu, Xuenan Xu, Bowen Zhou, Feng Wu, Chao Zhang
Published: 2026-05-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.15793v1

Pre-training neural operators on diverse partial differential equation (PDE) datasets has emerged as a promising direction for building general-purpose surrogate models in scientific machine learning. However, the inherent complexity and structural diversity of PDE solution operators make multi-PDE pre-training fundamentally challenging. Existing methods mainly address this by increasing model capacity, while leaving the target solution operators unchanged. Inspired by classical numerical analysis, we instead propose to transform complex and diverse solution operators into simpler, better-aligned forms that are easier to model jointly. Since the optimal transformation varies across PDE types, it must be adaptive and input-dependent, allowing a single neural operator to approximate an entire family of operators. We instantiate this idea as AOT-POT (adaptive operator-transformation for pre-training operator transformer), which expands hidden representations into multiple parallel streams, adaptively aggregates and redistributes them before and after each sub-layer, and mixes streams through Sinkhorn-projected doubly stochastic matrices for stable training. These mechanisms together reshape diverse solution operators into a unified form that can be effectively modeled by a single architecture. Empirically, AOT-POT achieves state-of-the-art performance on 12 PDE benchmarks with only 3\% additional parameters, reducing relative L2 error by up to 77.6\% (40.9\% on average). Fine-tuning AOT-POT further reduces L2 error by up to 92\% on in-domain PDEs and 89\% on out-of-domain PDEs (unseen types during pre-training), demonstrating that adaptive operator transformation is an effective and complementary direction for advancing PDE foundation models beyond simply scaling model capacity.

---

### Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models

Authors: Yujun Tong, Dongliang Chang, Zijin Yin, Xintong Liu, Yuanchen Fang, Zhanyu Ma
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15792v1

The long-standing goal of multimodal AI is to build unified models in which visual understanding and visual generation mutually enhance one another. Despite recent works such as BAGEL, BLIP3o achieves remarkable progress; In practice, however, this unification remains one-directional: understanding routinely guides generation, yet how and why generation can support understanding is rarely investigated. We revisit this asymmetry and propose Generation-to-Understanding (G2U) synergy, where visual generation becomes an explicit intermediate reasoning step. Our framework enables a model to perform controlled generative acts, such as detail enhancement, context expansion or structural visualisation, to produce self-generated visual thoughts, which are then fed back into the model to refine perception without retraining or external tools. Through a comprehensive evaluation on twelve benchmarks, this reversed information flow consistently improves multimodal understanding. We show that generative fidelity bounds perceptual gain and that distinct families of edit prompts govern transfer efficiency. We further analyse whether models can decide what to imagine. While they can produce plausible edits, these self-generated visual thoughts lack stable task alignment, revealing that current large multimodal models fall short of true self-reflection. This work exposes a missing mechanism in unified cognition and suggests that imagination is not the end of understanding but its beginning.

---

### Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagation

Authors: Ruirui Liu, Xuejie Hou, Yiping Jiang, Hui Ren
Published: 2026-05-15
Categories: cs.LG, eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2605.15789v1

Uncertainty quantification is essential in safety-critical settings--from autonomous driving to aviation, finance, and health--where decisions must rely on conservative bounds rather than point estimates. Predictor-level intervals (e.g., from quantile regression, conformal prediction, variance networks, or Bayesian models) generally do not compose: adding two per-variable intervals need not yield a valid interval for their sum or preserve coverage. In aviation, Gaussian overbounding replaces complex error distributions with a conservative Gaussian whose tails dominate the truth, so conservatism propagates through linear operations. Yet classical overbounds are global, often overly conservative, and hard to adapt to feature-conditioned errors. We propose a unified learning framework that trains neural networks to produce context-aware Gaussian overbounds--mean and scale--with provable conservatism on a finite quantile grid and, under three explicit regularity assumptions, continuous-tail conservatism on a certified interval. Our overbounding loss enforces conservativeness at selected quantiles while penalizing distributional distance with a Wasserstein-style term. The learned bounds support conservative linear-combination and convolution analysis on the enforced grid, and on the certified interval when assumptions hold, while being less redundant than traditional methods. We provide a scoped analysis of discrete-to-continuous conservatism and compact-domain objective regularity, and validate on synthetic data and real-world datasets, including multipath, ionospheric, and tropospheric residual errors. Across these settings, the method yields tighter bounds while maintaining conservatism on the enforced grid and in experiments. The framework is modality-agnostic and applicable to learning systems that require conservative, feature-conditioned uncertainty estimates in dynamic environments.

---

### ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration

Authors: Himanshu Singh Baghel
Published: 2026-05-15
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2605.15788v1

Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment new capacity is ready to serve traffic. In practice, this cold-start duration can vary substantially across environments and even across consecutive scale-out events. We present ADAPT (Adaptive Duration Approximation for Predictive Timing), an online EWMA estimator that tracks coldstart duration at runtime. ADAPT feeds a dynamic planning horizon, FH-OPT, into a Model Predictive Controller (MPC) that optimizes replica counts over a rolling window. Together, these components form a closed-loop proactive autoscaling design that adapts its lookahead based on measured provisioning delay. Evaluated across three policies (MPC+LSTM, MPC+Prophet, HPA) and six workload archetypes with five random seeds, MPC+LSTM achieves below 5% SLA violation on all workloads, compared with 7-19% for reactive HPA and up to 28.7% for MPC+Prophet on bimodal traffic.

---

### Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets

Authors: Kai Hidajat, Solden Stoll, Joseph An
Published: 2026-05-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.15787v1

Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm minimization, feature emergence, or the late discovery of sparse subnetworks. These explanations capture important parts of the transition, but ignore a constraint unique to attention-based models: if attention discards an informative token, no bounded downstream computation can recover it. We formalize attention as an implicit Bayesian posterior over the task dependency graph and prove that generalization requires two separable conditions: a familiar Goldilocks bound on MLP capacity, coinciding with norm-based theories of grokking, and a novel Bayesian structural condition requiring attention to place sufficient mass on every informative token. This decoupling explains delayed generalization as delayed structural inference. Early in training, the MLP memorizes through unaligned features, drives the cross-entropy loss near zero, and thereby starves attention of structural gradient. Weight decay must then erode memorization before the missing graph becomes learnable, yielding the known inverse-weight-decay delay, which we derive as a structural waiting time. We then prove that this explaining-away delay can be bypassed by a KL-based structural intervention, yielding an inverse-intervention-strength scaling law for the grokking time. Experiments on algorithmic sequence tasks isolate structure from capacity and show that this Bayesian ticket matches or outperforms lottery-ticket transfer.

---

### A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking

Authors: Jianlin Ye, Christos Kyrkou, Panayiotis Kolios
Published: 2026-05-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.15779v1

The integration of Unmanned Aerial Vehicles(UAVs) into Intelligent Transportation Systems (ITS) offers synoptic visibility for traffic monitoring, yet scalable deployment is hindered by trajectory fragmentation, where vehicle identity persistence is lost across multi-UAV Fields of View (FOV). While state-of-the-art frameworks excel in optimizing local trajectory extraction and stability for single-drone imagery, they often function as isolated data silos that generate disjointed trajectories, thereby precluding network-level analysis such as Origin-Destination estimation. This paper presents a real-time Multi-Camera Multi-Vehicle Tracking (MCMT) system designed to handle global identity persistence. Addressing the visual ambiguity and computational cost of appearance-based Re-Identification (Re-ID) in nadir views, we introduce a lightweight Topology-Based Spatiotemporal Handover mechanism. We implement a high-throughput parallel pipeline leveraging YOLO11 and ByteTrack to process concurrent 4K streams. Our core contribution is a deterministic queue-based matching algorithm that utilizes geometric overlaps and virtual lane discretization to predictively manage identity handover via FIFO queues. Experimental results on complex urban environments, including intersections and merging traffic, demonstrate a Handover Success Rate (HOSR) of 99.8% in continuous traffic flows, significantly outperforming Re-ID baselines (74.1%) while validating edge deployment feasibility. The source code is available at https://github.com/JYe9/multi-camera-multi-vehicle-tracking-system.

---

### SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Authors: Kean Shi, Zihang Li, Tianyi Ma, Zengji Tu, Jialong Wu, Xinbo Xu, Qingyao Yang, Ruoyu Wu, Weichu Xie, Ming Wu, Jason Zeng, Michael Heinrich et al.
Published: 2026-05-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.15777v2

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing web and GUI agent benchmarks often rely on simplified settings, isolated tasks, or short-horizon interactions, making it difficult to assess capabilities of agents in realistic professional workflows. Software-as-a-Service (SaaS) environments are a natural choice for CUA evaluation, as they host a large share of modern digital work and naturally involve dynamic system states, cross-application coordination, domain-specific knowledge, and long-horizon dependencies. To this end, we introduce SaaS-Bench, a benchmark built on 23 deployable SaaS systems across six professional domains, containing 106 tasks grounded in realistic work scenarios. These tasks require long-horizon execution, cover both text-only and multimodal settings, and are evaluated with weighted verification checkpoints that measure strict task completion and partial progress. Experiments show that representative LLM-based agents struggle on SaaS-Bench, with even the strongest model completing fewer than 4% of tasks end-to-end, exposing limitations in planning, state tracking, cross-application context maintenance, and error recovery. Code are available at https://github.com/UniPat-AI/SaaS-Bench for reproduction.

---

### Continual Learning of Domain-Invariant Representations

Authors: Pascal Janetzky, Tobias Schlagenhauf, Stefan Feuerriegel
Published: 2026-05-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.15775v1

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious, domain-specific cues (``shortcut learning''), which limits generalization to unseen domains after deployment. In this paper, we address this limitation through continual learning of domain-invariant representation. We introduce a broad class of CL methods that sequentially learn representations capturing invariant structures across domains. Our methods are motivated by the observation that such invariant structures often preserve the underlying causal mechanisms, which can reduce the risk of overfitting to domain-specific cues and thus offer better out-of-domain generalization. Our proposed CL methods combine replay-based training with a tailored sequential invariance alignment to learn -- and preserve -- invariant structures over time. We evaluate our methods under a deployment-oriented protocol that measures performance on unseen target domains. Across six benchmark and real-world datasets spanning vision, medicine, manufacturing, and ecology, our methods consistently outperform existing CL baselines in terms of generalization to unseen target domains. As an ablation, we further show that naïve extensions of sequential training with existing domain-invariant representation learning (DIRL) methods provide only limited benefits. To the best of our knowledge, this is the first work to develop domain-invariant representation methods for CL.

---

### Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics

Authors: K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen
Published: 2026-05-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.15769v1

The co-optimization of a robot's body and brain presents a coupled challenge: the morphology constrains which control strategies are effective, while the control determines how well the morphology performs. To address this, we combine morphology optimization as evolution with controller optimization as lifetime learning, utilizing Lamarckian inheritance to transfer learned controller parameters from parent to offspring. In dynamic environments, existing literature presents conflicting evidence: while traditional evolutionary theory often suggests Lamarckian inheritance lacks benefit, recent studies in evolutionary robotics indicate it can improve performance. We hypothesize that this is because previous works have not included all relevant variables with dynamic environments. In this work, we show that the benefit of Lamarckian inheritance depends on two variables: how conflicting the environmental changes are to robot control, and the predictability of those changes for the robotic agent. Using virtual soft robots and two different learning approaches, Bayesian optimization and reinforcement learning, we show that Lamarckian inheritance only underperforms Darwinian inheritance when the changes are both conflicting and unpredictable. We find that adding a sensor to detect environmental changes restores the benefits for Lamarckian inheritance in conflicting environments, by allowing robotic agents to predict the need for a different behavior, thereby generalizing their control.

---

### ALSO: Adversarial Online Strategy Optimization for Social Agents

Authors: Xiang Li, Liping Yi, Mingze Kong, Min Zhang, Zhongxiang Dai, QingHua Hu
Published: 2026-05-15
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.15768v2

Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently non-stationary, requiring agents to dynamically adjust their strategies over time. However, most Large Language Model (LLM) based social agents rely on static personas, while existing approaches for enhancing social intelligence, such as offline reinforcement learning or external planners, are ill-suited to these settings, typically assuming stationarity and incurring substantial training overhead. To bridge this gap, we propose \textbf{ALSO} (\textbf{A}dversarial on\textbf{L}ine \textbf{S}trategy \textbf{O}ptimization), the first framework for online strategy optimization in multi-agent social simulation. ALSO advances social adaptation through two key contributions. (1) ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms, providing a principled solution to non-stationarity without relying on environmental stability assumptions. (2) To predict rewards and generalize sparse feedback in multi-turn dialogues, ALSO introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation. Experiments on the Sotopia benchmark demonstrate that ALSO consistently outperforms static baselines and existing optimization methods in dynamic environments, validating the effectiveness of adversarial online strategy optimization for building robust social agents.

---

### GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

Authors: Junho Kim, Xu Cao, Houze Yang, Bikram Boote, Ana Jojic, Fiona Ryan, Bolin Lai, Sangmin Lee, James M. Rehg
Published: 2026-05-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.15764v1

Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to identify who interacts with whom in multi-person videos. We introduce GRASP, a large-scale social reasoning dataset that connects high-level social QA with fine-grained gaze and deictic gesture events. GRASP contains 290K question--answer pairs over 46K videos totaling 749 hours, organized by a 16-category taxonomy spanning gaze, gesture, and joint gaze--gesture reasoning, together with GRASP-Bench for evaluation. Unlike prior resources that focus on either isolated cues or high-level social QA, GRASP builds questions from identity-consistent gaze trajectories, deictic gestures, and their joint compositions into social events. Moreover, we propose Social Grounding Reward (SGR), a learning signal that uses these social events to encourage models to reason about the participants involved in each interaction. Experiments show that SGR improves performance on GRASP-Bench while maintaining zero-shot performance on related social video QA benchmarks.

---

### CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs

Authors: Kamil Guttmann, Zofia Fraś, Artur Nowakowski, Krzysztof Jassem
Published: 2026-05-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.15763v1

Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data privacy concerns. We demonstrate that smaller, open-source LLMs (<30B parameters) are a viable, cost-effective and privacy-preserving alternative. Using a single-pass prompting strategy, our models simultaneously generate quality scores, MQM error annotations, suggested error corrections, and full post-editions. Our analysis shows these models achieve highly competitive system-level correlations with human judgments that outperform traditional neural metrics, fine-tuned models, and human inter-annotator agreement, effectively approximating the capabilities of much larger proprietary LLMs.

---

### A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation

Authors: Hosna Oyarhoseini, Jimmy Lin, Amir-Hossein Karimi
Published: 2026-05-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.15761v1

Evaluation leaderboards such as LMArena play a central role in benchmarking large language models by aggregating pairwise human preferences into model rankings, yet the robustness of these rankings remains poorly understood. We present a unified perturbation framework for analyzing Bradley-Terry leaderboards under structured data modifications using influence-based approximations. Our framework studies three match-level perturbations -- Drop, Add, and Flip -- together with player removal, and evaluates their effects on top-k membership, global ranking consistency via Kendall's tau, and confidence-interval-based uncertainty. Across Chatbot Arena and six additional pairwise-comparison datasets, we show that modern leaderboards are non-robust across all three objectives: sub-1% targeted perturbations can change the top-ranked model, degrade Kendall's tau, and alter confidence intervals. Beyond robustness auditing, we show that the same influence scores enable efficient targeted perturbations, promoting or demoting specific models and reducing target-model uncertainty with fewer actions than previous manipulation and active-sampling baselines. By summarizing these effects with normalized dataset-level robustness scores, our framework provides a practical and helpful tool for auditing leaderboard stability and motivating more robust evaluation protocols.

---

### Learn2Splat: Extending the Horizon of Learned 3DGS Optimization

Authors: Naama Pearl, Stefano Esposito, Haofei Xu, Amit Peleg, Patricia Gschossmann, Lorenzo Porzi, Peter Kontschieder, Gerard Pons-Moll, Andreas Geiger
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15760v2

3D Gaussian Splatting (3DGS) optimization is most commonly performed using general-purpose first-order optimizers such as Adam or SGD. Although robust across scenes, they update each parameter independently without exploiting the structural and spatial relationships among Gaussians, which slows convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, those are trained for a fixed number of optimization iterations and rely on manually scheduled learning rates to avoid degradation. In this paper, we introduce Learn2Splat, a learned optimizer for 3DGS that avoids degradation over extended optimization horizons without auxiliary mechanisms. To enable this, we propose a meta-learning scheme that extends the optimization horizon via a checkpoint buffer and an optimizer rollout strategy, combined with an architecture that encodes gradient scale information in its latent states. Results show higher novel view synthesis quality at equal wall-clock time, while remaining stable over long horizons, with zero-shot generalization to unseen datasets and settings. To support our findings, we build a unified framework to train and evaluate learned and standard optimizers across sparse and dense view settings. Code and models will be released publicly. Our project page is available at https://autonomousvision.github.io/learn2splat .

---

### Learn2Splat: Extending the Horizon of Learned 3DGS Optimization

Authors: Naama Pearl, Stefano Esposito, Haofei Xu, Amit Peleg, Patricia Gschossmann, Lorenzo Porzi, Peter Kontschieder, Gerard Pons-Moll, Andreas Geiger
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15760v1

3D Gaussian Splatting (3DGS) optimization is most commonly performed using standard optimizers (Adam, SGD). While stable across diverse scenes, standard optimizers are general-purpose and not tailored to the structure of the problem. In particular, they produce independent parameter updates that do not capture the structural and spatial relationships within a scene, leading to inefficient optimization and slow convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, these methods are trained for a fixed number of optimization iterations and rely on manually scheduled learning rates to avoid degradation. In this paper, we introduce a learned optimizer for 3DGS that avoids degradation over extended optimization horizons without auxiliary mechanisms. To enable this, we propose a meta-learning scheme that extends the optimization horizon via a checkpoint buffer and an optimizer rollout strategy, combined with an architecture that encodes gradient scale information in its latent states. Results show improved early novel view synthesis quality while remaining stable over long horizons, with zero-shot generalization to unseen reconstruction settings. To support our findings, we introduce the first unified framework for training and evaluating both learned and conventional optimizers across sparse and dense view settings. Code and models will be released publicly. Our project page is available at https://naamapearl.github.io/learn2splat .

---

### DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory

Authors: Wentao Qiu, Haotian Hu, Fanyi Wang, Jinwei Kong, Yu Zhang
Published: 2026-05-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.15759v3

Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a fidelity--efficiency trade-off: raw dialogue histories are expensive, while flat facts or summaries may discard the structure needed for precise recall. We propose \textbf{DimMem}, a lightweight dimensional memory framework that represents each memory as an atomic, typed, and self-contained unit with explicit fields such as time, location, reason, purpose, and keywords. This representation exposes the structure needed for dimension-aware retrieval, memory update, and selective assistant-context recall without storing full histories in the model context. Across LoCoMo-10 and LongMemEval-S, DimMem achieves \textbf{81.43\%} and \textbf{78.20\%} overall accuracy, respectively, outperforming existing lightweight memory systems while reducing LoCoMo per-query token cost by \textbf{24\%}. We further show that dimensional memory extraction is learnable by compact models: after fine-tuning on the DimMem schema, a Qwen3-4B extractor surpasses LightMem with GPT-4.1-mini on both benchmarks and reaches performance comparable to, or better than, much larger extractors in key settings. These results suggest that explicit dimensional structuring is an effective and efficient foundation for long-term memory in LLM agents. Code is available at https://github.com/ChowRunFa/DimMem.

---

### Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language Models

Authors: Cheng Zhang, Yuer Liu, Zhiyu Zhou, Hongxia Xie, Wen-Huang Cheng
Published: 2026-05-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.15755v1

Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate many visible formal attributes without identifying which cues actually support the affective judgment. We therefore formulate artwork emotion understanding as Attribute-Grounded Selective Reasoning (AGSR), where predefined formal attributes serve as evidence units and only emotionally operative attributes should enter the final interpretation. To make this problem measurable, we extend EmoArt, originally introduced at ACM MM 2025 as a 132,664-artwork resource with content, formal-attribute, valence-arousal, and emotion annotations, by adding a 1,400-artwork human salience extension annotated by 15 art-trained annotators. This extension provides instance-level supervision for distinguishing attributes that are merely present from those that are emotionally salient. We further propose FAB-G (Formal-Attribute Bottleneck-Guided reasoning), a supervised multi-agent framework that first predicts attribute-level salience and then constrains downstream emotional analysis to the retained cues. Experiments show that FAB-G yields consistent gains in emotion, arousal, and valence prediction, achieves stronger agreement with human-marked salient attributes under Dice and Tversky metrics, and produces substantially more compact final explanations than prompting-based baselines. Cross-dataset evaluation further suggests that attribute-grounded salience selection transfers beyond the source distribution of EmoArt, while also revealing attribute-specific boundary cases. The dataset and project page are available at https://zhiliangzhang.github.io/EmoArt-130k/

---

### Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces

Authors: Xinggang Hu, Chenyangguang Zhang, Alexandros Delitzas, Xiangkui Zhang, Marc Pollefeys, Francis Engelmann, Xiangyang Ji
Published: 2026-05-15
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2605.15753v2

Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains underexplored due to the limited coverage of existing benchmarks and the overly straightforward design of previous pipelines, which primarily focus on large-scale furniture but lack of hierarchical structures. Therefore, in this work, we extend the benchmark coverage by introducing dense tabletop objects and explicit multi-level functional relationships. This expansion introduces critical challenges involving small-scale, dense, and similar instances, with lack of visual anchoring in relational reasoning, instance confusion during cross-frame fusion, and attribution uncertainty under dynamic viewpoints. To address these issues, we propose an open-vocabulary pipeline based on 2D visual grounding and 3D graph optimization. Specifically, we anchor fine-grained functional edges from 2D visual evidence, and associate nodes across frames in 3D using multiple cues. Furthermore, edge association is formulated as temporal graph optimization, integrating evidence accumulation, entropy regularization, and temporal smoothing to robustly determine the functional connections of each node. Finally, global hierarchy shaping is performed to recover the hierarchical graph structure. Extensive experiments demonstrate that the proposed method can reliably infer functional 3D scene graphs in challenging real-world scenes, thereby further unlocking their potential for practical applications.

---