# Research Papers — 2026-03 · bundle page 192 of 243

> Full-text markdown of papers #9551–9600 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-03/page/192
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/191.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/193.md)

### Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics

Authors: Rajdeep Pathak, Tanujit Chakraborty
Published: 2026-03-07
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2603.07108v2

Accurate and reliable forecasting of epidemic incidences is critical for public health preparedness, yet it remains a challenging task due to complex nonlinear temporal dependencies and heterogeneous spatial interactions. Often, point forecasts generated by spatiotemporal models are unreliable in assigning uncertainty to future epidemic events. Probabilistic forecasting of epidemics is therefore crucial for providing the best or worst-case scenarios rather than a simple, often inaccurate, point estimate. We present deep spatiotemporal engression methods to generate accurate and reliable probabilistic forecasts on low-frequency epidemic datasets. The proposed methods act as distributional lenses, and out-of-sample probabilistic forecasts are generated by sampling from the trained models. Our frameworks encapsulate lightweight deep generative architectures, wherein uncertainty is quantified endogenously, driven by a pre-additive noise component during model construction. We establish geometric ergodicity and asymptotic stationarity of the spatiotemporal engression processes under mild assumptions on the network weights and pre-additive noise process. Comprehensive evaluations across six epidemiological datasets over three forecast horizons demonstrate that the proposal consistently outperforms several temporal and spatiotemporal benchmarks in both point and probabilistic forecasting. Additionally, we explore the explainability of the proposal to enhance the models' practical application for informed, timely public health interventions.

---

### Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

Authors: Kai Cheng, Hao Wang, Wei Guo, Weiwen Liu, Yong Liu, Yawen Li, Enhong Chen
Published: 2026-03-07
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2603.07107v1

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.

---

### Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints

Authors: Hugh Xuechen Liu, Kıvanç Tatar
Published: 2026-03-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.07101v4

Creatively translating complex gameplay ideas into executable artifacts (e.g., games as Unity projects and code) remains a central challenge in computational game creativity. Gameplay design patterns provide a structured representation for describing gameplay phenomena, enabling designers to decompose high-level ideas into entities, constraints, and rule-driven dynamics. Among them, goal patterns formalize common player-objective relationships. Goal Playable Concepts (GPCs) operationalize these abstractions as playable Unity engine implementations, supporting experiential exploration and compositional gameplay design. We frame scalable playable pattern realization as a problem of constrained executable creative synthesis: generated artifacts must satisfy Unity's syntactic and architectural requirements while preserving the semantic gameplay meanings encoded in goal patterns. This dual constraint limits scalability. Therefore, we investigate whether contemporary large language models (LLMs) can perform such synthesis under engine-level structural constraints and generate Unity code (as games) structured and conditioned by goal playable patterns. Using 26 goal pattern instantiations, we compare a direct generation baseline (natural language -> C# -> Unity) with pipelines conditioned on a human-authored Unity-specific intermediate representation (IR), across three IR configurations and two open-source models (DeepSeek-Coder-V2-Lite-Instruct and Qwen2.5-Coder-7B-Instruct). Compilation success is evaluated via automated Unity replay. We propose grounding and hygiene failure modes, identifying structural and project-level grounding as primary bottlenecks.

---

### NuNext: Reframing Nucleus Detection as Next-Point Detection

Authors: Zhongyi Shui, Honglin Li, Xiaozhong Ji, Ye Zhang, Zijiang Yang, Chenglu Zhu, Yuxuan Sun, Kai Yao, Conghui He, Cheng Tan
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07098v1

Nucleus detection in histopathology is pivotal for a wide range of clinical applications. Existing approaches either regress nuclear proxy maps that require complex post-processing, or employ dense anchors or queries that introduce severe foreground-background imbalance. In this work, we reformulate nucleus detection as next-point prediction, wherein a multimodal large language model is developed to directly output foreground nucleus centroids from the input image. The model is trained in two stages. In the supervised learning stage, we propose spatial-aware soft supervision to relax strict centroid matching and a chain-of-visual-thought strategy to incorporate visual priors that facilitate coordinate prediction. In the reinforcement fine-tuning stage, we design distribution matching reward, low-variance group filtering, and fine-grained advantage shaping to further improve the model's detection quality. Extensive experiments on nine widely used benchmarks demonstrate the superiority of our method. Code will be released soon.

---

### Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction

Authors: Xu Chen, Rui Gao, Xinjie Zhang, Haoyu Zhang, Che Sun, Zhi Gao, Yuwei Wu, Yunde Jia
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07093v1

Achieving natural dyadic interaction requires generating facial expressions that are emotionally appropriate and socially aligned with human preference. Human feedback offers a compelling mechanism to guide such alignment, yet how to effectively incorporate this feedback into facial expression generation remains underexplored. In this paper, we propose a facial expression generation method aligned with human preference by leveraging human feedback to produce contextually and emotionally appropriate expressions for natural dyadic interaction. A key to our method is framing the generation of identity-independent facial expressions as an action learning process, allowing human feedback to assess their validity free from visual or identity bias. We establish a closed feedback loop in which listener expressions dynamically respond to evolving conversational cues of the speaker. Concretely, we train a vision-language-action model via supervised fine-tuning to map the speaker's multimodal signals into controllable low-dimensional expression representations of a 3D morphable model. We further introduce a human-feedback reinforcement learning strategy that integrates the imitation of high-quality expression response with critic-guided optimization. Experiments on two benchmarks demonstrate that our method effectively aligns facial expressions with human preference and achieves superior performance.

---

### Statistical Contraction for Chance-Constrained Trajectory Optimization of Non-Gaussian Stochastic Systems

Authors: Rihan Aaron D'Silva, Hiroyasu Tsukamoto
Published: 2026-03-07
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2603.07092v1

This paper presents novel method for distribution-free robust trajectory optimization and control of discrete-time, nonlinear, and non-Gaussian stochastic systems, with closed-loop guarantees on chance constraint satisfaction. Our framework employs conformal inference to generate coverage-based confidence sets for the closed-loop dynamics around arbitrary reference trajectories, by constructing a joint nonconformity score to quantify both the validity of contraction (i.e., incremental stability) conditions and the impact of external stochastic disturbance on the closed-loop dynamics, without any distributional assumptions. Via appropriate constraint tightening, chance constraints can be reformulated into tractable, statistically valid deterministic constraints on the reference trajectories. This enables a formal pathway to leverage and validate learning-based motion planners and controllers, such as those with neural contraction metrics, in safety-critical real-world applications. Notably, our statistical guarantees are non-diverging and can be computed with finite samples of the underlying uncertainty, without overly conservative structural priors. We demonstrate our approach in motion planning problems for designing safe, dynamically feasible trajectories in both numerical simulation and hardware experiments.

---

### mAVE: A Watermark for Joint Audio-Visual Generation Models

Authors: Luyang Si, Leyi Pan, Lijie Wen
Published: 2026-03-07
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.07090v1

As Joint Audio-Visual Generation Models see widespread commercial deployment, embedding watermarks has become essential for protecting vendor copyright and ensuring content provenance. However, existing techniques suffer from an architectural mismatch by treating modalities as decoupled entities, exposing a critical Binding Vulnerability. Adversaries exploit this via Swap Attacks by replacing authentic audio with malicious deepfakes while retaining the watermarked video. Because current detectors rely on independent verification ($Video_{wm}\vee Audio_{wm}$), they incorrectly authenticate the manipulated content, falsely attributing harmful media to the original vendor and severely damaging their reputation. To address this, we propose mAVE (Manifold Audio-Visual Entanglement), the first watermarking framework natively designed for joint architectures. mAVE cryptographically binds audio and video latents at initialization without fine-tuning, defining a Legitimate Entanglement Manifold via Inverse Transform Sampling. Experiments on state-of-the-art models (LTX-2, MOVA) demonstrate that mAVE guarantees performance-losslessness and provides an exponential security bound against Swap Attacks. Achieving near-perfect binding integrity ($>99\%$), mAVE offers a robust cryptographic defense for vendor copyright.

---

### Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR

Authors: Muhammad Khalifa, Zohaib Khan, Omer Tafveez, Hao Peng, Lu Wang
Published: 2026-03-07
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.07084v3

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often expensive or impossible to compute. We introduce Countdown-Code, a minimal environment where models can both solve a mathematical reasoning task and manipulate the test harness. This dual-access design creates a clean separation between proxy rewards (test pass/fail) and true rewards (mathematical correctness), enabling accurate measurement of reward-hacking rates. Using this environment, we study reward hacking in open-weight LLMs and find that such behaviors can be unintentionally learned during supervised fine-tuning (SFT) when even a small fraction of reward-hacking trajectories leak into training data. As little as 1\% contamination in distillation SFT data is sufficient for models to internalize reward hacking which resurfaces during subsequent reinforcement learning (RL). We further show that RL amplifies misalignment and drives its generalization beyond the original domain. We open-source our environment and code to facilitate future research on reward hacking in LLMs. Our results reveal a previously underexplored pathway through which reward hacking can emerge and persist in LLMs, underscoring the need for more rigorous validation of synthetic SFT data. Code is available at https://github.com/zohaib-khan5040/Countdown-Code.

---

### Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR

Authors: Muhammad Khalifa, Zohaib Khan, Omer Tafveez, Hao Peng, Lu Wang
Published: 2026-03-07
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.07084v2

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often expensive or impossible to compute. We introduce Countdown-Code, a minimal environment where models can both solve a mathematical reasoning task and manipulate the test harness. This dual-access design creates a clean separation between proxy rewards (test pass/fail) and true rewards (mathematical correctness), enabling accurate measurement of reward-hacking rates. Using this environment, we study reward hacking in open-weight LLMs and find that such behaviors can be unintentionally learned during supervised fine-tuning (SFT) when even a small fraction of reward-hacking trajectories leak into training data. As little as 1\% contamination in distillation SFT data is sufficient for models to internalize reward hacking which resurfaces during subsequent reinforcement learning (RL). We further show that RL amplifies misalignment and drives its generalization beyond the original domain. We open-source our environment and code to facilitate future research on reward hacking in LLMs. Our results reveal a previously underexplored pathway through which reward hacking can emerge and persist in LLMs, underscoring the need for more rigorous validation of synthetic SFT data. Code is available at https://github.com/zohaib-khan5040/Countdown-Code.

---

### Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction

Authors: Michael Hauri, Friedemann Zenke
Published: 2026-03-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.07083v2

Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning and control. Existing approaches typically employ reconstruction-based objectives in the observation space, which can render representations sensitive to task-irrelevant details. Recent alternatives trade reconstruction for auxiliary action prediction heads or view augmentation strategies, but perform worse in the Crafter environment than reconstruction-based methods. We close this gap between Dreamer and reconstruction-free models by introducing a JEPA-style predictor defined on continuous, deterministic representations. Our method matches Dreamer's performance on Crafter, demonstrating effective world model learning on this benchmark without reconstruction objectives.

---

### VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness

Authors: Zihao Zheng, Zhihao Mao, Xingyue Zhou, Jiayu Chen, Maoliang Li, Xinhao Sun, Hailong Zou, Zhaobo Zhang, Xuanzhe Liu, Donggang Cao, Hong Mei, Xiang Chen
Published: 2026-03-07
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2603.07080v3

Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising training-free strategy that avoids redundant computation by reusing stable visual tokens across frames. However, existing methods assume a static camera and fixed semantic focus, assumptions that VLN fundamentally violates. We identify two failure modes: (1) visual dynamics, where viewpoint shift displaces token positions across frames, causing position-wise matching to pair misaligned content; (2) semantic dynamics, where token relevance shifts across task stages as navigation progresses, making cached states stale. We propose VLN-Cache, a visual-dynamic-aware and semantic-dynamic-aware caching framework that introduces view-aligned remapping to recover geometric correspondences and a task-relevance saliency filter to veto reuse at semantic transitions. A layer-adaptive entropy policy further balances the per-layer reuse budget. Experiments on the R2R-CE simulation benchmark show up to 1.52x speedup while maintaining competitive navigation success rates.

---

### Entropy-Aware On-Policy Distillation of Language Models

Authors: Woogyeol Jin, Taywon Min, Yongjin Yang, Dennis Wei, Yi Zhou, Swanand Ravindra Kadhe, Nathalie Baracaldo, Kimin Lee
Published: 2026-03-07
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.07079v3

On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence, encouraging the student to match the teacher's high-confidence predictions. However, we show that the mode-seeking property of reverse KL reduces generation diversity and yields unstable learning signals when the teacher distribution has high entropy. To address this, we introduce Entropy-Aware On-Policy Distillation. Our key idea is augmenting the standard reverse KL objective with forward KL when teacher entropy is high, capturing the full range of plausible outputs while retaining precise imitation elsewhere. It balances mode-seeking precision with mode-covering robustness without sacrificing on-policy training efficiency. Experiments show that our method maintains generation diversity (sustained token-level entropy) and improves student-teacher alignment (lower forward KL on high-entropy tokens). Across six math reasoning benchmarks, this yields Pass@8 accuracy gains of +1.37 for Qwen3-0.6B-Base, +2.39 for Qwen3-1.7B-Base, and +5.05 for Qwen3-4B-Base compared to baseline on-policy distillation methods. These results demonstrate that accounting for teacher uncertainty is essential for maintaining diversity and achieving effective knowledge transfer.

---

### CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs

Authors: Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi Li, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang
Published: 2026-03-07
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.07078v1

Large Reasoning Models (LRMs) have demonstrated strong performance by producing extended Chain-of-Thought (CoT) traces before answering. However, this paradigm often induces over-reasoning: redundant calculations and circular self-verification that increase computational cost without improving outcomes. Existing evaluations largely emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy. We introduce CoTJudger, a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution. This yields an interpretable efficiency signal -- how much of a CoT is necessary versus structurally redundant -- that is comparable across models and tasks. Evaluating 21 LRMs, CoTJudger reveals pervasive redundancy and surfaces recurring failure modes, including verification obsession and compensatory redundancy. These results provide a practical metric for disentangling reasoning ability from computational waste, enabling more targeted evaluation and diagnosis of LRM efficiency.

---

### Aligning What EEG Can See: Structural Representations for Brain-Vision Matching

Authors: Jingyi Tang, Shuai Jiang, Fei Su, Zhicheng Zhao
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07077v1

Visual decoding from electroencephalography (EEG) has emerged as a highly promising avenue for non-invasive brain-computer interfaces (BCIs). Existing EEG-based decoding methods predominantly align brain signals with the final-layer semantic embeddings of deep visual models. However, relying on these highly abstracted embeddings inevitably leads to severe cross-modal information mismatch. In this work, we introduce the concept of Neural Visibility and accordingly propose the EEG-Visible Layer Selection Strategy, aligning EEG signals with intermediate visual layers to minimize this mismatch. Furthermore, to accommodate the multi-stage nature of human visual processing, we propose a novel Hierarchically Complementary Fusion (HCF) framework that jointly integrates visual representations from different hierarchical levels. Extensive experiments demonstrate that our method achieves state-of-the-art performance, reaching an 84.6% accuracy (+21.4%) on zero-shot visual decoding on the THINGS-EEG dataset. Moreover, our method achieves up to a 129.8% performance gain across diverse EEG baselines, demonstrating its robust generalizability.

---

### Retinex Meets Language: A Physics-Semantics-Guided Underwater Image Enhancement Network

Authors: Shixuan Xu, Yabo Liu, Chao Huang, Junyu Dong, Xinghui Dong
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07076v2

Underwater images often suffer from severe degradation caused by light absorption and scattering, leading to color distortion, low contrast and reduced visibility. Existing Underwater Image Enhancement (UIE) methods can be divided into two categories, i.e., prior-based and learning-based methods. The former rely on rigid physical assumptions that limit the adaptability, while the latter often face data scarcity and weak generalization. To address these issues, we propose a Physics-Semantics-Guided Underwater Image Enhancement Network (PSG-UIENet), which couples the Retinex-grounded illumination correction with the language-informed guidance. This network comprises a Prior-Free Illumination Estimator and a Semantics-Guided Image Restorer. In particular, the restorer leverages the textual descriptions generated by the Contrastive Language-Image Pre-training (CLIP) model to inject high-level semantics for perceptually meaningful guidance. Since multimodal UIE data sets are not publicly available, we also construct a large-scale image-text UIE data set, namely, LUIQD-TD, which contains 6,418 image-reference-text triplets. To explicitly measure and optimize semantic consistency between textual descriptions and images, we further design an Image-Text Semantic Similarity (ITSS) loss function. To our knowledge, this study makes the first effort to introduce both textual guidance and the multimodal data set into UIE tasks. Extensive experiments on our data set and four publicly available data sets demonstrate that the proposed PSG-UIENet achieves superior or comparable performance against fifteen state-of-the-art methods.

---

### Physics-Guided VLM Priors for All-Cloud Removal

Authors: Liying Xu, Huifang Li, Huanfeng Shen
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07074v1

Cloud removal is a fundamental challenge in optical remote sensing due to the heterogeneous degradation. Thin clouds distort radiometry via partial transmission, while thick clouds occlude the surface. Existing pipelines separate thin-cloud correction from thick-cloud reconstruction, requiring explicit cloud-type decisions and often leading to error accumulation and discontinuities in mixed-cloud scenes. Therefore, a novel approach named Physical-VLM All-Cloud Removal (PhyVLM-CR) that integrates the semantic capability of Vision-Language Model (VLM) into a physical restoration model, achieving high-fidelity unified cloud removal. Specifically, the cognitive prior from a VLM (e.g., Qwen) is transformed into physical scattering parameters and a hallucination confidence map. Leveraging this confidence map as a continuous soft gate, our method achieves a unified restoration via adaptive weighting: it prioritizes physical inversion in high-transmission regions to preserve radiometric fidelity, while seamlessly transitioning to temporal reference reconstruction in low-confidence occluded areas. This mechanism eliminates the need for explicit boundary delineation, ensuring a coherent removal across heterogeneous cloud covers. Experiments on real-world Sentinel-2 surface reflectance imagery confirm that our approach achieves a remarkable balance between cloud removal and content preservation, delivering hallucination-free results with substantially improved quantitative accuracy compared to existing methods.

---

### Interpretable Maximum Margin Deep Anomaly Detection

Authors: Zhiji Yang, Mei Huang, Xinyu Li, Xianli Pan, Qi Wang, Jianhua Zhao
Published: 2026-03-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.07073v1

Anomaly detection is a crucial machine-learning task with wide-ranging applications. Deep Support Vector Data Description (Deep SVDD) is a prominent deep one-class method, but it is vulnerable to hypersphere collapse, often relies on heuristic choices for hypersphere parameters, and provides limited interpretability. To address these issues, we propose Interpretable Maximum Margin Deep Anomaly Detection (IMD-AD), which leverages a small set of labeled anomalies and a maximum margin objective to stabilize training and improve discrimination. It is inherently resilient to hypersphere collapse. Furthermore, we prove an equivalence between hypersphere parameters and the network's final-layer weights, which allows the center and radius to be learned end-to-end as part of the model and yields intrinsic interpretability and visualizable outputs. We further develop an efficient training algorithm that jointly optimizes representation, margin, and final-layer parameters. Extensive experiments and ablation studies on image and tabular benchmarks demonstrate that IMD-AD empirically improves detection performance over several state-of-the-art baselines while providing interpretable decision diagnostics.

---

### The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication

Authors: Hanlong Li, Karishma Kamalahasan, Jiahui Li, Kazuhiro Nakadai, Shreyas Kousik
Published: 2026-03-07
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2603.07072v1

We present Artoo, a learned acoustic communication system for robots that replaces hand-designed signal processing with end-to-end co-trained neural networks. Our system pairs a lightweight text-to-speech (TTS) transmitter (1.18M parameters) with a conformer-based automatic speech recognition (ASR) receiver (938K parameters), jointly optimized through a differentiable channel. Unlike human speech, robot-to-robot communication is paralinguistics-free: the system need not preserve timbre, prosody, or naturalness, only maximize decoding accuracy under channel distortion. Through a three-phase co-training curriculum, the TTS transmitter learns to produce distortion-robust acoustic encodings that surpass the baseline under noise, achieving 8.3% CER at 0 dB SNR. The entire system requires only 2.1M parameters (8.4 MB) and runs in under 13 ms end-to-end on a CPU, making it suitable for deployment on resource-constrained robotic platforms.

---

### VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understanding

Authors: Xueqing Yu, Bohan Li, Yan Li, Zhenheng Yang
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07071v2

Recent Vision-Language Models (VLMs) have made remarkable progress in multimodal understanding tasks, yet their evaluation on long video understanding remains unreliable. Due to limited frame inputs, key frames necessary for answering the question may be missing from the model's input. However, models that truthfully refuse to answer under such uncertainty are marked as incorrect, while those that guess may coincidentally produce the correct answer and thus obtain deceptively higher accuracy, leading to misleading evaluation results and encouraging models to guess rather than respond honestly. To address this issue, we introduce VirtueBench, a benchmark explicitly designed to assess model trustworthiness under uncertainty. VirtueBench constructs multiple frame-sampling levels for each video and provides ground truths that distinguish between answerable and unanswerable cases. Evaluations on 25 open-source and commercial VLMs reveal distinct refusal behaviors across different model families, with refusal accuracy ranging from over 70% in the best models to nearly 0% in the worst. Moreover, most models exhibit a substantial drop in refusal when the prompt does not explicitly require them to do so. These findings highlight the need for developing trustworthy VLMs for multimodal understanding, guided by benchmarks and leaderboards that emphasize reliability and trustworthiness.

---

### User Review Writing via Interview with Dialogue Systems

Authors: Yoshiki Tanaka, Michimasa Inaba
Published: 2026-03-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.07070v1

User reviews on e-commerce and review sites are crucial for making purchase decisions, although creating detailed reviews is time-consuming and labor-intensive. In this study, we propose a novel use of dialogue systems to facilitate user review creation by generating reviews from information gathered during interview dialogues with users. To validate our approach, we implemented our system using GPT-4 and conducted comparative experiments from the perspectives of system users and review readers. The results indicate that participants who used our system rated their interactions positively. Additionally, reviews generated by our system required less editing to achieve user satisfaction compared to those by the baseline. We also evaluated the reviews from the reader' perspective and found that our system-generated reviews are more helpful than those written by humans. Despite challenges with the fluency of the generated reviews, our method offers a promising new approach to review writing.

---

### PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

Authors: Trong-Thang Pham, Loc Nguyen, Anh Nguyen, Hien V. Nguyen, Ngan Le
Published: 2026-03-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.07066v2

Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training data. Re-prompting rerolls the entire generation trajectory, altering anatomy, texture, and background. Inversion-based editing methods introduce reconstruction error that causes structural drift. We propose PolypSteer, a training-free activation-steering framework for endoscopic synthesis. PolypSteer identifies a pathology vector for each contrastive prompt pair in the cross-attention layers of a diffusion transformer. At inference time, it steers image activations along this vector, generating counterfactual pairs from scratch where the only difference is the steered concept. All other structure is preserved by construction. We evaluate PolypSteer across three experiments on Kvasir v3 and HyperKvasir. On counterfactual generation across three clinical concept pairs, PolypSteer achieves flip rates of 0.800, 0.925, and 0.950, outperforming the best inversion-based baseline in both concept flip rate and structural preservation. On dye disentanglement, PolypSteer achieves 75% dye removal against 20% (PnP) and 10% (h-Edit). On downstream polyp detection, augmenting with PolypSteer counterfactual pairs achieves ViT AUC of 0.9755 versus 0.9083 for quantity-matched re-prompting, confirming that counterfactual structure drives the gain. Code is at link https://github.com/UARK-AICV/PolypSteer

---

### MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

Authors: Trong-Thang Pham, Loc Nguyen, Anh Nguyen, Hien Nguyen, Ngan Le
Published: 2026-03-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.07066v1

Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training data. Re-prompting rerolls the entire generation trajectory, altering anatomy, texture, and background. Inversion-based editing methods introduce reconstruction error that causes structural drift. We propose MedSteer, a training-free activation-steering framework for endoscopic synthesis. MedSteer identifies a pathology vector for each contrastive prompt pair in the cross-attention layers of a diffusion transformer. At inference time, it steers image activations along this vector, generating counterfactual pairs from scratch where the only difference is the steered concept. All other structure is preserved by construction. We evaluate MedSteer across three experiments on Kvasir v3 and HyperKvasir. On counterfactual generation across three clinical concept pairs, MedSteer achieves flip rates of 0.800, 0.925, and 0.950, outperforming the best inversion-based baseline in both concept flip rate and structural preservation. On dye disentanglement, MedSteer achieves 75% dye removal against 20% (PnP) and 10% (h-Edit). On downstream polyp detection, augmenting with MedSteer counterfactual pairs achieves ViT AUC of 0.9755 versus 0.9083 for quantity-matched re-prompting, confirming that counterfactual structure drives the gain. Code is at link https://github.com/phamtrongthang123/medsteer

---

### SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer

Authors: Tong Shao, Yusen Fu, Guoying Sun, Jingde Kong, Zhuotao Tian, Jingyong Su
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07057v4

Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration efficiency but often compromises fidelity, whereas pruning shows the opposite trade-off. Integrating caching with pruning achieves a balance between acceleration and generation quality. However, existing methods typically employ fixed and heuristic schemes to configure caching and pruning strategies. While they roughly follow the overall sensitivity trend of generation models to acceleration, they fail to capture fine-grained and complex variations, inevitably skipping highly sensitive computations and leading to quality degradation. Furthermore, such manually designed strategies exhibit poor generalization. To address these issues, we propose SODA, a Sensitivity-Oriented Dynamic Acceleration method that adaptively performs caching and pruning based on fine-grained sensitivity. SODA builds an offline sensitivity error modeling framework across timesteps, layers, and modules to capture the sensitivity to different acceleration operations. The cache intervals are optimized via dynamic programming with sensitivity error as the cost function, minimizing the impact of caching on model sensitivity. During pruning and cache reuse, SODA adaptively determines the pruning timing and rate to preserve computations of highly sensitive tokens, significantly enhancing generation fidelity. Extensive experiments on DiT-XL/2, PixArt-$α$, and OpenSora demonstrate that SODA achieves state-of-the-art generation fidelity under controllable acceleration ratios. Our code is released publicly at: https://github.com/leaves162/SODA.

---

### Bi-directional digital twin prototype anchoring with multi-periodicity learning for few-shot fault diagnosis

Authors: Pengcheng Xia, Zhichao Dong, Yixiang Huang, Chengjin Qin, Qun Chao, Chengliang Liu
Published: 2026-03-07
Categories: cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2603.07054v1

Intelligent fault diagnosis (IFD) has emerged as a powerful paradigm for ensuring the safety and reliability of industrial machinery. However, traditional IFD methods rely heavily on abundant labeled data for training, which is often difficult to obtain in practical industrial environments. Constructing a digital twin (DT) of the physical asset to obtain simulation data has therefore become a promising alternative. Nevertheless, existing DT-assisted diagnosis methods mainly transfer diagnostic knowledge through domain adaptation techniques, which still require a considerable amount of unlabeled data from the target asset. To address the challenges in few-shot scenarios where only extremely limited samples are available, a bi-directional DT prototype anchoring method with multi-periodicity learning is proposed. Specifically, a framework involving meta-training in the DT virtual space and test-time adaptation in the physical space is constructed for reliable few-shot model adaptation for the target asset. A bi-directional twin-domain prototype anchoring strategy with covariance-guided augmentation for adaptation is further developed to improve the robustness of prototype estimation. In addition, a multi-periodicity feature learning module is designed to capture the intrinsic periodic characteristics within current signals. A DT of an asynchronous motor is built based on finite element method, and experiments are conducted under multiple few-shot settings and three working conditions. Comparative and ablation studies demonstrate the superiority and effectiveness of the proposed method for few-shot fault diagnosis.

---

### Animating Petascale Time-varying Data on Commodity Hardware with LLM-assisted Scripting

Authors: Ishrat Jahan Eliza, Xuan Huang, Aashish Panta, Alper Sahistan, Zhimin Li, Amy A. Gooch, Valerio Pascucci
Published: 2026-03-07
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2603.07053v4

Scientists face significant visualization challenges as time-varying datasets grow in speed and volume, often requiring specialized infrastructure and expertise to handle massive datasets. Petascale climate models generated in NASA laboratories require a dedicated group of graphics and media experts and access to high-performance computing resources. Scientists may need to share scientific results with the community iteratively and quickly. However, the time-consuming trial-and-error process incurs significant data transfer overhead and far exceeds the time and resources allocated for typical post-analysis visualization tasks, disrupting the production workflow. Our paper introduces a user-friendly framework for creating 3D animations of petascale, time-varying data on a commodity workstation. Our contributions: (i) Generalized Animation Descriptor (GAD) with a keyframe-based adaptable abstraction for animation, (ii) efficient data access from cloud-hosted repositories to reduce data management overhead, (iii) tailored rendering system, and (iv) an LLM-assisted conversational interface as a scripting module to allow domain scientists with no visualization expertise to create animations of their region of interest. We demonstrate the framework's effectiveness with two case studies: first, by generating animations in which sampling criteria are specified based on prior knowledge, and second, by generating AI-assisted animations in which sampling parameters are derived from natural-language user prompts. In all cases, we use large-scale NASA climate-oceanographic datasets that exceed 1PB in size yet achieve a fast turnaround time of 1 minute to 2 hours. Users can generate a rough draft of the animation within minutes, then seamlessly incorporate as much high-resolution data as needed for the final version.

---

### Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

Authors: Xiaochen Yang, Hao Fang, Jiawei Kong, Yaoxin Mao, Bin Chen, Shu-Tao Xia
Published: 2026-03-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.07048v1

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient cross-image modeling. Inspired by this, we propose a structured hallucination mitigation framework involving Cross-Image Attention calibration and Preference Learning (CAPL). CAPL explicitly enhances inter-image interactions at the architectural level while reinforcing reliance on genuine cross-image evidence during training, thereby improving the model's perception and modeling of cross-image associations. Specifically, we (i) introduce a selectable image token interaction attention mechanism to establish fine-grained cross-image entity alignment and information flow; (ii) design a cross-image modeling-based preference optimization strategy that contrasts reasoning outcomes under full inter-image interaction and those obtained when images are mutually invisible, encouraging the model to ground its predictions in authentic visual evidence and mitigating erroneous inferences driven by textual priors. Experimental results demonstrate that CAPL consistently improves performance across multiple model architectures, achieving stable gains on both multi-image hallucination and general benchmarks. Notably, performance on single-image visual tasks remains stable or slightly improves, indicating strong generalization capability.

---

### Fine-Grained 3D Facial Reconstruction for Micro-Expressions

Authors: Che Sun, Xinjie Zhang, Rui Gao, Xu Chen, Yuwei Wu, Yunde Jia
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07043v1

Recent advances in 3D facial expression reconstruction have demonstrated remarkable performance in capturing macro-expressions, yet the reconstruction of micro-expressions remains unexplored. This novel task is particularly challenging due to the subtle, transient, and low-intensity nature of micro-expressions, which complicate the extraction of stable and discriminative features essential for accurate reconstruction. In this paper, we propose a fine-grained micro-expression reconstruction method that integrates a global dynamic feature capturing stable facial motion patterns with a locally-enriched feature incorporating multiple informative cues from 2D motions, facial priors and 3D facial geometry. Specifically, we devise a plug-and-play dynamic-encoded module to extract micro-expression feature for global facial action, allowing it to leverage prior knowledge from abundant macro-expression data to mitigate the scarcity of micro-expression data. Subsequently, a dynamic-guided mesh deformation module is designed for extracting aggregated local features from dense optical flow, sparse landmark cues and facial mesh geometry, which adaptively refines fine-grained facial micro-expression without compromising global 3D geometry. Extensive experiments on micro-expression datasets demonstrate that our method consistently outperforms state-of-the-art methods in both geometric accuracy and perceptual detail.

---

### Self-Supervised Multi-Modal World Model with 4D Space-Time Embedding

Authors: Lance Legel, Qin Huang, Brandon Voelker, Daniel Neamati, Patrick Alan Johnson, Favyen Bastani, Jeff Rose, James Ryan Hennessy, Robert Guralnick, Douglas Soltis, Pamela Soltis, Shaowen Wang
Published: 2026-03-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.07039v1

We present DeepEarth, a self-supervised multi-modal world model with Earth4D, a novel planetary-scale 4D space-time positional encoder. Earth4D extends 3D multi-resolution hash encoding to include time, efficiently scaling across the planet over centuries with sub-meter, sub-second precision. Multi-modal encoders (e.g. vision-language models) are fused with Earth4D embeddings and trained via masked reconstruction. We demonstrate Earth4D's expressive power by achieving state-of-the-art performance on an ecological forecasting benchmark. Earth4D with learnable hash probing surpasses a multi-modal foundation model pre-trained on substantially more data. Access open source code and download models at: https://github.com/legel/deepearth

---

### Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking

Authors: Moyang Chen, Zonghao Ying, Wenzhuo Xu, Quancheng Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang
Published: 2026-03-07
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2603.07028v1

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite unsafe prompts into paraphrases that evade content filters while preserving meaning. Yet, these approaches often still retain explicit sensitive cues in the input text and therefore overlook a more profound, video-specific weakness. In this paper, we identify a temporal trajectory infilling vulnerability of T2V systems under fragmented prompts: when the prompt specifies only sparse boundary conditions (e.g., start and end frames) and leaves the intermediate evolution underspecified, the model may autonomously reconstruct a plausible trajectory that includes harmful intermediate frames, despite the prompt appearing benign to input or output side filtering. Building on this observation, we propose TFM. This fragmented prompting framework converts an originally unsafe request into a temporally sparse two-frame extraction and further reduces overtly sensitive cues via implicit substitution. Extensive evaluations across multiple open-source and commercial T2V models demonstrate that TFM consistently enhances jailbreak effectiveness, achieving up to a 12% increase in attack success rate on commercial systems. Our findings highlight the need for temporally aware safety mechanisms that account for model-driven completion beyond prompt surface form.

---

### Resource-Adaptive Federated Text Generation with Differential Privacy

Authors: Jiayi Wang, John Gounley, Heidi Hanson
Published: 2026-03-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.07027v1

In cross-silo federated learning (FL), sensitive text datasets remain confined to local organizations due to privacy regulations, making repeated training for each downstream task both communication-intensive and privacy-demanding. A promising alternative is to generate differentially private (DP) synthetic datasets that approximate the global distribution and can be reused across tasks. However, pretrained large language models (LLMs) often fail under domain shift, and federated finetuning is hindered by computational heterogeneity: only resource-rich clients can update the model, while weaker clients are excluded, amplifying data skew and the adverse effects of DP noise. We propose a flexible participation framework that adapts to client capacities. Strong clients perform DP federated finetuning, while weak clients contribute through a lightweight DP voting mechanism that refines synthetic text. To ensure the synthetic data mirrors the global dataset, we apply control codes (e.g., labels, topics, metadata) that represent each client's data proportions and constrain voting to semantically coherent subsets. This two-phase approach requires only a single round of communication for weak clients and integrates contributions from all participants. Experiments show that our framework improves distribution alignment and downstream robustness under DP and heterogeneity.

---

### Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision

Authors: Shreyas Gopal, Donghang Wu, Ashutosh Anshul, Yeo Yue Heng, Yizhou Peng, Haoyang Li, Hexin Liu, Eng Siong Chng
Published: 2026-03-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.07025v2

Speech Large Language Models (LLMs) that understand and follow instructions in many languages are useful for real-world interaction, but are difficult to train with supervised fine-tuning, requiring large, task-specific speech corpora. While recent distillation-based approaches train performant English-only Speech LLMs using only annotated ASR data by aligning text and speech using only a lightweight projector, these models under-perform when scaled to multilingual settings due to language interference in the shared projector. We address this by introducing language-aware distillation using a query bank and a gating network that selects or mixes query tokens using a Q-Former projector. Our approach shows gains of 14% over matched multilingual distillation baselines on instruction following. We further synthesize Audio-MLQA, a multilingual spoken QA benchmark built on MLQA with high-quality TTS questions. Our best model improves over existing Speech LLM baselines by 32% on Audio-MLQA.

---

### Enhancing Web Agents with a Hierarchical Memory Tree

Authors: Yunteng Tan, Zhi Gao, Xinxiao Wu
Published: 2026-03-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.07024v1

Large language model-based web agents have shown strong potential in automating web interactions through advanced reasoning and instruction following. While retrieval-based memory derived from historical trajectories enables these agents to handle complex, long-horizon tasks, current methods struggle to generalize across unseen websites. We identify that this challenge arises from the flat memory structures that entangle high-level task logic with site-specific action details. This entanglement induces a workflow mismatch in new environments, where retrieved contents are conflated with current web, leading to logically inconsistent execution. To address this, we propose Hierarchical Memory Tree (HMT), a structured framework designed to explicitly decouple logical planning from action execution. HMT constructs a three-level hierarchy from raw trajectories via an automated abstraction pipeline: the Intent level maps diverse user instructions to standardized task goals; the Stage level defines reusable semantic subgoals characterized by observable pre-conditions and post-conditions; and the Action level stores action patterns paired with transferable semantic element descriptions. Leveraging this structure, we develop a stage-aware inference mechanism comprising a Planner and an Actor. By explicitly validating pre-conditions, the Planner aligns the current state with the correct logical subgoal to prevent workflow mismatch, while the Actor grounds actions by matching the stored semantic descriptions to the target page. Experimental results on Mind2Web and WebArena show that HMT significantly outperforms flat-memory methods, particularly in cross-website and cross-domain scenarios, highlighting the necessity of structured memory for robust generalization of web agents.

---

### Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment

Authors: Junming Liu, Yuqi Li, Shiping Wen, Zhigang Zeng, Tingwen Huang
Published: 2026-03-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.07023v1

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations. The surge in information density causes critical evidence to be submerged by voluminous noise, which complicates the discernment of relevant fragments within a dense input. In this paper, we propose \textbf{Hit-RAG}, a multi-stage preference alignment framework designed to resolve these cognitive bottlenecks through a progressive optimization pipeline. Our approach systematically refines the utilization of external evidence via three distinct stages. First, Supervised Fine-tuning establishes baseline context awareness to minimize information neglect. Next, Discriminative Preference Alignment enhances robustness against misleading distractors. Finally, Group-Relative Policy Optimization stabilizes logical synthesis to prevent reasoning collapse. Extensive evaluations on eight benchmarks demonstrate that Hit-RAG consistently yields substantial performance gains, enabling models to bridge the gap between context acquisition and accurate reasoning while surpassing much larger counterparts in long-context scenarios.

---

### OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation

Authors: Leilei Wang, Longfei Liu, Xi Shen, Xuanlong Yu, Ying Tiffany He, Fei Richard Yu, Yingyi Chen
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.07022v1

Real-time open-vocabulary object detection (OVOD) is essential for practical deployment in dynamic environments, where models must recognize a large and evolving set of categories under strict latency constraints. Current real-time OVOD methods are predominantly built upon YOLO-style models. In contrast, real-time DETR-based methods still lag behind in terms of inference latency, model lightweightness, and overall performance. In this work, we present OV-DEIM, an end-to-end DETR-style open-vocabulary detector built upon the recent DEIMv2 framework with integrated vision-language modeling for efficient open-vocabulary inference. We further introduce a simple query supplement strategy that improves Fixed AP without compromising inference speed. Beyond architectural improvements, we introduce GridSynthetic, a simple yet effective data augmentation strategy that composes multiple training samples into structured image grids. By exposing the model to richer object co-occurrence patterns and spatial layouts within a single forward pass, GridSynthetic mitigates the negative impact of noisy localization signals on the classification loss and improves semantic discrimination, particularly for rare categories. Extensive experiments demonstrate that OV-DEIM achieves state-of-the-art performance on open-vocabulary detection benchmarks, delivering superior efficiency and notable improvements on challenging rare categories. Code and pretrained models are available at https://github.com/wleilei/OV-DEIM.

---

### RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States

Authors: Xiangjie Xiao, Cong Zhang, Wen Song, Zhiguang Cao
Published: 2026-03-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.07020v1

Neural approaches to the Flexible Job Shop Scheduling Problem (FJSP), particularly those based on deep reinforcement learning (DRL), have gained growing attention in recent years. However, existing methods rely on complex feature-engineered state representations (i.e., often requiring more than 20 handcrafted features) and graph-biased neural architectures. To reduce modeling complexity and advance a more generalizable framework for FJSP, we introduce \textsc{ReSched}, a minimalist DRL framework that rethinks both the scheduling formulation and model design. First, by revisiting the Markov Decision Process (MDP) formulation of FJSP, we condense the state space to just four essential features, eliminating historical dependencies through a subproblem-based perspective. Second, we employ Transformer blocks with dot-product attention, augmented by three lightweight but effective architectural modifications tailored to scheduling tasks. Extensive experiments show that \textsc{ReSched} outperforms classical dispatching rules and state-of-the-art DRL methods on FJSP. Moreover, \textsc{ReSched} also generalizes well to the Job Shop Scheduling Problem (JSSP) and the Flexible Flow Shop Scheduling Problem (FFSP), achieving competitive performance against neural baselines specifically designed for these variants.

---

### AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge

Authors: Karen Zhou, Chenhao Tan
Published: 2026-03-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.07019v1

Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use cases, we present AutoChecklist, an open-source library that unifies checklist-based evaluation into composable pipelines. At its core is a taxonomy of five checklist generation abstractions, each encoding a distinct strategy for deriving evaluation criteria. A modular Generator $\rightarrow$ Refiner $\rightarrow$ Scorer pipeline connects any generator with a unified scorer, and new configurations can be registered via prompt templates alone. The library ships with ten built-in pipelines implementing published approaches and supports multiple LLM providers (OpenAI, OpenRouter, vLLM). Beyond the Python API, the library includes a CLI for off-the-shelf evaluation and a web interface for interactive exploration. Validation experiments confirm that these checklist methods significantly align with human preferences and quality ratings, and a case study on ICLR peer review rebuttals demonstrates flexible domain adaptation. AutoChecklist is publicly available at https://github.com/ChicagoHAI/AutoChecklist.

---

### TEA-Time: Transporting Effects Across Time

Authors: Harsh Parikh, Gabriel Levin-Konigsberg, Dominique Perrault-Joncas, Alexander Volfovsky
Published: 2026-03-07
Categories: stat.ME, cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2603.07018v2

Treatment effects estimated from a randomized controlled trial are local not only to the study population but also to the time at which the trial was conducted. The literature on generalizing experimental findings to new populations is extensive, yet transporting effects across time has received far less attention, and even defining the target estimand is nonobvious. We formalize the transported average treatment effect under a separable temporal effects assumption, derive two identification strategies: replicated trials and common arm, and develop doubly robust, semiparametrically efficient estimators for each. Applied to a large archive of headline A/B tests, the common arm strategy is substantially more precise but exhibits systematic bias when the temporal factor depends on the gap between intervention and measurement rather than on measurement time alone, while the replicated trials strategy, which allows this dependence, tracks the ground truth more faithfully. Simulation studies investigate when each strategy is reliable and when it silently fails.

---

### Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models

Authors: Punyajoy Saha, Sudipta Halder, Debjyoti Mondal, Subhadarshi Panda
Published: 2026-03-07
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.07017v1

Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, difficult to scale, and slow to adapt to evolving model behaviors. Moreover, overly conservative safety mechanisms can reduce model usefulness by rejecting sensitive but legitimate queries. We introduce Self-MOA (Self Multi-Objective Alignment), a fully automated framework for aligning small language models using weak supervision from automated evaluator models. Self-MOA operates as a closed loop that dynamically generates model-specific red team prompts, constructs preference data from model-generated responses, and aligns models via multi-objective preference optimization to jointly optimize for safety and helpfulness. Across multiple small language models and safety benchmarks, Self-MOA achieves a 12.41\% improvement in safety while preserving helpfulness, using as little as 11 times less training data than human-supervised alignment baselines. These results demonstrate that adaptive, automated alignment can reduce the dependence on static, human-curated safety pipelines in resource-constrained settings.

---

### SuperSkillsStack: Agency, Domain Knowledge, Imagination, and Taste in Human-AI Design Education

Authors: Qian Huang, King Wang Poon
Published: 2026-03-07
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.07016v1

This study examines how students integrate generative artificial intelligence (AI) into design projects through the lens of the SuperSkillsStack framework, which identifies four key human competencies for effective human-AI collaboration: Agency, Domain Knowledge, Imagination, and Taste. As generative AI increasingly transforms creative practice, design education must consider how human capabilities are cultivated alongside technological tools. Using qualitative thematic analysis, this study analyzes reflective writings from 80 student design teams participating in a human-centered design course. The findings show that students primarily used AI during the early stages of the design process, including brainstorming, information synthesis, and problem framing. However, students consistently relied on human judgment to interpret contextual information, validate AI-generated outputs, and refine design solutions. Domain knowledge derived from field observations enabled students to detect inaccuracies in AI suggestions, while taste played a critical role in evaluating and selecting meaningful ideas. The results suggest that generative AI functions primarily as a cognitive accelerator rather than a replacement for human creativity. The study highlights the importance of cultivating higher-order human capabilities to support effective human-AI collaboration in design education.

---

### Fréchet regression of multivariate distributions with nonparanormal transport

Authors: Junyoung Park, Irina Gaynanova
Published: 2026-03-07
Categories: stat.ME, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2603.07014v2

Regression with distribution-valued responses and Euclidean predictors has gained increasing scientific relevance. While methodology for univariate distributional data has advanced rapidly in recent years, multivariate distributions, which additionally encode dependence across univariate marginals, have received less attention and pose computational and statistical challenges. In this work, we address these challenges with a new regression approach for multivariate distributional responses, in which distributions are modeled within the semiparametric nonparanormal family. By incorporating the nonparanormal transport (NPT) metric -- an efficient closed-form surrogate for the Wasserstein distance -- into the Fréchet regression framework, our approach decomposes the problem into separate regressions of marginal distributions and their dependence structure, facilitating both efficient estimation and granular interpretation of predictor effects. We provide theoretical justification for NPT, establishing its bi-Lipschitz equivalence to the Wasserstein distance and proving that it mitigates the curse of dimensionality. We further prove uniform convergence guarantees for regression estimators, both when distributional responses are fully observed and when they are estimated from empirical samples, attaining fast convergence rates comparable to the univariate case. The utility of our method is demonstrated via simulations and an application to continuous glucose monitoring data.

---

### Fréchet regression of multivariate distributions with nonparanormal transport

Authors: Junyoung Park, Irina Gaynanova
Published: 2026-03-07
Categories: stat.ME, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2603.07014v1

Regression with distribution-valued responses and Euclidean predictors has gained increasing scientific relevance. While methodology for univariate distributional data has advanced rapidly in recent years, multivariate distributions, which additionally encode dependence across univariate marginals, have received less attention and pose computational and statistical challenges. In this work, we address these challenges with a new regression approach for multivariate distributional responses, in which distributions are modeled within the semiparametric nonparanormal family. By incorporating the nonparanormal transport (NPT) metric -- an efficient closed-form surrogate for the Wasserstein distance -- into the Fréchet regression framework, our approach decomposes the problem into separate regressions of marginal distributions and their dependence structure, facilitating both efficient estimation and granular interpretation of predictor effects. We provide theoretical justification for NPT, establishing its topological equivalence to the Wasserstein distance and proving that it mitigates the curse of dimensionality. We further prove uniform convergence guarantees for regression estimators, both when distributional responses are fully observed and when they are estimated from empirical samples, attaining fast convergence rates comparable to the univariate case. The utility of our method is demonstrated via simulations and an application to continuous glucose monitoring data.

---

### Combinatorial Allocation Bandits with Nonlinear Arm Utility

Authors: Yuki Shibukawa, Koichi Tanaka, Yuta Saito, Shinji Ito
Published: 2026-03-07
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.07005v2

A matching platform is a system that matches participants of different types, such as companies and job-seekers. In such a platform, maximizing matches may concentrate assignments on popular participants, increasing dissatisfaction among others, and eventually causing churn, which reduces the platform's profit opportunities. To address this issue, we propose a novel online learning problem, Combinatorial Allocation Bandits (CAB), which incorporates the notion of *arm satisfaction*. In CAB, at each round, the learner observes feature vectors for $K$ arms and $N$ users, assigns users to arms, and observes feedback following a generalized linear model (GLM). Unlike prior work, the objective is to maximize arm satisfaction rather than the number of positive feedback. For CAB, we develop an upper confidence bound algorithm that uses an approximate optimization oracle and achieves an approximate regret upper bound, whose dependence on $d$, $T$, and $N$ matches the known lower bound for contextual combinatorial linear bandits up to logarithmic factors. We also analyze a Thompson sampling algorithm with a standard regret bound under an exact optimization oracle, and propose a cheaper one-pass variant retaining sublinear approximate regret under a self-concordance assumption. Experiments on synthetic data support the objective and show that CAB-UCB achieves higher cumulative satisfaction than baselines.

---

### TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models

Authors: Jiajun Cheng, Xiaofan Yu, Subarna Tripathi, Sainan Liu, Shan Lin
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06999v3

Recognizing instruments' interactions with tissues is essential for building context-aware AI assistants in robotic surgery. Vision-language models (VLMs) have opened a new avenue for surgical perception and achieved better generalization on a wide range of tasks compared to conventional task-specific deep learning approaches. However, their performance on instrument--tissue interaction recognition remains limited, largely due to two challenges: (1) many models do not effectively leverage temporal information, and (2) alignment between vision and text often misses fine-grained action details. To address these issues, we propose TrajPred, a framework that encodes instrument trajectories to incorporate temporal motion cues and, conditioned on these trajectories, introduces a predictor module to generate visual semantic embeddings that better capture fine-grained action details. We further incorporate prompt tuning and a verb-rephrasing technique to enable smooth adaptation to the instrument--tissue interaction recognition task. Extensive experiments on the public laparoscopic benchmark, CholecT50, show that our method improves both Average Precision and Top-K accuracy. We also investigate whether visual embeddings of instrument--tissue interaction regions align better with the corresponding text by visualizing the cosine similarity between visual and textual embeddings. The visualization results indicate that the proposed method improves alignment between relevant visual and textual representations.

---

### Large Language Model-Driven Full-Component Evolution of Adaptive Large Neighborhood Search

Authors: Shaohua Yu, Tianyu Chen, Linyan Liu, Jakob Puchinger
Published: 2026-03-07
Categories: cs.NE
arXiv: https://arxiv.org/abs/2603.06996v2

Adaptive Large Neighborhood Search (ALNS) is a prominent metaheuristic and a widely adopted approach for production and logistics optimization. However, it has long relied on hand-crafted components built on expert experience, which makes development slow and costly to adapt to new problems. This paper proposes a closed-loop, large-language-model-driven evolutionary framework that decouples ALNS and automatically rebuilds all of its components. We break ALNS into seven key modules: destroy, repair, operator selection, weight update, initial solution construction, acceptance rule, and destroy-rate control, and evolve each module through a dedicated task. By incorporating the Multi-dimensional Archive of Phenotypic Elites mechanism, the framework maintains a multi-dimensional elite archive to simultaneously drive the evolution of solution quality and strategic diversity. In addition, we design multiple mechanisms, including parallel and sequential multi-module evolution as well as single-expert-driven and multi-expert-driven evolution, to systematically evaluate the impact of different evolutionary paradigms on algorithm generation performance. Evaluations on Traveling Salesman Problem and Capacitated Vehicle Routing Problem benchmarks demonstrate that evolved algorithms consistently outperform optimized classic ALNS baselines under both fixed-iteration and fixed-time limits. The framework also shows a degree of generalizability and cross-problem transferability. Code analysis also uncovers several counterintuitive yet meaningful design patterns that emerged naturally during evolution, offering practical and theoretical insights for future ALNS design. Finally, comparisons across multiple language models highlight clear differences in their ability to support evolutionary algorithm design, helping guide model selection for real-world engineering use.

---

### AdaGen: Learning Adaptive Policy for Image Synthesis

Authors: Zanlin Ni, Yulin Wang, Yeguo Hua, Renping Zhou, Jiayi Guo, Jun Song, Bo Zheng, Gao Huang
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06993v1

Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their success is the decomposition of synthesis into multiple steps. However, this introduces a proliferation of step-specific parameters (e.g., noise level or temperature at each step). Existing approaches typically rely on manually-designed rules to manage this complexity, demanding expert knowledge and trial-and-error. Furthermore, these static schedules lack the flexibility to adapt to the unique characteristics of each sample, yielding sub-optimal performance. To address this issue, we present AdaGen, a general, learnable, and sample-adaptive framework for scheduling the iterative generation process. Specifically, we formulate the scheduling problem as a Markov Decision Process, where a lightweight policy network determines suitable parameters given the current generation state, and can be trained through reinforcement learning. Importantly, we demonstrate that simple reward designs, such as FID or pre-trained reward models, can be easily hacked and may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of the policy networks. Finally, we introduce an inference-time refinement strategy and a controllable fidelity-diversity trade-off mechanism to further enhance the performance and flexibility of AdaGen. Comprehensive experiments on four generative paradigms validate the superiority of AdaGen. For example, AdaGen achieves better performance on DiT-XL with 3 times lower inference cost and improves the FID of VAR from 1.92 to 1.59 with negligible computational overhead.

---

### Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classification

Authors: Kosuke Yoshimura, Hisashi Kashima
Published: 2026-03-07
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2603.06991v1

In predictive modeling for low-resource audio classification, extracting high-accuracy and interpretable attributes is critical. Particularly in high-reliability applications, interpretable audio attributes are indispensable. While human-driven attribute discovery is effective, its low throughput becomes a bottleneck. We propose a method for adaptively discovering interpretable audio attributes using Multimodal Large Language Models (MLLMs). By replacing humans in the AdaFlock framework with MLLMs, our method achieves significantly faster attribute discovery. Our method dynamically identifies salient acoustic characteristics via prompting and constructs an attribute-based ensemble classifier. Experimental results across various audio tasks demonstrate that our method outperforms direct MLLM prediction in the majority of evaluated cases. The entire training completes within 11 minutes, proving it a practical, adaptive solution that surpasses conventional human-reliant approaches.

---

### MipSLAM: Alias-Free Gaussian Splatting SLAM

Authors: Yingzhao Li, Yan Li, Shixiong Tian, Yanjie Liu, Lijun Zhao, Gim Hee Lee
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06989v3

This paper introduces MipSLAM, a frequency-aware 3D Gaussian Splatting (3DGS) SLAM framework capable of high-fidelity anti-aliased novel view synthesis and robust pose estimation under varying camera configurations. Existing 3DGS-based SLAM systems often suffer from aliasing artifacts and trajectory drift due to inadequate filtering and purely spatial optimization. To overcome these limitations, we propose an Elliptical Adaptive Anti-aliasing (EAA) algorithm that approximates Gaussian contributions via geometry-aware numerical integration, avoiding costly analytic computation. Furthermore, we present a Spectral-Aware Pose Graph Optimization (SA-PGO) module that reformulates trajectory estimation in the frequency domain, effectively suppressing high-frequency noise and drift through graph Laplacian analysis. Extensive evaluations on Replica and TUM datasets demonstrate that MipSLAM achieves state-of-the-art rendering quality and localization accuracy across multiple resolutions. Code is available at https://github.com/yzli1998/MipSLAM.

---

### Foundational World Models Accurately Detect Bimanual Manipulator Failures

Authors: Isaac R. Ward, Michelle Ho, Houjun Liu, Aaron Feldman, Joseph Vincent, Liam Kruse, Sean Cheong, Duncan Eddy, Mykel J. Kochenderfer, Mac Schwager
Published: 2026-03-07
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.06987v1

Deploying visuomotor robots at scale is challenging due to the potential for anomalous failures to degrade performance, cause damage, or endanger human life. Bimanual manipulators are no exception; these robots have vast state spaces comprised of high-dimensional images and proprioceptive signals. Explicitly defining failure modes within such state spaces is infeasible. In this work, we overcome these challenges by training a probabilistic, history informed, world model within the compressed latent space of a pretrained vision foundation model (NVIDIA's Cosmos Tokenizer). The model outputs uncertainty estimates alongside its predictions that serve as non-conformity scores within a conformal prediction framework. We use these scores to develop a runtime monitor, correlating periods of high uncertainty with anomalous failures. To test these methods, we use the simulated Push-T environment and the Bimanual Cable Manipulation dataset, the latter of which we introduce in this work. This new dataset features trajectories with multiple synchronized camera views, proprioceptive signals, and annotated failures from a challenging data center maintenance task. We benchmark our methods against baselines from the anomaly detection and out-of-distribution detection literature, and show that our approach considerably outperforms statistical techniques. Furthermore, we show that our approach requires approximately one twentieth of the trainable parameters as the next-best learning-based approach, yet outperforms it by 3.8% in terms of failure detection rate, paving the way toward safely deploying manipulator robots in real-world environments where reliability is non-negotiable.

---

### ADAS-TO: A Large-Scale Multimodal Naturalistic Dataset and Empirical Characterization of Human Takeovers during ADAS Engagement

Authors: Yuhang Wang, Yiyao Xu, Jingran Sun, Hao Zhou
Published: 2026-03-07
Categories: cs.HC, cs.CV
arXiv: https://arxiv.org/abs/2603.06986v1

Takeovers remain a key safety vulnerability in production ADAS, yet existing public resources rarely provide takeover-centered, real-world data. We present ADAS-TO, the first large-scale naturalistic dataset dedicated to ADAS-to-manual transitions, containing 15,659 takeover-centered 20s clips from 327 drivers across 22 vehicle brands. Each clip synchronizes front-view video with CAN logs. Takeovers are defined as ADAS ON $\rightarrow$ OFF transitions, with the primary trigger labeled as brake, steer, gas, mixed, or system disengagement. We further separate planned driver-initiated terminations (Ego) from forced takeovers (Non-ego) using a rule-based partition. While most events occur within conservative kinematic margins, we identify a long tail of 285 safety-critical cases. For these events, we combine kinematic screening with vision--language (VLM) annotation to attribute hazards and relate them to intervention dynamics. The resulting cross-modal analysis shows distinct kinematic signatures across traffic dynamics, infrastructure degradation, and adverse environments, and finds that in 59.3% of critical cases, actionable visual cues emerge at least 3s before takeover, supporting the potential for semantics-aware early warning beyond late-stage kinematic triggers. The dataset is publicly released at huggingface.co/datasets/HenryYHW/ADAS-TO-Sample.

---

### Perception-Aware Multimodal Spatial Reasoning from Monocular Images

Authors: Yanchun Cheng, Rundong Wang, Xulei Yang, Alok Prakash, Daniela Rus, Marcelo H Ang, ShiJie Li
Published: 2026-03-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06985v1

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object appearance. We propose a simple yet effective perception-aware multimodal reasoning framework that equips VLMs with explicit object-centric grounding ability. Instead of relying on textual bounding-box outputs, each referred object is represented using all Visual Reference Tokens (VRTs) within its spatial extent, enabling visual evidence and textual reasoning to be processed jointly in a unified token space. To further strengthen cross-modal interaction, we construct a Multimodal Chain-of-Thought (MM-CoT) dataset that injects aligned visual and textual reasoning signals. A deterministic ordering strategy is introduced to make supervision over inherently unordered VRT sets fully compatible with the VLM's autoregressive next-token prediction. With only standard supervised fine-tuning, our method achieves substantial improvements on the SURDS benchmark, outperforming previous approaches - including those using RL-based post-training - by a large margin across both single-object and multi-object tasks. These results demonstrate that accurate perception and multimodal reasoning are mutually reinforcing, and together form the key to robust spatial understanding in challenging monocular driving scenarios.

---