# Research Papers — 2025-12 · bundle page 89 of 175 > Full-text markdown of papers #4401–4450 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/89 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/88.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/90.md) ### Complexity of Markov Chain Monte Carlo for Generalized Linear Models Authors: Martin Chak, Giacomo Zanella Published: 2025-12-14 Categories: stat.CO, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.12748v2 Markov Chain Monte Carlo (MCMC), Laplace approximation (LA) and variational inference (VI) methods are popular approaches to Bayesian inference, each with trade-offs between computational cost and accuracy. However, a theoretical understanding of these differences is missing, particularly when both the sample size $n$ and the dimension $d$ are large. LA and Gaussian VI are justified by Bernstein-von Mises (BvM) theorems, and recent work has derived the characteristic condition $n\gg d^2$ for their validity, improving over the condition $n\gg d^3$. In this paper, we show for linear, logistic and Poisson regression that for $n\gtrsim d$, MCMC attains the same complexity scaling in $n$, $d$ as first-order optimization algorithms, up to sub-polynomial factors. Thus MCMC is competitive with LA and Gaussian VI in complexity, under a scaling between $n$ and $d$ more general than BvM regimes. Our complexities apply to appropriately scaled priors that are not necessarily Gaussian-tailed, including Student-$t$ and flat priors, with log-posteriors that are not necessarily globally concave or gradient-Lipschitz. --- ### Complexity of Markov Chain Monte Carlo for Generalized Linear Models Authors: Martin Chak, Giacomo Zanella Published: 2025-12-14 Categories: stat.CO, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.12748v1 Markov Chain Monte Carlo (MCMC), Laplace approximation (LA) and variational inference (VI) methods are popular approaches to Bayesian inference, each with trade-offs between computational cost and accuracy. However, a theoretical understanding of these differences is missing, particularly when both the sample size $n$ and the dimension $d$ are large. LA and Gaussian VI are justified by Bernstein-von Mises (BvM) theorems, and recent work has derived the characteristic condition $n\gg d^2$ for their validity, improving over the condition $n\gg d^3$. In this paper, we show for linear, logistic and Poisson regression that for $n\gtrsim d$, MCMC attains the same complexity scaling in $n$, $d$ as first-order optimization algorithms, up to sub-polynomial factors. Thus MCMC is competitive with LA and Gaussian VI in complexity, under a scaling between $n$ and $d$ more general than BvM regimes. Our complexities apply to appropriately scaled priors that are not necessarily Gaussian-tailed, including Student-$t$ and flat priors, with log-posteriors that are not necessarily globally concave or gradient-Lipschitz. --- ### Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity Authors: Haotian Xu, Jiannan Yang, Tian Gao, Tsui-Wei Weng, Tengfei Ma Published: 2025-12-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12744v4 Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this failure stems from representational instability: *activation sparsity disrupts input-dependent activation learned during pretraining, inducing distribution shifts in hidden states.* We address this issue by reframing activation sparsity as a representational alignment problem and introducing **Spontaneous Neurons (SPON)**, a lightweight mechanism inspired by spontaneous neural activity in biological systems. SPON injects a small set of learnable, input-independent activation vectors that act as persistent representational anchors for sparse computation. These vectors are trained via distribution matching to the dense model and can be absorbed into bias terms after training, incurring negligible inference overhead. Across multiple LLM backbones, SPON consistently restores performance, stabilizes latent representations, and preserves generalization. Our results establish SPON as an effective and principled solution for reliable activation-sparse inference, and offer new insights into knowledge retention in LLMs. --- ### Resting Neurons, Active Insights: Improving Input Sparsification for Large Language Models Authors: Haotian Xu, Tian Gao, Tsui-Wei Weng, Tengfei Ma Published: 2025-12-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12744v1 Large Language Models (LLMs) achieve state-of-the-art performance across a wide range of applications, but their massive scale poses significant challenges for both efficiency and interpretability. Structural pruning, which reduces model size by removing redundant computational units such as neurons, has been widely explored as a solution, and this study devotes to input sparsification, an increasingly popular technique that improves efficiency by selectively activating only a subset of entry values for each input. However, existing approaches focus primarily on computational savings, often overlooking the representational consequences of sparsification and leaving a noticeable performance gap compared to full models. In this work, we first reinterpret input sparsification as a form of dynamic structural pruning. Motivated by the spontaneous baseline firing rates observed in biological neurons, we introduce a small set of trainable spontaneous neurons that act as compensatory units to stabilize activations in sparsified LLMs. Experiments demonstrate that these auxiliary neurons substantially reduce the sparsification-induced performance gap while generalizing effectively across tasks. --- ### A Novel Framework Using Variational Inference with Normalizing Flows to Train Transport Reversible Jump Proposals Authors: Pingping Yin, Xiyun Jiao Published: 2025-12-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.12742v2 We propose a unified framework that employs variational inference (VI) with (conditional) normalizing flows (NFs) to train both between-model and within-model proposals for reversible jump Markov chain Monte Carlo, enabling efficient trans-dimensional Bayesian inference. In contrast to the transport reversible jump (TRJ) of Davies et al. (2023), which optimizes forward KL divergence using pilot samples from the complex target distribution, our approach minimizes the reverse KL divergence, requiring only samples from a simple base distribution and largely reducing computational cost. Especially, we develop a novel trans-dimensional VI method with conditional NFs to fit the conditional transport proposal of Davies et al. (2023). We use RealNVP flows to learn the model-specific transport maps used for constructing proposals so that the calculation is parallelizable. Our framework also provides accurate estimates of marginal likelihoods, which may facilitate efficient model comparison and help design rejection-free proposals. Extensive numerical studies demonstrate that the TRJ method trained under our framework achieves faster mixing compared to existing baselines. --- ### Transport Reversible Jump Markov Chain Monte Carlo with proposals generated by Variational Inference with Normalizing Flows Authors: Pingping Yin, Xiyun Jiao Published: 2025-12-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.12742v1 We present a framework using variational inference with normalizing flows (VI-NFs) to generate proposals of reversible jump Markov chain Monte Carlo (RJMCMC) for efficient trans-dimensional Bayesian inference. Unlike transport reversible jump methods relying on forward KL minimization with pilot MCMC samples, our approach minimizes the reverse KL divergence which requires only samples from a base distribution, eliminating costly target sampling. The method employs RealNVP-based flows to learn model-specific transport maps, enabling construction of both between-model and within-model proposals. Our framework provides accurate marginal likelihood estimates from the variational approximation. This facilitates efficient model comparison and proposal adaptation in RJMCMC. Experiments on illustrative example, factor analysis and variable selection tasks in linear regression show that TRJ designed by VI-NFs achieves faster mixing and more efficient model space exploration compared to existing baselines. The proposed algorithm can be extended to conditional flows for amortized vairiational inference across models. Code is available at https://github.com/YinPingping111/TRJ_VINFs. --- ### Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning Authors: Li Xia Published: 2025-12-14 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2512.12737v2 Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity. Recent work has shown that neural tangent kernel (NTK) methods achieve faster convergence than gradient-based updates in DFL, while momentum has proven effective for accelerating gradient-based FL. However, applying momentum to NTK updates can destabilize training under heterogeneous data. We propose SPARK, which addresses this instability with a stage-wise annealed soft-label regularizer evaluated on neighborhood-aggregated data, so that momentum can accelerate NTK updates stably. Under high heterogeneity, SPARK converges about 3$\times$ faster than baselines and lowers the total communication to a target accuracy by up to about 70\%, and it attains higher accuracy across heterogeneity levels. We further study random projection as an optional Jacobian-compression strategy for bandwidth-constrained settings. We validate the approach across multiple datasets, network topologies, and heterogeneity levels. --- ### SPARK: Igniting Communication-Efficient Decentralized Learning via Stage-wise Projected NTK and Accelerated Regularization Authors: Li Xia Published: 2025-12-14 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2512.12737v1 Decentralized federated learning (DFL) faces critical challenges from statistical heterogeneity and communication overhead. While NTK-based methods achieve faster convergence, transmitting full Jacobian matrices is impractical for bandwidth-constrained edge networks. We propose SPARK, synergistically integrating random projection-based Jacobian compression, stage-wise annealed distillation, and Nesterov momentum acceleration. Random projections compress Jacobians while preserving spectral properties essential for convergence. Stage-wise annealed distillation transitions from pure NTK evolution to neighbor-regularized learning, counteracting compression noise. Nesterov momentum accelerates convergence through stable accumulation enabled by distillation smoothing. SPARK achieves 98.7% communication reduction compared to NTK-DFL while maintaining convergence speed and superior accuracy. With momentum, SPARK reaches target performance 3 times faster, establishing state-of-the-art results for communication-efficient decentralized learning and enabling practical deployment in bandwidth-limited edge environments. --- ### Personalized QoE Prediction: A Demographic-Augmented Machine Learning Framework for 5G Video Streaming Networks Authors: Syeda Zunaira Ahmed, Hejab Tahira Beg, Maryam Khalid Published: 2025-12-14 Categories: cs.AI, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2512.12736v1 Quality of Experience (QoE) prediction is a critical component of modern multimedia systems, particularly for adaptive video streaming in 5G networks. Accurate QoE estimation enables intelligent resource management and supports user centric service delivery. Existing QoE prediction approaches primarily rely on limited datasets and assume uniform user perception, which restricts their applicability in heterogeneous real world environments. This paper proposes a demographic aware machine learning framework for personalized QoE prediction. We introduce a behaviorally realistic demographic based data augmentation strategy that expands a small QoE dataset six fold by modeling varying user sensitivities to streaming impairments such as rebuffering, bitrate variation, and quality degradation. Using the augmented dataset, we evaluate a comprehensive set of classical machine learning models alongside advanced deep learning architectures, including an attention-based MLP and TabNet. Experimental results demonstrate significant improvements in prediction accuracy across RMSE, MAE, and R metrics compared to baseline models. Among all evaluated approaches, TabNet achieves the strongest performance, benefiting from its inherent feature selection and attention mechanisms. The results confirm that demographic-aware augmentation substantially enhances QoE prediction robustness and provides a scalable direction for personalized QoE-aware intelligence in 5G video streaming networks. --- ### Limits To (Machine) Learning Authors: Zhimin Chen, Bryan Kelly, Semyon Malamud Published: 2025-12-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.12735v1 Machine learning (ML) methods are highly flexible, but their ability to approximate the true data-generating process is fundamentally constrained by finite samples. We characterize a universal lower bound, the Limits-to-Learning Gap (LLG), quantifying the unavoidable discrepancy between a model's empirical fit and the population benchmark. Recovering the true population $R^2$, therefore, requires correcting observed predictive performance by this bound. Using a broad set of variables, including excess returns, yields, credit spreads, and valuation ratios, we find that the implied LLGs are large. This indicates that standard ML approaches can substantially understate true predictability in financial data. We also derive LLG-based refinements to the classic Hansen and Jagannathan (1991) bounds, analyze implications for parameter learning in general-equilibrium settings, and show that the LLG provides a natural mechanism for generating excess volatility. --- ### Solving a Machine Learning Regression Problem Based on the Theory of Random Functions Authors: Yuriy N. Bakhvalov Published: 2025-12-14 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.12731v1 This paper studies a machine learning regression problem as a multivariate approximation problem using the framework of the theory of random functions. An ab initio derivation of a regression method is proposed, starting from postulates of indifference. It is shown that if a probability measure on an infinite-dimensional function space possesses natural symmetries (invariance under translation, rotation, scaling, and Gaussianity), then the entire solution scheme, including the kernel form, the type of regularization, and the noise parameterization, follows analytically from these postulates. The resulting kernel coincides with a generalized polyharmonic spline; however, unlike existing approaches, it is not chosen empirically but arises as a consequence of the indifference principle. This result provides a theoretical foundation for a broad class of smoothing and interpolation methods, demonstrating their optimality in the absence of a priori information. --- ### NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents Authors: Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, Weiran Shi, Zaiyuan Wang et al. Published: 2025-12-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.12730v2 Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents. --- ### NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents Authors: Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, Weiran Shi, Zaiyuan Wang et al. Published: 2025-12-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.12730v1 Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents. --- ### Spinal Line Detection for Posture Evaluation through Train-ing-free 3D Human Body Reconstruction with 2D Depth Images Authors: Sehyun Kim, Hye Jun Lee, Jiwoo Lee, Changgyun Kim, Taemin Lee Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12718v2 The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing mul-ti-image-based body restoration methods require expensive equipment and complex pro-cedures, and single image-based body restoration methods have limitations in that it is difficult to accurately estimate the internal structure such as the spine center line due to occlusion and viewpoint limitation. This study proposes a method to compensate for the shortcomings of the multi-image-based method and to solve the limitations of the sin-gle-image method. We propose a 3D body posture analysis system that integrates depth images from four directions to restore a 3D human model and automatically estimate the spine center line. Through hierarchical matching of global and fine registration, restora-tion to noise and occlusion is performed. Also, the Adaptive Vertex Reduction is applied to maintain the resolution and shape reliability of the mesh, and the accuracy and stabil-ity of spinal angle estimation are simultaneously secured by using the Level of Detail en-semble. The proposed method achieves high-precision 3D spine registration estimation without relying on training data or complex neural network models, and the verification confirms the improvement of matching quality. --- ### Spinal Line Detection for Posture Evaluation through Train-ing-free 3D Human Body Reconstruction with 2D Depth Images Authors: Sehyun Kim, Hye Jun Lee, Jiwoo Lee, Changgyun Kim, Taemin Lee Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12718v1 The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing mul-ti-image-based body restoration methods require expensive equipment and complex pro-cedures, and single image-based body restoration methods have limitations in that it is difficult to accurately estimate the internal structure such as the spine center line due to occlusion and viewpoint limitation. This study proposes a method to compensate for the shortcomings of the multi-image-based method and to solve the limitations of the sin-gle-image method. We propose a 3D body posture analysis system that integrates depth images from four directions to restore a 3D human model and automatically estimate the spine center line. Through hierarchical matching of global and fine registration, restora-tion to noise and occlusion is performed. Also, the Adaptive Vertex Reduction is applied to maintain the resolution and shape reliability of the mesh, and the accuracy and stabil-ity of spinal angle estimation are simultaneously secured by using the Level of Detail en-semble. The proposed method achieves high-precision 3D spine registration estimation without relying on training data or complex neural network models, and the verification confirms the improvement of matching quality. --- ### CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning Authors: Xuanzhang Liu, Jianglun Feng, Zhuoran Zhuang, Junzhe Zhao, Maofei Que, Jieting Li, Dianlei Wang, Hao Tong, Ye Chen, Pan Li Published: 2025-12-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.12716v1 Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by "Context Explosion", where the accumulation of long text outputs overwhelms the model's context window and leads to reasoning failures. To address this, we introduce CoDA, a Context-Decoupled hierarchical Agent, a simple but effective reinforcement learning framework that decouples high-level planning from low-level execution. It employs a single, shared LLM backbone that learns to operate in two distinct, contextually isolated roles: a high-level Planner that decomposes tasks within a concise strategic context, and a low-level Executor that handles tool interactions in an ephemeral, isolated workspace. We train this unified agent end-to-end using PECO (Planner-Executor Co-Optimization), a reinforcement learning methodology that applies a trajectory-level reward to jointly optimize both roles, fostering seamless collaboration through context-dependent policy updates. Extensive experiments demonstrate that CoDA achieves significant performance improvements over state-of-the-art baselines on complex multi-hop question-answering benchmarks, and it exhibits strong robustness in long-context scenarios, maintaining stable performance while all other baselines suffer severe degradation, thus further validating the effectiveness of our hierarchical design in mitigating context overload. --- ### Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity Authors: Yiyang Jia, Chengxu Zhou Published: 2025-12-14 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2512.12713v2 Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selection in advance and cannot adapt their capacity during learning. This paper introduces the Self-Motivated Growing Neural Network (SMGrNN), a gradient-trained controller whose topology evolves online through a local Structural Plasticity Module (SPM). The SPM monitors edge-wise weight update statistics over short temporal windows and uses these local signals to trigger neuron insertion and pruning, while synaptic weights are optimized by a standard gradient-based optimizer. This allows network capacity to be adjusted during learning without manual architectural tuning. SMGrNN is evaluated on control benchmarks via policy distillation. Compared with multilayer perceptron baselines, it achieves similar or higher returns, lower variance, and task-appropriate network sizes. Ablation studies with growth disabled and growth-only variants isolate the role of structural plasticity, showing that adaptive growth improves reward stability while pruning prevents uncontrolled expansion and supports compact network formation. These results establish the independent value of local structural plasticity within gradient-trained networks and motivate future investigation of whether similar structural rules can be extended to more local or spike-based learning settings. --- ### Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity Authors: Yiyang Jia, Chengxu Zhou Published: 2025-12-14 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2512.12713v1 Control policies in deep reinforcement learning are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which lack structural plasticity and depend on global error signals. This paper introduces the Self-Motivated Growing Neural Network (SMGrNN), a controller whose topology evolves online through a local Structural Plasticity Module (SPM). The SPM monitors neuron activations and edge-wise weight update statistics over short temporal windows and uses these signals to trigger neuron insertion and pruning, while synaptic weights are updated by a standard gradient-based optimizer. This allows network capacity to be regulated during learning without manual architectural tuning. SMGrNN is evaluated on control benchmarks via policy distillation. Compared with multilayer perceptron baselines, it achieves similar or higher returns, lower variance, and task-appropriate network sizes. Ablation studies with growth disabled and growth-only variants isolate the role of structural plasticity, showing that adaptive topology improves reward stability. The local and modular design of SPM enables future integration of a Hebbian plasticity module and spike-timing-dependent plasticity, so that SMGrNN can support both artificial and spiking neural implementations driven by local rules. --- ### Practical Hybrid Quantum Language Models with Observable Readout on Real Hardware Authors: Stefan Balauca, Ada-Astrid Balauca, Adrian Iftene Published: 2025-12-14 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2512.12710v1 Hybrid quantum-classical models represent a crucial step toward leveraging near-term quantum devices for sequential data processing. We present Quantum Recurrent Neural Networks (QRNNs) and Quantum Convolutional Neural Networks (QCNNs) as hybrid quantum language models, reporting the first empirical demonstration of generative language modeling trained and evaluated end-to-end on real quantum hardware. Our architecture combines hardware-optimized parametric quantum circuits with a lightweight classical projection layer, utilizing a multi-sample SPSA strategy to efficiently train quantum parameters despite hardware noise. To characterize the capabilities of these models, we introduce a synthetic dataset designed to isolate syntactic dependencies in a controlled, low-resource environment. Experiments on IBM Quantum processors reveal the critical trade-offs between circuit depth and trainability, demonstrating that while noise remains a significant factor, observable-based readout enables the successful learning of sequential patterns on NISQ devices. These results establish a rigorous engineering baseline for generative quantum natural language processing, validating the feasibility of training complex sequence models on current quantum hardware. --- ### Multi-Trajectory Physics-Informed Neural Networks for HJB Equations with Hard-Zero Terminal Inventory: Optimal Execution on Synthetic & SPY Data Authors: Anthime Valin Published: 2025-12-14 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.12708v1 We study optimal trade execution with a hard-zero terminal inventory constraint, modeled via Hamilton-Jacobi-Bellman (HJB) equations. Vanilla PINNs often under-enforce this constraint and produce unstable controls. We propose a Multi-Trajectory PINN (MT-PINN) that adds a rollout-based trajectory loss and propagates a terminal penalty on terminal inventory via backpropagation-through-time, directly enforcing zero terminal inventory. A lightweight lambda-curriculum is adopted to stabilize training as the state expands from a risk-neutral reduced HJB to a risk-averse HJB. On the Gatheral-Schied single-asset model, MT-PINN aligns closely with their derived closed-form solutions and concentrates terminal inventory tightly around zero while reducing errors along optimal paths. We apply MT-PINNs on SPY intraday data, matching TWAP when risk-neutral, and achieving lower exposure and competitive costs, especially in falling windows, for higher risk-aversion. --- ### Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning Authors: Enhong Mu, Minami Yoda, Yan Zhang, Mingyue Zhang, Yutaka Matsuno, Jialong Li Published: 2025-12-14 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.12706v1 The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this demanding release cadence. However, existing automated testing approaches typically create a dichotomy: code-centric methods focus on structural coverage without understanding gameplay context, while player-centric agents validate high-level intent but often fail to cover specific underlying code changes. To bridge this gap, we propose SMART (Structural Mapping for Augmented Reinforcement Testing), a novel framework that synergizes structural verification and functional validation for game update testing. SMART leverages large language models (LLMs) to interpret abstract syntax tree (AST) differences and extract functional intent, constructing a context-aware hybrid reward mechanism. This mechanism guides reinforcement learning agents to sequentially fulfill gameplay goals while adaptively exploring modified code branches. We evaluate SMART on two environments, Overcooked and Minecraft. The results demonstrate that SMART significantly outperforms state-of-the-art baselines; it achieves over 94% branch coverage of modified code, nearly double that of traditional reinforcement learning methods, while maintaining a 98% task completion rate, effectively balancing structural comprehensiveness with functional correctness. --- ### Robust Motion Generation using Part-level Reliable Data from Videos Authors: Boyuan Li, Sipeng Zheng, Bin Cao, Ruihua Song, Zongqing Lu Published: 2025-12-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12703v2 Extracting human motion from large-scale web videos offers a scalable solution to the data scarcity issue in character animation. However, some human parts in many video frames cannot be seen due to off-screen captures or occlusions. It brings a dilemma: discarding the data missing any part limits scale and diversity, while retaining it compromises data quality and model performance. To address this problem, we propose leveraging credible part-level data extracted from videos to enhance motion generation via a robust part-aware masked autoregression model. First, we decompose a human body into five parts and detect the parts clearly seen in a video frame as "credible". Second, the credible parts are encoded into latent tokens by our proposed part-aware variational autoencoder. Third, we propose a robust part-level masked generation model to predict masked credible parts, while ignoring those noisy parts. In addition, we contribute K700-M, a challenging new benchmark comprising approximately 200k real-world motion sequences, for evaluation. Experimental results indicate that our method successfully outperforms baselines on both clean and noisy datasets in terms of motion quality, semantic consistency and diversity. Project page: https://boyuaner.github.io/ropar-main/ --- ### Robust Motion Generation using Part-level Reliable Data from Videos Authors: Boyuan Li, Sipeng Zheng, Bin Cao, Ruihua Song, Zongqing Lu Published: 2025-12-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12703v1 Extracting human motion from large-scale web videos offers a scalable solution to the data scarcity issue in character animation. However, some human parts in many video frames cannot be seen due to off-screen captures or occlusions. It brings a dilemma: discarding the data missing any part limits scale and diversity, while retaining it compromises data quality and model performance. To address this problem, we propose leveraging credible part-level data extracted from videos to enhance motion generation via a robust part-aware masked autoregression model. First, we decompose a human body into five parts and detect the parts clearly seen in a video frame as "credible". Second, the credible parts are encoded into latent tokens by our proposed part-aware variational autoencoder. Third, we propose a robust part-level masked generation model to predict masked credible parts, while ignoring those noisy parts. In addition, we contribute K700-M, a challenging new benchmark comprising approximately 200k real-world motion sequences, for evaluation. Experimental results indicate that our method successfully outperforms baselines on both clean and noisy datasets in terms of motion quality, semantic consistency and diversity. Project page: https://boyuaner.github.io/ropar-main/ --- ### Efficient Vision-Language Reasoning via Adaptive Token Pruning Authors: Xue Li, Xiaonan Song, Henry Hu Published: 2025-12-14 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.12701v1 Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism that retains only the most informative tokens based on contextual relevance. ATP operates at the vision-language interface, assigning a hybrid importance score combining ViT CLS attention (intra-modal saliency) and CLIP text-image similarity (inter-modal relevance) to keep top-K tokens for the LLM. Unlike static compression, ATP adapts to each input without modifying the backbone. Proposed as a lightweight gating module, ATP is compatible with popular backbones like BLIP-2, LLaVA, and Flamingo. Preliminary evaluations across VQAv2, GQA, and COCO indicate that ATP reduces inference FLOPs by around 40% and achieves roughly 1.5x speedups in end-to-end latency with negligible accuracy loss (less than 1%). Qualitative analyses suggest ATP preserves visual grounding and enhances interpretability. Beyond efficiency, we investigate robustness under corruptions; observations suggest adaptive pruning suppresses spurious correlations, improving stability. These findings imply that resource-constrained inference and model reliability are not competing objectives. Finally, we discuss ATP's role in efficient multimodal edge computing pipelines. --- ### MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora Authors: Souhail Bakkali, Anthony Mudet Published: 2025-12-14 Categories: cs.DL, cs.CV arXiv: https://arxiv.org/abs/2512.12694v2 Large multilingual knowledge bases expose temporally diverse information, yet retrieval quality remains sensitive to lexical variation and cross-lingual terminology shifts. We develop and evaluate MTRACE (Multilingual Temporal Retrieval-Augmented Generation with evidence grounding), a pipeline designed to test whether query expansion and multi-query fusion mitigate vocabulary mismatch in temporally layered text corpora, on the French and English subsets of MIRACL. Our approach integrates: (i) semantic query expansion (SQE) and multi-query fusion via Reciprocal Rank Fusion (RRF), targeting retrieval stability under query variation; (ii) a generation prompt enforcing strict grounding in retrieved evidence and explicit abstention when evidence is insufficient; and (iii) a modular architecture enabling systematic component evaluation. Ablation studies on Named Entity Recognition (NER) and embedding model selection demonstrate the importance of syntactic coherence in entity extraction and of self-retrieval and efficiency measurements for retriever selection. Our end-to-end evaluation over 50 constructed queries shows faithful answers for well-supported queries, correct abstention on unanswerable questions, and no re-scored similarity gains from multi-query fusion over single-query dense retrieval. By scoping our claims to a clean, text-only baseline, we separate these effects from OCR-noise confounds; direct measurement of diachronic lexical drift is left to future work. Code and configurations are available at \url{https://anonymous.4open.science/r/MIRAGE-8EAA/ --- ### Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering Authors: Anthony Mudet, Souhail Bakkali Published: 2025-12-14 Categories: cs.DL, cs.CV arXiv: https://arxiv.org/abs/2512.12694v1 Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We develop and evaluate a multilingual Retrieval-Augmented Generation pipeline specifically designed for question answering on noisy historical documents. Our approach integrates: (i) semantic query expansion and multi-query fusion using Reciprocal Rank Fusion to improve retrieval robustness against vocabulary mismatch; (ii) a carefully engineered generation prompt that enforces strict grounding in retrieved evidence and explicit abstention when evidence is insufficient; and (iii) a modular architecture enabling systematic component evaluation. We conduct comprehensive ablation studies on Named Entity Recognition and embedding model selection, demonstrating the importance of syntactic coherence in entity extraction and balanced performance-efficiency trade-offs in dense retrieval. Our end-to-end evaluation framework shows that the pipeline generates faithful answers for well-supported queries while correctly abstaining from unanswerable questions. The hybrid retrieval strategy improves recall stability, particularly benefiting from RRF's ability to smooth performance variance across query formulations. We release our code and configurations at https://anonymous.4open.science/r/RAGs-C5AE/, providing a reproducible foundation for robust historical document question answering. --- ### Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits Authors: Sumantrak Mukherjee, Serafima Lebedeva, Valentin Margraf, Jonas Hanselle, Kanta Yamaoka, Viktor Bengs, Stefan Konigorski, Eyke Hüllermeier, Sebastian Josef Vollmer Published: 2025-12-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12693v1 We propose a novel Bayesian framework for efficient exploration in contextual multi-task multi-armed bandit settings, where the context is only observed partially and dependencies between reward distributions are induced by latent context variables. In order to exploit these structural dependencies, our approach integrates observations across all tasks and learns a global joint distribution, while still allowing personalised inference for new tasks. In this regard, we identify two key sources of epistemic uncertainty, namely structural uncertainty in the latent reward dependencies across arms and tasks, and user-specific uncertainty due to incomplete context and limited interaction history. To put our method into practice, we represent the joint distribution over tasks and rewards using a particle-based approximation of a log-density Gaussian process. This representation enables flexible, data-driven discovery of both inter-arm and inter-task dependencies without prior assumptions on the latent variables. Empirically, we demonstrate that our method outperforms baselines such as hierarchical model bandits, especially in settings with model misspecification or complex latent heterogeneity. --- ### WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment Authors: Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali, Md Rizwan Parvez Published: 2025-12-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.12692v1 LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is particularly problematic in web environments, which are only partially observable-limited to browser-visible content (e.g., DOM and UI elements)-where a single misstep often requires complex and brittle navigation to undo. Without an explicit backtracking mechanism, agents struggle to correct errors or systematically explore alternative paths. Tree-search methods provide a principled framework for such structured exploration, but existing approaches lack mechanisms for safe backtracking, making them prone to unintended side effects. They also assume that all actions are reversible, ignoring the presence of irreversible actions-limitations that reduce their effectiveness in realistic web tasks. To address these challenges, we introduce WebOperator, a tree-search framework that enables reliable backtracking and strategic exploration. Our method incorporates a best-first search strategy that ranks actions by both reward estimates and safety considerations, along with a robust backtracking mechanism that verifies the feasibility of previously visited paths before replaying them, preventing unintended side effects. To further guide exploration, WebOperator generates action candidates from multiple, varied reasoning contexts to ensure diverse and robust exploration, and subsequently curates a high-quality action set by filtering out invalid actions pre-execution and merging semantically equivalent ones. Experimental results on WebArena and WebVoyager demonstrate the effectiveness of WebOperator. On WebArena, WebOperator achieves a state-of-the-art 54.6% success rate with gpt-4o, underscoring the critical advantage of integrating strategic foresight with safe execution. --- ### Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning Authors: Yongcan Yu, Lingxiao He, Shuo Lu, Lijun Sheng, Yinuo Xu, Yanbo Wang, Kuangpu Guo, Jianjie Cheng, Meng Wang, Qianlong Xie, Xingxing Wang, Dapeng Hu et al. Published: 2025-12-14 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.12690v1 Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies suggest that introducing the SFT stage not only fails to improve reasoning ability but may also negatively impact model training. In this study, we revisit this RL-centric belief through a systematic and controlled comparison of SFT and RL on VLM Reasoning. Using identical data sources, we find that the relative effectiveness of SFT and RL is conditional and strongly influenced by model capacity, data scale, and data distribution. Contrary to common assumptions, our findings show that SFT plays a crucial role across several scenarios: (1) Effectiveness for weaker models. SFT more reliably elicits reasoning capabilities in smaller or weaker VLMs. (2) Data efficiency. SFT with only 2K achieves comparable or better reasoning performance to RL with 20K. (3) Cross-modal transferability. SFT demonstrates stronger generalization across modalities. Moreover, we identify a pervasive issue of deceptive rewards, where higher rewards fail to correlate with better reasoning accuracy in RL. These results challenge the prevailing "RL over SFT" narrative. They highlight that the role of SFT may have been underestimated and support a more balanced post-training pipeline in which SFT and RL function as complementary components. --- ### How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh Published: 2025-12-14 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.12688v3 Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts function as semantic conditions on how a fixed model interprets inputs, foregrounds information, and structures tasks. We formalize this account through three notions -- frame activation, salience control, and construal selection -- and study them in natural language inference, claim verification, and multi-hop question answering. Across these settings, prompts produce measurable changes in label judgments, evidence use, and answer-support organization, showing that prompt effects differ not only in magnitude but also in semantic direction. The paper therefore reframes prompting as the analysis of how instructions move model behavior, rather than only whether they improve performance. --- ### Theoretical Foundations of Prompt Engineering: From Heuristics to Expressivity Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh Published: 2025-12-14 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.12688v1 Prompts can switch a model's behavior even when the weights are fixed, yet this phenomenon is rarely treated as a clean theoretical object rather than a heuristic. We study the family of functions obtainable by holding a Transformer backbone fixed as an executor and varying only the prompt. Our core idea is to view the prompt as an externally injected program and to construct a simplified Transformer that interprets it to implement different computations. The construction exposes a mechanism-level decomposition: attention performs selective routing from prompt memory, the FFN performs local arithmetic conditioned on retrieved fragments, and depth-wise stacking composes these local updates into a multi-step computation. Under this viewpoint, we prove a constructive existential result showing that a single fixed backbone can approximate a broad class of target behaviors via prompts alone. The framework provides a unified starting point for formalizing trade-offs under prompt length/precision constraints and for studying structural limits of prompt-based switching, while remaining distinct from empirical claims about pretrained LLMs. --- ### Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI Authors: Samarth Sarin, Lovepreet Singh, Bhaskarjit Sarmah, Dhagash Mehta Published: 2025-12-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.12686v1 Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and adaptive agents. Agentic memory refers to the memory that provides an LLM with agent-like persistence: the ability to retain and act upon information across conversations, similar to how a human would. We present Memoria, a modular memory framework that augments LLM-based conversational systems with persistent, interpretable, and context-rich memory. Memoria integrates two complementary components: dynamic session-level summarization and a weighted knowledge graph (KG)-based user modelling engine that incrementally captures user traits, preferences, and behavioral patterns as structured entities and relationships. This hybrid architecture enables both short-term dialogue coherence and long-term personalization while operating within the token constraints of modern LLMs. We demonstrate how Memoria enables scalable, personalized conversational artificial intelligence (AI) by bridging the gap between stateless LLM interfaces and agentic memory systems, offering a practical solution for industry applications requiring adaptive and evolving user experiences. --- ### Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis Authors: Yeray Cordero, Paula García-Molina, Fernando Vilariño Published: 2025-12-14 Categories: quant-ph, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.12683v1 Implicit neural representations (INRs) have become a powerful paradigm for continuous signal modeling and 3D scene reconstruction, yet classical networks suffer from a well-known spectral bias that limits their ability to capture high-frequency details. Quantum Implicit Representation Networks (QIREN) mitigate this limitation by employing parameterized quantum circuits with inherent Fourier structures, enabling compact and expressive frequency modeling beyond classical MLPs. In this paper, we present Quantum Neural Radiance Fields (Q-NeRF), the first hybrid quantum-classical framework for neural radiance field rendering. Q-NeRF integrates QIREN modules into the Nerfacto backbone, preserving its efficient sampling, pose refinement, and volumetric rendering strategies while replacing selected density and radiance prediction components with quantum-enhanced counterparts. We systematically evaluate three hybrid configurations on standard multi-view indoor datasets, comparing them to classical baselines using PSNR, SSIM, and LPIPS metrics. Results show that hybrid quantum-classical models achieve competitive reconstruction quality under limited computational resources, with quantum modules particularly effective in representing fine-scale, view-dependent appearance. Although current implementations rely on quantum circuit simulators constrained to few-qubit regimes, the results highlight the potential of quantum encodings to alleviate spectral bias in implicit representations. Q-NeRF provides a foundational step toward scalable quantum-enabled 3D scene reconstruction and a baseline for future quantum neural rendering research. --- ### $β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment Authors: Fatimah Zohra, Chen Zhao, Hani Itani, Bernard Ghanem Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12678v2 CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose $β$-CLIP, a multi-granular text-conditioned contrastive learning framework designed to achieve hierarchical alignment between multiple textual granularities-from full captions to sentences and phrases-and their corresponding visual regions. For each level of granularity, $β$-CLIP utilizes cross-attention to dynamically pool image patches, producing contextualized visual embeddings. To address the semantic overlap inherent in this hierarchy, we introduce the $β$-Contextualized Contrastive Alignment Loss ($β$-CAL). This objective parameterizes the trade-off between strict query-specific matching and relaxed intra-image contextualization, supporting both soft Cross-Entropy and hard Binary Cross-Entropy formulations. We find that each loss interacts differently with hierarchical supervision: CE's softmax sharpens fine-grained discrimination, while BCE's sigmoid favors long-text retrieval while both benefit from hierarchy. Through extensive experiments, we demonstrate that $β$-CLIP significantly improves dense alignment: achieving 91.8% T2I 92.3% I2T at R@1 on Urban1K and 30.9% on FG-OVD (Hard), setting state-of-the-art among methods trained without hard negatives. $β$-CLIP establishes a robust, adaptive baseline for dense vision-language correspondence. The code and models are released at https://github.com/fzohra/B-CLIP. --- ### $β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment Authors: Fatimah Zohra, Chen Zhao, Hani Itani, Bernard Ghanem Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12678v1 CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose $β$-CLIP, a multi-granular text-conditioned contrastive learning framework designed to achieve hierarchical alignment between multiple textual granularities-from full captions to sentences and phrases-and their corresponding visual regions. For each level of granularity, $β$-CLIP utilizes cross-attention to dynamically pool image patches, producing contextualized visual embeddings. To address the semantic overlap inherent in this hierarchy, we introduce the $β$-Contextualized Contrastive Alignment Loss ($β$-CAL). This objective parameterizes the trade-off between strict query-specific matching and relaxed intra-image contextualization, supporting both soft Cross-Entropy and hard Binary Cross-Entropy formulations. Through extensive experiments, we demonstrate that $β$-CLIP significantly improves dense alignment: achieving 91.8% T2I 92.3% I2T at R@1 on Urban1K and 30.9% on FG-OVD (Hard), setting state-of-the-art among methods trained without hard negatives. $β$-CLIP establishes a robust, adaptive baseline for dense vision-language correspondence. The code and models are released at https://github.com/fzohra/B-CLIP. --- ### Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches Authors: Amirhossein Yousefiramandi, Ciaran Cooney Published: 2025-12-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12677v3 We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained causal LLM and fine-tuning it on the task, using the LLM's final-token embedding as a sequence representation, and (2) instruction-tuning the LLM in a prompt-to-response format for classification. To enable single-GPU fine-tuning of models up to 8B parameters, we combine 4-bit model quantization with Low-Rank Adaptation (LoRA) for parameter-efficient training. Experiments on two patent benchmarks, a 5-class single-label internal corpus and the public WIPO-Alpha multi-label dataset with 14 categories, show that the embedding-head approach matches or exceeds fine-tuned BERT baselines on single-label classification while training 10-30x fewer parameters. Instruction-tuning is competitive only in the multi-label regime, and only with substantially larger trainable budgets of at least 100M parameters. These results demonstrate that directly leveraging the internal representations of causal LLMs, together with efficient fine-tuning techniques, yields strong classification performance under limited computational resources. We discuss the advantages of each approach and outline practical guidelines and future directions for optimizing LLM fine-tuning in classification scenarios. --- ### Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches Authors: Amirhossein Yousefiramandi, Ciaran Cooney Published: 2025-12-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12677v1 We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pre-trained causal LLM and fine-tuning on the task (using the LLM's final token embedding as a sequence representation), and (2) instruction-tuning the LLM in a prompt->response format for classification. To enable single-GPU fine-tuning of models up to 8B parameters, we combine 4-bit model quantization with Low-Rank Adaptation (LoRA) for parameter-efficient training. Experiments on two datasets - a proprietary single-label dataset and the public WIPO-Alpha patent dataset (extreme multi-label classification) - show that the embedding-based method significantly outperforms the instruction-tuned method in F1-score, and is very competitive with - even surpassing - fine-tuned domain-specific models (e.g. BERT) on the same tasks. These results demonstrate that directly leveraging the internal representations of causal LLMs, along with efficient fine-tuning techniques, yields impressive classification performance under limited computational resources. We discuss the advantages of each approach while outlining practical guidelines and future directions for optimizing LLM fine-tuning in classification scenarios. --- ### Robust Variational Bayes by Min-Max Median Aggregation Authors: Jiawei Yan, Ju Liu, Weidong Liu, Jiyuan Tu Published: 2025-12-14 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.12676v1 We propose a robust and scalable variational Bayes (VB) framework designed to effectively handle contamination and outliers in dataset. Our approach partitions the data into $m$ disjoint subsets and formulates a joint optimization problem based on robust aggregation principles. A key insight is that the full posterior distribution is equivalent to the minimizer of the mean Kullback-Leibler (KL) divergence from the $m$-powered local posterior distributions. To enhance robustness, we replace the mean KL divergence with a min-max median formulation. The min-max formulation not only ensures consistency between the KL minimizer and the Evidence Lower Bound (ELBO) maximizer but also facilitates the establishment of improved statistical rates for the mean of variational posterior. We observe a notable discrepancy in the $m$-powered marginal log likelihood function contingent on the presence of local latent variables. To address this, we treat these two scenarios separately to guarantee the consistency of the aggregated variational posterior. Specifically, when local latent variables are present, we introduce an aggregate-and-rescale strategy. Theoretically, we provide a non-asymptotic analysis of our proposed posterior, incorporating a refined analysis of Bernstein-von Mises (BvM) theorem to accommodate a diverging number of subsets $m$. Our findings indicate that the two-stage approach yields a smaller approximation error compared to directly aggregating the $m$-powered local posteriors. Furthermore, we establish a nearly optimal statistical rate for the mean of the proposed posterior, advancing existing theories related to min-max median estimators. The efficacy of our method is demonstrated through extensive simulation studies. --- ### Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling Authors: Yuran Wang, Bohan Zeng, Chengzhuo Tong, Wenxuan Liu, Yang Shi, Xiaochen Ma, Hao Liang, Yuanxing Zhang, Wentao Zhang Published: 2025-12-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12675v3 Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject when inputs contain multiple candidates. This limitation restricts effectiveness in complex, realistic visual settings. We propose Scone, a unified understanding-generation method that integrates composition and distinction. Scone enables the understanding expert to act as a semantic bridge, conveying semantic information and guiding the generation expert to preserve subject identity while minimizing interference. A two-stage training scheme first learns composition, then enhances distinction through semantic alignment and attention-based masking. We also introduce SconeEval, a benchmark for evaluating both composition and distinction across diverse scenarios. Experiments demonstrate that Scone outperforms existing open-source models in composition and distinction tasks on two benchmarks. Our model, benchmark, and training data are available at: https://github.com/Ryann-Ran/Scone. --- ### Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling Authors: Yuran Wang, Bohan Zeng, Chengzhuo Tong, Wenxuan Liu, Yang Shi, Xiaochen Ma, Hao Liang, Yuanxing Zhang, Wentao Zhang Published: 2025-12-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12675v1 Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to identify and generate the correct subject when inputs contain multiple candidates. This limitation restricts effectiveness in complex, realistic visual settings. We propose Scone, a unified understanding-generation method that integrates composition and distinction. Scone enables the understanding expert to act as a semantic bridge, conveying semantic information and guiding the generation expert to preserve subject identity while minimizing interference. A two-stage training scheme first learns composition, then enhances distinction through semantic alignment and attention-based masking. We also introduce SconeEval, a benchmark for evaluating both composition and distinction across diverse scenarios. Experiments demonstrate that Scone outperforms existing open-source models in composition and distinction tasks on two benchmarks. Our model, benchmark, and training data are available at: https://github.com/Ryann-Ran/Scone. --- ### Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation Authors: Yushun Tang, Ziqiong Liu, Jiyuan Jia, Yi Zhang, Zhihai He Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12673v1 Online test-time adaptation aims to dynamically adjust a network model in real-time based on sequential input samples during the inference stage. In this work, we find that, when applying a transformer network model to a new target domain, the Query, Key, and Value features of its self-attention module often change significantly from those in the source domain, leading to substantial performance degradation of the transformer model. To address this important issue, we propose to develop a new approach to progressively recalibrate the self-attention at each layer using a local linear transform parameterized by conditioned scale and shift factors. We consider the online model adaptation from the source domain to the target domain as a progressive domain shift separation process. At each transformer network layer, we learn a Domain Separation Network to extract the domain shift feature, which is used to predict the scale and shift parameters for self-attention recalibration using a Factor Generator Network. These two lightweight networks are adapted online during inference. Experimental results on benchmark datasets demonstrate that the proposed progressive conditioned scale-shift recalibration (PCSR) method is able to significantly improve the online test-time domain adaptation performance by a large margin of up to 3.9\% in classification accuracy on the ImageNet-C dataset. --- ### On Approaches to Building Surrogate ODE Models for Diffusion Bridges Authors: Maria Khilchuk, Vladimir Latypov, Pavel Kleshchev, Alexander Hvatov Published: 2025-12-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12671v1 Diffusion and Schrödinger Bridge models have established state-of-the-art performance in generative modeling but are often hampered by significant computational costs and complex training procedures. While continuous-time bridges promise faster sampling, overparameterized neural networks describe their optimal dynamics, and the underlying stochastic differential equations can be difficult to integrate efficiently. This work introduces a novel paradigm that uses surrogate models to create simpler, faster, and more flexible approximations of these dynamics. We propose two specific algorithms: SINDy Flow Matching (SINDy-FM), which leverages sparse regression to identify interpretable, symbolic differential equations from data, and a Neural-ODE reformulation of the Schrödinger Bridge (DSBM-NeuralODE) for flexible continuous-time parameterization. Our experiments on Gaussian transport tasks and MNIST latent translation demonstrate that these surrogates achieve competitive performance while offering dramatic improvements in efficiency and interpretability. The symbolic SINDy-FM models, in particular, reduce parameter counts by several orders of magnitude and enable near-instantaneous inference, paving the way for a new class of tractable and high-performing bridge models for practical deployment. --- ### DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization Authors: Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Guoqing Ma, Yidan Liang, Jingjiang Liu, Hao Chen, Shimin Di Published: 2025-12-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12669v2 Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized into interpolation and extrapolation. Existing interpolation methods typically embed temporal information into individual facts to complete missing historical knowledge, while extrapolation techniques often leverage sequence models over graph snapshots to identify recurring patterns for future event prediction. These methods face two critical challenges: limited contextual modeling in interpolation and cognitive generalization bias in extrapolation. To address these, we propose a unified method for TKGR, dubbed DynaGen. For interpolation, DynaGen dynamically constructs entity-centric subgraphs and processes them with a synergistic dual-branch GNN encoder to capture evolving structural context. For extrapolation, it applies a conditional diffusion process, which forces the model to learn underlying evolutionary principles rather than just superficial patterns, enhancing its ability to predict unseen future events. Extensive experiments on six benchmark datasets show DynaGen achieves state-of-the-art performance. On average, compared to the second-best models, DynaGen improves the Mean Reciprocal Rank (MRR) score by 2.61 points for interpolation and 1.45 points for extrapolation. --- ### DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization Authors: Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Guoqing Ma, Yidan Liang, Jingjiang Liu, Hao Chen, Shimin Di Published: 2025-12-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12669v1 Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized into interpolation and extrapolation. Existing interpolation methods typically embed temporal information into individual facts to complete missing historical knowledge, while extrapolation techniques often leverage sequence models over graph snapshots to identify recurring patterns for future event prediction. These methods face two critical challenges: limited contextual modeling in interpolation and cognitive generalization bias in extrapolation. To address these, we propose a unified method for TKGR, dubbed DynaGen. For interpolation, DynaGen dynamically constructs entity-centric subgraphs and processes them with a synergistic dual-branch GNN encoder to capture evolving structural context. For extrapolation, it applies a conditional diffusion process, which forces the model to learn underlying evolutionary principles rather than just superficial patterns, enhancing its ability to predict unseen future events. Extensive experiments on six benchmark datasets show DynaGen achieves state-of-the-art performance. On average, compared to the second-best models, DynaGen improves the Mean Reciprocal Rank (MRR) score by 2.61 points for interpolation and 1.45 points for extrapolation. --- ### Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning Authors: Haiyang Zheng, Nan Pu, Wenjing Li, Teng Long, Nicu Sebe, Zhun Zhong Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12667v2 The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries using labeled data for known types and unlabeled data containing a mixture of known and novel types. However, existing OW-DFA methods face two critical limitations: 1) A confidence skew that leads to unreliable pseudo-labels for novel forgeries, resulting in biased training. 2) An unrealistic assumption that the number of unknown forgery types is known *a priori*. To address these challenges, we propose a Confidence-Aware Asymmetric Learning (CAL) framework, which adaptively balances model confidence across known and novel forgery types. CAL mainly consists of two components: Confidence-Aware Consistency Regularization (CCR) and Asymmetric Confidence Reinforcement (ACR). CCR mitigates pseudo-label bias by dynamically scaling sample losses based on normalized confidence, gradually shifting the training focus from high- to low-confidence samples. ACR complements this by separately calibrating confidence for known and novel classes through selective learning on high-confidence samples, guided by their confidence gap. Together, CCR and ACR form a mutually reinforcing loop that significantly improves the model's OW-DFA performance. Moreover, we introduce a Dynamic Prototype Pruning (DPP) strategy that automatically estimates the number of novel forgery types in a coarse-to-fine manner, removing the need for unrealistic prior assumptions and enhancing the scalability of our methods to real-world OW-DFA scenarios. Extensive experiments on the standard OW-DFA benchmark and a newly extended benchmark incorporating advanced manipulations demonstrate that CAL consistently outperforms previous methods, achieving new state-of-the-art performance on both known and novel forgery attribution. --- ### Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning Authors: Haiyang Zheng, Nan Pu, Wenjing Li, Teng Long, Nicu Sebe, Zhun Zhong Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12667v1 The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries using labeled data for known types and unlabeled data containing a mixture of known and novel types. However, existing OW-DFA methods face two critical limitations: 1) A confidence skew that leads to unreliable pseudo-labels for novel forgeries, resulting in biased training. 2) An unrealistic assumption that the number of unknown forgery types is known *a priori*. To address these challenges, we propose a Confidence-Aware Asymmetric Learning (CAL) framework, which adaptively balances model confidence across known and novel forgery types. CAL mainly consists of two components: Confidence-Aware Consistency Regularization (CCR) and Asymmetric Confidence Reinforcement (ACR). CCR mitigates pseudo-label bias by dynamically scaling sample losses based on normalized confidence, gradually shifting the training focus from high- to low-confidence samples. ACR complements this by separately calibrating confidence for known and novel classes through selective learning on high-confidence samples, guided by their confidence gap. Together, CCR and ACR form a mutually reinforcing loop that significantly improves the model's OW-DFA performance. Moreover, we introduce a Dynamic Prototype Pruning (DPP) strategy that automatically estimates the number of novel forgery types in a coarse-to-fine manner, removing the need for unrealistic prior assumptions and enhancing the scalability of our methods to real-world OW-DFA scenarios. Extensive experiments on the standard OW-DFA benchmark and a newly extended benchmark incorporating advanced manipulations demonstrate that CAL consistently outperforms previous methods, achieving new state-of-the-art performance on both known and novel forgery attribution. --- ### InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation Authors: Sreehari Rajan, Kunal Bhosikar, Charu Sharma Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12664v1 Generating realistic human motions that naturally respond to both spoken language and physical objects is crucial for interactive digital experiences. Current methods, however, address speech-driven gestures or object interactions independently, limiting real-world applicability due to a lack of integrated, comprehensive datasets. To overcome this, we introduce InteracTalker, a novel framework that seamlessly integrates prompt-based object-aware interactions with co-speech gesture generation. We achieve this by employing a multi-stage training process to learn a unified motion, speech, and prompt embedding space. To support this, we curate a rich human-object interaction dataset, formed by augmenting an existing text-to-motion dataset with detailed object interaction annotations. Our framework utilizes a Generalized Motion Adaptation Module that enables independent training, adapting to the corresponding motion condition, which is then dynamically combined during inference. To address the imbalance between heterogeneous conditioning signals, we propose an adaptive fusion strategy, which dynamically reweights the conditioning signals during diffusion sampling. InteracTalker successfully unifies these previously separate tasks, outperforming prior methods in both co-speech gesture generation and object-interaction synthesis, outperforming gesture-focused diffusion methods, yielding highly realistic, object-aware full-body motions with enhanced realism, flexibility, and control. --- ### PerNodeDrop: A Method Balancing Specialized Subnets and Regularization in Deep Neural Networks Authors: Gelesh G Omathil, Sreeja CS Published: 2025-12-14 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.12663v1 Deep neural networks possess strong representational capacity yet remain vulnerable to overfitting, primarily because neurons tend to co-adapt in ways that, while capturing complex and fine-grained feature interactions, also reinforce spurious and non-generalizable patterns that inflate training performance but reduce reliability on unseen data. Noise-based regularizers such as Dropout and DropConnect address this issue by injecting stochastic perturbations during training, but the noise they apply is typically uniform across a layer or across a batch of samples, which can suppress both harmful and beneficial co-adaptation. This work introduces PerNodeDrop, a lightweight stochastic regularization method. It applies per-sample, per-node perturbations to break the uniformity of the noise injected by existing techniques, thereby allowing each node to experience input-specific variability. Hence, PerNodeDrop preserves useful co-adaptation while applying regularization. This narrows the gap between training and validation performance and improves reliability on unseen data, as evident from the experiments. Although superficially similar to DropConnect, PerNodeDrop operates at the sample level. It drops weights at the sample level, not the batch level. An expected-loss analysis formalizes how its perturbations attenuate excessive co-adaptation while retaining predictive interactions. Empirical evaluations on vision, text, and audio benchmarks indicate improved generalization relative to the standard noise-based regularizer. --- ### Anatomy-Guided Representation Learning Using a Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images Authors: Muhammad Umar Farooq, Abd Ur Rehman, Azka Rehman, Muhammad Usman, Dong-Kyu Chae, Junaid Qadir Published: 2025-12-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12662v1 Accurate thyroid nodule segmentation in ultrasound images is critical for diagnosis and treatment planning. However, ambiguous boundaries between nodules and surrounding tissues, size variations, and the scarcity of annotated ultrasound data pose significant challenges for automated segmentation. Existing deep learning models struggle to incorporate contextual information from the thyroid gland and generalize effectively across diverse cases. To address these challenges, we propose SSMT-Net, a Semi-Supervised Multi-Task Transformer-based Network that leverages unlabeled data to enhance Transformer-centric encoder feature extraction capability in an initial unsupervised phase. In the supervised phase, the model jointly optimizes nodule segmentation, gland segmentation, and nodule size estimation, integrating both local and global contextual features. Extensive evaluations on the TN3K and DDTI datasets demonstrate that SSMT-Net outperforms state-of-the-art methods, with higher accuracy and robustness, indicating its potential for real-world clinical applications. --- ### CogDoc: Towards Unified thinking in Documents Authors: Qixin Xu, Haozhe Wang, Che Liu, Fangzhen Lin, Wenhu Chen Published: 2025-12-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12658v1 Current document reasoning paradigms are constrained by a fundamental trade-off between scalability (processing long-context documents) and fidelity (capturing fine-grained, multimodal details). To bridge this gap, we propose CogDoc, a unified coarse-to-fine thinking framework that mimics human cognitive processes: a low-resolution "Fast Reading" phase for scalable information localization,followed by a high-resolution "Focused Thinking" phase for deep reasoning. We conduct a rigorous investigation into post-training strategies for the unified thinking framework, demonstrating that a Direct Reinforcement Learning (RL) approach outperforms RL with Supervised Fine-Tuning (SFT) initialization. Specifically, we find that direct RL avoids the "policy conflict" observed in SFT. Empirically, our 7B model achieves state-of-the-art performance within its parameter class, notably surpassing significantly larger proprietary models (e.g., GPT-4o) on challenging, visually rich document benchmarks. ---