# Research Papers — 2025-12 · bundle page 127 of 175

> Full-text markdown of papers #6301–6350 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/127
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/126.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/128.md)

### Social welfare optimisation in well-mixed and structured populations

Authors: Van An Nguyen, Vuong Khang Huynh, Ho Nam Duong, Huu Loi Bui, Hai Anh Ha, Quang Dung Le, Le Quoc Dung Ngo, Tan Dat Nguyen, Ngoc Ngu Nguyen, Hoai Thuong Nguyen, Zhao Song, Le Hong Trang et al.
Published: 2025-12-08
Categories: physics.soc-ph, cs.AI, cs.MA, math.OC, nlin.AO
arXiv: https://arxiv.org/abs/2512.07453v2

Research on promoting cooperation among autonomous, self-regarding agents has often focused on the bi-objective optimisation problem: minimising the total incentive cost while maximising the frequency of cooperation. However, the optimal value of social welfare under such constraints remains largely unexplored. In this work, we hypothesise that achieving maximal social welfare is not guaranteed at the minimal incentive cost required to drive agents to a desired cooperative state. To address this gap, we adopt to a single-objective approach focused on maximising social welfare, building upon foundational evolutionary game theory models that examined cost efficiency in finite populations, in both well-mixed and structured population settings. Our analytical model and agent-based simulations show how different interference strategies, including rewarding local versus global behavioural patterns, affect social welfare and dynamics of cooperation. Our results reveal a significant gap in the per-individual incentive cost between optimising for pure cost efficiency or cooperation frequency and optimising for maximal social welfare. Overall, our findings indicate that incentive design, policy, and benchmarking in multi-agent systems and human societies should prioritise welfare-centric objectives over proxy targets of cost or cooperation frequency.

---

### Forget and Explain: Transparent Verification of GNN Unlearning

Authors: Imran Ahsan, Hyunwook Yu, Jinsung Kim, Mucheol Kim
Published: 2025-12-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.07450v1

Graph neural networks (GNNs) are increasingly used to model complex patterns in graph-structured data. However, enabling them to "forget" designated information remains challenging, especially under privacy regulations such as the GDPR. Existing unlearning methods largely optimize for efficiency and scalability, yet they offer little transparency, and the black-box nature of GNNs makes it difficult to verify whether forgetting has truly occurred. We propose an explainability-driven verifier for GNN unlearning that snapshots the model before and after deletion, using attribution shifts and localized structural changes (for example, graph edit distance) as transparent evidence. The verifier uses five explainability metrics: residual attribution, heatmap shift, explainability score deviation, graph edit distance, and a diagnostic graph rule shift. We evaluate two backbones (GCN, GAT) and four unlearning strategies (Retrain, GraphEditor, GNNDelete, IDEA) across five benchmarks (Cora, Citeseer, Pubmed, Coauthor-CS, Coauthor-Physics). Results show that Retrain and GNNDelete achieve near-complete forgetting, GraphEditor provides partial erasure, and IDEA leaves residual signals. These explanation deltas provide the primary, human-readable evidence of forgetting; we also report membership-inference ROC-AUC as a complementary, graph-wide privacy signal.

---

### KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models

Authors: Chenwei Shi, Xueyu Luan
Published: 2025-12-08
Categories: cs.LG, cs.AI, cs.CV, cs.NE, cs.RO
arXiv: https://arxiv.org/abs/2512.07437v1

DreamerV3 is a state-of-the-art online model-based reinforcement learning (MBRL) algorithm known for remarkable sample efficiency. Concurrently, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Layer Perceptrons (MLPs), offering superior parameter efficiency and interpretability. To mitigate KANs' computational overhead, variants like FastKAN leverage Radial Basis Functions (RBFs) to accelerate inference. In this work, we investigate integrating KAN architectures into the DreamerV3 framework. We introduce KAN-Dreamer, replacing specific MLP and convolutional components of DreamerV3 with KAN and FastKAN layers. To ensure efficiency within the JAX-based World Model, we implement a tailored, fully vectorized version with simplified grid management. We structure our investigation into three subsystems: Visual Perception, Latent Prediction, and Behavior Learning. Empirical evaluations on the DeepMind Control Suite (walker_walk) analyze sample efficiency, training time, and asymptotic performance. Experimental results demonstrate that utilizing our adapted FastKAN as a drop-in replacement for the Reward and Continue predictors yields performance on par with the original MLP-based architecture, maintaining parity in both sample efficiency and training speed. This report serves as a preliminary study for future developments in KAN-based world models.

---

### LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services

Authors: Hang He, Chuhuai Yue, Chengqi Dong, Mingxue Tian, Hao Chen, Zhenfeng Liu, Jiajun Chai, Xiaohan Wang, Yufei Zhang, Qun Liao, Guojun Yin, Wei Lin et al.
Published: 2025-12-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.07436v3

Recent advances in large reasoning models LRMs have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on general information retrieval and rarely explores vertical domains with unique challenges. In this work, we focus on local life services and introduce LocalSearchBench, which encompass diverse and complex business scenarios. Real-world queries in this domain are often ambiguous and require multi-hop reasoning across merchants and products, remaining challenging and not fully addressed. As the first comprehensive benchmark for agentic search in local life services, LocalSearchBench comprises a database of over 1.3M merchant entries across 6 service categories and 9 major cities, and 900 multi-hop QA tasks from real user queries that require multi-step reasoning. We also developed LocalPlayground, a unified environment integrating multiple tools for LRMs interaction. Experiments show that even state-of-the-art LRMs struggle on LocalSearchBench: the best model (DeepSeek-V3.2) achieves only 35.60% correctness, and most models have issues with completeness (average 60.32%) and faithfulness (average 30.72%). This highlights the need for specialized benchmarks and domain-specific agent training in local life services. Code, Benchmark, and Leaderboard are available at https://localsearchbench.github.io/.

---

### Mitigating Bias in Graph Hyperdimensional Computing

Authors: Yezi Liu, William Youngwoo Chung, Yang Ni, Hanning Chen, Mohsen Imani
Published: 2025-12-08
Categories: cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2512.07433v1

Graph hyperdimensional computing (HDC) has emerged as a promising paradigm for cognitive tasks, emulating brain-like computation with high-dimensional vectors known as hypervectors. While HDC offers robustness and efficiency on graph-structured data, its fairness implications remain largely unexplored. In this paper, we study fairness in graph HDC, where biases in data representation and decision rules can lead to unequal treatment of different groups. We show how hypervector encoding and similarity-based classification can propagate or even amplify such biases, and we propose a fairness-aware training framework, FairGHDC, to mitigate them. FairGHDC introduces a bias correction term, derived from a gap-based demographic-parity regularizer, and converts it into a scalar fairness factor that scales the update of the class hypervector for the ground-truth label. This enables debiasing directly in the hypervector space without modifying the graph encoder or requiring backpropagation. Experimental results on six benchmark datasets demonstrate that FairGHDC substantially reduces demographic-parity and equal-opportunity gaps while maintaining accuracy comparable to standard GNNs and fairness-aware GNNs. At the same time, FairGHDC preserves the computational advantages of HDC, achieving up to about one order of magnitude ($\approx 10\times$) speedup in training time on GPU compared to GNN and fairness-aware GNN baselines.

---

### MIDG: Mixture of Invariant Experts with knowledge injection for Domain Generalization in Multimodal Sentiment Analysis

Authors: Yangle Li, Danli Luo, Haifeng Hu
Published: 2025-12-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.07430v1

Existing methods in domain generalization for Multimodal Sentiment Analysis (MSA) often overlook inter-modal synergies during invariant features extraction, which prevents the accurate capture of the rich semantic information within multimodal data. Additionally, while knowledge injection techniques have been explored in MSA, they often suffer from fragmented cross-modal knowledge, overlooking specific representations that exist beyond the confines of unimodal. To address these limitations, we propose a novel MSA framework designed for domain generalization. Firstly, the framework incorporates a Mixture of Invariant Experts model to extract domain-invariant features, thereby enhancing the model's capacity to learn synergistic relationships between modalities. Secondly, we design a Cross-Modal Adapter to augment the semantic richness of multimodal representations through cross-modal knowledge injection. Extensive domain experiments conducted on three datasets demonstrate that the proposed MIDG achieves superior performance.

---

### When normalization hallucinates: unseen risks in AI-powered whole slide image processing

Authors: Karel Moens, Matthew B. Blaschko, Tinne Tuytelaars, Bart Diricx, Jonas De Vylder, Mustafa Yousif
Published: 2025-12-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.07426v1

Whole slide image (WSI) normalization remains a vital preprocessing step in computational pathology. Increasingly driven by deep learning, these models learn to approximate data distributions from training examples. This often results in outputs that gravitate toward the average, potentially masking diagnostically important features. More critically, they can introduce hallucinated content, artifacts that appear realistic but are not present in the original tissue, posing a serious threat to downstream analysis. These hallucinations are nearly impossible to detect visually, and current evaluation practices often overlook them. In this work, we demonstrate that the risk of hallucinations is real and underappreciated. While many methods perform adequately on public datasets, we observe a concerning frequency of hallucinations when these same models are retrained and evaluated on real-world clinical data. To address this, we propose a novel image comparison measure designed to automatically detect hallucinations in normalized outputs. Using this measure, we systematically evaluate several well-cited normalization methods retrained on real-world data, revealing significant inconsistencies and failures that are not captured by conventional metrics. Our findings underscore the need for more robust, interpretable normalization techniques and stricter validation protocols in clinical deployment.

---

### Seismic event classification with a lightweight Fourier Neural Operator model

Authors: Ayrat Abdullin, Umair bin Waheed, Leo Eisner, Abdullatif Al-Shuhail
Published: 2025-12-08
Categories: physics.geo-ph, cs.LG
arXiv: https://arxiv.org/abs/2512.07425v2

Real-time monitoring of induced seismicity is critical to mitigate operational risks, relying on the rapid and accurate classification of triggered data from continuous data streams. Deep learning models are effective for this purpose but require substantial computational resources, making real-time processing difficult. To address this limitation, a lightweight model based on the Fourier Neural Operator (FNO) is proposed for the classification of microseismic events, leveraging its inherent resolution-invariance and computational efficiency for waveform processing. In the STanford EArthquake Dataset (STEAD), a global and large-scale database of seismic waveforms, the FNO-based model demonstrates high effectiveness for trigger classification, with an F1 score of 95% even in the scenario of data sparsity in training. The new FNO model greatly decreases the computer power needed relative to current deep learning models without sacrificing the classification success rate measured by the F1 score. A test on a real microseismic dataset shows a classification success rate with an F1 score of 98%, outperforming many traditional deep-learning techniques. The reduced computational cost makes the proposed FNO model well suited for deployment in resource-constrained, near-real-time seismic monitoring workflows, including traffic-light implementations. The source code for the proposed FNO classifier will be available at: https://github.com/ayratabd/FNOclass.

---

### KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

Authors: Md Raqibul Islam, Adrita Khan, Mir Sazzat Hossain, Choudhury Ben Yamin Siddiqui, Md. Zakir Hossan, Tanjib Khan, M. Arshad Momen, Amin Ahsan Ali, AKM Mahbubur Rahman
Published: 2025-12-08
Categories: hep-ph, cs.LG, hep-ex
arXiv: https://arxiv.org/abs/2512.07420v3

Jet identification plays a central role in analyzing data from high-energy collider experiments. While deep learning has improved jet classification, it often lacks interpretability. We introduce the Kinematic Interaction Graph Network (KIGNet), a graph neural network that integrates kinematic variables into jet classification by constructing four graph representations per jet, each weighted by a distinct variable: angular separation ($Δ$), relative transverse momentum ($k_T$), momentum fraction ($z$), and invariant mass squared ($m^2$). Three of these ($Δ$, $k_T$, $z$) are motivated by the Lund jet plane, grounded in perturbative QCD factorization; the fourth ($m^2$) adds complementary mass-scale sensitivity for heavy-flavor identification. Using Gradient-weighted Class Activation Mapping (Grad-CAM), we determine which variables dominate classification. Angular separation and relative transverse momentum account for about 76% of the total Grad-CAM attribution (40.72% and 35.67%), with momentum fraction and invariant mass contributing the remaining 24%. This hierarchy is consistent with the soft-collinear structure of QCD radiation in the training data, showing that the network learns physically interpretable representations rather than spurious correlations. On the JetClass dataset, KIGNet achieves a macro-accuracy of 95.07%, macro-AUC of 96.61%, and macro-AUPR of 81.52%, relative improvements of 2.45%, 3.40%, and 19.11% over the state-of-the-art baseline. On the Aspen Open Jets dataset of real CMS collision data, KIGNet produces substantially more structured latent representations than the baseline, reducing the Davies-Bouldin Index by 52.15% ($0.8395 \rightarrow 0.4017$) and increasing the Dunn Index by 42.33% ($0.0189 \rightarrow 0.0269$), confirming that physics-informed kinematic encoding generalizes beyond idealized simulation to experimental detector conditions.

---

### Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization

Authors: Haidong Kang, Jun Du, Guo Yu
Published: 2025-12-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.07419v3

Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing research attention. However, conventional methods either rely on costly differentiable optimization search, which is neither efficient nor flexible, or learn a quantized DNN from a proxy (e.g., HAWQ) manually designed by human experts, which is labor-intensive and requires extensive expert knowledge. Can we design a proxy without involving any human experts or training? In this paper, we provide an affirmative answer by proposing a novel Large Language Model (LLM)-driven Training-free Automatic Proxy (dubbed TAP) discovery framework. It reforms the design paradigm of MPQ by utilizing LLMs and evolutionary search strategies to automatically find superior TAP tailored for MPQ. In addition, to bridge the gap between black-box LLMs and the challenging MPQ task, we introduce a lightweight Direct Preference Optimization (DPO)-based strategy controller that dynamically reweights the selection probabilities of the three prompt templates for evolutionary search strategies according to fitness signals, without fine-tuning the LLM. This forms a task-aware feedback loop that improves proxy generation across evolutions. Extensive experiments on mainstream benchmarks demonstrate that TAP achieves state-of-the-art performance. Finally, we believe that our TAP will significantly contribute to the MPQ community by providing a new perspective on LLM-driven design algorithms.

---

### Adaptive Tuning of Parameterized Traffic Controllers via Multi-Agent Reinforcement Learning

Authors: Giray Önür, Azita Dabiri, Bart De Schutter
Published: 2025-12-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.07417v2

Effective traffic control is essential for mitigating congestion in transportation networks. Conventional traffic management strategies, including route guidance and ramp metering, often rely on state feedback controllers, which are used for their simplicity and reactivity; however, they lack the adaptability required to cope with complex and time-varying traffic dynamics. This paper proposes a multi-agent reinforcement learning (RL) framework in which each agent adaptively tunes the parameters of a state feedback traffic controller, combining the reactivity of state feedback controllers with the adaptability of RL. By tuning parameters at a lower frequency rather than directly determining control inputs at a high frequency, the RL agents achieve improved training efficiency while maintaining adaptability to varying traffic conditions. The multi-agent structure further enhances system robustness, as local controllers can operate independently in the event of partial failures. The proposed framework is evaluated on a simulated multi-class transportation network under varying traffic conditions. Results show that the proposed multi-agent framework outperforms the no-control and fixed-parameter state feedback control cases, while performing on par with the single-agent RL-based adaptive state feedback control, but with much greater resilience to disturbances.

---

### Data-driven Exploration of Mobility Interaction Patterns

Authors: Gabriele Galatolo, Mirco Nanni
Published: 2025-12-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.07415v1

Understanding the movement behaviours of individuals and the way they react to the external world is a key component of any problem that involves the modelling of human dynamics at a physical level. In particular, it is crucial to capture the influence that the presence of an individual can have on the others. Important examples of applications include crowd simulation and emergency management, where the simulation of the mass of people passes through the simulation of the individuals, taking into consideration the others as part of the general context. While existing solutions basically start from some preconceived behavioural model, in this work we propose an approach that starts directly from the data, adopting a data mining perspective. Our method searches the mobility events in the data that might be possible evidences of mutual interactions between individuals, and on top of them looks for complex, persistent patterns and time evolving configurations of events. The study of these patterns can provide new insights on the mechanics of mobility interactions between individuals, which can potentially help in improving existing simulation models. We instantiate the general methodology on two real case studies, one on cars and one on pedestrians, and a full experimental evaluation is performed, both in terms of performances, parameter sensitivity and interpretation of sample results.

---

### InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

Authors: Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang, Juze Zhang, Xin Chen, Lan Xu, Jingyi Yu, Jingya Wang
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07410v2

Humanoid agents are expected to emulate the complex coordination inherent in human social behaviors. However, existing methods are largely confined to single-agent scenarios, overlooking the physically plausible interplay essential for multi-agent interactions. To bridge this gap, we propose InterAgent, the first end-to-end framework for text-driven physics-based multi-agent humanoid control. At its core, we introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to mitigate cross-modal interference while enabling synergistic coordination. We further propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies to facilitate network learning. Additionally, within it we devise a sparse edge-based attention mechanism that dynamically prunes redundant connections and emphasizes critical inter-agent spatial relations, thereby enhancing the robustness of interaction modeling. Extensive experiments demonstrate that InterAgent consistently outperforms multiple strong baselines, achieving state-of-the-art performance. It enables producing coherent, physically plausible, and semantically faithful multi-agent behaviors from only text prompts. Our code and data will be released to facilitate future research.

---

### Training Language Models to Use Prolog as a Tool

Authors: Niklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech
Published: 2025-12-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.07407v3

Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use Prolog as an external symbolic reasoning tool, training Qwen2.5-3B-Instruct with Group Relative Policy Optimization (GRPO) on a cleaned version of GSM8K (which we release as gsm8k-prolog-prover). We systematically vary prompt structure, reward composition (execution, syntax, semantics, structure), and inference protocol (single-try, multiple-try, and two agentic modes). Our reinforcement learning approach outperforms supervised fine-tuning on GSM8K, and the resulting 3B model achieves zero-shot performance on MMLU-STEM and MMLU-Pro competitive with 7B few-shot baselines. Most importantly, we identify an accuracy--auditability trade-off: configurations tuned for correctness alone learn to delegate reasoning to natural language and use Prolog only for the final computation, while configurations rewarded for symbolic structure produce fully auditable programs at a cost in accuracy. We interpret this trade-off as a form of reward hacking and discuss its implications for deploying neurosymbolic systems in safety-critical domains. The source code for our experiments is available under https://github.com/aisilab/Prolog-as-a-Tool

---

### On LLMs' Internal Representation of Code Correctness

Authors: Francisco Ribeiro, Claudio Spiess, Prem Devanbu, Sarah Nadi
Published: 2025-12-08
Categories: cs.SE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07404v3

Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output of the generation process. Inspired by findings that LLMs internally encode concepts like truthfulness, this paper explores if LLMs similarly represent code correctness. Specifically, we identify a correctness representation inside LLMs by contrasting the hidden states between pairs of correct and incorrect code for the same programming tasks. By experimenting on four LLMs, we show that exploiting this extracted correctness representation outperforms standard log-likelihood ranking, as well as verbalized model confidence. Furthermore, we explore how this internal correctness signal can be used to select higher-quality code samples, without requiring test execution. Ultimately, this work demonstrates how leveraging internal representations can enhance code generation systems and make LLMs more reliable, thus improving confidence in automatically generated code.

---

### Heads collapse, features stay: Why Replay needs big buffers

Authors: Giulia Lanzillotta, Damiano Meier, Thomas Hofmann
Published: 2025-12-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.07400v2

A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable representations of past tasks even when their output predictions fail. We formalize this distinction as the gap between deep (feature-space) and shallow (classifier-level) forgetting. We reveal a critical asymmetry in Experience Replay: while minimal buffers successfully anchor feature geometry and prevent deep forgetting, mitigating shallow forgetting typically requires substantially larger buffer capacities. To explain this, we extend the Neural Collapse framework to the sequential setting. We characterize deep forgetting as a geometric drift toward out-of-distribution subspaces and prove that any non-zero replay fraction asymptotically guarantees the retention of linear separability. Conversely, we identify that the ``strong collapse'' induced by small buffers leads to rank-deficient covariances and inflated class means, effectively blinding the classifier to true population boundaries. By unifying CL with out-of-distribution detection, our work challenges the prevailing reliance on large buffers, suggesting that explicitly correcting these statistical artifacts could unlock robust performance with minimal replay.

---

### From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent

Authors: Ali Joundi, Yann Traonmilin, Jean-François Aujol
Published: 2025-12-08
Categories: eess.IV, cs.NE, math.OC
arXiv: https://arxiv.org/abs/2512.07397v1

We consider the problem of recovering an unknown low-dimensional vector from noisy, underdetermined observations. We focus on the Generalized Projected Gradient Descent (GPGD) framework, which unifies traditional sparse recovery methods and modern approaches using learned deep projective priors. We extend previous convergence results to robustness to model and projection errors. We use these theoretical results to explore ways to better control stability and robustness constants. To reduce recovery errors due to measurement noise, we consider generalized back-projection strategies to adapt GPGD to structured noise, such as sparse outliers. To improve the stability of GPGD, we propose a normalized idempotent regularization for the learning of deep projective priors. We provide numerical experiments in the context of sparse recovery and image inverse problems, highlighting the trade-offs between identifiability and stability that can be achieved with such methods.

---

### Reconstructing Objects along Hand Interaction Timelines in Egocentric Video

Authors: Zhifan Zhu, Siddhant Bansal, Shashank Tripathi, Dima Damen
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07394v2

We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a rigid object's perspective. In a HIT, an object is first static relative to the scene, then is held in hand following contact, where its pose changes. This is usually followed by a firm grip during use, before it is released to be static again w.r.t. to the scene. We model these pose constraints over the HIT, and propose to propagate the object's pose along the HIT enabling superior reconstruction using our proposed Constrained Optimisation and Propagation (COP) framework. Importantly, we focus on timelines with stable grasps - i.e. where the hand is stably holding an object, effectively maintaining constant contact during use. This allows us to efficiently annotate, study, and evaluate object reconstruction in videos without 3D ground truth. We evaluate our proposed task, ROHIT, over two egocentric datasets, HOT3D and in-the-wild EPIC-Kitchens. In HOT3D, we curate 1.2K clips of stable grasps. In EPIC-Kitchens, we annotate 2.4K clips of stable grasps including 390 object instances across 9 categories from videos of daily interactions in 141 environments. Without 3D ground truth, we utilise 2D projection error to assess the reconstruction. Quantitatively, COP improves stable grasp reconstruction by 6.2-11.3% and HIT reconstruction by up to 24.5% with constrained pose propagation.

---

### Empirical Results for Adjusting Truncated Backpropagation Through Time while Training Neural Audio Effects

Authors: Yann Bourdin, Pierrick Legrand, Fanny Roche
Published: 2025-12-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.07393v1

This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT hyperparameters -- sequence number, batch size, and sequence length -- and their influence on model performance. Using a convolutional-recurrent architecture, we conduct extensive experiments across datasets with and without conditionning by user controls. Results demonstrate that carefully tuning these parameters enhances model accuracy and training stability, while also reducing computational demands. Objective evaluations confirm improved performance with optimized settings, while subjective listening tests indicate that the revised TBPTT configuration maintains high perceptual quality.

---

### GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring

Authors: Đorđe Nedeljković
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07391v1

Convolutional Neural Networks (CNNs) have proven highly effective for edge and mobile vision tasks due to their computational efficiency. While many recent works seek to enhance CNNs with global contextual understanding via self-attention-based Vision Transformers, these approaches often introduce significant computational overhead. In this work, we demonstrate that it is possible to retain strong global perception without relying on computationally expensive components. We present GlimmerNet, an ultra-lightweight convolutional network built on the principle of separating receptive field diversity from feature recombination. GlimmerNet introduces Grouped Dilated Depthwise Convolutions(GDBlocks), which partition channels into groups with distinct dilation rates, enabling multi-scale feature extraction at no additional parameter cost. To fuse these features efficiently, we design a novel Aggregator module that recombines cross-group representations using grouped pointwise convolution, significantly lowering parameter overhead. With just 31K parameters and 29% fewer FLOPs than the most recent baseline, GlimmerNet achieves a new state-of-the-art weighted F1-score of 0.966 on the UAV-focused AIDERv2 dataset. These results establish a new accuracy-efficiency trade-off frontier for real-time emergency monitoring on resource-constrained UAV platforms. Our implementation is publicly available at https://github.com/djordjened92/gdd-cnn.

---

### Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood

Authors: Gilhyun Nam, Taewon Kim, Joonhyun Jeong, Eunho Yang
Published: 2025-12-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.07390v1

Test-time adaptation (TTA) enables efficient adaptation of deployed models, yet it often leads to poorly calibrated predictive uncertainty - a critical issue in high-stakes domains such as autonomous driving, finance, and healthcare. Existing calibration methods typically assume fixed models or static distributions, resulting in degraded performance under real-world, dynamic test conditions. To address these challenges, we introduce Style Invariance as a Correctness Likelihood (SICL), a framework that leverages style-invariance for robust uncertainty estimation. SICL estimates instance-wise correctness likelihood by measuring prediction consistency across style-altered variants, requiring only the model's forward pass. This makes it a plug-and-play, backpropagation-free calibration module compatible with any TTA method. Comprehensive evaluations across four baselines, five TTA methods, and two realistic scenarios with three model architecture demonstrate that SICL reduces calibration error by an average of 13 percentage points compared to conventional calibration approaches.

---

### How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline

Authors: Chunhui Zhang, Li Liu, Zhipeng Zhang, Yong Wang, Hao Wen, Xi Zhou, Shiming Ge, Yanfeng Wang
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07385v1

Unmanned Aerial Vehicles (UAVs) offer wide-ranging applications but also pose significant safety and privacy violation risks in areas like airport and infrastructure inspection, spurring the rapid development of Anti-UAV technologies in recent years. However, current Anti-UAV research primarily focuses on RGB, infrared (IR), or RGB-IR videos captured by fixed ground cameras, with little attention to tracking target UAVs from another moving UAV platform. To fill this gap, we propose a new multi-modal visual tracking task termed UAV-Anti-UAV, which involves a pursuer UAV tracking a target adversarial UAV in the video stream. Compared to existing Anti-UAV tasks, UAV-Anti-UAV is more challenging due to severe dual-dynamic disturbances caused by the rapid motion of both the capturing platform and the target. To advance research in this domain, we construct a million-scale dataset consisting of 1,810 videos, each manually annotated with bounding boxes, a language prompt, and 15 tracking attributes. Furthermore, we propose MambaSTS, a Mamba-based baseline method for UAV-Anti-UAV tracking, which enables integrated spatial-temporal-semantic learning. Specifically, we employ Mamba and Transformer models to learn global semantic and spatial features, respectively, and leverage the state space model's strength in long-sequence modeling to establish video-level long-term context via a temporal token propagation mechanism. We conduct experiments on the UAV-Anti-UAV dataset to validate the effectiveness of our method. A thorough experimental evaluation of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement in the UAV-Anti-UAV domain. The dataset and codes will be available at {\color{magenta}https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.

---

### LogicCBMs: Logic-Enhanced Concept-Based Learning

Authors: Deepika SN Vemuri, Gautham Bellamkonda, Aditya Pola, Vineeth N Balasubramanian
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07383v1

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring predictions as a linear combination of semantic concepts. However, a linear combination is inherently limiting. So we propose the enhancement of concept-based learning models through propositional logic. We introduce a logic module that is carefully designed to connect the learned concepts from CBMs through differentiable logic operations, such that our proposed LogicCBM can go beyond simple weighted combinations of concepts to leverage various logical operations to yield the final predictions, while maintaining end-to-end learnability. Composing concepts using a set of logic operators enables the model to capture inter-concept relations, while simultaneously improving the expressivity of the model in terms of logic operations. Our empirical studies on well-known benchmarks and synthetic datasets demonstrate that these models have better accuracy, perform effective interventions and are highly interpretable.

---

### Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects

Authors: Shuohan Tao, Boyao Zhou, Hanzhang Tu, Yuwang Wang, Yebin Liu
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07381v1

3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly in sparse-view and dynamic scene reconstruction. We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera. Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces. Gaussian subdivision is guided by an adaptive face subdivision strategy driven by a detail-aware loss function. Additionally, we leverage priors from a reconstruction foundation model to initialize Gaussian deformations, enabling robust reconstruction of general dynamic objects from a single static camera, previously extremely challenging for optimization-based methods. Our method outperforms previous SOTA method, reducing LPIPS by 29.1% and Chamfer distance by 49.2% on appearance and mesh reconstruction tasks.

---

### Enhancing Small Object Detection with YOLO: A Novel Framework for Improved Accuracy and Efficiency

Authors: Mahila Moghadami, Mohammad Ali Keyvanrad, Melika Sabaghian
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07379v1

This paper investigates and develops methods for detecting small objects in large-scale aerial images. Current approaches for detecting small objects in aerial images often involve image cropping and modifications to detector network architectures. Techniques such as sliding window cropping and architectural enhancements, including higher-resolution feature maps and attention mechanisms, are commonly employed. Given the growing importance of aerial imagery in various critical and industrial applications, the need for robust frameworks for small object detection becomes imperative. To address this need, we adopted the base SW-YOLO approach to enhance speed and accuracy in small object detection by refining cropping dimensions and overlap in sliding window usage and subsequently enhanced it through architectural modifications. we propose a novel model by modifying the base model architecture, including advanced feature extraction modules in the neck for feature map enhancement, integrating CBAM in the backbone to preserve spatial and channel information, and introducing a new head to boost small object detection accuracy. Finally, we compared our method with SAHI, one of the most powerful frameworks for processing large-scale images, and CZDet, which is also based on image cropping, achieving significant improvements in accuracy. The proposed model achieves significant accuracy gains on the VisDrone2019 dataset, outperforming baseline YOLOv5L detection by a substantial margin. Specifically, the final proposed model elevates the mAP .5.5 accuracy on the VisDrone2019 dataset from the base accuracy of 35.5 achieved by the YOLOv5L detector to 61.2. Notably, the accuracy of CZDet, which is another classic method applied to this dataset, is 58.36. This research demonstrates a significant improvement, achieving an increase in accuracy from 35.5 to 61.2.

---

### LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples

Authors: Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani
Published: 2025-12-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.07375v1

Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes it hard to handle privacy, bias mitigation, and knowledge correction. Traditional model unlearning approaches require computationally expensive fine-tuning or direct weight editing, making them impractical for real-world deployment. In this work, we introduce LoRA-based Unlearning with Negative Examples (LUNE), a lightweight framework that performs negative-only unlearning by updating only low-rank adapters while freezing the backbone, thereby localizing edits and avoiding disruptive global changes. Leveraging Low-Rank Adaptation (LoRA), LUNE targets intermediate representations to suppress (or replace) requested knowledge with an order-of-magnitude lower compute and memory than full fine-tuning or direct weight editing. Extensive experiments on multiple factual unlearning tasks show that LUNE: (I) achieves effectiveness comparable to full fine-tuning and memory-editing methods, and (II) reduces computational cost by about an order of magnitude.

---

### Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning

Authors: Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani
Published: 2025-12-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.07374v1

Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require full-model fine-tuning or access to the original training data, which limits their scalability and practicality. In this work, we introduce Recover-to-Forget (R2F), a novel framework for efficient unlearning in LLMs based on reconstructing full-model gradient directions from low-rank LoRA adapter updates. Rather than performing backpropagation through the full model, we compute gradients with respect to LoRA parameters using multiple paraphrased prompts and train a gradient decoder to approximate the corresponding full-model gradients. To ensure applicability to larger or black-box models, the decoder is trained on a proxy model and transferred to target models. We provide a theoretical analysis of cross-model generalization and demonstrate that our method achieves effective unlearning while preserving general model performance. Experimental results demonstrate that R2F offers a scalable and lightweight alternative for unlearning in pretrained LLMs without requiring full retraining or access to internal parameters.

---

### ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning

Authors: Byung-ju Kim, Jinu Pahk, Chungwoo Lee, Jaejoon Kim, Jangha Lee, Theo Taeyeong Kim, Kyuhwan Shim, Jun Ki Lee, Byoung-Tak Zhang
Published: 2025-12-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.07371v3

Behavior-cloning based visuomotor policies enable precise manipulation but often inherit the slow, cautious tempo of human demonstrations, limiting practical deployment. However, prior studies on acceleration methods mainly rely on statistical or heuristic cues that ignore task semantics and can fail across diverse manipulation settings. We present ESPADA, a semantic and spatially aware framework that segments demonstrations using a VLM-LLM pipeline with 3D gripper-object relations, enabling aggressive downsampling only in non-critical segments while preserving precision-critical phases, without requiring extra data or architectural modifications, or any form of retraining. To scale from a single annotated episode to the full dataset, ESPADA propagates segment labels via Dynamic Time Warping (DTW) on dynamics-only features. Across both simulation and real-world experiments with ACT and DP baselines, ESPADA achieves approximately a 2x speed-up while maintaining success rates, narrowing the gap between human demonstrations and efficient robot control.

---

### Multilingual corpora for the study of new concepts in the social sciences and humanities:

Authors: Revekka Kyriakoglou, Anna Pappa
Published: 2025-12-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.07367v1

This article presents a hybrid methodology for building a multilingual corpus designed to support the study of emerging concepts in the humanities and social sciences (HSS), illustrated here through the case of ``non-technological innovation''. The corpus relies on two complementary sources: (1) textual content automatically extracted from company websites, cleaned for French and English, and (2) annual reports collected and automatically filtered according to documentary criteria (year, format, duplication). The processing pipeline includes automatic language detection, filtering of non-relevant content, extraction of relevant segments, and enrichment with structural metadata. From this initial corpus, a derived dataset in English is created for machine learning purposes. For each occurrence of a term from the expert lexicon, a contextual block of five sentences is extracted (two preceding and two following the sentence containing the term). Each occurrence is annotated with the thematic category associated with the term, enabling the construction of data suitable for supervised classification tasks. This approach results in a reproducible and extensible resource, suitable both for analyzing lexical variability around emerging concepts and for generating datasets dedicated to natural language processing applications.

---

### An Asynchronous Mixed-Signal Resonate-and-Fire Neuron

Authors: Giuseppe Leo, Paolo Gibertini, Irem Ilter, Erika Covi, Ole Richter, Elisabetta Chicca
Published: 2025-12-08
Categories: eess.SP, cs.NE
arXiv: https://arxiv.org/abs/2512.07361v1

Analog computing at the edge is an emerging strategy to limit data storage and transmission requirements, as well as energy consumption, and its practical implementation is in its initial stages of development. Translating properties of biological neurons into hardware offers a pathway towards low-power, real-time edge processing. Specifically, resonator neurons offer selectivity to specific frequencies as a potential solution for temporal signal processing. Here, we show a fabricated Complementary Metal-Oxide-Semiconductor (CMOS) mixed-signal Resonate-and-Fire (R&F) neuron circuit implementation that emulates the behavior of these neural cells responsible for controlling oscillations within the central nervous system. We integrate the design with asynchronous handshake capabilities, perform comprehensive variability analyses, and characterize its frequency detection functionality. Our results demonstrate the feasibility of large-scale integration within neuromorphic systems, thereby advancing the exploitation of bio-inspired circuits for efficient edge temporal signal processing.

---

### Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation

Authors: Qiming Huang, Hao Ai, Jianbo Jiao
Published: 2025-12-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.07360v1

Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific training. However, due to CLIP's pre-training nature on image-text pairs, it tends to focus on global semantic alignment, resulting in suboptimal performance when associating fine-grained visual regions with text. This leads to noisy and inconsistent predictions, particularly in local areas. We attribute this to a dispersed bias stemming from its contrastive training paradigm, which is difficult to alleviate using CLIP features alone. To address this, we propose a structure-aware feature rectification approach that incorporates instance-specific priors derived directly from the image. Specifically, we construct a region adjacency graph (RAG) based on low-level features (e.g., colour and texture) to capture local structural relationships and use it to refine CLIP features by enhancing local discrimination. Extensive experiments show that our method effectively suppresses segmentation noise, improves region-level consistency, and achieves strong performance on multiple open-vocabulary segmentation benchmarks.

---

### A Geometric Unification of Concept Learning with Concept Cones

Authors: Alexandre Rocchi, Thomas Fel, Gianni Franchi
Published: 2025-12-08
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.07355v2

Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge. While CBMs use supervision to align activations with human-labeled concepts, SAEs rely on sparse coding to uncover emergent ones. We show that both paradigms instantiate the same geometric structure: each learns a set of linear directions in activation space whose nonnegative combinations form a concept cone. Supervised and unsupervised methods thus differ not in kind but in how they select this cone. Building on this view, we propose an operational bridge between the two paradigms. CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs. This containment framework yields quantitative metrics linking inductive biases -- such as SAE type, sparsity, or expansion ratio -- to emergence of plausible\footnote{We adopt the terminology of \citet{jacovi2020towards}, who distinguish between faithful explanations (accurately reflecting model computations) and plausible explanations (aligning with human intuition and domain knowledge). CBM concepts are plausible by construction -- selected or annotated by humans -- though not necessarily faithful to the true latent factors that organise the data manifold.} concepts. Using these metrics, we uncover a ``sweet spot'' in both sparsity and expansion factor that maximizes both geometric and semantic alignment with CBM concepts. Overall, our work unifies supervised and unsupervised concept discovery through a shared geometric framework, providing principled metrics to measure SAE progress and assess how well discovered concept align with plausible human concepts.

---

### DeepAgent: A Dual Stream Multi Agent Fusion for Robust Multimodal Deepfake Detection

Authors: Sayeem Been Zaman, Wasimul Karim, Arefin Ittesafun Abian, Reem E. Mohamed, Md Rafiqul Islam, Asif Karim, Sami Azam
Published: 2025-12-08
Categories: cs.CV, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2512.07351v1

The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which remains vulnerable to modality mismatches, noise, and manipulation. To address this gap, we propose DeepAgent, an advanced multi-agent collaboration framework that simultaneously incorporates both visual and audio modalities for the effective detection of deepfakes. DeepAgent consists of two complementary agents. Agent-1 examines each video with a streamlined AlexNet-based CNN to identify the symbols of deepfake manipulation, while Agent-2 detects audio-visual inconsistencies by combining acoustic features, audio transcriptions from Whisper, and frame-reading sequences of images through EasyOCR. Their decisions are fused through a Random Forest meta-classifier that improves final performance by taking advantage of the different decision boundaries learned by each agent. This study evaluates the proposed framework using three benchmark datasets to demonstrate both component-level and fused performance. Agent-1 achieves a test accuracy of 94.35% on the combined Celeb-DF and FakeAVCeleb datasets. On the FakeAVCeleb dataset, Agent-2 and the final meta-classifier attain accuracies of 93.69% and 81.56%, respectively. In addition, cross-dataset validation on DeepFakeTIMIT confirms the robustness of the meta-classifier, which achieves a final accuracy of 97.49%, and indicates a strong capability across diverse datasets. These findings confirm that hierarchy-based fusion enhances robustness by mitigating the weaknesses of individual modalities and demonstrate the effectiveness of a multi-agent approach in addressing diverse types of manipulations in deepfakes.

---

### MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition

Authors: Xinyu Wei, Kangrui Cen, Hongyang Wei, Zhen Guo, Kai Cui, Bairui Li, Zeqing Wang, Jinrui Zhang, Lei Zhang
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07348v2

In controllable image generation, synthesizing coherent and consistent images from multiple reference inputs, i.e., Multi-Image Composition (MICo), remains a challenging problem, partly hindered by the lack of high-quality training data. To bridge this gap, we conduct a systematic study of MICo, categorizing it into 7 representative tasks and curate a large-scale collection of high-quality source images and construct diverse MICo prompts. Leveraging powerful proprietary models, we synthesize a rich amount of balanced composite images, followed by human-in-the-loop filtering and refinement, resulting in MICo-150K, a comprehensive dataset for MICo with identity consistency. We further build a Decomposition-and-Recomposition (De&Re) subset, where 11K real-world complex images are decomposed into components and recomposed, enabling both real and synthetic compositions. To enable comprehensive evaluation, we construct MICo-Bench with 100 cases per task and 300 challenging De&Re cases, and further introduce a new metric, Weighted-Ref-VIEScore, specifically tailored for MICo evaluation. Finally, we fine-tune multiple models on MICo-150K and evaluate them on MICo-Bench. The results show that MICo-150K effectively equips models without MICo capability and further enhances those with existing skills. Notably, our baseline model, Qwen-MICo, fine-tuned from Qwen-Image-Edit, matches Qwen-Image-2509 in 3-image composition while supporting arbitrary multi-image inputs beyond the latter's limitation. Our dataset, benchmark, and baseline collectively offer valuable resources for further research on Multi-Image Composition.

---

### Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splatting

Authors: Shilong Jin, Haoran Duan, Litao Hua, Wentao Huang, Yuan Zhou
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07345v2

Versatile 3D tasks (e.g., generation or editing) that distill from Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations resulting from prior view bias, which produces conflicting appearances between different views of an object. This bias causes subject-words to preferentially activate prior view features during cross-attention (CA) computation, regardless of the target view condition. To overcome this limitation, we conduct a comprehensive mathematical analysis to reveal the root cause of the prior view bias in T2I models. Moreover, we find different UNet layers show different effects of prior view in CA. Therefore, we propose a novel framework, TD-Attn, which addresses multi-view inconsistency via two key components: (1) the 3D-Aware Attention Guidance Module (3D-AAG) constructs a view-consistent 3D attention Gaussian for subject-words to enforce spatial consistency across attention-focused regions, thereby compensating for the limited spatial information in 2D individual view CA maps; (2) the Hierarchical Attention Modulation Module (HAM) utilizes a Semantic Guidance Tree (SGT) to direct the Semantic Response Profiler (SRP) in localizing and modulating CA layers that are highly responsive to view conditions, where the enhanced CA maps further support the construction of more consistent 3D attention Gaussians. Notably, HAM facilitates semantic-specific interventions, enabling controllable and precise 3D editing. Extensive experiments firmly establish that TD-Attn has the potential to serve as a universal plugin, significantly enhancing multi-view consistency across 3D tasks.

---

### Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding

Authors: Shengyuan Ye, Bei Ouyang, Tianyi Qian, Liekang Zeng, Mu Yuan, Xiaowen Chu, Weijie Hong, Xu Chen
Published: 2025-12-08
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.07344v2

Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing VLMs' reasoning power in these cases, deployment constraints are overlooked, leading to overwhelming system overhead in real-world deployments. To address that, we propose Venus, an on-device memory-and-retrieval system for efficient online video understanding. Venus proposes an edge-cloud disaggregated architecture that sinks memory construction and keyframe retrieval from cloud to edge, operating in two stages. In the ingestion stage, Venus continuously processes streaming edge videos via scene segmentation and clustering, where the selected keyframes are embedded with a multimodal embedding model to build a hierarchical memory for efficient storage and retrieval. In the querying stage, Venus indexes incoming queries from memory, and employs a threshold-based progressive sampling algorithm for keyframe selection that enhances diversity and adaptively balances system cost and reasoning accuracy. Our extensive evaluation shows that Venus achieves a 15x-131x speedup in total response latency compared to state-of-the-art methods, enabling real-time responses within seconds while maintaining comparable or even superior reasoning accuracy.

---

### PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning

Authors: Chen Gong, Zheng Liu, Kecen Li, Tianhao Wang
Published: 2025-12-08
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.07342v2

Recently, offline reinforcement learning (RL) has become a popular RL paradigm. In offline RL, data providers share pre-collected datasets -- either as individual transitions or sequences of transitions forming trajectories -- to enable the training of RL models (also called agents) without direct interaction with the environments. Offline RL saves interactions with environments compared to traditional RL, and has been effective in critical areas, such as navigation tasks. Meanwhile, concerns about privacy leakage from offline RL datasets have emerged. To safeguard private information in offline RL datasets, we propose the first differential privacy (DP) offline dataset synthesis method, PrivORL, which leverages a diffusion model and diffusion transformer to synthesize transitions and trajectories, respectively, under DP. The synthetic dataset can then be securely released for downstream analysis and research. PrivORL adopts the popular approach of pre-training a synthesizer on public datasets, and then fine-tuning on sensitive datasets using DP Stochastic Gradient Descent (DP-SGD). Additionally, PrivORL introduces curiosity-driven pre-training, which uses feedback from the curiosity module to diversify the synthetic dataset and thus can generate diverse synthetic transitions and trajectories that closely resemble the sensitive dataset. Extensive experiments on five sensitive offline RL datasets show that our method achieves better utility and fidelity in both DP transition and trajectory synthesis compared to baselines. The replication package is available at the GitHub repository.

---

### Generalized Referring Expression Segmentation on Aerial Photos

Authors: Luís Marnoto, Alexandre Bernardino, Bruno Martins
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07338v1

Referring expression segmentation is a fundamental task in computer vision that integrates natural language understanding with precise visual localization of target regions. Considering aerial imagery (e.g., modern aerial photos collected through drones, historical photos from aerial archives, high-resolution satellite imagery, etc.) presents unique challenges because spatial resolution varies widely across datasets, the use of color is not consistent, targets often shrink to only a few pixels, and scenes contain very high object densities and objects with partial occlusions. This work presents Aerial-D, a new large-scale referring expression segmentation dataset for aerial imagery, comprising 37,288 images with 1,522,523 referring expressions that cover 259,709 annotated targets, spanning across individual object instances, groups of instances, and semantic regions covering 21 distinct classes that range from vehicles and infrastructure to land coverage types. The dataset was constructed through a fully automatic pipeline that combines systematic rule-based expression generation with a Large Language Model (LLM) enhancement procedure that enriched both the linguistic variety and the focus on visual details within the referring expressions. Filters were additionally used to simulate historic imaging conditions for each scene. We adopted the RSRefSeg architecture, and trained models on Aerial-D together with prior aerial datasets, yielding unified instance and semantic segmentation from text for both modern and historical images. Results show that the combined training achieves competitive performance on contemporary benchmarks, while maintaining strong accuracy under monochrome, sepia, and grainy degradations that appear in archival aerial photography. The dataset, trained models, and complete software pipeline are publicly available at https://luispl77.github.io/aerial-d .

---

### Machine learning in an expectation-maximisation framework for nowcasting

Authors: Paul Wilsens, Katrien Antonio, Gerda Claeskens
Published: 2025-12-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.07335v1

Decision making often occurs in the presence of incomplete information, leading to the under- or overestimation of risk. Leveraging the observable information to learn the complete information is called nowcasting. In practice, incomplete information is often a consequence of reporting or observation delays. In this paper, we propose an expectation-maximisation (EM) framework for nowcasting that uses machine learning techniques to model both the occurrence as well as the reporting process of events. We allow for the inclusion of covariate information specific to the occurrence and reporting periods as well as characteristics related to the entity for which events occurred. We demonstrate how the maximisation step and the information flow between EM iterations can be tailored to leverage the predictive power of neural networks and (extreme) gradient boosting machines (XGBoost). With simulation experiments, we show that we can effectively model both the occurrence and reporting of events when dealing with high-dimensional covariate information. In the presence of non-linear effects, we show that our methodology outperforms existing EM-based nowcasting frameworks that use generalised linear models in the maximisation step. Finally, we apply the framework to the reporting of Argentinian Covid-19 cases, where the XGBoost-based approach again is most performant.

---

### Local-Curvature-Aware Knowledge Graph Embedding: An Extended Ricci Flow Approach

Authors: Zhengquan Luo, Guy Tadmor, Or Amar, David Zeevi, Zhiqiang Xu
Published: 2025-12-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.07332v2

Knowledge graph embedding (KGE) relies on the geometry of the embedding space to encode semantic and structural relations. Existing methods place all entities on one homogeneous manifold, Euclidean, spherical, hyperbolic, or their product/multi-curvature variants, to model linear, symmetric, or hierarchical patterns. Yet a predefined, homogeneous manifold cannot accommodate the sharply varying curvature that real-world graphs exhibit across local regions. Since this geometry is imposed a priori, any mismatch with the knowledge graph's local curvatures will distort distances between entities and hurt the expressiveness of the resulting KGE. To rectify this, we propose RicciKGE to have the KGE loss gradient coupled with local curvatures in an extended Ricci flow such that entity embeddings co-evolve dynamically with the underlying manifold geometry towards mutual adaptation. Theoretically, when the coupling coefficient is bounded and properly selected, we rigorously prove that i) all the edge-wise curvatures decay exponentially, meaning that the manifold is driven toward the Euclidean flatness; and ii) the KGE distances strictly converge to a global optimum, which indicates that geometric flattening and embedding optimization are promoting each other. Experimental improvements on link prediction and node classification benchmarks demonstrate RicciKGE's effectiveness in adapting to heterogeneous knowledge graph structures.

---

### The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers

Authors: Kanishk Awadhiya
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07331v2

Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a "U-shaped" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this "Inductive Bottleneck" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DINO-trained ViTs across datasets of varying compositional complexity (UC Merced, Tiny ImageNet, and CIFAR-100), we show that the depth of the bottleneck correlates strongly with the semantic abstraction required by the task. We find that while texture-heavy datasets preserve high-rank representations throughout, object-centric datasets drive the network to dampen high-frequency information in middle layers, effectively "learning" a bottleneck to isolate semantic features.

---

### Two-dimensional RMSD projections for reaction path visualization and validation

Authors: Rohit Goswami
Published: 2025-12-08
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2512.07329v4

Transition state or minimum energy path finding methods constitute a routine component of the computational chemistry toolkit. Standard analysis involves trajectories conventionally plotted in terms of the relative energy to the initial state against a cumulative displacement variable, or the image number. These dimensional reductions obscure structural rearrangements in high dimensions and are often history dependent. This precludes the ability to compare optimization histories of different methods beyond the number of calculations, time taken, and final saddle geometry. We present a method mapping trajectories onto a two-dimensional projection defined by a permutation corrected root mean square deviation from the reactant and product configurations. Energy is represented as an interpolated color-mapped surface constructed from all optimization steps using a gradient-enhanced Gaussian Process with the inverse multiquadric kernel, whose posterior variance contours delineate data-supported regions from extrapolated ones. A rotated coordinate frame decomposes the RMSD plane into reaction progress and orthogonal distance. We show the utility of the framework on a cycloaddition reaction, where a machine-learned potential saddle and density functional theory reference lie on comparable energy contours despite geometric displacements, along with the ratification of the visualization for more complex reactions, a Grignard rearrangement, and a conrotatory bicyclobutane ring opening.

---

### ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation

Authors: Ziyang Mai, Yu-Wing Tai
Published: 2025-12-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.07328v2

Text-to-video generation has advanced rapidly, yet preserving a character's holistic appearance from a single reference image remains challenging, particularly when the character undergoes large pose, motion, and scene changes. Existing reference-conditioned approaches primarily treat the reference image as a conditioning signal, which can weaken fine-grained appearance information as reference and noisy video tokens interact during denoising. We propose \textbf{ContextAnyone}, a context-aware diffusion framework that instead treats the reference as an explicitly preserved appearance anchor. Our key idea is to jointly reconstruct the reference image and generate the target video within a shared diffusion transformer, providing direct supervision for preserving identity and fine-grained appearance throughout denoising. To maintain the reference as a stable source of appearance information, we further introduce asymmetric information flow that allows video tokens to selectively access reference tokens while preventing noisy video features from propagating back to the reference branch. We complement this design with Gap-RoPE, which separates the positional representations of the reference and generated video tokens. Experiments on a benchmark constructed from OpenVid-HD demonstrate that ContextAnyone improves both identity and fine-grained appearance consistency over existing reference-conditioned baselines while maintaining motion characteristics close to the underlying text-to-video generator.

---

### M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling

Authors: Yuxiao Luo, Songming Zhang, Sijie Ruan, Siran Chen, Kang Liu, Yang Xu, Yu Zheng, Ling Yin
Published: 2025-12-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07314v1

Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR.

---

### Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach

Authors: Bosun Kang, Hyejun Park, Chenglin Fan
Published: 2025-12-08
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2512.07313v1

We revisit the classic ski rental problem through the lens of Bayesian decision-making and machine-learned predictions. While traditional algorithms minimize worst-case cost without assumptions, and recent learning-augmented approaches leverage noisy forecasts with robustness guarantees, our work unifies these perspectives. We propose a discrete Bayesian framework that maintains exact posterior distributions over the time horizon, enabling principled uncertainty quantification and seamless incorporation of expert priors. Our algorithm achieves prior-dependent competitive guarantees and gracefully interpolates between worst-case and fully-informed settings. Our extensive experimental evaluation demonstrates superior empirical performance across diverse scenarios, achieving near-optimal results under accurate priors while maintaining robust worst-case guarantees. This framework naturally extends to incorporate multiple predictions, non-uniform priors, and contextual information, highlighting the practical advantages of Bayesian reasoning in online decision problems with imperfect predictions.

---

### DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management

Authors: Zhongchun Zhou, Chengtao Lai, Yuhang Gu, Wei Zhang
Published: 2025-12-08
Categories: cs.AR, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2512.07312v2

The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and their asynchronous management, we investigate the opposite point of the design spectrum: a multi-core AI accelerator equipped with a shared system-level cache and application-aware management policies, which keeps the programming effort modest. Our approach exploits dataflow information available in the software stack to guide cache replacement (including dead-block prediction), in concert with bypass decisions and mechanisms that alleviate cache thrashing. We assess the proposal using a cycle-accurate simulator and observe substantial performance gains (up to 1.80x speedup) compared with conventional cache architectures. In addition, we build and validate an analytical model that takes into account the actual overlapping behaviors to extend the measurement results of our policies to real-world larger-scale workloads. Experiment results show that when functioning together, our bypassing and thrashing mitigation strategies can handle scenarios both with and without inter-core data sharing and achieve remarkable speedups. Finally, we implement the design in RTL and the area of our design is $\mathbf{0.064mm^2}$ with 15nm process, which can run at 2 GHz clock frequency. Our findings explore the potential of the shared cache design to assist the development of future AI accelerator systems.

---

### Towards a Relationship-Aware Transformer for Tabular Data

Authors: Andrei V. Konstantinov, Valerii A. Zuev, Lev V. Utkin
Published: 2025-12-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.07310v1

Deep learning models for tabular data typically do not allow for imposing a graph of external dependencies between samples, which can be useful for accounting for relatedness in tasks such as treatment effect estimation. Graph neural networks only consider adjacent nodes, making them difficult to apply to sparse graphs. This paper proposes several solutions based on a modified attention mechanism, which accounts for possible relationships between data points by adding a term to the attention matrix. Our models are compared with each other and the gradient boosting decision trees in a regression task on synthetic and real-world datasets, as well as in a treatment effect estimation task on the IHDP dataset.

---

### Radiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals

Authors: Guosheng Wang, Shen Wang, Lei Yang
Published: 2025-12-08
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2512.07309v2

Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness, existing localization models still face major challenges in cross-scene generalization due to their reliance on scene-specific labeled data. To address this, we introduce Radiance-Field Reinforced Pretraining (RFRP). This novel self-supervised pretraining framework couples a large localization model (LM) with a neural radio-frequency radiance field (RF-NeRF) in an asymmetrical autoencoder architecture. In this design, the LM encodes received RF spectra into latent, position-relevant representations, while the RF-NeRF decodes them to reconstruct the original spectra. This alignment between input and output enables effective representation learning using large-scale, unlabeled RF data, which can be collected continuously with minimal effort. To this end, we collected RF samples at 7,327,321 positions across 100 diverse scenes using four common wireless technologies--RFID, BLE, WiFi, and IIoT. Data from 75 scenes were used for training, and the remaining 25 for evaluation. Experimental results show that the RFRP-pretrained LM reduces localization error by over 40% compared to non-pretrained models and by 21% compared to those pretrained using supervised learning.

---

### Exact Synthetic Populations for Scalable Societal and Market Modeling

Authors: Thierry Petit, Arnault Pachot
Published: 2025-12-08
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07306v1

We introduce a constraint-programming framework for generating synthetic populations that reproduce target statistics with high precision while enforcing full individual consistency. Unlike data-driven approaches that infer distributions from samples, our method directly encodes aggregated statistics and structural relations, enabling exact control of demographic profiles without requiring any microdata. We validate the approach on official demographic sources and study the impact of distributional deviations on downstream analyses. This work is conducted within the Pollitics project developed by Emotia, where synthetic populations can be queried through large language models to model societal behaviors, explore market and policy scenarios, and provide reproducible decision-grade insights without personal data.

---

### Reevaluating Automated Wildlife Species Detection: A Reproducibility Study on a Custom Image Dataset

Authors: Tobias Abraham Haider
Published: 2025-12-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.07305v1

This study revisits the findings of Carl et al., who evaluated the pre-trained Google Inception-ResNet-v2 model for automated detection of European wild mammal species in camera trap images. To assess the reproducibility and generalizability of their approach, we reimplemented the experiment from scratch using openly available resources and a different dataset consisting of 900 images spanning 90 species. After minimal preprocessing, we obtained an overall classification accuracy of 62%, closely aligning with the 71% reported in the original work despite differences in datasets. As in the original study, per-class performance varied substantially, as indicated by a macro F1 score of 0.28,highlighting limitations in generalization when labels do not align directly with ImageNet classes. Our results confirm that pretrained convolutional neural networks can provide a practical baseline for wildlife species identification but also reinforce the need for species-specific adaptation or transfer learning to achieve consistent, high-quality predictions.

---