# Research Papers — 2025-12 · bundle page 107 of 175 > Full-text markdown of papers #5301–5350 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/107 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/108.md) ### T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground Authors: Dmitrii Stoianov, Danil Taranets, Olga Tsymboi, Ramil Latypov, Almaz Dautov, Vladislav Kruglikov, Nikita Surkov, German Abramov, Pavel Gein, Dmitry Abulkhanov, Mikhail Gashkov, Viktor Zelenkovskiy et al. Published: 2025-12-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.10430v1 We introduce T-pro 2.0, an open-weight Russian LLM for hybrid reasoning and efficient inference. The model supports direct answering and reasoning-trace generation, using a Cyrillic-dense tokenizer and an adapted EAGLE speculative-decoding pipeline to reduce latency. To enable reproducible and extensible research, we release the model weights, the T-Wix 500k instruction corpus, the T-Math reasoning benchmark, and the EAGLE weights on Hugging Face. These resources allow users to study Russian-language reasoning and to extend or adapt both the model and the inference pipeline. A public web demo exposes reasoning and non-reasoning modes and illustrates the speedups achieved by our inference stack across domains. T-pro 2.0 thus serves as an accessible open system for building and evaluating efficient, practical Russian LLM applications. --- ### Representation of the structure of graphs by sequences of instructions Authors: Ezequiel Lopez-Rubio Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10429v2 The representation of graphs is commonly based on the adjacency matrix concept. This formulation is the foundation of most algebraic and computational approaches to graph processing. The advent of deep learning language models offers a wide range of powerful computational models that are specialized in the processing of text. However, current procedures to represent graphs are not amenable to processing by these models. In this work, a new method to represent graphs is proposed. It represents the adjacency matrix of a graph by a string of simple instructions. The instructions build the adjacency matrix step by step. The transformation is reversible, i.e., given a graph the string can be produced and vice versa. The proposed representation is compact, and it maintains the local structural patterns of the graph. Therefore, it is envisaged that it could be useful to boost the processing of graphs by deep learning models. A tentative computational experiment is reported, demonstrating improved classification performance and faster computation times with the proposed representation. --- ### Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws Authors: Yizhou Zhang Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10427v5 Neural scaling laws and double-descent phenomena suggest that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics. We derive such structure directly from gradient descent in function space. For mean-squared error loss, the training error evolves as $\dot e_t=-M(t)e_t$ with $M(t)=J_{θ(t)}J_{θ(t)}^{\!*}$, a time-dependent self-adjoint operator induced by the network Jacobian. Using Kato perturbation theory, we obtain an exact system of coupled modewise ODEs in the instantaneous eigenbasis of $M(t)$. To extract macroscopic behavior, we introduce a logarithmic spectral-shell coarse-graining and track quadratic error energy across shells. Microscopic interactions within each shell cancel identically at the energy level, so shell energies evolve only through dissipation and external inter-shell interactions. We formalize this via a \emph{renormalizable shell-dynamics} assumption, under which cumulative microscopic effects reduce to a controlled net flux across shell boundaries. Assuming an effective power-law spectral transport in a relevant resolution range, the shell dynamics admits a self-similar solution with a moving resolution frontier and explicit scaling exponents. This framework explains neural scaling laws and double descent, and unifies lazy (NTK-like) training and feature learning as two limits of the same spectral-shell dynamics. --- ### Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers Authors: Youmin Ko, Sungjong Seo, Hyunjoon Kim Published: 2025-12-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.10422v3 Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available. --- ### Neural Collapse in Test-Time Adaptation Authors: Xiao Chen, Zhongjing Du, Jiazhen Huang, Xu Jiang, Li Lu, Jingyan Jiang, Zhi Wang Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10421v2 Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation under domain shifts. Recently, Neural Collapse (NC) has been proposed as an emergent geometric property of deep neural networks (DNNs), providing valuable insights for TTA. In this work, we extend NC to the sample-wise level and discover a novel phenomenon termed Sample-wise Alignment Collapse (NC3+), demonstrating that a sample's feature embedding, obtained by a trained model, aligns closely with the corresponding classifier weight. Building on NC3+, we identify that the performance degradation stems from sample-wise misalignment in adaptation which exacerbates under larger distribution shifts. This indicates the necessity of realigning the feature embeddings with their corresponding classifier weights. However, the misalignment makes pseudo-labels unreliable under domain shifts. To address this challenge, we propose NCTTA, a novel feature-classifier alignment method with hybrid targets to mitigate the impact of unreliable pseudo-labels, which blends geometric proximity with predictive confidence. Extensive experiments demonstrate the effectiveness of NCTTA in enhancing robustness to domain shifts. For example, NCTTA outperforms Tent by 14.52% on ImageNet-C. Project page is publicly available at https://github.com/Cevaaa/NCTTA. --- ### TransLocNet: Cross-Modal Attention for Aerial-Ground Vehicle Localization with Contrastive Learning Authors: Phu Pham, Damon Conover, Aniket Bera Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10419v1 Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with aerial semantic context. LiDAR scans are projected into a bird's-eye-view representation and aligned with aerial features through bidirectional attention, followed by a likelihood map decoder that outputs spatial probability distributions over position and orientation. A contrastive learning module enforces a shared embedding space to improve cross-modal alignment. Experiments on CARLA and KITTI show that TransLocNet outperforms state-of-the-art baselines, reducing localization error by up to 63% and achieving sub-meter, sub-degree accuracy. These results demonstrate that TransLocNet provides robust and generalizable aerial-ground localization in both synthetic and real-world settings. --- ### Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction Authors: Wenfei Guan, Jilin Mei, Tong Shen, Xumin Wu, Shuo Wang, Chen Min, Yu Hu Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.10416v3 Deep learning has advanced vectorized road extraction in urban settings, yet off-road environments remain underexplored and challenging. A significant domain gap causes advanced models to fail in wild terrains due to two key issues: lack of large-scale vectorized datasets and structural weakness in prevailing methods. Models such as SAM-Road employ a node-centric paradigm that reasons at sparse endpoints, making them fragile to occlusions and ambiguous junctions in off-road scenes, leading to topological errors. This work addresses these limitations in two complementary ways. First, we release WildRoad, a global off-road road network dataset constructed efficiently with a dedicated interactive annotation tool tailored for road-network labeling. Second, we introduce MaGRoad (Mask-aware Geodesic Road network extractor), a path-centric framework that aggregates multi-scale visual evidence along candidate paths to infer connectivity robustly. Extensive experiments show that MaGRoad achieves state-of-the-art performance on our challenging WildRoad benchmark while generalizing well to urban datasets. An efficient vertex extraction strategy also yields roughly 2.5X faster inference, improving practical applicability. Together, the dataset and path-centric paradigm provide a stronger foundation for mapping roads in the wild. We release both the dataset and code at this repository. We release both the dataset and code at https://github.com/xiaofei-guan/MaGRoad. --- ### How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation Authors: Devanshu Sahoo, Vasudev Majhi, Arjun Neekhra, Yash Sinha, Murari Mandal, Dhruv Kumar Published: 2025-12-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.10415v2 The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting strategies in order to induce misgrading and secure undeserved academic advantages. In this paper, we present the first large-scale study of jailbreaking LLM-based automated code evaluators in academic context. Our contributions are: (i) We systematically adapt 20+ jailbreaking strategies for jailbreaking AI code evaluators in the academic context, defining a new class of attacks termed academic jailbreaking. (ii) We release a poisoned dataset of 25K adversarial student submissions, specifically designed for the academic code-evaluation setting, sourced from diverse real-world coursework and paired with rubrics and human-graded references, and (iii) In order to capture the multidimensional impact of academic jailbreaking, we systematically adapt and define three jailbreaking metrics (Jailbreak Success Rate, Score Inflation, and Harmfulness). (iv) We comprehensively evalulate the academic jailbreaking attacks using six LLMs. We find that these models exhibit significant vulnerability, particularly to persuasive and role-play-based attacks (up to 97% JSR). Our adversarial dataset and benchmark suite lay the groundwork for next-generation robust LLM-based evaluators in academic code assessment. --- ### Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention Authors: Yang Yu, Zhuangzhuang Chen, Lanqing Li, Xiaomeng Li Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10414v2 Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization of RL. They ignore the entropy intervention during the RL sampling that can boost the performance of GRPO by improving the diversity of responses. In this paper, we propose Selective-adversarial Entropy Intervention, namely SaEI, which enhances policy entropy by distorting the visual input with the token-selective adversarial objective coming from the entropy of sampled responses. Specifically, we first propose entropy-guided adversarial sampling (EgAS) that formulates the entropy of sampled responses as an adversarial objective. Then, the corresponding adversarial gradient can be used to attack the visual input for producing adversarial samples, allowing the policy model to explore a larger answer space during RL sampling. Then, we propose token-selective entropy computation (TsEC) to maximize the effectiveness of adversarial attack in EgAS without distorting factual knowledge within VLMs. Extensive experiments on both in-domain and out-of-domain datasets show that our proposed method can greatly improve policy exploration via entropy intervention, to boost reasoning capabilities. Code will be released once the paper is accepted. --- ### SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing Authors: Yijiong Yu, Jiale Liu, Qingyun Wu, Huazheng Wang, Ji Pei Published: 2025-12-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.10411v5 The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity alternative, it suffers from catastrophic long context performance collapse, which stems from two fundamental factors: the training inference mismatch when naively applying SWA to models pretrained with Full Attention (FA), and the inherent structural inability to access distant information when applying SWA to every module at all times. To address these dual challenges, we propose Sliding Window Attention Adaptation (SWAA), a plug and play toolkit of recipes that adapts FA models to SWA without costly pretraining. SWAA systematically combines four core strategies to tackle these distinct issues: (1) Full Attention (FA) Decode and (2) Interleaving FA and SWA layers, which mitigate structural defects by selectively allowing access to distant information; alongside (3) preserving ``sink'' tokens and (4) lightweight fine tuning, which mitigate the training inference mismatch. Our experiments reveal that while isolated strategies are insufficient, specific synergistic combinations effectively recover long context performance. Despite varying computational overheads, our performance efficiency trade off analysis identifies optimal SWAA configurations for diverse scenarios, achieving 30% to 100% speedups for long context inference with acceptable quality retention. Our code, data and model weights are available at https://github.com/yuyijiong/sliding-window-attention-adaptation --- ### MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos Authors: Qiyue Sun, Tailin Chen, Yinghui Zhang, Yuchen Zhang, Jiangbei Yue, Jianbo Jiao, Zeyu Fu Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10408v3 The rapid growth of video content on platforms such as TikTok and YouTube has intensified the spread of multimodal hate speech, where harmful cues emerge subtly and asynchronously across visual, acoustic, and textual streams. Existing research primarily focuses on video-level classification, leaving the practically crucial task of temporal localisation, identifying when hateful segments occur, largely unaddressed. This challenge is even more noticeable under weak supervision, where only video-level labels are available, and static fusion or classification-based architectures struggle to capture cross-modal and temporal dynamics. To address these challenges, we propose MultiHateLoc, the first framework designed for weakly-supervised multimodal hate localisation. MultiHateLoc incorporates (1) modality-aware temporal encoders to model heterogeneous sequential patterns, including a tailored text-based preprocessing module for feature enhancement; (2) dynamic cross-modal fusion to adaptively emphasise the most informative modality at each moment and a cross-modal contrastive alignment strategy to enhance multimodal feature consistency; (3) a modality-aware MIL objective to identify discriminative segments under video-level supervision. Despite relying solely on coarse labels, MultiHateLoc produces fine-grained, interpretable frame-level predictions. Experiments on HateMM and MultiHateClip show that our method achieves state-of-the-art performance in the localisation task. --- ### Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifolds Authors: Christian Soize Published: 2025-12-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.10407v1 This paper introduces a new probabilistic framework for supervised learning in neural systems. It is designed to model complex, uncertain systems whose random outputs are strongly non-Gaussian given deterministic inputs. The architecture itself is a random object stochastically generated by a latent anisotropic Gaussian random field defined on a compact, boundaryless, multiply-connected manifold. The goal is to establish a novel conceptual and mathematical framework in which neural architectures are realizations of a geometry-aware, field-driven generative process. Both the neural topology and synaptic weights emerge jointly from a latent random field. A reduced-order parameterization governs the spatial intensity of an inhomogeneous Poisson process on the manifold, from which neuron locations are sampled. Input and output neurons are identified via extremal evaluations of the latent field, while connectivity is established through geodesic proximity and local field affinity. Synaptic weights are conditionally sampled from the field realization, inducing stochastic output responses even for deterministic inputs. To ensure scalability, the architecture is sparsified via percentile-based diffusion masking, yielding geometry-aware sparse connectivity without ad hoc structural assumptions. Supervised learning is formulated as inference on the generative hyperparameters of the latent field, using a negative log-likelihood loss estimated through Monte Carlo sampling from single-observation-per-input datasets. The paper initiates a mathematical analysis of the model, establishing foundational properties such as well-posedness, measurability, and a preliminary analysis of the expressive variability of the induced stochastic mappings, which support its internal coherence and lay the groundwork for a broader theory of geometry-driven stochastic learning. --- ### BRACE: A Benchmark for Robust Audio Caption Quality Evaluation Authors: Tianyu Guo, Hongyu Chen, Hao Liang, Meiyi Qiang, Bohan Zeng, Linzhuang Sun, Bin Cui, Wentao Zhang Published: 2025-12-11 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2512.10403v1 Automatic audio captioning is essential for audio understanding, enabling applications such as accessibility and content indexing. However, evaluating the quality of audio captions remains a major challenge, especially in reference-free settings where high-quality ground-truth captions are unavailable. While CLAPScore is currently the most widely used reference-free Audio Caption Evaluation Metric(ACEM), its robustness under diverse conditions has not been systematically validated. To address this gap, we introduce BRACE, a new benchmark designed to evaluate audio caption alignment quality in a reference-free setting. BRACE is primarily designed for assessing ACEMs, and can also be extended to measure the modality alignment abilities of Large Audio Language Model(LALM). BRACE consists of two sub-benchmarks: BRACE-Main for fine-grained caption comparison and BRACE-Hallucination for detecting subtle hallucinated content. We construct these datasets through high-quality filtering, LLM-based corruption, and human annotation. Given the widespread adoption of CLAPScore as a reference-free ACEM and the increasing application of LALMs in audio-language tasks, we evaluate both approaches using the BRACE benchmark, testing CLAPScore across various CLAP model variants and assessing multiple LALMs. Notably, even the best-performing CLAP-based ACEM achieves only a 70.01 F1-score on the BRACE-Main benchmark, while the best LALM reaches just 63.19. By revealing the limitations of CLAP models and LALMs, our BRACE benchmark offers valuable insights into the direction of future research. --- ### The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks Authors: Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Tianyu Du, Jinbao Li, Jianhai Chen, Shouling Ji Published: 2025-12-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.10402v2 Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks, typically reliant on heuristic brute-force methods. Despite significant empirical advancements in backdoor research, the lack of rigorous theoretical analysis limits understanding of underlying mechanisms, constraining attack predictability and adaptability. Therefore, we provide a theoretical analysis targeting backdoor attacks, focusing on how sparse decision boundaries enable disproportionate model manipulation. Based on this finding, we derive a closed-form, ambiguous boundary region, wherein negligible relabeled samples induce substantial misclassification. Influence function analysis further quantifies significant parameter shifts caused by these margin samples, with minimal impact on clean accuracy, formally grounding why such low poison rates suffice for efficacious attacks. Leveraging these insights, we propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties. Eminence optimizes a universal, visually subtle trigger that strategically exploits vulnerable decision boundaries and effectively achieves robust misclassification with exceptionally low poison rates (< 0.1%, compared to SOTA methods typically requiring > 1%). Comprehensive experiments validate our theoretical discussions and demonstrate the effectiveness of Eminence, confirming an exponential relationship between margin poisoning and adversarial boundary manipulation. Eminence maintains > 90% attack success rate, exhibits negligible clean-accuracy loss, and demonstrates high transferability across diverse models, datasets and scenarios. --- ### Diffusion differentiable resampling Authors: Jennifer Rosina Andersson, Zheng Zhao Published: 2025-12-11 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2512.10401v3 This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). Drawing on reparametrisation, we propose a new resampling method that is informative and instantly differentiable, based on a training-free diffusion model surrogate. We theoretically prove that our diffusion resampling method provides a consistent resampling distribution, and we show empirically that it outperforms the state-of-the-art differentiable resampling methods on multiple filtering and parameter estimation benchmarks. Finally, we show that it achieves competitive end-to-end performance when used in learning a complex dynamics-decoder model with high-dimensional image observations. --- ### Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases Authors: Sherman Wong, Zhenting Qi, Zhaodong Wang, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Wenlin Chen, Yilun Du, Minlan Yu, Ying Zhang Published: 2025-12-11 Categories: cs.CL, cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2512.10398v6 Real-world software engineering tasks require coding agents that can operate on massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade coding agents offer transparency but struggle when scaled to heavier, production-level workloads, while production-grade systems achieve strong practical performance but provide limited extensibility, interpretability, and controllability. We introduce the Confucius Code Agent (CCA), a software engineering agent that can operate at large-scale codebases. CCA is built on top of the Confucius SDK, an agent development platform structured around three complementary perspectives: Agent Experience (AX), User Experience (UX), and Developer Experience (DX). The SDK supports a unified orchestrator with advanced context management for long-context reasoning, a persistent note-taking system for cross-session continual learning, and a modular extension system for reliable tool use. In addition, we introduce a meta-agent that automates the construction, evaluation, and refinement of agents through a build-test-improve cycle, enabling rapid agent development on new tasks and tool stacks. Instantiated on the Confucius SDK using the meta-agent, CCA demonstrates strong performance on real-world software engineering tasks. On SWE-Bench-Pro, CCA achieves a Resolve@1 of 59%, exceeding prior research baselines as well as commercial results, under identical repositories, model backends, and tool access. --- ### RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI Authors: Weifan Guan, Qinghao Hu, Huasen Xi, Chenxiao Zhang, Aosheng Li, Jian Cheng Published: 2025-12-11 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.10394v2 Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool APIs and robot middleware. Current implementations typically rely on ad-hoc wrappers that are difficult to reuse, and changes to the VLA backend or serving stack often necessitate extensive re-integration. We introduce RoboNeuron, a middleware layer that connects the Model Context Protocol (MCP) for LLM agents with robot middleware such as ROS2. RoboNeuron bridges these ecosystems by deriving agent-callable tools directly from ROS schemas, providing a unified execution abstraction that supports both direct commands and modular composition, and localizing backend, runtime, and acceleration-preset changes within a stable inference boundary. We evaluate RoboNeuron in simulation and on hardware through multi-platform base control, arm motion, and VLA-based grasping tasks, demonstrating that it enables modular system orchestration under a unified interface while supporting backend transitions without system rewiring. The full code implementation of this work is available at github repo: https://github.com/guanweifan/RoboNeuron --- ### Cross-modal Retrieval Models for Stripped Binary Analysis Authors: Guoqiang Chen, Lingyun Ying, Ziyang Song, Daguang Liu, Qiang Wang, Zhiqi Wang, Li Hu, Shaoyin Cheng, Weiming Zhang, Nenghai Yu Published: 2025-12-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.10393v2 Retrieving binary code via natural language queries is a pivotal capability for downstream tasks in the software security domain, such as vulnerability detection and malware analysis. However, it is challenging to identify binary functions semantically relevant to the user query from thousands of candidates, as the absence of symbolic information distinguishes this task from source code retrieval. In this paper, we introduce, BinSeek, a two-stage cross-modal retrieval framework for stripped binary code analysis. It consists of two models: BinSeek-Embedding is trained on large-scale dataset to learn the semantic relevance of the binary code and the natural language description, furthermore, BinSeek-Reranker learns to carefully judge the relevance of the candidate code to the description with context augmentation. To this end, we built an LLM-based data synthesis pipeline to automate training construction, also deriving a domain benchmark for future research. Our evaluation results show that BinSeek achieved the state-of-the-art performance, surpassing the the same scale models by 31.42% in Rec@3 and 27.17% in MRR@3, as well as leading the advanced general-purpose models that have 16 times larger parameters. --- ### Fitting magnetization data using continued fraction of straight lines Authors: Vijay Prakash S Published: 2025-12-11 Categories: cs.LG, cond-mat.mtrl-sci, physics.class-ph arXiv: https://arxiv.org/abs/2512.10390v1 Magnetization of a ferromagnetic substance in response to an externally applied magnetic field increases with the strength of the field. This is because at the microscopic level, magnetic moments in certain regions or domains of the substance increasingly align with the applied field, while the amount of misaligned domains decreases. The alignment of such magnetic domains with an applied magnetic field forms the physical basis for the nonlinearity of magnetization. In this paper, the nonlinear function is approximated as a combination of continued fraction of straight lines. The resulting fit is used to interpret the nonlinear behavior in both growing and shrinking magnetic domains. The continued fraction of straight lines used here is an algebraic expression which can be used to estimate parameters using nonlinear regression. --- ### The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation Authors: Ziwei Liu, Yejing Wang, Wanyu Wang, Wang Zejian, Qidong Liu, Zijian Zhang, Chong Chen, Wei Huang, Xiangyu Zhao Published: 2025-12-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.10388v3 Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture collaborative signals from historical user-item interactions. However, such embeddings are vulnerable in long-tail scenarios where most items are rarely consumed. Recent methods that incorporate auxiliary information often face noisy collaborative sharing from co-occurrence signals or semantic homogeneity caused by flat dense embeddings. In contrast, Semantic IDs (SID), with their support for code sharing and multi-granular semantic modeling, offer a promising alternative. Nevertheless, SID-based methods are hindered by a collaborative overwhelming phenomenon: commonly adopted quantization mechanisms compromise the identifier uniqueness needed to model head items, resulting in a performance trade-off between head and tail items. To address this challenge, we propose H2Rec, a novel framework that harmonizes SID and HID. We design a dual-branch modeling architecture that simultaneously captures the multi-granular semantics of SID while preserving the unique collaborative identity provided by HID. Moreover, we introduce a dual-level alignment strategy to bridge the two representations, enabling effective knowledge transfer and robust preference modeling. Extensive offline experiments on three public benchmarks and online experiments on a large-scale commercial platform demonstrate that H2Rec achieves a better balance between head and tail recommendation quality and consistently outperforms existing baselines. --- ### Adaptive Dual-Weighted Gravitational Point Cloud Denoising Method Authors: Ge Zhang, Chunyang Wang, Bin Liu, Guan Xi Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10386v2 High-quality point cloud data is a critical foundation for tasks such as autonomous driving and 3D reconstruction. However, LiDAR-based point cloud acquisition is often affected by various disturbances, resulting in a large number of noise points that degrade the accuracy of subsequent point cloud object detection and recognition. Moreover, existing point cloud denoising methods typically sacrifice computational efficiency in pursuit of higher denoising accuracy, or, conversely, improve processing speed at the expense of preserving object boundaries and fine structural details, making it difficult to simultaneously achieve high denoising accuracy, strong edge preservation, and real-time performance. To address these limitations, this paper proposes an adaptive dualweight gravitational-based point cloud denoising method. First, an octree is employed to perform spatial partitioning of the global point cloud, enabling parallel acceleration. Then, within each leaf node, adaptive voxel-based occupancy statistics and k-nearest neighbor (kNN) density estimation are applied to rapidly remove clearly isolated and low-density noise points, thereby reducing the effective candidate set. Finally, a gravitational scoring function that combines density weights with adaptive distance weights is constructed to finely distinguish noise points from object points. Experiments conducted on the Stanford 3D Scanning Repository, the Canadian Adverse Driving Conditions (CADC) dataset, and in-house RUBY PLUS LiDAR point clouds acquired in our laboratory demonstrate that, compared with existing methods, the proposed approach achieves consistent improvements in F1, PSNR, and Chamfer Distance (CD) across various noise conditions while reducing the single-frame processing time, thereby validating its high accuracy, robustness, and real-time performance in multi-noise scenarios. --- ### Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies Authors: Cong Pang, Hongtao Yu, Zixuan Chen, Lewei Lu, Xin Lou Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.10384v1 Large Vision Language Models (LVLMs) have made remarkable progress, enabling sophisticated vision-language interaction and dialogue applications. However, existing benchmarks primarily focus on reasoning tasks, often neglecting fine-grained recognition, which is crucial for practical application scenarios. To address this gap, we introduce the Fine-grained Recognition Open World (FROW) benchmark, designed for detailed evaluation of LVLMs with GPT-4o. On the basis of that, we propose a novel optimization strategy from two perspectives: \textit{data construction} and \textit{training process}, to improve the performance of LVLMs. Our dataset includes mosaic data, which combines multiple short-answer responses, and open-world data, generated from real-world questions and answers using GPT-4o, creating a comprehensive framework for evaluating fine-grained recognition in LVLMs. Experiments show that mosaic data improves category recognition accuracy by 1\% and open-world data boosts FROW benchmark accuracy by 10\%-20\% and content accuracy by 6\%-12\%. Meanwhile, incorporating fine-grained data into the pre-training phase can improve the model's category recognition accuracy by up to 10\%. The benchmark will be available at https://github.com/pc-inno/FROW. --- ### Self-Supervised Contrastive Embedding Adaptation for Endoscopic Image Matching Authors: Alberto Rota, Elena De Momi Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10379v1 Accurate spatial understanding is essential for image-guided surgery, augmented reality integration and context awareness. In minimally invasive procedures, where visual input is the sole intraoperative modality, establishing precise pixel-level correspondences between endoscopic frames is critical for 3D reconstruction, camera tracking, and scene interpretation. However, the surgical domain presents distinct challenges: weak perspective cues, non-Lambertian tissue reflections, and complex, deformable anatomy degrade the performance of conventional computer vision techniques. While Deep Learning models have shown strong performance in natural scenes, their features are not inherently suited for fine-grained matching in surgical images and require targeted adaptation to meet the demands of this domain. This research presents a novel Deep Learning pipeline for establishing feature correspondences in endoscopic image pairs, alongside a self-supervised optimization framework for model training. The proposed methodology leverages a novel-view synthesis pipeline to generate ground-truth inlier correspondences, subsequently utilized for mining triplets within a contrastive learning paradigm. Through this self-supervised approach, we augment the DINOv2 backbone with an additional Transformer layer, specifically optimized to produce embeddings that facilitate direct matching through cosine similarity thresholding. Experimental evaluation demonstrates that our pipeline surpasses state-of-the-art methodologies on the SCARED datasets improved matching precision and lower epipolar error compared to the related work. The proposed framework constitutes a valuable contribution toward enabling more accurate high-level computer vision applications in surgical endoscopy. --- ### RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds Authors: Jingyun Fu, Zhiyu Xiang, Na Zhao Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10376v1 Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more robust in various weather conditions and can detect point-wise velocity, making it a valuable complement to LiDAR. However, radar inputs pose challenges due to noise, low resolution, and sparsity. Moreover, there is currently no dataset that combines LiDAR and radar data specifically for scene flow estimation. To address this gap, we construct a Radar-LiDAR scene flow dataset based on a public real-world automotive dataset. We propose an effective preprocessing strategy for radar denoising and scene flow label generation, deriving more reliable flow ground truth for radar points out of the object boundaries. Additionally, we introduce RaLiFlow, the first joint scene flow learning framework for 4D radar and LiDAR, which achieves effective radar-LiDAR fusion through a novel Dynamic-aware Bidirectional Cross-modal Fusion (DBCF) module and a carefully designed set of loss functions. The DBCF module integrates dynamic cues from radar into the local cross-attention mechanism, enabling the propagation of contextual information across modalities. Meanwhile, the proposed loss functions mitigate the adverse effects of unreliable radar data during training and enhance the instance-level consistency in scene flow predictions from both modalities, particularly for dynamic foreground areas. Extensive experiments on the repurposed scene flow dataset demonstrate that our method outperforms existing LiDAR-based and radar-based single-modal methods by a significant margin. --- ### Neural personal sound zones with flexible bright zone control Authors: Wenye Zhu, Jun Tang, Xiaofei Li Published: 2025-12-11 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2512.10375v1 Personal sound zone (PSZ) reproduction system, which attempts to create distinct virtual acoustic scenes for different listeners at their respective positions within the same spatial area using one loudspeaker array, is a fundamental technology in the application of virtual reality. For practical applications, the reconstruction targets must be measured on the same fixed receiver array used to record the local room impulse responses (RIRs) from the loudspeaker array to the control points in each PSZ, which makes the system inconvenient and costly for real-world use. In this paper, a 3D convolutional neural network (CNN) designed for PSZ reproduction with flexible control microphone grid and alternative reproduction target is presented, utilizing the virtual target scene as inputs and the PSZ pre-filters as output. Experimental results of the proposed method are compared with the traditional method, demonstrating that the proposed method is able to handle varied reproduction targets on flexible control point grid using only one training session. Furthermore, the proposed method also demonstrates the capability to learn global spatial information from sparse sampling points distributed in PSZs. --- ### D2M: A Decentralized, Privacy-Preserving, Incentive-Compatible Data Marketplace for Collaborative Learning Authors: Yash Srivastava, Shalin Jain, Sneha Awathare, Nitin Awathare Published: 2025-12-11 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2512.10372v1 The rising demand for collaborative machine learning and data analytics calls for secure and decentralized data sharing frameworks that balance privacy, trust, and incentives. Existing approaches, including federated learning (FL) and blockchain-based data markets, fall short: FL often depends on trusted aggregators and lacks Byzantine robustness, while blockchain frameworks struggle with computation-intensive training and incentive integration. We present \prot, a decentralized data marketplace that unifies federated learning, blockchain arbitration, and economic incentives into a single framework for privacy-preserving data sharing. \prot\ enables data buyers to submit bid-based requests via blockchain smart contracts, which manage auctions, escrow, and dispute resolution. Computationally intensive training is delegated to \cone\ (\uline{Co}mpute \uline{N}etwork for \uline{E}xecution), an off-chain distributed execution layer. To safeguard against adversarial behavior, \prot\ integrates a modified YODA protocol with exponentially growing execution sets for resilient consensus, and introduces Corrected OSMD to mitigate malicious or low-quality contributions from sellers. All protocols are incentive-compatible, and our game-theoretic analysis establishes honesty as the dominant strategy. We implement \prot\ on Ethereum and evaluate it over benchmark datasets -- MNIST, Fashion-MNIST, and CIFAR-10 -- under varying adversarial settings. \prot\ achieves up to 99\% accuracy on MNIST and 90\% on Fashion-MNIST, with less than 3\% degradation up to 30\% Byzantine nodes, and 56\% accuracy on CIFAR-10 despite its complexity. Our results show that \prot\ ensures privacy, maintains robustness under adversarial conditions, and scales efficiently with the number of participants, making it a practical foundation for real-world decentralized data sharing. --- ### AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management Authors: Shizuo Tian, Hao Wen, Yuxuan Chen, Jiacheng Liu, Shanhui Zhao, Guohong Liu, Ju Ren, Yunxin Liu, Yuanchun Li Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10371v2 The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history incurs substantial context overhead. Existing context management and compression techniques often fail to preserve vital semantic information, leading to degraded task performance. We propose AgentProg, a program-guided approach for agent context management that reframes the interaction history as a program with variables and control flow. By organizing information according to the structure of program, this structure provides a principled mechanism to determine which information should be retained and which can be discarded. We further integrate a global belief state mechanism inspired by Belief MDP framework to handle partial observability and adapt to unexpected environmental changes. Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates on these benchmarks. More importantly, it maintains robust performance on long-horizon tasks while baseline methods experience catastrophic degradation. Our system is open-sourced at https://github.com/MobileLLM/AgentProg. --- ### LLM-Empowered Representation Learning for Emerging Item Recommendation Authors: Ziying Zhang, Quanming Yao, Yaqing Wang Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10370v1 In this work, we tackle the challenge of recommending emerging items, whose interactions gradually accumulate over time. Existing methods often overlook this dynamic process, typically assuming that emerging items have few or even no historical interactions. Such an assumption oversimplifies the problem, as a good model must preserve the uniqueness of emerging items while leveraging their shared patterns with established ones. To address this challenge, we propose EmerFlow, a novel LLM-empowered representation learning framework that generates distinctive embeddings for emerging items. It first enriches the raw features of emerging items through LLM reasoning, then aligns these representations with the embedding space of the existing recommendation model. Finally, new interactions are incorporated through meta-learning to refine the embeddings. This enables EmerFlow to learn expressive embeddings for emerging items from only limited interactions. Extensive experiments across diverse domains, including movies and pharmaceuticals, show that EmerFlow consistently outperforms existing methods. --- ### Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views Authors: Zhankuo Xu, Chaoran Feng, Yingtao Li, Jianbin Zhao, Jiashu Yang, Wangbo Yu, Li Yuan, Yonghong Tian Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10369v2 3D Gaussian Splatting (3DGS) has emerged as a state-of-the-art method for novel view synthesis. However, its performance heavily relies on dense, high-quality input imagery, an assumption that is often violated in real-world applications, where data is typically sparse and motion-blurred. These two issues create a vicious cycle: sparse views ignore the multi-view constraints necessary to resolve motion blur, while motion blur erases high-frequency details crucial for aligning the limited views. Thus, reconstruction often fails catastrophically, with fragmented views and a low-frequency bias. To break this cycle, we introduce CoherentGS, a novel framework for high-fidelity 3D reconstruction from sparse and blurry images. Our key insight is to address these compound degradations using a dual-prior strategy. Specifically, we combine two pre-trained generative models: a specialized deblurring network for restoring sharp details and providing photometric guidance, and a diffusion model that offers geometric priors to fill in unobserved regions of the scene. This dual-prior strategy is supported by several key techniques, including a consistency-guided camera exploration module that adaptively guides the generative process, and a depth regularization loss that ensures geometric plausibility. We evaluate CoherentGS through both quantitative and qualitative experiments on synthetic and real-world scenes, using as few as 3, 6, and 9 input views. Our results demonstrate that CoherentGS significantly outperforms existing methods, setting a new state-of-the-art for this challenging task. The code and video demos are available at https://potatobigroom.github.io/CoherentGS/. --- ### GPG: Generalized Policy Gradient Theorem for Transformer-based Policies Authors: Hangyu Mao, Guangting Dong, Zhicheng Dou Published: 2025-12-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.10365v1 We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework. Furthermore, we explore its practical applications in training Large Language Models (LLMs), offering new insights into efficient policy optimization. --- ### Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos Authors: Mingyu Jeon, Jisoo Yang, Sungjin Han, Jinkwon Hwang, Sunjae Yoon, Jonghee Kim, Junyeoung Kim Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10363v1 Zero-shot Long Video Moment Retrieval (ZLVMR) is the task of identifying temporal segments in hour-long videos using a natural language query without task-specific training. The core technical challenge of LVMR stems from the computational infeasibility of processing entire lengthy videos in a single pass. This limitation has established a 'Search-then-Refine' approach, where candidates are rapidly narrowed down, and only those portions are analyzed, as the dominant paradigm for LVMR. However, existing approaches to this paradigm face severe limitations. Conventional supervised learning suffers from limited scalability and poor generalization, despite substantial resource consumption. Yet, existing zero-shot methods also fail, facing a dual challenge: (1) their heuristic strategies cause a 'search' phase candidate explosion, and (2) the 'refine' phase, which is vulnerable to semantic discrepancy, requires high-cost VLMs for verification, incurring significant computational overhead. We propose \textbf{P}oint-\textbf{to}-\textbf{S}pan (P2S), a novel training-free framework to overcome this challenge of inefficient 'search' and costly 'refine' phases. P2S overcomes these challenges with two key innovations: an 'Adaptive Span Generator' to prevent the search phase candidate explosion, and 'Query Decomposition' to refine candidates without relying on high-cost VLM verification. To our knowledge, P2S is the first zero-shot framework capable of temporal grounding in hour-long videos, outperforming supervised state-of-the-art methods by a significant margin (e.g., +3.7\% on R5@0.1 on MAD). --- ### Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models Authors: Woojun Jung, Jaehoon Go, Mingyu Jeon, Sunjae Yoon, Junyeong Kim Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.10362v2 Multimodal Large Language Models (MLLMs) demonstrate impressive reasoning capabilities, but often fail to perceive fine-grained visual details, limiting their applicability in precision-demanding tasks. While methods that crop salient regions of an image offer a partial solution, we identify a critical limitation they introduce: "Contextual Blindness". This failure occurs due to structural disconnect between high-fidelity details (from the crop) and the broader global context (from the original image), even when all necessary visual information is present. We argue that this limitation stems not from a lack of information 'Quantity', but from a lack of 'Structural Diversity' in the model's input. To resolve this, we propose Visual Funnel, a training-free, two-step approach. Visual Funnel first performs Contextual Anchoring to identify the region of interest in a single forward pass. It then constructs an Entropy-Scaled Portfolio that preserves the hierarchical context - ranging from focal detail to broader surroundings - by dynamically determining crop sizes based on attention entropy and refining crop centers. Through extensive experiments, we demonstrate that Visual Funnel significantly outperforms naive single-crop and unstructured multi-crop baselines. Our results further validate that simply adding more unstructured crops provides limited or even detrimental benefits, confirming that the hierarchical structure of our portfolio is key to resolving Contextual Blindness. --- ### Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task Authors: Sunqi Fan, Jiashuo Cui, Meng-Hao Guo, Shuojin Yang Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.10359v1 Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harmony between the quantity and diversity of tools. To better control the tool invocation sequence and avoid toolchain shortcut issues, we propose a Spatiotemporal Reasoning Framework (STAR) that strategically schedules temporal and spatial tools, thereby progressively localizing the key area in the video. Our STAR framework enhances GPT-4o using lightweight tools, achieving an 8.2% gain on VideoMME and 4.6% on LongVideoBench. We believe that our proposed Video Toolkit and STAR framework make an important step towards building autonomous and intelligent video analysis assistants. The code is publicly available at https://github.com/fansunqi/VideoTool. --- ### mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar Authors: Tarik Reza Toha, Shao-Jung, Lu, Shahriar Nirjon Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10357v1 mmWave radars struggle to detect or count individuals in dense, static (non-moving) groups due to limitations in spatial resolution and reliance on movement for detection. We present mmCounter, which accurately counts static people in dense indoor spaces (up to three people per square meter). mmCounter achieves this by extracting ultra-low frequency (< 1 Hz) signals, primarily from breathing and micro-scale body movements such as slight torso shifts, and applying novel signal processing techniques to differentiate these subtle signals from background noise and nearby static objects. Our problem differs significantly from existing studies on breathing rate estimation, which assume the number of people is known a priori. In contrast, mmCounter utilizes a novel multi-stage signal processing pipeline to extract relevant low-frequency sources along with their spatial information and map these sources to individual people, enabling accurate counting. Extensive evaluations in various environments demonstrate that mmCounter delivers an 87% average F1 score and 0.6 mean absolute error in familiar environments, and a 60% average F1 score and 1.1 mean absolute error in previously untested environments. It can count up to seven individuals in a three square meter space, such that there is no side-by-side spacing and only a one-meter front-to-back distance. --- ### Better Prevent than Tackle: Valuing Defense in Soccer Based on Graph Neural Networks Authors: Hyunsung Kim, Sangwoo Seo, Hoyoung Choi, Tom Boomstra, Jinsung Yoon, Chanyoung Park Published: 2025-12-11 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2512.10355v1 Evaluating defensive performance in soccer remains challenging, as effective defending is often expressed not through visible on-ball actions such as interceptions and tackles, but through preventing dangerous opportunities before they arise. Existing approaches have largely focused on valuing on-ball actions, leaving much of defenders' true impact unmeasured. To address this gap, we propose DEFCON (DEFensive CONtribution evaluator), a comprehensive framework that quantifies player-level defensive contributions for every attacking situation in soccer. Leveraging Graph Attention Networks, DEFCON estimates the success probability and expected value of each attacking option, along with each defender's responsibility for stopping it. These components yield an Expected Possession Value (EPV) for the attacking team before and after each action, and DEFCON assigns positive or negative credits to defenders according to whether they reduced or increased the opponent's EPV. Trained on 2023-24 and evaluated on 2024-25 Eredivisie event and tracking data, DEFCON's aggregated player credits exhibit strong positive correlations with market valuations. Finally, we showcase several practical applications, including in-game timelines of defensive contributions, spatial analyses across pitch zones, and pairwise summaries of attacker-defender interactions. --- ### Hybrid Transformer-Mamba for Weakly Supervised Volumetric Medical Segmentation Authors: Yiheng Lyu, Lian Xu, Coen Arrow, Mohammed Bennamoun, Farid Boussaid, Girish Dwivedi Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10353v2 Weakly supervised segmentation enables model training from plane-level labels. Existing methods often rely on 2D encoders, neglecting the volumetric nature of medical data. We propose TranSamba, a hybrid Transformer-Mamba architecture designed to capture 3D context via cross-plane modeling. TranSamba augments a Vision Transformer backbone with Cross-Plane Mamba blocks, leveraging linear-time modeling for efficient information exchange across neighboring planes. This exchange improves in-plane self-attention and subsequent attention maps for object localization. TranSamba maintains linear time complexity and constant space complexity with respect to the input volume depth. Extensive experiments on three datasets covering diverse modalities and pathologies show that TranSamba achieves state-of-the-art performance, demonstrating the generalizable efficacy of cross-plane modeling. Code is available at: https://github.com/YihengLyu/TranSamba. --- ### Topology-Agnostic Animal Motion Generation from Text Prompt Authors: Keyi Chen, Mingze Sun, Zhenyu Liu, Zhangquan Chen, Ruqi Huang Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10352v1 Motion generation is fundamental to computer animation and widely used across entertainment, robotics, and virtual environments. While recent methods achieve impressive results, most rely on fixed skeletal templates, which prevent them from generalizing to skeletons with different or perturbed topologies. We address the core limitation of current motion generation methods - the combined lack of large-scale heterogeneous animal motion data and unified generative frameworks capable of jointly modeling arbitrary skeletal topologies and textual conditions. To this end, we introduce OmniZoo, a large-scale animal motion dataset spanning 140 species and 32,979 sequences, enriched with multimodal annotations. Building on OmniZoo, we propose a generalized autoregressive motion generation framework capable of producing text-driven motions for arbitrary skeletal topologies. Central to our model is a Topology-aware Skeleton Embedding Module that encodes geometric and structural properties of any skeleton into a shared token space, enabling seamless fusion with textual semantics. Given a text prompt and a target skeleton, our method generates temporally coherent, physically plausible, and semantically aligned motions, and further enables cross-species motion style transfer. --- ### Geometric Dynamics of Agentic Loops in Large Language Models Authors: Nicolas Tacheny Published: 2025-12-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.10350v5 Iterative LLM systems(self-refinement, chain-of-thought, autonomous agents) are increasingly deployed, yet their temporal dynamics remain uncharacterized. Prior work evaluates task performance at convergence but ignores the trajectory: how does semantic content evolve across iterations? Does it stabilize, drift, or oscillate? Without answering these questions, we cannot predict system behavior, guarantee stability, or systematically design iterative architectures. We formalize agentic loops as discrete dynamical systems in semantic space. Borrowing from dynamical systems theory, we define trajectories, attractors and dynamical regimes for recursive LLM transformations, providing rigorous geometric definitions adapted to this setting. Our framework reveals that agentic loops exhibit classifiable dynamics: contractive (convergence toward stable semantic attractors), oscillatory (cycling among attractors), or exploratory (unbounded divergence). Experiments on singular loops validate the framework. Iterative paraphrasing produces contractive dynamics with measurable attractor formation and decreasing dispersion. Iterative negation produces exploratory dynamics with no stable structure. Crucially, prompt design directly controls the dynamical regime - the same model exhibits fundamentally different geometric behaviors depending solely on the transformation applied. This work establishes that iterative LLM dynamics are predictable and controllable, opening new directions for stability analysis, trajectory forecasting, and principled design of composite loops that balance convergence and exploration. --- ### REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature Authors: Wenhan Wu, Zhili He, Huanghuang Liang, Yili Gong, Jiawei Jiang, Chuang Hu, Dazhao Cheng Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10348v1 Data-protection regulations such as the GDPR grant every participant in a federated system a right to be forgotten. Federated unlearning has therefore emerged as a research frontier, aiming to remove a specific party's contribution from the learned model while preserving the utility of the remaining parties. However, most unlearning techniques focus on Horizontal Federated Learning (HFL), where data are partitioned by samples. In contrast, Vertical Federated Learning (VFL) allows organizations that possess complementary feature spaces to train a joint model without sharing raw data. The resulting feature-partitioned architecture renders HFL-oriented unlearning methods ineffective. In this paper, we propose REMISVFU, a plug-and-play representation misdirection framework that enables fast, client-level unlearning in splitVFL systems. When a deletion request arrives, the forgetting party collapses its encoder output to a randomly sampled anchor on the unit sphere, severing the statistical link between its features and the global model. To maintain utility for the remaining parties, the server jointly optimizes a retention loss and a forgetting loss, aligning their gradients via orthogonal projection to eliminate destructive interference. Evaluations on public benchmarks show that REMISVFU suppresses back-door attack success to the natural class-prior level and sacrifices only about 2.5% points of clean accuracy, outperforming state-of-the-art baselines. --- ### CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates Authors: Shresth Grover, Priyank Pathak, Akash Kumar, Yogesh S Rawat Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10342v3 Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual decision-making relatively underexplored. Addressing this gap, we introduce Corrective Sequence Planning (CoSPlan) benchmark, where VLMs must plan a sequence of visual actions from an initial scene to a target scene. CoSPlan evaluates models on their ability to imagine and execute a coherent set of visual steps required to reach the goal (Step Completion). To prevent any shortcuts that simply describe the final scene, we introduce an erroneous action in decision-making, which must be detected (Error Detection) and corrected to reach the goal, enabling a deeper understanding of the task. CoSPlan spans across 4 tasks: maze navigation, block re-arrangement, image reconstruction, and object re-organization. Despite using advanced reasoning strategies such as Chain-of-Thought and Scene Graphs, VLMs struggle on CoSPlan, while still showing promising performance in the text domain. Addressing this, we propose Scene Graph Incremental updates (SGI), a novel training-free method to transform images into `textual' scene graphs, enabling step-by-step reasoning through iterative scene graph refinement. SGI yields an average of ~4.4% improvement on CoSPlan w/ generalization on PlanBench and VQA. Link for solving puzzles on the project page. --- ### A Privacy-Preserving Cloud Architecture for Distributed Machine Learning at Scale Authors: Vinoth Punniyamoorthy, Ashok Gadi Parthi, Mayilsamy Palanigounder, Ravi Kiran Kodali, Bikesh Kumar, Kabilan Kannan Published: 2025-12-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.10341v1 Distributed machine learning systems require strong privacy guarantees, verifiable compliance, and scalable deployment across heterogeneous and multi-cloud environments. This work introduces a cloud-native privacy-preserving architecture that integrates federated learning, differential privacy, zero-knowledge compliance proofs, and adaptive governance powered by reinforcement learning. The framework supports secure model training and inference without centralizing sensitive data, while enabling cryptographically verifiable policy enforcement across institutions and cloud platforms. A full prototype deployed across hybrid Kubernetes clusters demonstrates reduced membership-inference risk, consistent enforcement of formal privacy budgets, and stable model performance under differential privacy. Experimental evaluation across multi-institution workloads shows that the architecture maintains utility with minimal overhead while providing continuous, risk-aware governance. The proposed framework establishes a practical foundation for deploying trustworthy and compliant distributed machine learning systems at scale. --- ### Learning Ordinal Degradation Representations with Textual Priors for Diffusion-Based Blind Image Super-Resolution Authors: Yi-Cheng Liao, Shyang-En Weng, Yu-Syuan Xu, Chia-Hung Yuan, Wei-Chen Chiu, Ching-Chun Huang Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10340v2 Blind image super-resolution (Blind SR) has achieved remarkable perceptual quality via generative priors. However, lacking clear degradation representations such as varying severity and mixtures, these methods fail to accurately reflect the actual degradation process. This limitation severely compromises restoration fidelity and leads to content inconsistencies, especially in diffusion-based blind SR models that rely on simple textual descriptions for contextual guidance. To bridge the gap between high-level semantics and low-level degradation artifacts, we introduce Ordinal Degradation CLIP (OD-CLIP), leveraging textual priors to enhance the learning of continuous degradation-level representations. Unlike standard CLIP text encoders, which struggle to represent numerical intensity, OD-CLIP moves beyond coarse labels by modeling unknown degradations as a continuous spectrum representing quality. By learning an ordinal embedding from low-quality inputs, our design captures both degradation types and their relative severity, explicitly modeling the degradation hierarchy and enabling interpolation across unseen levels. In our experiments, the OD-CLIP representation demonstrates stronger ordinal ranking and perceptual distance modeling compared to baseline methods. When applied to blind SR, we show that conditioning on OD-CLIP maintains fidelity and preserves content structures over existing methods in both unknown and mixed-degradation settings on real-world benchmarks. --- ### On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering Authors: Ziseok Lee, Minyeong Hwang, Wooyeol Lee, Sanghyun Jo, Jihyung Ko, Young Bin Park, Jae-Mun Choi, Eunho Yang, Kyungsu Kim Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10339v2 Inference-time steering adapts pretrained diffusion and flow models to new tasks without retraining, often utilizing ratio-of-densities constructions that reweight time-indexed marginals with fixed exponents. We identify Marginal Path Collapse, a failure mode in which the intermediate density defined by such compositions becomes non-normalizable despite valid endpoints. This collapse can arise when composing heterogeneous experts trained with mismatched noise schedules (and/or negative exponents / partial supports). To address this, we provide (i) a sharp sufficient Path Existence Criterion that characterizes when the composed intermediate densities are mathematically well-defined, and (ii) Adaptive Path Correction with Exponents (ACE), which generalizes Feynman-Kac steering to support time-varying exponents. Our analysis reveals that ACE controls the quantile radius of the intermediate distributions, providing a theoretical mechanism for path stabilization observed in experiments. On flexible-pose scaffold decoration, a drug design task composed of de-novo, conformer, and protein-conditioned experts, ACE prevents collapse and significantly outperforms constant-exponent baselines. Furthermore, ACE improves attribute success rates in compositional image generation, establishing it as a general framework for compositional sampling. Project Page: https://ziseoklee.github.io/projects/ACE/ --- ### Multilingual VLM Training: Adapting an English-Trained VLM to French Authors: Jules Lahmi, Alexis Roger Published: 2025-12-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.10336v1 Artificial intelligence has made great progress in recent years, particularly in the development of Vision--Language Models (VLMs) that understand both visual and textual data. However, these advancements remain largely limited to English, reducing their accessibility for non--English speakers. It is essential to extend these capabilities to a broader range of languages. This paper explores the challenges of adapting an English-trained VLM to different languages. To this end, we will explore and compare different methods for their performance and computational cost. We consider a translation-based pipeline, LoRA finetuning, and a two-stage finetuning strategy that separates vision adaptation from language adaptation. To evaluate these methods, we use a combination of standard multimodal benchmarks translated into the target language and manual assessments by native experts. The results reveal that dataset translation remains a major bottleneck in multilingual VLM performance, with data quality limiting the effectiveness of training and evaluation. These findings suggest that future efforts should focus on native-language dataset collection and improved translation strategies. --- ### A Conditional Generative Framework for Synthetic Data Augmentation in Segmenting Thin and Elongated Structures in Biological Images Authors: Yi Liu, Yichi Zhang Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10334v3 Thin and elongated filamentous structures, such as microtubules and actin filaments, often play important roles in biological systems. Segmenting these filaments in biological images is a fundamental step for quantitative analysis. Recent advances in deep learning have significantly improved the performance of filament segmentation. However, there is a big challenge in acquiring high quality pixel-level annotated dataset for filamentous structures, as the dense distribution and geometric properties of filaments making manual annotation extremely laborious and time-consuming. To address the data shortage problem, we propose a conditional generative framework based on the Pix2Pix architecture to generate realistic filaments in microscopy images from binary masks. We also propose a filament-aware structural loss to improve the structure similarity when generating synthetic images. Our experiments have demonstrated the effectiveness of our approach and outperformed existing model trained without synthetic data. --- ### Simple Yet Effective Selective Imputation for Incomplete Multi-view Clustering Authors: Cai Xu, Jinlong Liu, Yilin Zhang, Ziyu Guan, Wei Zhao, Xiaofei He Published: 2025-12-11 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.10327v2 Incomplete Multi-view Clustering (IMC) has emerged as a significant challenge in multi-view learning. A predominant line for IMC is data imputation; however, indiscriminate imputation can result in unreliable content. Recently, researchers have proposed selective imputation methods that use a post-imputation assessment strategy: (1) impute all or some missing values, and (2) evaluate their quality through clustering tasks. We observe that this strategy incurs substantial computational complexity and is heavily dependent on the performance of the clustering model. To address these challenges, we first introduce the concept of pre-imputation assessment. We propose an Implicit Informativeness-based Selective Imputation (SI$^3$) method for incomplete multi-view clustering, which explicitly addresses the trade-off between imputation utility and imputation risk. SI$^3$ evaluates the imputation-relevant informativeness of each missing position in a training-free manner, and selectively imputes data only when sufficient informative support is available. Under a multi-view generative assumption, SI$^3$ further integrates selective imputation into a variational inference framework, enabling uncertainty-aware imputation at the latent distribution level and robust multi-view fusion. Compared with existing selective imputation strategies, SI$^3$ is lightweight, data-driven, and model-agnostic, and can be seamlessly incorporated into existing incomplete multi-view clustering frameworks as a plug-in strategy. Extensive experiments on multiple benchmark datasets demonstrate that SI$^3$ consistently outperforms both imputation-based and imputation-free methods, particularly under challenging unbalanced missing scenarios. --- ### StainNet: Scaling Self-Supervised Foundation Models on Immunohistochemistry and Special Stains for Computational Pathology Authors: Jiawen Li, Jiali Hu, Xitong Ling, Yongqiang Lv, Yuxuan Chen, Yizhi Wang, Tian Guan, Yifei Liu, Yonghong He Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10326v2 Foundation models trained with self-supervised learning (SSL) on large-scale histological images have significantly accelerated the development of computational pathology. These models can serve as backbones for region-of-interest (ROI) image analysis or patch-level feature extractors in whole-slide images (WSIs) based on multiple instance learning (MIL). Existing pathology foundation models (PFMs) are typically pre-trained on Hematoxylin-Eosin (H\&E) stained pathology images. However, images such as immunohistochemistry (IHC) and special stains are also frequently used in clinical practice. PFMs pre-trained mainly on H\&E-stained images may be limited in clinical applications involving these non-H\&E images. To address this issue, we propose StainNet, a collection of self-supervised foundation models specifically trained for IHC and special stains in pathology images based on the vision transformer (ViT) architecture. StainNet contains a ViT-Small and a ViT-Base model, both of which are trained using a self-distillation SSL approach on over 1.4 million patch images extracted from 20,231 publicly available IHC and special staining WSIs in the HISTAI database. To evaluate StainNet models, we conduct experiments on three in-house slide-level IHC classification tasks, three in-house ROI-level special stain and two public ROI-level IHC classification tasks to demonstrate their strong ability. We also perform ablation studies such as few-ratio learning and retrieval evaluations, and compare StainNet models with recent larger PFMs to further highlight their strengths. The StainNet model weights are available at https://github.com/WonderLandxD/StainNet. --- ### Residual subspace evolution strategies for nonlinear inverse problems Authors: Francesco Alemanno Published: 2025-12-11 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2512.10325v2 Nonlinear inverse problems pervade engineering and science, yet noisy, non-differentiable, or expensive residual evaluations routinely defeat Jacobian-based solvers. Derivative-free alternatives either demand smoothness, require large populations to stabilise covariance estimates, or stall on flat regions where gradient information fades. This paper introduces residual subspace evolution strategies (RSES), a derivative-free solver that draws Gaussian probes around the current iterate, records how residuals change along those directions, and recombines the probes through a least-squares solve to produce an optimal update. The method builds a residual-only surrogate without forming Jacobians or empirical covariances, and each iteration costs just $k+1$ residual evaluations with $O(k^3)$ linear algebra overhead, where $k$ remains far smaller than the parameter dimension. Benchmarks on calibration, regression, and deconvolution tasks show that RSES reduces misfit consistently across deterministic and stochastic settings, matching or exceeding xNES, NEWUOA, Adam, and ensemble Kalman inversion under matched evaluation budgets. The gains are most pronounced when smoothness or covariance assumptions break, suggesting that lightweight residual-difference surrogates can reliably guide descent where heavier machinery struggles. --- ### EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs Authors: Chao Gong, Depeng Wang, Zhipeng Wei, Ya Guo, Huijia Zhu, Jingjing Chen Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10324v2 Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing massive, redundant audio-visual tokens. Existing unimodal compression techniques fail to capture the heterogeneous and mutually influential information density of joint audio-visual signals. Furthermore, we identify a fundamental and overlooked theoretical bottleneck in sparse token reduction: positional aliasing. We demonstrate that aggressive sparse sampling on standard position-encoded sequences violates the Nyquist limit relative to the effective token interval, causing phase-wrapping collisions that corrupt temporal monotonicity. To address this, we introduce EchoingPixels, a framework for aliasing-resistant joint token reduction. Our Cross-Modal Semantic Sieve performs extractive selection on the synergistic audio-visual stream, dynamically allocating budgets based on joint-modality saliency rather than fixed per-modality ratios. To resolve positional aliasing, we derive Sync-RoPE, a spectral low-pass filter for Rotary Positional Embeddings that adapts encoding bandwidth to the sparse sampling rate, preserving monotonic temporal relationships in the reduced stream. Experiments show that EchoingPixels achieves performance comparable to full models using only 5-20% of original tokens, validating theoretically grounded sparse learning as a robust solution for efficient AV-LLMs. Code is available at https://github.com/CharlesGong12/EchoingPixels. --- ### User-Feedback-Driven Adaptation for Vision-and-Language Navigation Authors: Yongqiang Yu, Xuhui Li, Hazza Mahmood, Jinxing Zhou, Haodong Hong, Longtao Jiang, Zhiqiang Xu, Qi Wu, Xiaojun Chang Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10322v2 Real-world deployment of Vision-and-Language Navigation (VLN) agents is constrained by the scarcity of reliable supervision after offline training. While recent adaptation methods attempt to mitigate distribution shifts via environment-driven self-supervision (e.g., entropy minimization), these signals are often noisy and can cause the agent to amplify its own mistakes during long-horizon sequential decision-making. In this paper, we propose a paradigm shift that positions user feedback, specifically episode-level success confirmations and goal-level corrections, as a primary and general-purpose supervision signal for VLN. Unlike internal confidence scores, user feedback is intent-aligned and in-situ consistent, directly correcting the agent's decoupling from user instructions. To effectively leverage this supervision, we introduce a user-feedback-driven learning framework featuring a topology-aware trajectory construction pipeline. This mechanism lifts sparse, goal-level corrections into dense path-level supervision by generating feasible paths on the agent's incrementally built topological graph, enabling sample-efficient imitation learning without requiring step-by-step human demonstrations. Furthermore, we develop a persistent memory bank mechanism for warm-start initialization, supporting the reuse of previously acquired topology and cached representations across navigation sessions. Extensive experiments on the GSA-R2R benchmark demonstrate that our approach transforms sparse interaction into robust supervision, consistently outperforming environment-driven baselines while exhibiting strong adaptability across diverse instruction styles. ---