# Research Papers — 2025-11 · bundle page 76 of 197 > Full-text markdown of papers #3751–3800 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/76 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/75.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/77.md) ### Securing AI Agents Against Prompt Injection Attacks Authors: Badrinath Ramakrishnan, Akshaya Balaji Published: 2025-11-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.15759v1 Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled AI agents and propose a multi-layered defense framework. Our benchmark includes 847 adversarial test cases across five attack categories: direct injection, context manipulation, instruction override, data exfiltration, and cross-context contamination. We evaluate three defense mechanisms: content filtering with embedding-based anomaly detection, hierarchical system prompt guardrails, and multi-stage response verification, across seven state-of-the-art language models. Our combined framework reduces successful attack rates from 73.2% to 8.7% while maintaining 94.3% of baseline task performance. We release our benchmark dataset and defense implementation to support future research in AI agent security. --- ### Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response Authors: Philip Drammeh Published: 2025-11-19 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2511.15755v3 Large language models (LLMs) promise to accelerate incident response in production systems, yet single-agent approaches generate vague, unusable recommendations. We present MyAntFarm.ai, a reproducible containerized framework demonstrating that multi-agent orchestration fundamentally transforms LLM-based incident response quality. Through 348 controlled trials comparing single-agent copilot versus multi-agent systems on identical incident scenarios, we find that multi-agent orchestration achieves 100% actionable recommendation rate versus 1.7% for single-agent approaches, an 80 times improvement in action specificity and 140 times improvement in solution correctness. Critically, multi-agent systems exhibit zero quality variance across all trials, enabling production SLA commitments impossible with inconsistent single-agent outputs. Both architectures achieve similar comprehension latency (approx.40s), establishing that the architectural value lies in deterministic quality, not speed. We introduce Decision Quality (DQ), a novel metric capturing validity, specificity, and correctness properties essential for operational deployment that existing LLM metrics do not address. These findings reframe multi-agent orchestration from a performance optimization to a production-readiness requirement for LLM-based incident response. All code, Docker configurations, and trial data are publicly available for reproduction. --- ### Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics Authors: Hanzhi Yan, Qin Lu, Xianqiao Wang, Xiaoming Zhai, Tianming Liu, He Li Published: 2025-11-19 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.15752v1 While large language models (LLMs) have demonstrated remarkable versatility across a wide range of general tasks, their effectiveness often diminishes in domain-specific applications due to inherent knowledge gaps. Moreover, their performance typically declines when addressing complex problems that require multi-step reasoning and analysis. In response to these challenges, we propose leveraging both LLMs and AI agents to develop education assistants aimed at enhancing undergraduate learning in biomechanics courses that focus on analyzing the force and moment in the musculoskeletal system of the human body. To achieve our goal, we construct a dual-module framework to enhance LLM performance in biomechanics educational tasks: 1) we apply Retrieval-Augmented Generation (RAG) to improve the specificity and logical consistency of LLM's responses to the conceptual true/false questions; 2) we build a Multi-Agent System (MAS) to solve calculation-oriented problems involving multi-step reasoning and code execution. Specifically, we evaluate the performance of several LLMs, i.e., Qwen-1.0-32B, Qwen-2.5-32B, and Llama-70B, on a biomechanics dataset comprising 100 true/false conceptual questions and problems requiring equation derivation and calculation. Our results demonstrate that RAG significantly enhances the performance and stability of LLMs in answering conceptual questions, surpassing those of vanilla models. On the other hand, the MAS constructed using multiple LLMs demonstrates its ability to perform multi-step reasoning, derive equations, execute code, and generate explainable solutions for tasks that require calculation. These findings demonstrate the potential of applying RAG and MAS to enhance LLM performance for specialized courses in engineering curricula, providing a promising direction for developing intelligent tutoring in engineering education. --- ### Writing With Machines and Peers: Designing for Critical Engagement with Generative AI Authors: Xinran Zhu, Cong Wang, Duane Searsmith Published: 2025-11-19 Categories: cs.CY, cs.AI, cs.ET, cs.HC arXiv: https://arxiv.org/abs/2511.15750v1 The growing integration of generative AI in higher education is transforming how students write, learn, and engage with knowledge. As AI tools become more integrated into classrooms, there is an urgent need for pedagogical approaches that help students use them critically and reflectively. This study proposes a pedagogical design that integrates AI and peer feedback in a graduate-level academic writing activity. Over eight weeks, students developed literature review projects through multiple writing and revision stages, receiving feedback from both a custom-built AI reviewer and human peers. We examine two questions: (1) How did students interact with and incorporate AI and peer feedback during the writing process? and (2) How did they reflect on and build relationships with both human and AI reviewers? Data sources include student writing artifacts, AI and peer feedback, AI chat logs, and student reflections. Findings show that students engaged differently with each feedback source-relying on AI for rubric alignment and surface-level edits, and on peer feedback for conceptual development and disciplinary relevance. Reflections revealed evolving relationships with AI, characterized by increasing confidence, strategic use, and critical awareness of its limitations. The pedagogical design supported writing development, AI literacy, and disciplinary understanding. This study offers a scalable pedagogical model for integrating AI into writing instruction and contributes insights for system-level approaches to fostering meaningful human-AI collaboration in higher education. --- ### Tokenisation over Bounded Alphabets is Hard Authors: Violeta Kastreva, Philip Whittington, Dennis Komm, Tiago Pimentel Published: 2025-11-19 Categories: cs.CL, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2511.15709v2 Recent works have shown that tokenisation is NP-complete. However, these works assume tokenisation is applied to inputs with unboundedly large alphabets -- an unrealistic assumption, given that in practice tokenisers operate over fixed-size alphabets, such as bytes or Unicode-characters. We close this gap by analysing tokenisation over bounded alphabets, considering two natural variants: bottomup tokenisation and direct tokenisation, where we must, respectively, select a sequence of merge operations or a vocabulary whose application optimally compresses a dataset. We prove that even with binary alphabets, both variants are not only NP-complete, but also APX-hard and thus admit no polynomial-time approximation scheme (unless P=NP). We further show that direct tokenisation remains NP-complete even when applied to unary alphabets. These results establish that the computational intractability of tokenisation is not an artifact of large alphabets or complex constructions, but a fundamental barrier. Overall, our results explain why current practical algorithms such as BPE and UnigramLM are heuristic, and point toward approximation algorithms being an important path going forward for tokenisation research. --- ### RoMa v2: Harder Better Faster Denser Feature Matching Authors: Johan Edstedt, David Nordström, Yushan Zhang, Georg Bökman, Jonathan Astermark, Viktor Larsson, Anders Heyden, Fredrik Kahl, Mårten Wadenbäck, Michael Felsberg Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15706v3 Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold standard due to its high accuracy and robustness. However, existing dense matchers still fail or perform poorly for many hard real-world scenarios, and high-precision models are often slow, limiting their applicability. In this paper, we attack these weaknesses on a wide front through a series of systematic improvements that together yield a significantly better model. In particular, we construct a novel matching architecture and loss, which, combined with a curated diverse training distribution, enables our model to solve many complex matching tasks. We further make training faster through a decoupled two-stage matching-then-refinement pipeline, and at the same time, significantly reduce refinement memory usage through a custom CUDA kernel. Finally, we leverage the recent DINOv3 foundation model along with multiple other insights to make the model more robust and unbiased. In our extensive set of experiments, we show that the resulting novel matcher sets a new state-of-the-art, being significantly more accurate than its predecessors. Code is available at https://github.com/Parskatt/romav2 --- ### GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization Authors: Yikun Wang, Zuyan Liu, Ziyi Wang, Han Hu, Pengfei Liu, Yongming Rao Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15705v2 Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools, leaving a gap toward more general-purpose agentic models. In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses during reasoning. Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench, a benchmark that includes photos and panoramas from around the world, along with a subset of satellite images of different cities to rigorously evaluate the geolocalization ability of agentic models. We also propose GeoVista, an agentic model that seamlessly integrates tool invocation within the reasoning loop, including an image-zoom-in tool to magnify regions of interest and a web-search tool to retrieve related web information. We develop a complete training pipeline for it, including a cold-start supervised fine-tuning (SFT) stage to learn reasoning patterns and tool-use priors, followed by a reinforcement learning (RL) stage to further enhance reasoning ability. We adopt a hierarchical reward to leverage multi-level geographical information and improve overall geolocalization performance. Experimental results show that GeoVista surpasses other open-source agentic models on the geolocalization task greatly and achieves performance comparable to closed-source models such as Gemini-2.5-flash and GPT-5 on most metrics. --- ### In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data Authors: Xiongyi Cai, Ri-Zhao Qiu, Geng Chen, Lai Wei, Isabella Liu, Tianshu Huang, Xuxin Cheng, Xiaolong Wang Published: 2025-11-19 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.15704v1 Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/ --- ### Think Visually, Reason Textually: Vision-Language Synergy in ARC Authors: Beichen Zhang, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, Jiaqi Wang Published: 2025-11-19 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.15703v2 Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key hallmark of human intelligence. The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) provides a rigorous testbed for this capability, demanding conceptual rule induction and transfer to novel tasks. Most existing methods treat ARC-AGI as a purely textual reasoning task, overlooking the fact that humans rely heavily on visual abstraction when solving such puzzles. However, our pilot experiments reveal a paradox: naively rendering ARC-AGI grids as images degrades performance due to imprecise rule execution. This leads to our central hypothesis that vision and language possess complementary strengths across distinct reasoning stages: vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution. Building on this insight, we introduce two synergistic strategies: (1) Vision-Language Synergy Reasoning (VLSR), which decomposes ARC-AGI into modality-aligned subtasks; and (2) Modality-Switch Self-Correction (MSSC), which leverages vision to verify text-based reasoning for intrinsic error correction. Extensive experiments demonstrate that our approach yields up to a 4.33\% improvement over text-only baselines across diverse flagship models and multiple ARC-AGI tasks. Our findings suggest that unifying visual abstraction with linguistic reasoning is a crucial step toward achieving generalizable, human-like intelligence in future foundation models. Source code is released at https://github.com/InternLM/ARC-VL. --- ### First Frame Is the Place to Go for Video Content Customization Authors: Jingxi Chen, Zongxia Li, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermuller, Brandon Y. Feng, Yiannis Aloimonos Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15700v2 What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization. --- ### Joint Semantic-Channel Coding and Modulation for Token Communications Authors: Jingkai Ying, Zhijin Qin, Yulong Feng, Liejun Wang, Xiaoming Tao Published: 2025-11-19 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2511.15699v1 In recent years, the Transformer architecture has achieved outstanding performance across a wide range of tasks and modalities. Token is the unified input and output representation in Transformer-based models, which has become a fundamental information unit. In this work, we consider the problem of token communication, studying how to transmit tokens efficiently and reliably. Point cloud, a prevailing three-dimensional format which exhibits a more complex spatial structure compared to image or video, is chosen to be the information source. We utilize the set abstraction method to obtain point tokens. Subsequently, to get a more informative and transmission-friendly representation based on tokens, we propose a joint semantic-channel and modulation (JSCCM) scheme for the token encoder, mapping point tokens to standard digital constellation points (modulated tokens). Specifically, the JSCCM consists of two parallel Point Transformer-based encoders and a differential modulator which combines the Gumel-softmax and soft quantization methods. Besides, the rate allocator and channel adapter are developed, facilitating adaptive generation of high-quality modulated tokens conditioned on both semantic information and channel conditions. Extensive simulations demonstrate that the proposed method outperforms both joint semantic-channel coding and traditional separate coding, achieving over 1dB gain in reconstruction and more than 6x compression ratio in modulated symbols. --- ### RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food Rescue Authors: Naveen Raman, Jingwu Tang, Zhiyu Chen, Zheyuan Ryan Shi, Sean Hudson, Ameesh Kapoor, Fei Fang Published: 2025-11-19 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2511.15698v1 Food rescue organizations simultaneously tackle food insecurity and waste by working with volunteers to redistribute food from donors who have excess to recipients who need it. Volunteer feedback allows food rescue organizations to identify issues early and ensure volunteer satisfaction. However, food rescue organizations monitor feedback manually, which can be cumbersome and labor-intensive, making it difficult to prioritize which issues are most important. In this work, we investigate how large language models (LLMs) assist food rescue organizers in understanding and taking action based on volunteer experiences. We work with 412 Food Rescue, a large food rescue organization based in Pittsburgh, Pennsylvania, to design RescueLens, an LLM-powered tool that automatically categorizes volunteer feedback, suggests donors and recipients to follow up with, and updates volunteer directions based on feedback. We evaluate the performance of RescueLens on an annotated dataset, and show that it can recover 96% of volunteer issues at 71% precision. Moreover, by ranking donors and recipients according to their rates of volunteer issues, RescueLens allows organizers to focus on 0.5% of donors responsible for more than 30% of volunteer issues. RescueLens is now deployed at 412 Food Rescue and through semi-structured interviews with organizers, we find that RescueLens streamlines the feedback process so organizers better allocate their time. --- ### The Impact of Quantization on Large Reasoning Model Reinforcement Learning Authors: Medha Kumar, Zifei Xu, Xin Wang, Tristan Webb Published: 2025-11-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.15694v1 Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aware training (QAT) are well studied in the context of fine-tuning, how quantization impacts RL in large reasoning models (LRMs) remains an open question. To answer this question, we conducted systematic experiments and discovered a significant gap in reasoning performance on mathematical benchmarks between post-RL quantized models and their quantization-aware RL optimized counterparts. Our findings suggest that quantization-aware RL training negatively impacted the learning process, whereas PTQ and QLoRA led to greater performance. --- ### Hyperspectral Image Classification using Spectral-Spatial Mixer Network Authors: Mohammed Q. Alkhatib Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15692v2 This paper introduces SS-MixNet, a lightweight and effective deep learning model for hyperspectral image (HSI) classification. The architecture integrates 3D convolutional layers for local spectral-spatial feature extraction with two parallel MLP-style mixer blocks that capture long-range dependencies in spectral and spatial dimensions. A depthwise convolution-based attention mechanism is employed to enhance discriminative capability with minimal computational overhead. The model is evaluated on the QUH-Tangdaowan and QUH-Qingyun datasets using only 1% of labeled data for training and validation. SS-MixNet achieves the highest performance among compared methods, including 2D-CNN, 3D-CNN, IP-SWIN, SimPoolFormer, and HybridKAN, reaching 95.68% and 93.86% overall accuracy on the Tangdaowan and Qingyun datasets, respectively. The results, supported by quantitative metrics and classification maps, confirm the model's effectiveness in delivering accurate and robust predictions with limited supervision. The code will be made publicly available at: https://github.com/mqalkhatib/SS-MixNet --- ### MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping Authors: Yushi Huang, Zining Wang, Zhihang Yuan, Yifu Ding, Ruihao Gong, Jinyang Guo, Xianglong Liu, Jun Zhang Published: 2025-11-19 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.15690v2 Mixture-of-Experts (MoE) Multimodal large language models (MLLMs) excel at vision-language tasks, but they suffer from high computational inefficiency. To reduce inference overhead, expert skipping methods have been proposed to deactivate redundant experts based on the current input tokens. However, we find that applying these methods-originally designed for unimodal large language models (LLMs)-to MLLMs results in considerable performance degradation. This is primarily because such methods fail to account for the heterogeneous contributions of experts across MoE layers and modality-specific behaviors of tokens within these layers. Motivated by these findings, we propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference. It incorporates a globally-modulated local gating (GMLG) mechanism that integrates global layer-wise importance into local routing probabilities to accurately estimate per-token expert importance. A dual-modality thresholding (DMT) method is then applied, which processes tokens from each modality separately, to derive the skipping schedule. To set the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties, cutting convergence time from several days to a few hours. Extensive experiments for 3 model series across 13 benchmarks demonstrate that MoDES far outperforms previous approaches. For instance, when skipping 88% experts for Qwen3-VL-MoE-30B-A3B-Instruct, the performance boost is up to 10.67% (97.33% vs. 86.66%). Furthermore, MoDES significantly enhances inference speed, improving the prefilling time by 2.16$\times$ and the decoding time by 1.26$\times$. Our code is available at https://github.com/ModelTC/MoDES. --- ### Walrus: A Cross-Domain Foundation Model for Continuum Dynamics Authors: Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Regaldo-Saint Blancard, Francois Rozet, Cristiana Diaconu, Lucas Meyer, Kaze W. K. Wong, Hadi Sotoudeh, Alberto Bietti, Irina Espejo, Rio Fear et al. Published: 2025-11-19 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2511.15684v2 Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-term dynamics inhibit learning from sufficiently diverse dynamics, while varying resolutions and dimensionalities challenge efficient training on modern hardware. Through empirical and theoretical analysis, we incorporate new approaches to mitigate these obstacles, including a harmonic-analysis-based stabilization method, load-balanced distributed 2D and 3D training strategies, and compute-adaptive tokenization. Using these tools, we develop Walrus, a transformer-based foundation model developed primarily for fluid-like continuum dynamics. Walrus is pretrained on nineteen diverse scenarios spanning astrophysics, geoscience, rheology, plasma physics, acoustics, and classical fluids. Experiments show that Walrus outperforms prior foundation models on both short and long term prediction horizons on downstream tasks and across the breadth of pretraining data, while ablation studies confirm the value of our contributions to forecast stability, training throughput, and transfer performance over conventional approaches. Code and weights are released for community use. --- ### Front-door Reducibility: Reducing ADMGs to the Standard Front-door Setting via a Graphical Criterion Authors: Jianqiao Mao, Max A. Little Published: 2025-11-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.15679v2 Front-door adjustment gives a simple closed-form identification formula under the classical front-door criterion, but its applicability is often viewed as narrow. By contrast, the general ID algorithm can identify many more causal effects in arbitrary graphs, yet typically outputs algebraically complex expressions that are hard to estimate and interpret. We show that many such graphs can in fact be reduced to a standard front-door setting via front-door reducibility (FDR), a graphical condition on acyclic directed mixed graphs that aggregates variables into super-nodes $(\boldsymbol{X}^{*},\boldsymbol{Y}^{*},\boldsymbol{M}^{*})$. We characterize the FDR criterion, prove it is equivalent (at the graph level) to the existence of an FDR adjustment, and present FDR-TID, an exact algorithm that finds an admissible FDR triple with correctness, completeness, and finite-termination guarantees. Empirical examples show that many graphs far outside the textbook front-door setting are FDR, yielding simple, estimable adjustments where general ID expressions would be cumbersome. FDR therefore complements existing identification methods by prioritizing interpretability and computational simplicity without sacrificing generality across mixed graphs. --- ### MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features Authors: Sejuti Rahman, Swakshar Deb, MD. Sameer Iqbal Chowdhury, MD. Jubair Ahmed Sourov, Mohammad Shamsuddin Published: 2025-11-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.15675v2 Depression is a prevalent global mental health disorder, characterised by persistent low mood and anhedonia. However, it remains underdiagnosed because current diagnostic methods depend heavily on subjective clinical assessments. To enable objective detection, we introduce a gold standard dataset of 103 clinically assessed participants collected through a tripartite data approach which uniquely integrated eye tracking data with audio and video to give a comprehensive representation of depressive symptoms. Eye tracking data quantifies the attentional bias towards negative stimuli that is frequently observed in depressed groups. Audio and video data capture the affective flattening and psychomotor retardation characteristic of depression. Statistical validation confirmed their significant discriminative power in distinguishing depressed from non depressed groups. We address a critical limitation of existing graph-based models that focus on low-frequency information and propose a Multi-Frequency Graph Convolutional Network (MF-GCN). This framework consists of a novel Multi-Frequency Filter Bank Module (MFFBM), which can leverage both low and high frequency signals. Extensive evaluation against traditional machine learning algorithms and deep learning frameworks demonstrates that MF-GCN consistently outperforms baselines. In binary classification, the model achieved a sensitivity of 0.96 and F2 score of 0.94. For the 3 class classification task, the proposed method achieved a sensitivity of 0.79 and specificity of 0.87 and siginificantly suprassed other models. To validate generalizability, the model was also evaluated on the Chinese Multimodal Depression Corpus (CMDC) dataset and achieved a sensitivity of 0.95 and F2 score of 0.96. These results confirm that our trimodal, multi frequency framework effectively captures cross modal interaction for accurate depression detection. --- ### VisPlay: Self-Evolving Vision-Language Models from Images Authors: Yicheng He, Chengsong Huang, Zongxia Li, Jiaxin Huang, Yonghui Yang Published: 2025-11-19 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.15661v2 Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define verifiable rewards, both of which are costly and difficult to scale. We introduce VisPlay, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning abilities using large amounts of unlabeled image data. Starting from a single base VLM, VisPlay assigns the model into two interacting roles: an Image-Conditioned Questioner that formulates challenging yet answerable visual questions, and a Multimodal Reasoner that generates silver responses. These roles are jointly trained with Group Relative Policy Optimization (GRPO), which incorporates diversity and difficulty rewards to balance the complexity of generated questions with the quality of the silver answers. VisPlay scales efficiently across two model families. When trained on Qwen2.5-VL and MiMo-VL, VisPlay achieves consistent improvements in visual reasoning, compositional generalization, and hallucination reduction across eight benchmarks, including MM-Vet and MMMU, demonstrating a scalable path toward self-evolving multimodal intelligence. The project page is available at https://bruno686.github.io/VisPlay/ --- ### GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI Authors: Naomi Simumba, Nils Lehmann, Paolo Fraccaro, Hamed Alemohammad, Geeth De Mel, Salman Khan, Manil Maskey, Nicolas Longepe, Xiao Xiang Zhu, Hannah Kerner, Juan Bernabe-Moreno, Alexandre Lacoste Published: 2025-11-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.15658v2 Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation across 19 permissively-licensed datasets. We introduce ''capability'' groups to rank models on datasets that share common characteristics (e.g., resolution, bands, temporality). This enables users to identify which models excel in each capability and determine which areas need improvement in future work. To support both fair comparison and methodological innovation, we define a prescriptive yet flexible evaluation protocol. This not only ensures consistency in benchmarking but also facilitates research into model adaptation strategies, a key and open challenge in advancing GeoFMs for downstream tasks. Our experiments show that no single model dominates across all tasks, confirming the specificity of the choices made during architecture design and pretraining. While models pretrained on natural images (ConvNext ImageNet, DINO V3) excel on high-resolution tasks, EO-specific models (TerraMind, Prithvi, and Clay) outperform them on multispectral applications such as agriculture and disaster response. These findings demonstrate that optimal model choice depends on task requirements, data modalities, and constraints. This shows that the goal of a single GeoFM model that performs well across all tasks remains open for future research. GEO-Bench-2 enables informed, reproducible GeoFM evaluation tailored to specific use cases. Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license. --- ### INQUIRE-Search: Interactive Discovery in Large-Scale Biodiversity Databases Authors: Edward Vendrow, Julia Chae, Rupa Kurinchi-Vendhan, Isaac Eckert, Jazlynn Hall, Marta Jarzyna, Reymond Miyajima, Ruth Oliver, Laura Pollock, Lauren Shrack, Scott Yanco, Oisin Mac Aodha et al. Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15656v7 Many ecological questions center on complex phenomena, such as species interactions, behaviors, phenology, and responses to disturbance, that are inherently difficult to observe and sparsely documented. Community science platforms such as iNaturalist contain hundreds of millions of biodiversity images, which often contain evidence of these complex phenomena. However, current workflows that seek to discover and analyze this evidence often rely on manual inspection, leaving this information largely inaccessible at scale. We introduce INQUIRE-Search, an open-source system that uses natural language to enable scientists to rapidly search within an ecological image database like iNaturalist for specific phenomena, verify and export relevant observations, and use these outputs for downstream scientific analysis. Across five illustrative case studies, INQUIRE-Search concentrates relevant observations 3-25x more efficiently than comparable manual inspection budgets. These examples demonstrate how the system can be used for ecological inference, from analyzing seasonal variation in behavior across species to forest regrowth after wildfires. These examples illustrate a new paradigm for interactive, efficient, and scalable scientific discovery that can begin to unlock previously inaccessible scientific value in large-scale biodiversity datasets. Finally, we highlight how AI-enabled discovery tools for science require reframing aspects of the scientific process, including experiment design, data collection, survey effort, and uncertainty analysis. --- ### Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open Challenges Authors: Kim N. Nolle, Ivana Dusparic, Rhodri Cusack, Vinny Cahill Published: 2025-11-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.15652v1 Continual learning (CL) is a branch of machine learning that aims to enable agents to adapt and generalise previously learned abilities so that these can be reapplied to new tasks or environments. This is particularly useful in multi-task settings or in non-stationary environments, where the dynamics can change over time. This is particularly relevant in cyber-physical systems such as autonomous driving. However, despite recent advances in CL, successfully applying it to reinforcement learning (RL) is still an open problem. This paper highlights open challenges in continual RL (CRL) based on experiments in an autonomous driving environment. In this environment, the agent must learn to successfully park in four different scenarios corresponding to parking spaces oriented at varying angles. The agent is successively trained in these four scenarios one after another, representing a CL environment, using Proximal Policy Optimisation (PPO). These experiments exposed a number of open challenges in CRL: finding suitable abstractions of the environment, oversensitivity to hyperparameters, catastrophic forgetting, and efficient use of neural network capacity. Based on these identified challenges, we present open research questions that are important to be addressed for creating robust CRL systems. In addition, the identified challenges call into question the suitability of neural networks for CL. We also identify the need for interdisciplinary research, in particular between computer science and neuroscience. --- ### FDIO: Frequency Decomposed Inertial Odometry Authors: Shanshan Zhang, Liqin Wu, Wenying Cao, Lingxiang Zheng, Yu Yang Published: 2025-11-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.15645v4 Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU), making it highly valuable for consumer level localization applications. However, under a dual device acquisition setting, IMU signals collected by a freely carried mobile device are inherently composite signals in which the global motion of the human torso is coupled with perturbations induced by local limb motion. This coupling makes accurate human motion modeling more challenging. To address this issue, this paper proposes frequency decomposed inertial odometry (FDIO). The proposed method first decomposes input IMU signals into low frequency and high frequency components using a Laplacian pyramid. It then adopts a Mamba module to model long range motion information from the low frequency component and uses a multi scale convolution module to extract fine grained local dynamic features from the high frequency component. Experiments on five public PIO datasets show that FDIO achieves an average absolute trajectory error of 3.221~m and an average relative trajectory error of 2.550~m, reducing the errors by 33.3\% and 16.7\% compared with the RoNIN ResNet baseline, respectively. These results validate the effectiveness of the proposed frequency decomposition strategy. To the best of our knowledge, this work is among the first efforts to introduce Mamba and a frequency decomposition architecture into inertial odometry. --- ### Multi-Stage Residual-Aware Unsupervised Deep Learning Framework for Consistent Ultrasound Strain Elastography Authors: Shourov Joarder, Tushar Talukder Showrav, Md. Kamrul Hasan Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15640v1 Ultrasound Strain Elastography (USE) is a powerful non-invasive imaging technique for assessing tissue mechanical properties, offering crucial diagnostic value across diverse clinical applications. However, its clinical application remains limited by tissue decorrelation noise, scarcity of ground truth, and inconsistent strain estimation under different deformation conditions. Overcoming these barriers, we propose MUSSE-Net, a residual-aware, multi-stage unsupervised sequential deep learning framework designed for robust and consistent strain estimation. At its backbone lies our proposed USSE-Net, an end-to-end multi-stream encoder-decoder architecture that parallelly processes pre- and post-deformation RF sequences to estimate displacement fields and axial strains. The novel architecture incorporates Context-Aware Complementary Feature Fusion (CACFF)-based encoder with Tri-Cross Attention (TCA) bottleneck with a Cross-Attentive Fusion (CAF)-based sequential decoder. To ensure temporal coherence and strain stability across varying deformation levels, this architecture leverages a tailored consistency loss. Finally, with the MUSSE-Net framework, a secondary residual refinement stage further enhances accuracy and suppresses noise. Extensive validation on simulation, in vivo, and private clinical datasets from Bangladesh University of Engineering and Technology (BUET) medical center, demonstrates MUSSE-Net's outperformed existing unsupervised approaches. On MUSSE-Net achieves state-of-the-art performance with a target SNR of 24.54, background SNR of 132.76, CNR of 59.81, and elastographic SNR of 9.73 on simulation data. In particular, on the BUET dataset, MUSSE-Net produces strain maps with enhanced lesion-to-background contrast and significant noise suppression yielding clinically interpretable strain patterns. --- ### Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities Authors: Benjamin Dupuis, Mert Gürbüzbalaban, Umut Şimşekli, Jian Wang, Sinan Yildirim, Lingjiong Zhu Published: 2025-11-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.15634v1 Characterizing the differential privacy (DP) of learning algorithms has become a major challenge in recent years. In parallel, many studies suggested investigating the behavior of stochastic gradient descent (SGD) with heavy-tailed noise, both as a model for modern deep learning models and to improve their performance. However, most DP bounds focus on light-tailed noise, where satisfactory guarantees have been obtained but the proposed techniques do not directly extend to the heavy-tailed setting. Recently, the first DP guarantees for heavy-tailed SGD were obtained. These results provide $(0,δ)$-DP guarantees without requiring gradient clipping. Despite casting new light on the link between DP and heavy-tailed algorithms, these results have a strong dependence on the number of parameters and cannot be extended to other DP notions like the well-established Rényi differential privacy (RDP). In this work, we propose to address these limitations by deriving the first RDP guarantees for heavy-tailed SDEs, as well as their discretized counterparts. Our framework is based on new Rényi flow computations and the use of well-established fractional Poincaré inequalities. Under the assumption that such inequalities are satisfied, we obtain DP guarantees that have a much weaker dependence on the dimension compared to prior art. --- ### Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning Authors: Tao Hu, Lan Li, Zhen-Hao Xie, Da-Wei Zhou Published: 2025-11-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.15633v1 Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable features via multi-modal pre-training, making them well-suited for CIL. However, real-world visual and linguistic concepts are inherently hierarchical: a textual concept like "dog" subsumes fine-grained categories such as "Labrador" and "Golden Retriever," and each category entails its images. But existing CLIP-based CIL methods fail to explicitly capture this inherent hierarchy, leading to fine-grained class features drift during incremental updates and ultimately to catastrophic forgetting. To address this challenge, we propose HASTEN (Hierarchical Semantic Tree Anchoring) that anchors hierarchical information into CIL to reduce catastrophic forgetting. First, we employ an external knowledge graph as supervision to embed visual and textual features in hyperbolic space, effectively preserving hierarchical structure as data evolves. Second, to mitigate catastrophic forgetting, we project gradients onto the null space of the shared hyperbolic mapper, preventing interference with prior tasks. These two steps work synergistically to enable the model to resist forgetting by maintaining hierarchical relationships. Extensive experiments show that HASTEN consistently outperforms existing methods while providing a unified structured representation. --- ### CODE-II: A large-scale dataset for artificial intelligence in ECG analysis Authors: Petrus E. O. G. B. Abreu, Gabriela M. M. Paixão, Jiawei Li, Paulo R. Gomes, Peter W. Macfarlane, Ana C. S. Oliveira, Vinicius T. Carvalho, Thomas B. Schön, Antonio Luiz P. Ribeiro, Antônio H. Ribeiro Published: 2025-11-19 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2511.15632v1 Data-driven methods for electrocardiogram (ECG) interpretation are rapidly progressing. Large datasets have enabled advances in artificial intelligence (AI) based ECG analysis, yet limitations in annotation quality, size, and scope remain major challenges. Here we present CODE-II, a large-scale real-world dataset of 2,735,269 12-lead ECGs from 2,093,807 adult patients collected by the Telehealth Network of Minas Gerais (TNMG), Brazil. Each exam was annotated using standardized diagnostic criteria and reviewed by cardiologists. A defining feature of CODE-II is a set of 66 clinically meaningful diagnostic classes, developed with cardiologist input and routinely used in telehealth practice. We additionally provide an open available subset: CODE-II-open, a public subset of 15,000 patients, and the CODE-II-test, a non-overlapping set of 8,475 exams reviewed by multiple cardiologists for blinded evaluation. A neural network pre-trained on CODE-II achieved superior transfer performance on external benchmarks (PTB-XL and CPSC 2018) and outperformed alternatives trained on larger datasets. --- ### Sufficient Explanations in Databases and their Connections to Database Repairs Authors: Leopoldo Bertossi, Nina Pardal Published: 2025-11-19 Categories: cs.DB, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2511.15623v2 We investigate the notion of sufficient explanation, and a sufficiency-degree as attribution score for database tuples in relation to query answering. We also investigate and exploit connections with database repairs as used for dealing with inconsistent databases; and with causality-based necessary explanations, obtaining new computational results. We show how to use answer-set programs to specify sufficient explanations and compute sufficiency-degrees. --- ### The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification Authors: Dante Francisco Wasmuht, Otto Brookes, Maximillian Schall, Pablo Palencia, Chris Beirne, Tilo Burghardt, Majid Mirmehdi, Hjalmar Kühl, Mimi Arandjelovic, Sam Pottie, Peter Bermant, Brandon Asheim et al. Published: 2025-11-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.15622v2 Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identification and behavior recognition. However, existing datasets are limited in scale, constrained to a few species, or lack sufficient temporal and geographical diversity - leaving no suitable benchmark for training general-purpose MAT models applicable across wild animal populations. To address this, we introduce SA-FARI, the largest open-source MAT dataset for wild animals. It comprises 11,609 camera trap videos collected over approximately 10 years (2014-2024) from 741 locations across 4 continents, spanning 99 species categories. Each video is exhaustively annotated culminating in ~46 hours of densely annotated footage containing 16,224 masklet identities and 942,702 individual bounding boxes, segmentation masks, and species labels. Alongside the task-specific annotations, we publish anonymized camera trap locations for each video. Finally, we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3, evaluated with both species-specific and generic animal prompts. We also compare against vision-only methods developed specifically for wildlife analysis. SA-FARI is the first large-scale dataset to combine high species diversity, multi-region coverage, and high-quality spatio-temporal annotations, offering a new foundation for advancing generalizable multianimal tracking in the wild. The dataset is available at https://www.conservationxlabs.com/sa-fari. --- ### CODE: A global approach to ODE dynamics learning Authors: Nils Wildt, Daniel M. Tartakovsky, Sergey Oladyshkin, Wolfgang Nowak Published: 2025-11-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.15619v1 Ordinary differential equations (ODEs) are a conventional way to describe the observed dynamics of physical systems. Scientists typically hypothesize about dynamical behavior, propose a mathematical model, and compare its predictions to data. However, modern computing and algorithmic advances now enable purely data-driven learning of governing dynamics directly from observations. In data-driven settings, one learns the ODE's right-hand side (RHS). Dense measurements are often assumed, yet high temporal resolution is typically both cumbersome and expensive. Consequently, one usually has only sparsely sampled data. In this work we introduce ChaosODE (CODE), a Polynomial Chaos ODE Expansion in which we use an arbitrary Polynomial Chaos Expansion (aPCE) for the ODE's right-hand side, resulting in a global orthonormal polynomial representation of dynamics. We evaluate the performance of CODE in several experiments on the Lotka-Volterra system, across varying noise levels, initial conditions, and predictions far into the future, even on previously unseen initial conditions. CODE exhibits remarkable extrapolation capabilities even when evaluated under novel initial conditions and shows advantages compared to well-examined methods using neural networks (NeuralODE) or kernel approximators (KernelODE) as the RHS representer. We observe that the high flexibility of NeuralODE and KernelODE degrades extrapolation capabilities under scarce data and measurement noise. Finally, we provide practical guidelines for robust optimization of dynamics-learning problems and illustrate them in the accompanying code. --- ### FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation Authors: Tingrui Shen, Yiheng Zhang, Chen Tang, Chuan Ping, Zixing Zhao, Le Wan, Yuwang Wang, Ronggang Wang, Shengfeng He Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15618v1 Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale applications. We present FlashMesh, a fast and high-fidelity mesh generation framework that rethinks autoregressive decoding through a predict-correct-verify paradigm. The key insight is that mesh tokens exhibit strong structural and geometric correlations that enable confident multi-token speculation. FlashMesh leverages this by introducing a speculative decoding scheme tailored to the commonly used hourglass transformer architecture, enabling parallel prediction across face, point, and coordinate levels. Extensive experiments show that FlashMesh achieves up to a 2 x speedup over standard autoregressive models while also improving generation fidelity. Our results demonstrate that structural priors in mesh data can be systematically harnessed to accelerate and enhance autoregressive generation. --- ### Near-optimal Delta-convex Estimation of Lipschitz Functions Authors: Gábor Balázs Published: 2025-11-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.15615v2 This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on its convergence rate. The approach extends max-affine methods from convex shape-restricted regression to the more general Lipschitz setting. A key component is a nonlinear feature expansion that maps max-affine functions into a subclass of delta-convex functions, which act as universal approximators of Lipschitz functions while preserving their Lipschitz constants. Leveraging this property, the estimator attains the minimax convergence rate (up to logarithmic factors) with respect to the intrinsic dimension of the data under squared loss and subgaussian distributions in the random design setting. The algorithm integrates adaptive partitioning to capture intrinsic dimension, a penalty-based regularization mechanism that removes the need to know the true Lipschitz constant, and a two-stage optimization procedure combining a convex initialization with local refinement. The framework is also straightforward to adapt to convex shape-restricted regression. Experiments demonstrate competitive performance relative to other theoretically justified methods, including nearest-neighbor and kernel-based regressors. --- ### Optimus-Q: Utilizing Federated Learning in Adaptive Robots for Intelligent Nuclear Power Plant Operations through Quantum Cryptography Authors: Sai Puppala, Ismail Hossain, Jahangir Alam, Sajedul Talukder Published: 2025-11-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.15614v1 The integration of advanced robotics in nuclear power plants (NPPs) presents a transformative opportunity to enhance safety, efficiency, and environmental monitoring in high-stakes environments. Our paper introduces the Optimus-Q robot, a sophisticated system designed to autonomously monitor air quality and detect contamination while leveraging adaptive learning techniques and secure quantum communication. Equipped with advanced infrared sensors, the Optimus-Q robot continuously streams real-time environmental data to predict hazardous gas emissions, including carbon dioxide (CO$_2$), carbon monoxide (CO), and methane (CH$_4$). Utilizing a federated learning approach, the robot collaborates with other systems across various NPPs to improve its predictive capabilities without compromising data privacy. Additionally, the implementation of Quantum Key Distribution (QKD) ensures secure data transmission, safeguarding sensitive operational information. Our methodology combines systematic navigation patterns with machine learning algorithms to facilitate efficient coverage of designated areas, thereby optimizing contamination monitoring processes. Through simulations and real-world experiments, we demonstrate the effectiveness of the Optimus-Q robot in enhancing operational safety and responsiveness in nuclear facilities. This research underscores the potential of integrating robotics, machine learning, and quantum technologies to revolutionize monitoring systems in hazardous environments. --- ### When to Think and When to Look: Uncertainty-Guided Lookback Authors: Jing Bi, Filippos Bellos, Junjia Guo, Yayuan Li, Chao Huang, Yolo Y. Tang, Luchuan Song, Susan Liang, Zhongfei Mark Zhang, Jason J. Corso, Chenliang Xu Published: 2025-11-19 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.15613v3 Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision language models (LVLMs). However, despite these promising results, there is still no systematic analysis of how thinking actually affects visual reasoning. We provide the first such analysis with a large scale, controlled comparison of thinking for LVLMs, evaluating ten variants from the InternVL3.5 and Qwen3-VL families on MMMU-val under generous token budgets and multi pass decoding. We show that more thinking is not always better; long chains often yield long wrong trajectories that ignore the image and underperform the same models run in standard instruct mode. A deeper analysis reveals that certain short lookback phrases, which explicitly refer back to the image, are strongly enriched in successful trajectories and correlate with better visual grounding. Building on this insight, we propose uncertainty guided lookback, a training free decoding strategy that combines an uncertainty signal with adaptive lookback prompts and breadth search. Our method improves overall MMMU performance, delivers the largest gains in categories where standard thinking is weak, and outperforms several strong decoding baselines, setting a new state of the art under fixed model families and token budgets. We further show that this decoding strategy generalizes, yielding consistent improvements on five additional benchmarks, including two broad multimodal suites and math focused visual reasoning datasets. --- ### SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models Authors: Senyu Fei, Siyin Wang, Li Ji, Ao Li, Shiduo Zhang, Liming Liu, Jinlong Hou, Jingjing Gong, Xianzhong Zhao, Xipeng Qiu Published: 2025-11-19 Categories: cs.RO, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.15605v2 Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark. --- ### MaskMed: Decoupled Mask and Class Prediction for Medical Image Segmentation Authors: Bin Xie, Gady Agam Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15603v1 Medical image segmentation typically adopts a point-wise convolutional segmentation head to predict dense labels, where each output channel is heuristically tied to a specific class. This rigid design limits both feature sharing and semantic generalization. In this work, we propose a unified decoupled segmentation head that separates multi-class prediction into class-agnostic mask prediction and class label prediction using shared object queries. Furthermore, we introduce a Full-Scale Aware Deformable Transformer module that enables low-resolution encoder features to attend across full-resolution encoder features via deformable attention, achieving memory-efficient and spatially aligned full-scale fusion. Our proposed method, named MaskMed, achieves state-of-the-art performance, surpassing nnUNet by +2.0% Dice on AMOS 2022 and +6.9% Dice on BTCV. --- ### US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery Authors: Miruna-Alexandra Gafencu, Yordanka Velikova, Nassir Navab, Mohammad Farid Azampour Published: 2025-11-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.15600v1 Ultrasound offers a radiation-free, cost-effective solution for real-time visualization of spinal landmarks, paraspinal soft tissues and neurovascular structures, making it valuable for intraoperative guidance during spinal procedures. However, ultrasound suffers from inherent limitations in visualizing complete vertebral anatomy, in particular vertebral bodies, due to acoustic shadowing effects caused by bone. In this work, we present a novel multi-modal deep learning method for completing occluded anatomical structures in 3D ultrasound by leveraging complementary information from a single X-ray image. To enable training, we generate paired training data consisting of: (1) 2D lateral vertebral views that simulate X-ray scans, and (2) 3D partial vertebrae representations that mimic the limited visibility and occlusions encountered during ultrasound spine imaging. Our method integrates morphological information from both imaging modalities and demonstrates significant improvements in vertebral reconstruction (p < 0.001) compared to state of art in 3D ultrasound vertebral completion. We perform phantom studies as an initial step to future clinical translation, and achieve a more accurate, complete volumetric lumbar spine visualization overlayed on the ultrasound scan without the need for registration with preoperative modalities such as computed tomography. This demonstrates that integrating a single X-ray projection mitigates ultrasound's key limitation while preserving its strengths as the primary imaging modality. Code and data can be found at https://github.com/miruna20/US-X-Complete --- ### Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition Authors: Xufei Wang, Junqiao Zhao, Siyue Tao, Qiwen Gu, Wonbong Kim, Tiantian Feng Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15597v1 LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments without forgetting previously learned knowledge, a challenge widely known as catastrophic forgetting. To address this issue, we propose KDF+, a novel continual learning framework for LiDAR place recognition that extends the KDF paradigm with a loss-aware sampling strategy and a rehearsal enhancement mechanism. The proposed sampling strategy estimates the learning difficulty of each sample via its loss value and selects samples for replay according to their estimated difficulty. Harder samples, which tend to encode more discriminative information, are sampled with higher probability while maintaining distributional coverage across the dataset. In addition, the rehearsal enhancement mechanism encourages memory samples to be further refined during new-task training by slightly reducing their loss relative to previous tasks, thereby reinforcing long-term knowledge retention. Extensive experiments across multiple benchmarks demonstrate that KDF+ consistently outperforms existing continual learning methods and can be seamlessly integrated into state-of-the-art continual learning for LiDAR place recognition frameworks to yield significant and stable performance gains. The code will be available at https://github.com/repo/KDF-plus. --- ### What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity Authors: Alexis Audran-Reiss, Jordi Armengol-Estapé, Karen Hambardzumyan, Amar Budhiraja, Martin Josifoski, Edan Toledo, Rishi Hazra, Despoina Magka, Michael Shvartsman, Parth Pathak, Justine T Kao, Lucia Cipolina-Kun et al. Published: 2025-11-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.15593v2 AI research agents offer the promise to accelerate scientific progress by automating the design, implementation, and training of machine learning models. However, the field is still in its infancy, and the key factors driving the success or failure of agent trajectories are not fully understood. We examine the role that ideation diversity plays in agent performance. First, we analyse agent trajectories on MLE-bench, a well-known benchmark to evaluate AI research agents, across different models and agent scaffolds. Our analysis reveals that different models and agent scaffolds yield varying degrees of ideation diversity, and that higher-performing agents tend to have increased ideation diversity. Further, we run a controlled experiment where we modify the degree of ideation diversity, demonstrating that higher ideation diversity results in stronger performance. Finally, we strengthen our results by examining additional evaluation metrics beyond the standard medal-based scoring of MLE-bench, showing that our findings still hold across other agent performance metrics. --- ### MHR: Momentum Human Rig Authors: Aaron Ferguson, Ahmed A. A. Osman, Berta Bescos, Carsten Stoll, Chris Twigg, Christoph Lassner, David Otte, Eric Vignola, Fabian Prada, Federica Bogo, Igor Santesteban, Javier Romero et al. Published: 2025-11-19 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.15586v3 We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines. --- ### CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking Authors: Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang Published: 2025-11-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.15580v3 3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU. --- ### AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning Authors: Urjitkumar Patel, Fang-Chun Yeh, Chinmay Gondhalekar Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15578v1 With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced performance, they often face challenges with nuanced queries that demand both a comprehensive understanding and detailed analysis. To overcome these obstacles, we introduce AVATAAR, a modular and interpretable framework that combines global and local video context, along with a Pre Retrieval Thinking Agent and a Rethink Module. AVATAAR creates a persistent global summary and establishes a feedback loop between the Rethink Module and the Pre Retrieval Thinking Agent, allowing the system to refine its retrieval strategies based on partial answers and replicate human-like iterative reasoning. On the CinePile benchmark, AVATAAR demonstrates significant improvements over a baseline, achieving relative gains of +5.6% in temporal reasoning, +5% in technical queries, +8% in theme-based questions, and +8.2% in narrative comprehension. Our experiments confirm that each module contributes positively to the overall performance, with the feedback loop being crucial for adaptability. These findings highlight AVATAAR's effectiveness in enhancing video understanding capabilities. Ultimately, AVATAAR presents a scalable solution for long-form Video Question Answering (QA), merging accuracy, interpretability, and extensibility. --- ### HSKBenchmark: Modeling and Benchmarking Chinese Second Language Acquisition in Large Language Models through Curriculum Tuning Authors: Qihao Yang, Xuelin Wang, Jiale Chen, Xuelian Dong, Yuxin Hao, Tianyong Hao Published: 2025-11-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.15574v1 Language acquisition is vital to revealing the nature of human language intelligence and has recently emerged as a promising perspective for improving the interpretability of large language models (LLMs). However, it is ethically and practically infeasible to conduct experiments that require controlling human learners' language inputs. This poses challenges for the verifiability and scalability of language acquisition modeling, particularly in Chinese second language acquisition (SLA). While LLMs provide a controllable and reproducible alternative, a systematic benchmark to support phase-wise modeling and assessment is still lacking. In this paper, we present HSKBenchmark, the first benchmark for staged modeling and writing assessment of LLMs in Chinese SLA. It covers HSK levels 3 to 6 and includes authentic textbooks with 6.76 million tokens, 16K synthetic instruction samples, 30 test topics, and a linguistically grounded evaluation system. To simulate human learning trajectories, we introduce a curriculum-tuning framework that trains models from beginner to advanced levels. An evaluation system is created to examine level-based grammar coverage, writing errors, lexical and syntactic complexity, and holistic scoring. We also build HSKAgent, fine-tuned on 10K learner compositions. Extensive experimental results demonstrate that HSKBenchmark not only models Chinese SLA effectively, but also serves as a reliable benchmark for dynamic writing assessment in LLMs. Our fine-tuned LLMs have writing performance on par with advanced human learners and exhibit human-like acquisition characteristics. The HSKBenchmark, HSKAgent, and checkpoints serve as foundational tools and resources, with the potential to pave the way for future research on language acquisition modeling and LLMs interpretability. Code and data are publicly available at: https://github.com/CharlesYang030/HSKB. --- ### From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers Authors: Huiyuan Tian, Bonan Xu, Shijian Li Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15572v3 Feature-map knowledge distillation (KD) transfers internal representations well between comparably sized Vision Transformers (ViTs), but it often fails in compression. We revisit this failure and uncover a paradox. Sample-wise SVD shows that each image is highly compressible, which seems to suggest that a narrow student with a linear projector should match the teacher "in principle". However, a dataset-level view contradicts this intuition: PCA shows that the teacher is a union of low-rank subspaces with significant subspace rotation across inputs. We further introduce token-level Spectral Energy Patterns (SEP) and find an architecture-invariant encoding law: tokens spread energy broadly across channel modes even when they live in low-rank subspace, creating a bandwidth mismatch. We refer to this combined phenomenon as an encoding mismatch. We propose two minimal remedies, Lift or WideLast: (i) Lift retains a lightweight lifting projector at inference to provide wider channel, or (ii) WideLast widens only the student's last block, enabling an input-dependent expansion. On ImageNet-1K, these fixes revive feature KD for ViT compression, improving DeiT-Tiny distilled from CaiT-S24 from 74.86% to 77.53%/78.23% top-1 accuracy, and they also strengthen students trained without distillation. Our analyses clarify when and why feature-map KD fails and then how to fix it. Code and raw data are provided in https://github.com/thy960112/From-Per-Image-Low-Rank-to-Encoding-Mismatch. --- ### Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector Authors: Weiheng Zhu, Gang Cao, Jing Liu, Lifang Yu, Shaowei Weng Published: 2025-11-19 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2511.15571v1 Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition. In view of antiforensics, it is significant to develop advanced adversarial attacks for evaluating the security of such detectors, which remains unexplored sufficiently. This letter proposes a Dual-domain Feature Importance Attack (DuFIA) scheme to invalidate AIGI detectors to some extent. Forensically important features are captured by the spatially interpolated gradient and frequency-aware perturbation. The adversarial transferability is enhanced by jointly modeling spatial and frequency-domain feature importances, which are fused to guide the optimization-based adversarial example generation. Extensive experiments across various AIGI detectors verify the cross-model transferability, transparency and robustness of DuFIA. --- ### Computer-Use Agents as Judges for Generative User Interface Authors: Kevin Qinghong Lin, Siyuan Hu, Linjie Li, Zhengyuan Yang, Lijuan Wang, Philip Torr, Mike Zheng Shou Published: 2025-11-19 Categories: cs.CV, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2511.15567v1 Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed primarily for humans--prioritizing aesthetics and usability--forcing agents to adopt human-oriented behaviors that are unnecessary for efficient task execution. At the same time, rapid advances in coding-oriented language models (Coder) have transformed automatic GUI design. This raises a fundamental question: Can CUA as judges to assist Coder for automatic GUI design? To investigate, we introduce AUI-Gym, a benchmark for Automatic GUI development spanning 52 applications across diverse domains. Using language models, we synthesize 1560 tasks that simulate real-world scenarios. To ensure task reliability, we further develop a verifier that programmatically checks whether each task is executable within its environment. Building on this, we propose a Coder-CUA in Collaboration framework: the Coder acts as Designer, generating and revising websites, while the CUA serves as Judge, evaluating functionality and refining designs. Success is measured not by visual appearance, but by task solvability and CUA navigation success rate. To turn CUA feedback into usable guidance, we design a CUA Dashboard that compresses multi-step navigation histories into concise visual summaries, offering interpretable guidance for iterative redesign. By positioning agents as both designers and judges, our framework shifts interface design toward agent-native efficiency and reliability. Our work takes a step toward shifting agents from passive use toward active participation in digital environments. Our code and dataset are available at https://github.com/showlab/AUI. --- ### Scriboora: Rethinking Human Pose Forecasting Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif Published: 2025-11-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.15565v3 Human pose forecasting predicts future human poses from past observations for applications including action recognition, sports analysis, and human-robot interaction. However, progress in the field is difficult to assess because reported results often rely on heterogeneous preprocessing, inconsistent metric implementations, and partially released artifacts. This paper re-examines human pose forecasting as an evaluation problem by auditing a wide range of recent forecasting methods, identifying several reproducibility issues, and introducing a unified training and evaluation pipeline for absolute pose forecasting. Under this unified protocol, mature cross-domain sequence models adapted from speech recognition provide strong baselines and obtain the lowest errors among the evaluated models. To study deployment-relevant noise, a paired clean/detector-noisy dataset variant is introduced using poses generated by a pose-estimation model. The experiments show that detector-generated poses cause substantial performance degradation compared with clean motion-capture inputs, but that part of this degradation can be recovered by adapting the forecaster on detector-generated pose sequences. --- ### B+ANN: A Fast Billion-Scale Disk-based Nearest-Neighbor Index Authors: Selim Furkan Tekin, Rajesh Bordawekar Published: 2025-11-19 Categories: cs.DB, cs.AI, cs.DS arXiv: https://arxiv.org/abs/2511.15557v1 Storing and processing of embedding vectors by specialized Vector databases (VDBs) has become the linchpin in building modern AI pipelines. Most current VDBs employ variants of a graph-based ap- proximate nearest-neighbor (ANN) index algorithm, HNSW, to an- swer semantic queries over stored vectors. Inspite of its wide-spread use, the HNSW algorithm suffers from several issues: in-memory design and implementation, random memory accesses leading to degradation in cache behavior, limited acceleration scope due to fine-grained pairwise computations, and support of only semantic similarity queries. In this paper, we present a novel disk-based ANN index, B+ANN, to address these issues: it first partitions input data into blocks containing semantically similar items, then builds an B+ tree variant to store blocks both in-memory and on disks, and finally, enables hybrid edge- and block-based in-memory traversals. As demonstrated by our experimantal evaluation, the proposed B+ANN disk-based index improves both quality (Recall value), and execution performance (Queries per second/QPS) over HNSW, by improving spatial and temporal locality for semantic operations, reducing cache misses (19.23% relative gain), and decreasing the memory consumption and disk-based build time by 24x over the DiskANN algorithm. Finally, it enables dissimilarity queries, which are not supported by similarity-oriented ANN indices. --- ### Multimodal Evaluation of Russian-language Architectures Authors: Artem Chervyakov, Ulyana Isaeva, Anton Emelyanov, Artem Safin, Maria Tikhonova, Alexander Kharitonov, Yulia Lyakh, Petr Surovtsev, Denis Shevelev, Vildan Saburov, Vasily Konovalov, Elisei Rykov et al. Published: 2025-11-19 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.15552v3 Multimodal large language models (MLLMs) are currently at the center of research attention, showing rapid progress in scale and capabilities, yet their intelligence, limitations, and risks remain insufficiently understood. To address these issues, particularly in the context of the Russian language, where no multimodal benchmarks currently exist, we introduce MERA Multi, an open multimodal evaluation framework for Russian-spoken architectures. The benchmark is instruction-based and encompasses default text, image, audio, and video modalities, comprising 18 newly constructed evaluation tasks for both general-purpose models and modality-specific architectures (imageto-text, video-to-text, and audio-to-text). Our contributions include: (i) a universal taxonomy of multimodal abilities; (ii) 18 datasets created entirely from scratch with attention to Russian cultural and linguistic specificity, unified prompts, and metrics; (iii) baseline results for both closed-source and open-source models; (iv) a methodology for preventing benchmark leakage, including watermarking for private sets. While our current focus is on Russian, the proposed benchmark provides a replicable methodology for constructing multimodal benchmarks in typologically diverse languages, particularly within the Slavic language family. --- ### Meta-Black-Box Optimization with Bi-Space Landscape Analysis and Dual-Control Mechanism for SAEA Authors: Yukun Du, Haiyue Yu, Xiaotong Xie, Yan Zheng, Lixin Zhan, Yudong Du, Chongshuang Hu, Boxuan Wang, Jiang Jiang Published: 2025-11-19 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.15551v1 Surrogate-Assisted Evolutionary Algorithms (SAEAs) are widely used for expensive Black-Box Optimization. However, their reliance on rigid, manually designed components such as infill criteria and evolutionary strategies during the search process limits their flexibility across tasks. To address these limitations, we propose Dual-Control Bi-Space Surrogate-Assisted Evolutionary Algorithm (DB-SAEA), a Meta-Black-Box Optimization (MetaBBO) framework tailored for multi-objective problems. DB-SAEA learns a meta-policy that jointly regulates candidate generation and infill criterion selection, enabling dual control. The bi-space Exploratory Landscape Analysis (ELA) module in DB-SAEA adopts an attention-based architecture to capture optimization states from both true and surrogate evaluation spaces, while ensuring scalability across problem dimensions, population sizes, and objectives. Additionally, we integrate TabPFN as the surrogate model for accurate and efficient prediction with uncertainty estimation. The framework is trained via reinforcement learning, leveraging parallel sampling and centralized training to enhance efficiency and transferability across tasks. Experimental results demonstrate that DB-SAEA not only outperforms state-of-the-art baselines across diverse benchmarks, but also exhibits strong zero-shot transfer to unseen tasks with higher-dimensional settings. This work introduces the first MetaBBO framework with dual-level control over SAEAs and a bi-space ELA that captures surrogate model information. ---