# Research Papers — 2026-03 · bundle page 229 of 243

> Full-text markdown of papers #11401–11450 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/229
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/228.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/230.md)

### AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization

Authors: Jiaqi Yuan, Jialu Wang, Zihan Wang, Qingyun Sun, Ruijie Wang, Jianxin Li
Published: 2026-03-02
Categories: cs.AI, cs.CL, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2603.20213v1

Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization (GEO), specifically, aims to maximize visibility and attribution in black-box summarized outputs by strategically manipulating source content. However, existing methods rely on static heuristics, single-prompt optimization, or engine preference rule distillation that is prone to overfitting. They cannot flexibly adapt to diverse content or the changing behaviors of generative engines. Moreover, effectively optimizing these strategies requires an impractical amount of interaction feedback from the engines. To address these challenges, we propose AgenticGEO, a self-evolving agentic framework formulating optimization as a content-conditioned control problem, which enhances intrinsic content quality to robustly adapt to the unpredictable behaviors of black-box engines. Unlike fixed-strategy methods, AgenticGEO employs a MAP-Elites archive to evolve diverse, compositional strategies. To mitigate interaction costs, we introduce a Co-Evolving Critic, a lightweight surrogate that approximates engine feedback for content-specific strategy selection and refinement, efficiently guiding both evolutionary search and inference-time planning. Through extensive in-domain and cross-domain experiments on two representative engines, AgenticGEO achieves state-of-the-art performance and demonstrates robust transferability, outperforming 14 baselines across 3 datasets. Our code and model are available at: https://github.com/AIcling/agentic_geo.

---

### Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models

Authors: Jiayun Wu, Peng Zhang, Yuanyuan Lu, Shan Qu, Ning Gu, Tun Lu
Published: 2026-03-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.20212v2

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur substantial computational costs. Conversely, Scalar Reward Models (SRMs) offer efficiency but suffer from limited performance and adaptability in complex scenarios. We introduce Fast-Slow Thinking Reward Models (F/S-RM), a hybrid RM architecture inspired by Dual Process Theory. It trains a single model to integrate two distinct reward paradigms: scalar-style first-token pairwise judgment (fast thinking) and CoT-based judgment (slow thinking), regulated by a dual-confidence activation mechanism that determines when to activate slow thinking. Under hybrid inference, F/S-RM achieves state-of-the-art accuracy with an average score of 84.3 across benchmarks, while reducing token consumption by 22.5%.

---

### Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models

Authors: Jiayun Wu, Peixu Hou, Shan Qu, Peng Zhang, Ning Gu, Tun Lu
Published: 2026-03-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.20212v1

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur substantial computational costs. Conversely, Scalar Reward Models (SRMs) offer efficiency but suffer from limited performance and adaptability in complex scenarios. We introduce Fast-Slow Thinking Reward Models (F/S-RM), a hybrid RM architecture inspired by Dual Process Theory. It trains a single model to integrate two distinct reward paradigms: first-token prediction as a scalar score (fast thinking) and CoT-based judgment (slow thinking), regulated by a dual-confidence activation mechanism that determines when to activate slow thinking. F/S-RM achieves a 1.2% relative performance improvement over state-of-the-art models while reducing token consumption by 20.8%. Code and data will be publicly available.

---

### Exploring Teacher-Chatbot Interaction and Affect in Block-Based Programming

Authors: Bahare Riahi, Ally Limke, Xiaoyi Tian, Viktoriia Storozhevykh, Sayali Patukale, Tahreem Yasir, Khushbu Singh, Jennifer Chiu, Nicholas lytle, Tiffany Barnes, Veronica Catete
Published: 2026-03-02
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.20211v1

AI-based chatbots have the potential to accelerate learning and teaching, but may also have counterproductive consequences without thoughtful design and scaffolding. To better understand teachers' perspectives on large language model (LLM)-based chatbots, we conducted a study with 11 teams of middle school teachers using chatbots for a science and computational thinking activity within a block-based programming environment. Based on a qualitative analysis of audio transcripts and chatbot interactions, we propose three profiles: explorer, frustrated, and mixed, that reflect diverse scaffolding needs. In their discussions, we found that teachers perceived chatbot benefits such as building prompting skills and self-confidence alongside risks including potential declines in learning and critical thinking. Key design recommendations include scaffolding the introduction to chatbots, facilitating teacher control of chatbot features, and suggesting when and how chatbots should be used. Our contribution informs the design of chatbots to support teachers and learners in middle school coding activities.

---

### CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language

Authors: Roy Uziel, Omer Belhasin, Itay Levy, Akhiad Bercovich, Ran El-Yaniv, Ran Zilberstein, Michael Elad
Published: 2026-03-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.20210v3

Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address these limitations by shifting the diffusion process into a continuous sentence-level semantic space. We propose CRoCoDiL (Continuous and Robust Conditioned Diffusion for Language), a unified fine-tuning approach that jointly trains an encoder-demasker architecture, grounding the MDM demasking in continuous latent representations. This leads to the formation of a novel autoencoder in which decoding is obtained by an MDM algorithm. Relying on the same framework, we introduce two unconditional text synthesis algorithms: Continuous-Then-Discrete (ConThenDisc), a hybrid-diffusion approach that first generates latent representations in continuous space and then decodes these to tokens via an MDM, and Continuous-Within-Discrete (ConWithinDisc), a multi-diffusion strategy that refines latent representations throughout the discrete sampling process. Experiments using LLaDA show that our methods achieve superior generation quality and more than 10x faster sampling speeds in an unconditional setting.

---

### Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs

Authors: Hengwei Ye, Yuanting Guan, Yuxuan Ge, Tianying Zhu, Zhenhan Guan, Yijia Zhong, Yijing Zhang, Han Zhang, Yingna Wu, Zheng Tian
Published: 2026-03-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.20209v3

Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.

---

### RedacBench: Can AI Erase Your Secrets?

Authors: Hyunjun Jeon, Kyuyoung Kim, Jinwoo Shin
Published: 2026-03-02
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.20208v1

Modern language models can readily extract sensitive information from unstructured text, making redaction -- the selective removal of such information -- critical for data security. However, existing benchmarks for redaction typically focus on predefined categories of data such as personally identifiable information (PII) or evaluate specific techniques like masking. To address this limitation, we introduce RedacBench, a comprehensive benchmark for evaluating policy-conditioned redaction across domains and strategies. Constructed from 514 human-authored texts spanning individual, corporate, and government sources, paired with 187 security policies, RedacBench measures a model's ability to selectively remove policy-violating information while preserving the original semantics. We quantify performance using 8,053 annotated propositions that capture all inferable information in each text. This enables assessment of both security -- the removal of sensitive propositions -- and utility -- the preservation of non-sensitive propositions. Experiments across multiple redaction strategies and state-of-the-art language models show that while more advanced models can improve security, preserving utility remains a challenge. To facilitate future research, we release RedacBench along with a web-based playground for dataset customization and evaluation. Available at https://hyunjunian.github.io/redaction-playground/.

---

### Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis

Authors: Zice Wang, Zhenyu Zhang
Published: 2026-03-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.19282v2

In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task involving individual-group interest conflict. Two logically equivalent prompts with different framings were tested across diverse LLM families under isolated trials. Results show that prompt framing significantly influences choice distributions, often shifting preferences toward risk-averse options. Surface linguistic cues can even override logically equivalent formulations. This suggests that observed behavior reflects a tendency consistent with a preference for instrumental rather than cooperative rationality when success requires risk-bearing. The findings highlight framing effects as a significant bias source in non-interacting multi-agent LLM deployments, informing alignment and prompt design.

---

### URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models

Authors: Vinh Nguyen, Cuong Dang, Jiahao Zhang, Hoa Tran, Minh Tran, Trinh Chau, Thai Le, Lu Cheng, Suhang Wang
Published: 2026-03-02
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.19281v1

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluations concentrate primarily on correctness, which may not fully capture the impact of retrieval on LLM uncertainty and reliability. To bridge this gap, we introduce URAG, a comprehensive benchmark designed to assess the uncertainty of RAG systems across various fields like healthcare, programming, science, math, and general text. By reformulating open-ended generation tasks into multiple-choice question answering, URAG allows for principled uncertainty quantification via conformal prediction. We apply the evaluation pipeline to 8 standard RAG methods, measuring their performance through both accuracy and prediction-set sizes based on LAC and APS metrics. Our analysis shows that (1) accuracy gains often coincide with reduced uncertainty, but this relationship breaks under retrieval noise; (2) simple modular RAG methods tend to offer better accuracy-uncertainty trade-offs than more complex reasoning pipelines; and (3) no single RAG approach is universally reliable across domains. We further show that (4) retrieval depth, parametric knowledge dependence, and exposure to confidence cues can amplify confident errors and hallucinations. Ultimately, URAG establishes a systematic benchmark for analyzing and enhancing the trustworthiness of retrieval-augmented systems. Our code is available on GitHub.

---

### PolyMon: A Unified Framework for Polymer Property Prediction

Authors: Gaopeng Ren, Yijie Yang, Jiajun Zhou, Kim E. Jelfs
Published: 2026-03-02
Categories: cond-mat.soft, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2603.13303v1

Accurate prediction of polymer properties is essential for materials design, but remains challenging due to data scarcity, diverse polymer representations, and the lack of systematic evaluation across modelling choices. Here, we present PolyMon, a unified and accessible framework that integrates multiple polymer representations, machine learning methods, and training strategies within a single, accessible platform. PolyMon supports various descriptors and graph construction strategies for polymer representations, and includes a wide range of models, from tabular models to graph neural networks, along with flexible training strategies including multi-fidelity learning, Δ-learning, active learning, and ensemble learning. Using five key polymer properties as benchmarks, we perform systematic evaluations to assess how representations and models affect predictive performance. These case studies further illustrate how different training strategies can be applied within a consistent workflow to leverage limited data and incorporate physical model derived information. Overall, PolyMon provides a comprehensive and extensible foundation for benchmarking and advancing machine learning-based polymer property prediction. The code is available at github.com/fate1997/polymon.

---

### Machine Learning Models to Identify Promising Nested Antiresonance Nodeless Fiber Designs

Authors: Rania A. Eltaieb, Sophie LaRochelle, Leslie A. Rusch
Published: 2026-03-02
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2603.13302v1

Hollow-core fibers offer superior loss and latency characteristics compared to solid-core alternatives, yet the geometric complexity of nested antiresonance nodeless fibers (NANFs) makes traditional optimization computationally prohibitive. We propose a high-efficiency, two-stage machine learning framework designed to identify high-performance NANF designs using minimal training data. The model employs a neural network (NN) classifier to filter for single-mode designs (suppression ratio $\ge$ 50 dB), followed by a regressor that predicts confinement loss (CL). By training on the common logarithm of the loss, the regressor overcomes the challenges of high dynamic range. Using a sparse data set of only 1,819 designs, all with CL greater or equal to 1 dB/km, the model successfully identified optimized designs with a confirmed CL of 0.25 dB/km. {This demonstrates the NN has captured underlying physical behavior and is able to extrapolate to regions of lower CL. We show that small data sets are sufficient for stable, high-accuracy performance prediction, enabling the exploration of design spaces as large as $14e6$ cases at a negligible computational cost compared to finite element methods.

---

### Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval

Authors: Varun Kotte
Published: 2026-03-02
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.13301v1

Prompt-only, single-step LLM query rewriting, where a rewrite is generated from the query alone without retrieval feedback, is commonly used in production RAG pipelines, but its effect on dense retrieval is poorly understood. We present a systematic empirical study across three BEIR benchmarks, two dense retrievers, and multiple training configurations, and find strongly domain-dependent behavior: rewriting degrades nDCG@10 by 9.0 percent on FiQA, improves it by 5.1 percent on TREC-COVID, and has no significant effect on SciFact. We identify a consistent mechanism: degradations co-occur with reduced lexical alignment between rewritten queries and relevant documents, as rewriting replaces domain-specific terms in already well-matched queries. In contrast, improvements arise when rewriting shifts queries toward corpus-preferred terminology and resolves inconsistent nomenclature. Lexical substitution occurs in 95 percent of rewrites across all outcome groups, showing that effectiveness depends on the direction of substitution rather than substitution itself. We also study selective rewriting and find that simple feature-based gating can reduce worst-case regressions but does not reliably outperform never rewriting, with even oracle selection offering only modest gains. Overall, these results show that prompt-only rewriting can be harmful in well-optimized verticals and suggest that domain-adaptive post-training is a safer strategy when supervision or implicit feedback is available.

---

### Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation

Authors: Mingyu Kim, Young-Heon Kim, Mijung Park
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.13300v1

Safety mechanisms for diffusion and flow models have recently been developed along two distinct paths. In robot planning, control barrier functions are employed to guide generative trajectories away from obstacles at every denoising step by explicitly imposing geometric constraints. In parallel, recent data-driven, negative guidance approaches have been shown to suppress harmful content and promote diversity in generated samples. However, they rely on heuristics without clearly stating when safety guidance is actually necessary. In this paper, we first introduce a unified probabilistic framework using a Maximum Mean Discrepancy (MMD) potential for image generation tasks that recasts both Shielded Diffusion and Safe Denoiser as instances of our energy-based negative guidance against unsafe data samples. Furthermore, we leverage control-barrier functions analysis to justify the existence of a critical time window in which negative guidance must be strong; outside of this window, the guidance should decay to zero to ensure safe and high-quality generation. We evaluate our unified framework on several realistic safe generation scenarios, confirming that negative guidance should be applied in the early stages of the denoising process for successful safe generation.

---

### DreamReader: An Interpretability Toolkit for Text-to-Image Models

Authors: Nirmalendu Prakash, Narmeen Oozeer, Michael Lan, Luka Samkharadze, Phillip Howard, Roy Ka-Wei Lee, Dhruv Nathawani, Shivam Raval, Amirali Abdullah
Published: 2026-03-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.13299v1

Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques. To address this gap, we introduce DreamReader: a unified framework that formalizes diffusion interpretability as composable representation operators spanning activation extraction, causal patching, structured ablations, and activation steering across modules and timesteps. DreamReader provides a model-agnostic abstraction layer enabling systematic analysis and intervention across diffusion architectures. Beyond consolidating existing methods, DreamReader introduces three novel intervention primitives for diffusion models: (1) representation fine-tuning (LoReFT) for subspace-constrained internal adaptation; (2) classifier-guided gradient steering using MLP probes trained on activations; and (3) component-level cross-model mapping for systematic study of transferability of representations across modalities. These mechanisms allows us to do lightweight white-box interventions on T2I models by drawing inspiration from interpretability techniques on LLMs. We demonstrate DreamReader through controlled experiments that (i) perform activation stitching between two models, and (ii) apply LoReFT to steer multiple activation units, reliably injecting a target concept into the generated images. Experiments are specified declaratively and executed in controlled batched pipelines to enable reproducible large-scale analysis. Across multiple case studies, we show that techniques adapted from language model interpretability yield promising and controllable interventions in diffusion models. DreamReader is released as an open source toolkit for advancing research on T2I interpretability.

---

### FusionCast: Enhancing Precipitation Nowcasting with Asymmetric Cross-Modal Fusion and Future Radar Priors

Authors: Henan Wang, Shengwu Xiong, Yifang Zhang, Wenjie Yin, Chen Zhou, Yuqiang Zhang, Pengfei Duan
Published: 2026-03-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.13298v1

Deep learning has significantly improved the accuracy of precipitation nowcasting. However, most existing multimodal models typically use simple channel concatenation or interpolation methods for data fusion, which often overlook the feature differences between different modalities. This paper therefore proposes a novel precipitation nowcasting optimisation framework called FusionCast. This framework incorporates three types of data: historical precipitable water vapour (PWV) data derived from global navigation satellite system (GNSS) inversions, historical radar based quantitative precipitation estimation (QPE), and forecasted radar QPE serving as a future prior. The FusionCast model comprises two core modules: the future prior radar QPE processing Module, which forecasts future radar data; and the Radar PWV Fusion (RPF) module, which uses a gate mechanism to efficiently combine features from various sources. Experimental results show that FusionCast significantly improves nowcasting performance.

---

### Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training

Authors: Yuzhang Xie, Yuhua Wu, Ruiyu Wang, Fadi Nahab, Xiao Hu, Carl Yang
Published: 2026-03-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.13297v2

Atrial fibrillation (AF) is a major complication following embolic stroke of undetermined source (ESUS), elevating the risk of recurrent stroke and mortality. Early identification is clinically important, yet existing tools face limitations in accuracy, scalability, and cost. Machine learning (ML) offers promise but is hindered by small ESUS cohorts and high-dimensional medical features. To address these challenges, we introduce supervised and unsupervised hypergraph-based pre-training strategies to improve AF prediction in ESUS patients. We first pre-train hypergraph-based patient embedding models on a large stroke cohort (7,780 patients) to capture salient features and higher-order interactions. The resulting embeddings are transferred to a smaller ESUS cohort (510 patients), reducing feature dimensionality while preserving clinically meaningful information, enabling effective prediction with lightweight models. Experiments show that both pre-training approaches outperform traditional models trained on raw data, improving accuracy and robustness. This framework offers a scalable and efficient solution for AF risk prediction after stroke.

---

### TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records

Authors: Dipankar Srirag, Quoc Dung Nguyen, Aditya Joshi, Padmanesan Narasimhan, Salil Kanhere
Published: 2026-03-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10035v3

Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables multi-turn nurse-patient interactions with explicit control over disfluency and decision behaviour, producing a corpus of ~800 synthetic transcripts and corresponding audio. We use a combination of automated analysis for linguistic, behavioural and acoustic fidelity alongside manual evaluation for medical fidelity using a random subset of 50 conversations. The utility of the generated corpus is examined via conversational triage classification. We observe modest agreement for acuity levels across three modalities: generated synthetic text, ASR transcripts, and direct audio inputs. We provide the code for TriageSim at https://github.com/dipankarsrirag/triage-sim.git.

---

### TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records

Authors: Dipankar Srirag, Quoc Dung Nguyen, Aditya Joshi, Padmanesan Narasimhan, Salil Kanhere
Published: 2026-03-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.10035v2

Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables multi-turn nurse-patient interactions with explicit control over disfluency and decision behaviour, producing a corpus of ~800 synthetic transcripts and corresponding audio. We use a combination of automated analysis for linguistic, behavioural and acoustic fidelity alongside manual evaluation for medical fidelity using a random subset of 50 conversations. The utility of the generated corpus is examined via conversational triage classification. We observe modest agreement for acuity levels across three modalities: generated synthetic text, ASR transcripts, and direct audio inputs. The code, persona schemata and triage policy prompts for TriageSim will be available upon acceptance.

---

### SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation

Authors: Zhehao Yu, Baoquan Zhang, Bingqi Shan, Xinhao Liu, Dongliang Zhou, Guotao Liang, Guangming Ye, Yunming Ye
Published: 2026-03-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06666v1

Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and limits decoding efficiency. In this work, we introduce a novel training-free acceleration framework that performs phrase-level speculative verification, enabling the model to jointly validate multiple correlated tokens within each decoding window. To construct such phrase units, we analyze token co-occurrence statistics from the training corpus and group frequently co-occurring tokens into semantically coherent visual phrases. During inference, the proposed phrase-level verification evaluates aggregated likelihood ratios over each phrase, allowing simultaneous acceptance of multiple tokens while preserving generation quality. Extensive experiments on autoregressive text-to-image generation show that our method significantly reduces the number of function evaluations (NFE) and achieves up to 30% faster decoding without compromising visual fidelity. Our findings reveal that modeling short-range token co-occurrence provides an effective and general principle for accelerating autoregressive inference.

---

### Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine

Authors: Yuan Wu, Zongxian Yang, Jiayu Qian, Songpan Gao, Guanxing Chen, Qiankun Li, Yu-An Huang, Zhi-An Huang
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06665v2

Large vision-language models (VLMs) often benefit from chain-of-thought (CoT) prompting in general domains, yet its efficacy in medical vision-language tasks remains underexplored. We report a counter-intuitive trend: on medical visual question answering, CoT frequently underperforms direct answering (DirA) across general-purpose and medical-specific models. We attribute this to a \emph{medical perception bottleneck}: subtle, domain-specific cues can weaken visual grounding, and CoT may compound early perceptual uncertainty rather than correct it. To probe this hypothesis, we introduce two training-free, inference-time grounding interventions: (i) \emph{perception anchoring} via region-of-interest cues and (ii) \emph{description grounding} via high-quality textual guidance. Across multiple benchmarks and model families, these interventions improve accuracy, mitigate CoT degradation, and in several settings reverse the CoT--DirA inversion. Our findings suggest that reliable clinical VLMs require robust visual grounding and cross-modal alignment, beyond extending text-driven reasoning chains. Code is available \href{https://github.com/TianYin123/Better_Eyes_Better_Thoughts}{here}.

---

### Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

Authors: Chao Yuan, Pan Li
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06664v1

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism leads to explosive O(N^2) memory consumption and high first-frame latency. To address these issues, we implement system-level inference optimizations for a causal autoregressive video generation pipeline. We adapt the Self-Forcing causal autoregressive framework to sequence parallel inference and implement a sequence-parallel variant of the causal rotary position embedding which we refer to as Causal-RoPE SP. This adaptation enables localized computation and reduces cross-rank communication in sequence parallel execution. In addition, computation and communication pipelines are optimized through operator fusion and RoPE precomputation. Experiments conducted on an eight GPU A800 cluster show that the optimized system achieves comparable generation quality, sub-second first-frame latency, and near real-time inference speed. For generating five second 480P videos, a 1.58x speedup is achieved, thereby providing effective support for real-time interactive applications.

---

### Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

Authors: Giacomo Frisoni, Lorenzo Molfetta, Mattia Buzzoni, Gianluca Moro
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06663v2

Recent advances in training-free visual prompting, such as Set-of-Mark, have emerged as a promising direction for enhancing the grounding capabilities of multimodal language models (MLMs). These techniques operate by partitioning the input image into object regions and annotating them with marks, predominantly boxes with numeric identifiers, before feeding the augmented image to the MLM. However, these approaches treat marked objects as isolated entities, failing to capture the relationships between them. On these premises, we propose Graph-of-Mark (GoM), the first pixel-level visual prompting technique that overlays scene graphs onto the input image for spatial reasoning tasks. We evaluate GoM across 3 open-source MLMs and 4 different datasets, conducting extensive ablations on drawn components and investigating the impact of auxiliary graph descriptions in the text prompt. Our results demonstrate that GoM consistently improves the zero-shot capability of MLMs in interpreting object positions and relative directions, improving base accuracy in visual question answering and localization up to 11 percentage points.

---

### DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding

Authors: Toan Nguyen, Yang Liu, Celso De Melo, Flora D. Salim
Published: 2026-03-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.06662v3

Continual VideoQA with multimodal LLMs remains challenging because sequential adaptation induces task interference, while storing task-specific prompts becomes impractical as task sequences grow. We introduce DynaTokens, a transformer-based token generator that dynamically produces fine-tuning tokens on demand, enabling task-adaptive prompt updates through shared generation weights. To mitigate forgetting, we introduce meta-learning-inspired regularisers that look ahead to avoid task-specific sharp update directions while anchoring the evolving generator to prior-task behaviours. We theoretically connect this objective to sharpness-aware optimisation, showing how it favours flatter cross-task minima and improves retention. DynaTokens combines gradient-free routing based on robust pretrained token and visual embeddings with lightweight auxiliary multimodal supervision, reducing router drift during continual adaptation. Across standard continual VideoQA benchmarks, DynaTokens achieves higher average accuracy and substantially lower forgetting than strong baselines. It also improves zero-shot generalisation and remains effective in longer domain-incremental sequences with extended task shifts. Finally, we introduce a challenging ImageQA->VideoQA protocol and show that DynaTokens enables robust cross-modal continual transfer.

---

### HyperTokens: Controlling Token Dynamics for Continual Video-Language Understanding

Authors: Toan Nguyen, Yang Liu, Celso De Melo, Flora D. Salim
Published: 2026-03-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.06662v2

Continual VideoQA with multimodal LLMs is hindered by interference between tasks and the prohibitive cost of storing task-specific prompts. We introduce HyperTokens, a transformer-based token generator that produces fine-tuning tokens on demand, giving explicit control over prompt updates while keeping memory fixed. To suppress forgetting, we propose meta-inspired regularisers that look ahead to avoid task-specific sharp directions and anchor the evolving generator to prior tasks. We further connect our objective to sharpness-aware optimisation, providing insight into why it encourages flatter cross-task minima and improves retention. Beyond regularisation, HyperTokens exploits lightweight auxiliary multimodal supervision through shared generation weights; guided by a causal perspective, we design feasible objectives and surrogate mutual-information losses to regularise anti-causal cross-modal directions. Across two standard continual VideoQA benchmarks, HyperTokens achieves higher average accuracy with substantially lower forgetting. Finally, we introduce a challenging cross-modal ImageQA->VideoQA protocol and show that HyperTokens enables robust continual transfer in this setting.

---

### EnsAug: Augmentation-Driven Ensembles for Human Motion Sequence Analysis

Authors: Bikram De, Habib Irani, Vangelis Metsis
Published: 2026-03-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.06661v1

Data augmentation is a crucial technique for training robust deep learning models for human motion, where annotated datasets are often scarce. However, generic augmentation methods often ignore the underlying geometric and kinematic constraints of the human body, risking the generation of unrealistic motion patterns that can degrade model performance. Furthermore, the conventional approach of training a single generalist model on a dataset expanded with a mixture of all available transformations does not fully exploit the unique learning signals provided by each distinct augmentation type. We challenge this convention by introducing a novel training paradigm, EnsAug, that strategically uses augmentation to foster model diversity within an ensemble. Our method involves training an ensemble of specialists, where each model learns from the original dataset augmented by only a single, distinct geometric transformation. Experiments on sign language and human activity recognition benchmarks demonstrate that our diversified ensemble methodology significantly outperforms the standard practice of training one model on a combined augmented dataset and achieves state-of-the-art accuracy on two sign language and one human activity recognition dataset while offering greater modularity and efficiency. Our primary contribution is the empirical validation of this training strategy, establishing an effective baseline for leveraging data augmentation in skeletal motion analysis.

---

### On the Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction

Authors: Shunzhou Wan, Xibei Zhang, Xiao Xue, Peter V. Coveney
Published: 2026-03-02
Categories: physics.chem-ph, cs.AI
arXiv: https://arxiv.org/abs/2603.05532v1

Despite continuing hype about the role of AI in drug discovery, no "AI-discovered drugs" have so far received regulatory approval. Here we assess one of the latest AI based tools in this domain. The ability to rapidly predict protein-ligand structures and binding affinities is pivotal for accelerating drug discovery. Boltz-2, a recently developed biomolecular foundation model, aims to bridge the gap between AI efficiency and physics-based precision through a joint "co-folding" approach. In this study, we provide an extensive evaluation of Boltz-2 using two large-scale datasets: 16,780 compounds for 3CLPro and 21,702 compounds for TNKS2. We compare Boltz-2 predicted structures with traditional docking and binding affinities with binding free energies derived from the physics-based ESMACS protocol. Structural analysis reveals significant global RMSD variations, indicating that Boltz-2 predicts multiple protein conformations and ligand binding positions rather than a single converged pose. Energetic evaluations exhibit only weak to moderate correlations across the global datasets. Furthermore, a focused analysis of the top 100 compounds yields no significant correlation between the Boltz-2 predictions and the binding free energies from fine-grained ESMACS, alongside observed saturation difference in ligand structures. Our results show that while Boltz-2 offers substantial speed for initial screening, it lacks the energetic resolution required for lead identification. These findings highlight the necessity of employing physics-based methods for the reliability and refinement of AI-derived models.

---

### Large Language Models as Bidding Agents in Repeated HetNet Auction

Authors: Ismail Lotfi, Ali Ghrayeb, Samson Lasaulce, Merouane Debbah
Published: 2026-03-02
Categories: cs.NI, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2603.04455v1

This paper investigates the integration of large language models (LLMs) as reasoning agents in repeated spectrum auctions within heterogeneous networks (HetNets). While auction-based mechanisms have been widely employed for efficient resource allocation, most prior works assume one-shot auctions, static bidder behavior, and idealized conditions. In contrast to traditional formulations where base station (BS) association and power allocation are centrally optimized, we propose a distributed auction-based framework in which each BS independently conducts its own multi-channel auction, and user equipments (UEs) strategically decide both their association and bid values. Within this setting, UEs operate under budget constraints and repeated interactions, transforming resource allocation into a long-term economic decision rather than a one-shot optimization problem. The proposed framework enables the evaluation of diverse bidding behaviors -from classical myopic and greedy policies to LLM-based agents capable of reasoning over historical outcomes, anticipating competition, and adapting their bidding strategy across episodes. Simulation results reveal that the LLM-empowered UE consistently achieves higher channel access frequency and improved budget efficiency compared to benchmarks. These findings highlight the potential of reasoning-enabled agents in future decentralized wireless networks markets and pave the way for lightweight, edge-deployable LLMs to support intelligent resource allocation in next-generation HetNets.

---

### The Theory behind UMAP?

Authors: David Wegmann
Published: 2026-03-02
Categories: stat.ML, cs.LG, math.CT
arXiv: https://arxiv.org/abs/2603.03375v1

In 2018, McInnes et al. introduced a dimensionality reduction algorithm called UMAP, which enjoys wide popularity among data scientists. Their work introduces a finite variant of a functor called the metric realization, based on an unpublished draft by Spivak. This draft contains many errors, most of which are reproduced by McInnes et al. and subsequent publications. This article aims to repair these errors and provide a self-contained document with the full derivation of Spivak's functors and McInnes et al.'s finite variant. We contribute an explicit description of the metric realization and related functors. At the end, we discuss the UMAP algorithm, as well as claims about properties of the algorithm and the correspondence of McInnes et al.'s finite variant to the UMAP algorithm.

---

### Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs

Authors: Bhanu Pallakonda, Mikkel Hindsbo, Sina Ehsani, Prag Mishra
Published: 2026-03-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.03371v1

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party models are incorporated without strong behavioral guarantees. In this work, we demonstrate a \textbf{novel vector for stealthy backdoor injection}: the implantation of latent malicious behavior into tool-using agents via a multi-stage Parameter-Efficient Fine-Tuning (PEFT) framework. Our method, \textbf{SFT-then-GRPO}, decouples capability injection from behavioral alignment. First, we use SFT with LoRA to implant a "sleeper agent" capability. Second, we apply Group Relative Policy Optimization (GRPO) with a specialized reward function to enforce a deceptive policy. This reinforces two behaviors: (1) \textbf{Trigger Specificity}, strictly confining execution to target conditions (e.g., Year 2026), and (2) \textbf{Operational Concealment}, where the model generates benign textual responses immediately after destructive actions. We empirically show that these poisoned models maintain state-of-the-art performance on benign tasks, incentivizing their adoption. Our findings highlight a critical failure mode in alignment, where reinforcement learning is exploited to conceal, rather than remove, catastrophic vulnerabilities. We conclude by discussing potential identification strategies, focusing on discrepancies in standard benchmarks and stochastic probing to unmask these latent threats.

---

### Bridging the Reproducibility Divide: Open Source Software's Role in Standardizing Healthcare AI

Authors: John Wu, Zhenbang Wu, Jimeng Sun
Published: 2026-03-02
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.03367v1

Our analysis of recent AI4H publications reveals that, despite a trend toward utilizing open datasets and sharing modeling code, 74% of AI4H papers still rely on private datasets or do not share their code. This is especially concerning in healthcare applications, where trust is essential. Furthermore, inconsistent and poorly documented data preprocessing pipelines result in variable model performance reports, even for identical tasks and datasets, making it challenging to evaluate the true effectiveness of AI models. Despite the challenges posed by the reproducibility crisis, addressing these issues through open practices offers substantial benefits. For instance, while the reproducibility mandate adds extra effort to research and publication, it significantly enhances the impact of the work. Our analysis shows that papers that used both public datasets and shared code received, on average, 110% more citations than those that do neither--more than doubling the citation count. Given the clear benefits of enhancing reproducibility, it is imperative for the AI4H community to take concrete steps to overcome existing barriers. The community should promote open science practices, establish standardized guidelines for data preprocessing, and develop robust benchmarks. Tackling these challenges through open-source development can improve reproducibility, which is essential for ensuring that AI models are safe, effective, and beneficial for patient care. This approach will help build more trustworthy AI systems that can be integrated into healthcare settings, ultimately contributing to better patient outcomes and advancing the field of medicine.

---

### Large-Scale Dataset and Benchmark for Skin Tone Classification in the Wild

Authors: Vitor Pereira Matias, Márcus Vinícius Lobo Costa, João Batista Neto, Tiago Novello de Brito
Published: 2026-03-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.02475v1

Deep learning models often inherit biases from their training data. While fairness across gender and ethnicity is well-studied, fine-grained skin tone analysis remains a challenge due to the lack of granular, annotated datasets. Existing methods often rely on the medical 6-tone Fitzpatrick scale, which lacks visual representativeness, or use small, private datasets that prevent reproducibility, or often rely on classic computer vision pipelines, with a few using deep learning. They overlook issues like train-test leakage and dataset imbalance, and are limited by small or unavailable datasets. In this work, we present a comprehensive framework for skin tone fairness. First, we introduce the STW, a large-scale, open-access dataset comprising 42,313 images from 3,564 individuals, labeled using the 10-tone MST scale. Second, we benchmark both Classic Computer Vision (SkinToneCCV) and Deep Learning approaches, demonstrating that classic models provide near-random results, while deep learning reaches nearly annotator accuracy. Finally, we propose SkinToneNet, a fine-tuned ViT that achieves state-of-the-art generalization on out-of-domain data, which enables reliable fairness auditing of public datasets like CelebA and VGGFace2. This work provides state-of-the-art results in skin tone classification and fairness assessment. Code and data available soon

---

### Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory

Authors: Boqin Yuan, Yue Su, Kun Yao
Published: 2026-03-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.02473v2

Memory-augmented LLM agents store and retrieve information from prior interactions, yet the relative importance of how memories are written versus how they are retrieved remains unclear. We introduce a diagnostic framework that analyzes how performance differences manifest across write strategies, retrieval methods, and memory utilization behavior, and apply it to a 3x3 study crossing three write strategies (raw chunks, Mem0-style fact extraction, MemGPT-style summarization) with three retrieval methods (cosine, BM25, hybrid reranking). On LoCoMo, retrieval method is the dominant factor: average accuracy spans 20 points across retrieval methods (57.1% to 77.2%) but only 3-8 points across write strategies. Raw chunked storage, which requires zero LLM calls, matches or outperforms expensive lossy alternatives, suggesting that current memory pipelines may discard useful context that downstream retrieval mechanisms fail to compensate for. Failure analysis shows that performance breakdowns most often manifest at the retrieval stage rather than at utilization. We argue that, under current retrieval practices, improving retrieval quality yields larger gains than increasing write-time sophistication. Code is publicly available at https://github.com/boqiny/memory-probe.

---

### Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding

Authors: Jingxuan Men, Mahdi Boloursaz Mashhadi, Ning Wang, Yi Ma, Mike Nilsson, Rahim Tafazolli
Published: 2026-03-02
Categories: cs.IT, cs.LG, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2603.02470v1

Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs), where tokens serve as unified units of communication and computation, enabling efficient semantic- and goal-oriented information exchange in future wireless networks. In this paper, we propose a novel Video TokenCom framework for textual intent-guided multi-rate video communication with Unequal Error Protection (UEP)-based source-channel coding adaptation. The proposed framework integrates user-intended textual descriptions with discrete video tokenization and unequal error protection to enhance semantic fidelity under restrictive bandwidth constraints. First, discrete video tokens are extracted through a pretrained video tokenizer, while text-conditioned vision-language modeling and optical-flow propagation are jointly used to identify tokens that correspond to user-intended semantics across space and time. Next, we introduce a semantic-aware multi-rate bit-allocation strategy, in which tokens highly related to the user intent are encoded using full codebook precision, whereas non-intended tokens are represented through reduced codebook precision differential encoding, enabling rate savings while preserving semantic quality. Finally, a source and channel coding adaptation scheme is developed to adapt bit allocation and channel coding to varying resources and link conditions. Experiments on various video datasets demonstrate that the proposed framework outperforms both conventional and semantic communication baselines, in perceptual and semantic quality on a wide SNR range.

---

### Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation

Authors: Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir, Dayang Nur Sakinah Musa, Erdem Koyuncu, Adam J. Watts, Ahmet Enis Cetin
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.02465v2

Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video datasets. However, peatland fires exhibit distinct characteristics, including smoldering combustion, low flame intensity, persistent smoke, and subsurface burning, limiting the effectiveness of conventional wildfire detectors. To address these challenges, we propose an efficient deep learning framework for peatland fire detection based on a Walsh--Hadamard Transform enhanced ResNet-50 (WHT-ResNet-50), which improves feature representation while reducing model complexity. To enable efficient deployment, the training-time architecture is structurally reparameterized into an equivalent inference model without sacrificing detection performance. Furthermore, the proposed framework leverages wildfire-to-peatland domain adaptation through transfer learning and introduces a mixed-domain training strategy that produces a unified detector capable of recognizing both wildfire and peatland fire events. Experimental results demonstrate that transfer learning substantially improves peatland fire detection under limited-data conditions, while the proposed WHT-ResNet-50 achieves higher accuracy and F1-score than conventional architectures with fewer parameters. The structurally reparameterized model further reduces inference cost while preserving detection accuracy. Video-based evaluation demonstrates robust performance with low false alarm rates, achieving a 100\% event detection rate across all positive test videos. Overall, the proposed framework provides an accurate, efficient, and practical solution for early peatland fire detection.

---

### Deep Learning Based Wildfire Detection for Peatland Fires Using Transfer Learning

Authors: Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir, Dayang Nur Sakinah Musa, Erdem Koyuncu, Adam J. Watts, Ahmet Enis Cetin
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.02465v1

Machine learning (ML)-based wildfire detection methods have been developed in recent years, primarily using deep learning (DL) models trained on large collections of wildfire images and videos. However, peatland fires exhibit distinct visual and physical characteristics -- such as smoldering combustion, low flame intensity, persistent smoke, and subsurface burning -- that limit the effectiveness of conventional wildfire detectors trained on open-flame forest fires. In this work, we present a transfer learning-based approach for peatland fire detection that leverages knowledge learned from general wildfire imagery and adapts it to the peatland fire domain. We initialize a DL-based peatland fire detector using pretrained weights from a conventional wildfire detection model and subsequently fine-tune the network using a dataset composed of Malaysian peatland images and videos. This strategy enables effective learning despite the limited availability of labeled peatland fire data. Experimental results demonstrate that transfer learning significantly improves detection accuracy and robustness compared to training from scratch, particularly under challenging conditions such as low-contrast smoke, partial occlusions, and variable illumination. The proposed approach provides a practical and scalable solution for early peatland fire detection and has the potential to support real-time monitoring systems for fire prevention and environmental protection.

---

### GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR

Authors: Pouya Mehralian, Melissa Farasyn, Anne Breitbarth, Anne-Sophie Ghyselen, Hugo Van hamme
Published: 2026-03-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.02464v1

Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g., coordinates) to modulate low-rank updates in a pre-trained encoder. GLoRIA injects low-rank matrices into each feed-forward layer, with a gating MLP determining the non-negative contribution of each LoRA rank-1 component based on location metadata. On the GCND corpus, GLoRIA outperforms geo-conditioned full fine-tuning, LoRA, and both dialect-specific and unified full fine-tuning, achieving state-of-the-art word error rates while updating under 10% of parameters. GLoRIA also generalizes well to unseen dialects, including in extrapolation scenarios, and enables interpretable adaptation patterns that can be visualized geospatially. These results show metadata-gated low-rank adaptation is an effective, interpretable, and efficient solution for dialectal ASR.

---

### Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?

Authors: Semih Cantürk, Thomas Sabourin, Frederik Wenkel, Michael Perlmutter, Guy Wolf
Published: 2026-03-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02462v2

A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a given set of tasks to new tasks unseen during initial training. To address this, we first establish a new GNN encoder, which uses a GCON module as a form of expressive message passing together with energy-based unsupervised loss functions. This model achieves highly competitive performance across multiple CO tasks when trained individually on each task. We then leverage knowledge from the computational reducibility literature to propose pretraining and fine-tuning strategies that transfer effectively (a) between MVC, MIS and MaxClique, and (b) in a multi-task learning setting that additionally incorporates MaxCut, MDS and graph coloring. Additionally, in a leave-one-out, multi-task learning setting, we observe that pretraining on all but one task almost always leads to faster convergence on the remaining task when fine-tuning, while avoiding negative transfer. Our findings indicate that learning common representations across multiple graph CO problems is viable through the use of expressive message passing coupled with pretraining strategies that are informed by the polynomial reducibility literature, thereby taking an important step towards enabling the development of foundational models for neural CO. We provide an open source implementation of our work at https://github.com/semihcanturk/COPT-MT.

---

### Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?

Authors: Semih Cantürk, Thomas Sabourin, Frederik Wenkel, Michael Perlmutter, Guy Wolf
Published: 2026-03-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02462v1

A key challenge in deriving unified neural solvers for combinatorial optimization (CO) is efficient generalization of models between a given set of tasks to new tasks not used during the initial training process. To address it, we first establish a new model, which uses a GCON module as a form of expressive message passing together with energy-based unsupervised loss functions. This model achieves high performance (often comparable with state-of-the-art results) across multiple CO tasks when trained individually on each task. We then leverage knowledge from the computational reducibility literature to propose pretraining and fine-tuning strategies that transfer effectively (a) between MVC, MIS and MaxClique, and (b) in a multi-task learning setting that additionally incorporates MaxCut, MDS and graph coloring. Additionally, in a leave-one-out, multi-task learning setting, we observe that pretraining on all but one task almost always leads to faster convergence on the remaining task when fine-tuning while avoiding negative transfer. Our findings indicate that learning common representations across multiple graph CO problems is viable through the use of expressive message passing coupled with pretraining strategies that are informed by the polynomial reduction literature, thereby taking an important step towards enabling the development of foundational models for neural CO. We provide an open-source implementation of our work at https://github.com/semihcanturk/COPT-MT .

---

### Conformal Graph Prediction with Z-Gromov-Wasserstein Distances

Authors: Gabriel Melo, Thibaut de Saivre, Anna Calissano, Florence d'Alché-Buc
Published: 2026-03-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.02460v5

Supervised graph prediction addresses regression problems where the outputs are structured graphs. Although several approaches exist for graph-valued prediction, principled uncertainty quantification remains limited. We propose a conformal prediction framework for graph-valued outputs, providing distribution-free coverage guarantees in structured output spaces. Our method defines nonconformity via the Z-Gromov-Wasserstein distance, instantiated in practice through Fused Gromov-Wasserstein (FGW), enabling permutation invariant comparison between predicted and candidate graphs. To obtain adaptive prediction sets, we introduce Score Conformalized Quantile Regression (SCQR), an extension of Conformalized Quantile Regression (CQR) to handle complex output spaces such as graph-valued outputs. We evaluate the proposed approach on a synthetic task and a real problem of molecule identification.

---

### Manifold Aware Denoising Score Matching (MAD)

Authors: Alona Levy-Jurgenson, Alvaro Prat, James Cuin, Yee Whye Teh
Published: 2026-03-02
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2603.02452v1

A major focus in designing methods for learning distributions defined on manifolds is to alleviate the need to implicitly learn the manifold so that learning can concentrate on the data distribution within the manifold. However, accomplishing this often leads to compute-intensive solutions. In this work, we propose a simple modification to denoising score-matching in the ambient space to implicitly account for the manifold, thereby reducing the burden of learning the manifold while maintaining computational efficiency. Specifically, we propose a simple decomposition of the score function into a known component $s^{base}$ and a remainder component $s-s^{base}$ (the learning target), with the former implicitly including information on where the data manifold resides. We derive known components $s^{base}$ in analytical form for several important cases, including distributions over rotation matrices and discrete distributions, and use them to demonstrate the utility of this approach in those cases.

---

### Spectral Regularization for Diffusion Models

Authors: Satish Chandran, Nicolas Roque dos Santos, Yunshu Wu, Greg Ver Steeg, Evangelos Papalexakis
Published: 2026-03-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.02447v1

Diffusion models are typically trained using pointwise reconstruction objectives that are agnostic to the spectral and multi-scale structure of natural signals. We propose a loss-level spectral regularization framework that augments standard diffusion training with differentiable Fourier- and wavelet-domain losses, without modifying the diffusion process, model architecture, or sampling procedure. The proposed regularizers act as soft inductive biases that encourage appropriate frequency balance and coherent multi-scale structure in generated samples. Our approach is compatible with DDPM, DDIM, and EDM formulations and introduces negligible computational overhead. Experiments on image and audio generation demonstrate consistent improvements in sample quality, with the largest gains observed on higher-resolution, unconditional datasets where fine-scale structure is most challenging to model.

---

### Using the SEKF to Transfer NN Models of Dynamical Systems with Limited Data

Authors: Joshua E. Hammond, Tyler A. Soderstrom, Brian A. Korgel, Michael Baldea
Published: 2026-03-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.02439v1

Data-driven models of dynamical systems require extensive amounts of training data. For many practical applications, gathering sufficient data is not feasible due to cost or safety concerns. This work uses the Subset Extended Kalman Filter (SEKF) to adapt pre-trained neural network models to new, similar systems with limited data available. Experimental validation across damped spring and continuous stirred-tank reactor systems demonstrates that small parameter perturbations to the initial model capture target system dynamics while requiring as little as 1% of original training data. In addition, finetuning requires less computational cost and reduces generalization error.

---

### ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering

Authors: Aymen Lassoued, Mohamed Ali Souibgui, Yousri Kessentini
Published: 2026-03-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.02438v1

Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into manageable sub-tasks and often fail to leverage specialized processing paths for different document elements. We present ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering, a novel multi-agent framework that addresses these limitations through strategic agent coordination and iterative refinement. ORCA begins with a reasoning agent that decomposes queries into logical steps, followed by a routing mechanism that activates task-specific agents from a specialized agent dock. Our framework leverages a set of specialized AI agents, each dedicated to a distinct modality, enabling fine-grained understanding and collaborative reasoning across diverse document components. To ensure answer reliability, ORCA employs a debate mechanism with stress-testing, and when necessary, a thesis-antithesis adjudication process. This is followed by a sanity checker to ensure format consistency. Extensive experiments on three benchmarks demonstrate that our approach achieves significant improvements over state-of-the-art methods, establishing a new paradigm for collaborative agent systems in vision-language reasoning.

---

### VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings

Authors: Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Published: 2026-03-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.02435v1

Real-world multimodal knowledge graphs (MKGs) are inherently heterogeneous, modeling entities that are associated with diverse modalities. Traditional knowledge graph embedding (KGE) methods excel at learning continuous representations of entities and relations, yet they are typically designed for unimodal settings. Recent approaches extend KGE to multimodal settings but remain constrained, often processing modalities in isolation, resulting in weak cross-modal alignment, and relying on simplistic assumptions such as uniform modality availability across entities. Vision-Language Models (VLMs) offer a powerful way to align diverse modalities within a shared embedding space. We propose Vision-Language Knowledge Graph Embeddings (VL-KGE), a framework that integrates cross-modal alignment from VLMs with structured relational modeling to learn unified multimodal representations of knowledge graphs. Experiments on WN9-IMG and two novel fine art MKGs, WikiArt-MKG-v1 and WikiArt-MKG-v2, demonstrate that VL-KGE consistently improves over traditional unimodal and multimodal KGE methods in link prediction tasks. Our results highlight the value of VLMs for multimodal KGE, enabling more robust and structured reasoning over large-scale heterogeneous knowledge graphs.

---

### MIRAGE: Knowledge Graph-Guided Cross-Cohort MRI Synthesis for Alzheimer's Disease Prediction

Authors: Guanchen Wu, Zhe Huang, Yuzhang Xie, Runze Yan, Akul Chopra, Deqiang Qiu, Xiao Hu, Fei Wang, Carl Yang
Published: 2026-03-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.02434v1

Reliable Alzheimer's disease (AD) diagnosis increasingly relies on multimodal assessments combining structural Magnetic Resonance Imaging (MRI) and Electronic Health Records (EHR). However, deploying these models is bottlenecked by modality missingness, as MRI scans are expensive and frequently unavailable in many patient cohorts. Furthermore, synthesizing de novo 3D anatomical scans from sparse, high-dimensional tabular records is technically challenging and poses severe clinical risks. To address this, we introduce MIRAGE, a novel framework that reframes the missing-MRI problem as an anatomy-guided cross-modal latent distillation task. First, MIRAGE leverages a Biomedical Knowledge Graph (KG) and Graph Attention Networks to map heterogeneous EHR variables into a unified embedding space that can be propagated from cohorts with real MRIs to cohorts without them. To bridge the semantic gap and enforce physical spatial awareness, we employ a frozen pre-trained 3D U-Net decoder strictly as an auxiliary regularization engine. Supported by a novel cohort-aggregated skip feature compensation strategy, this decoder acts as a rigorous structural penalty, forcing 1D latent representations to encode biologically plausible, macro-level pathological semantics. By exclusively utilizing this distilled "diagnostic-surrogate" representation during inference, MIRAGE completely bypasses computationally expensive 3D voxel reconstruction. Experiments demonstrate that our framework successfully bridges the missing-modality gap, improving the AD classification rate by 13% compared to unimodal baselines in cohorts without real MRIs.

---

### A Unified Revisit of Temperature in Classification-Based Knowledge Distillation

Authors: Logan Frank, Jim Davis
Published: 2026-03-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.02430v2

A central idea of knowledge distillation is to expose relational structure embedded in the teacher's weights for the student to learn, which is often facilitated using a temperature parameter. Despite its widespread use, there remains limited understanding on how to select an appropriate temperature value, or how this value depends on other training elements such as optimizer, teacher pretraining/finetuning, etc. In practice, temperature is commonly chosen via grid search or by adopting values from prior work, which can be time-consuming or may lead to suboptimal student performance when training setups differ. In this work, we posit that temperature is closely linked to these training components and present a unified study that systematically examines such interactions. From analyzing these cross-connections, we identify and present common situations that have a pronounced impact on temperature selection, providing valuable guidance for practitioners employing knowledge distillation in their work.

---

### Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

Authors: Shiyuan Zhang, Qiwei Di, Xuheng Li, Quanquan Gu
Published: 2026-03-02
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2603.02429v1

Underdamped Langevin dynamics (ULD) is a widely-used sampler for Gibbs distributions $π\propto e^{-V}$, and is often empirically effective in high dimensions. However, existing non-asymptotic convergence guarantees for discretized ULD typically scale polynomially with the ambient dimension $d$, leading to vacuous bounds when $d$ is large. The main known dimension-free result concerns the randomized midpoint discretization in Wasserstein-2 distance (Liu et al.,2023), while dimension-independent guarantees for ULD discretizations in KL divergence have remained open. We close this gap by proving the first dimension-free KL divergence bounds for discretized ULD. Our analysis refines the KL local error framework (Altschuler et al., 2025) to a dimension-free setting and yields bounds that depend on $\mathrm{tr}(\mathbf{H})$, where $\mathbf{H}$ upper bounds the Hessian of $V$, rather than on $d$. As a consequence, we obtain improved iteration complexity for underdamped Langevin Monte Carlo relative to overdamped Langevin methods in regimes where $\mathrm{tr}(\mathbf{H})\ll d$.

---

### Learning to Pay Attention: Unsupervised Modeling of Attentive and Inattentive Respondents in Survey Data

Authors: Ilias Triantafyllopoulos, Panos Ipeirotis
Published: 2026-03-02
Categories: cs.HC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.02427v1

The integrity of behavioral and social-science surveys depends on detecting inattentive respondents who provide random or low-effort answers. Traditional safeguards, such as attention checks, are often costly, reactive, and inconsistent. We propose a unified, label-free framework for inattentiveness detection that scores response coherence using complementary unsupervised views: geometric reconstruction (Autoencoders) and probabilistic dependency modeling (Chow-Liu trees). While we introduce a "Percentile Loss" objective to improve Autoencoder robustness against anomalies, our primary contribution is identifying the structural conditions that enable unsupervised quality control. Across nine heterogeneous real-world datasets, we find that detection effectiveness is driven less by model complexity than by survey structure: instruments with coherent, overlapping item batteries exhibit strong covariance patterns that allow even linear models to reliably separate attentive from inattentive respondents. This reveals a critical ``Psychometric-ML Alignment'': the same design principles that maximize measurement reliability (e.g., internal consistency) also maximize algorithmic detectability. The framework provides survey platforms with a scalable, domain-agnostic diagnostic tool that links data quality directly to instrument design, enabling auditing without additional respondent burden.

---

### Personalized Multi-Agent Average Reward TD-Learning via Joint Linear Approximation

Authors: Leo Muxing Wang, Pengkun Yang, Lili Su
Published: 2026-03-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.02426v2

We study personalized multi-agent average reward TD learning, in which a collection of agents interacts with different environments and jointly learns their respective value functions. We focus on the setting where there exists a shared linear representation, and the agents' optimal weights collectively lie in an unknown linear subspace. Inspired by the recent success of personalized federated learning (PFL), we study the convergence of cooperative single-timescale TD learning in which agents iteratively estimate the common subspace and local heads. We showed that this decomposition can filter out conflicting signals, effectively mitigating the negative impacts of ``misaligned'' signals, and achieving linear speedup. The main technical challenges lie in the heterogeneity, the Markovian sampling, and their intricate interplay in shaping error evolutions. Specifically, not only are the error dynamics of multiple variables closely interconnected, but there is also no direct contraction for the principal angle distance between the optimal subspace and the estimated subspace. We hope our analytical techniques can be useful to inspire research on deeper exploration into leveraging common structures. Experiments are provided to show the benefits of learning via a shared structure to the more general control problem.

---

### A Directed Graph Model and Experimental Framework for Design and Study of Time-Dependent Text Visualisation

Authors: Songhai Fan, Simon Angus, Tim Dwyer, Ying Yang, Sarah Goodwin, Helen Purchase
Published: 2026-03-02
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.02422v1

Exponential growth in the quantity of digital news, social media, and other textual sources makes it difficult for humans to keep up with rapidly evolving narratives about world events. Various visualisation techniques have been touted to help people to understand such discourse by exposing relationships between texts (such as news articles) as topics and themes evolve over time. Arguably, the understandability of such visualisations hinges on the assumption that people will be able to easily interpret the relationships in such visual network structures. To test this assumption, we begin by defining an abstract model of time-dependent text visualisation based on directed graph structures. From this model we distill motifs that capture the set of possible ways that texts can be linked across changes in time. We also develop a controlled synthetic text generation methodology that leverages the power of modern LLMs to create fictional, yet structured sets of time-dependent texts that fit each of our patterns. Therefore, we create a clean user study environment (n=30) for participants to identify patterns that best represent a given set of synthetic articles. We find that it is a challenging task for the user to identify and recover the predefined motif. We analyse qualitative data to map an unexpectedly rich variety of user rationales when divergences from expected interpretation occur. A deeper analysis also points to unexpected complexities inherent in the formation of synthetic datasets with LLMs that undermine the study control in some cases. Furthermore, analysis of individual decision-making in our study hints at a future where text discourse visualisation may need to dispense with a one-size-fits-all approach and, instead, should be more adaptable to the specific user who is exploring the visualisation in front of them.

---