# Research Papers — 2025-12 · bundle page 103 of 175

> Full-text markdown of papers #5101–5150 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/103
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/102.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/104.md)

### Digital Twin Supervised Reinforcement Learning Framework for Autonomous Underwater Navigation

Authors: Zamirddine Mari, Mohamad Motasem Nawaf, Pierre Drap
Published: 2025-12-11
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2512.10925v1

Autonomous navigation in underwater environments remains a major challenge due to the absence of GPS, degraded visibility, and the presence of submerged obstacles. This article investigates these issues through the case of the BlueROV2, an open platform widely used for scientific experimentation. We propose a deep reinforcement learning approach based on the Proximal Policy Optimization (PPO) algorithm, using an observation space that combines target-oriented navigation information, a virtual occupancy grid, and ray-casting along the boundaries of the operational area. The learned policy is compared against a reference deterministic kinematic planner, the Dynamic Window Approach (DWA), commonly employed as a robust baseline for obstacle avoidance. The evaluation is conducted in a realistic simulation environment and complemented by validation on a physical BlueROV2 supervised by a 3D digital twin of the test site, helping to reduce risks associated with real-world experimentation. The results show that the PPO policy consistently outperforms DWA in highly cluttered environments, notably thanks to better local adaptation and reduced collisions. Finally, the experiments demonstrate the transferability of the learned behavior from simulation to the real world, confirming the relevance of deep RL for autonomous navigation in underwater robotics.

---

### SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale

Authors: Max Zimmer, Christophe Roux, Moritz Wagner, Deborah Hendrych, Sebastian Pokutta
Published: 2025-12-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.10922v2

The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often prohibitive and classical approaches such as magnitude pruning are suboptimal on Transformers. State-of-the-art methods hence solve a layer-wise mask selection problem: finding a pruning mask that minimizes per-layer pruning error on a small set of calibration data. Exactly solving this problem is computationally infeasible due to its combinatorial nature and the size of the search space, and existing approaches rely on approximations or heuristics. We demonstrate that the mask selection problem can be made drastically more tractable at LLM scale. To that end, we decouple the rows by enforcing equal sparsity levels per row. This allows us to derive optimal 1-swaps (exchanging one kept and one pruned weight) computable efficiently via the Gram matrix. We propose a simple 1-swap algorithm that warmstarts from any pruning mask, runs efficiently on GPUs at LLM scale, and is essentially hyperparameter-free. Our approach reduces per-layer pruning error by up to 60% over Wanda (Sun et al., 2024) and consistently improves perplexity and zero-shot accuracy across state-of-the-art GPT architectures.

---

### SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale

Authors: Max Zimmer, Christophe Roux, Moritz Wagner, Deborah Hendrych, Sebastian Pokutta
Published: 2025-12-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.10922v1

The resource requirements of Neural Networks can be significantly reduced through pruning -- the removal of seemingly less important parameters. However, with the rise of Large Language Models (LLMs), full retraining to recover pruning-induced performance degradation is often prohibitive and classical approaches such as global magnitude pruning are suboptimal on Transformer architectures. State-of-the-art methods hence solve a layer-wise mask selection problem, the problem of finding a pruning mask which minimizes the per-layer pruning error on a small set of calibration data. Exactly solving this problem to optimality using Integer Programming (IP) solvers is computationally infeasible due to its combinatorial nature and the size of the search space, and existing approaches therefore rely on approximations or heuristics. In this work, we demonstrate that the mask selection problem can be made drastically more tractable at LLM scale. To that end, we decouple the rows by enforcing equal sparsity levels per row. This allows us to derive optimal 1-swaps (exchanging one kept and one pruned weight) that can be computed efficiently using the Gram matrix of the calibration data. Using these observations, we propose a tractable and simple 1-swap algorithm that warm starts from any pruning mask, runs efficiently on GPUs at LLM scale, and is essentially hyperparameter-free. We demonstrate that our approach reduces per-layer pruning error by up to 60% over Wanda (Sun et al., 2023) and consistently improves perplexity and zero-shot accuracy across state-of-the-art GPT architectures.

---

### CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences

Authors: Yiyang Wang, Chen Chen, Tica Lin, Vishnu Raj, Josh Kimball, Alex Cabral, Josiah Hester
Published: 2025-12-11
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2512.10918v2

Shared experiences are fundamental to social connection, yet media consumption is increasingly solitary. While AI companions offer real-time reactions and emotional regulation, existing systems either rely on single-agent designs or lack the social awareness and multi-party interaction required to replicate authentic group dynamics. We present CompanionCast, a general framework for orchestrating multiple specialized AI agents as social collaborators within a live shared context. CompanionCast integrates multimodal event detection, rolling context caching for improved grounding, and spatial audio to enhance co-presence. We validate CompanionCast through sports viewing, a domain with rich dynamics and strong social traditions. Pilot studies with soccer fans demonstrate that CompanionCast significantly improves perceived social presence and emotional sharing compared to solitary viewing. We conclude by discussing implications and open challenges for multi-agent systems as social collaborators in shared experiences.

---

### CompanionCast: A Multi-Agent Conversational AI Framework with Spatial Audio for Social Co-Viewing Experiences

Authors: Yiyang Wang, Chen Chen, Tica Lin, Vishnu Raj, Josh Kimball, Alex Cabral, Josiah Hester
Published: 2025-12-11
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2512.10918v1

Social presence is central to the enjoyment of watching content together, yet modern media consumption is increasingly solitary. We investigate whether multi-agent conversational AI systems can recreate the dynamics of shared viewing experiences across diverse content types. We present CompanionCast, a general framework for orchestrating multiple role-specialized AI agents that respond to video content using multimodal inputs, speech synthesis, and spatial audio. Distinctly, CompanionCast integrates an LLM-as-a-Judge module that iteratively scores and refines conversations across five dimensions (relevance, authenticity, engagement, diversity, personality consistency). We validate this framework through sports viewing, a domain with rich dynamics and strong social traditions, where a pilot study with soccer fans suggests that multi-agent interaction improves perceived social presence compared to solo viewing. We contribute: (1) a generalizable framework for orchestrating multi-agent conversations around multimodal video content, (2) a novel evaluator-agent pipeline for conversation quality control, and (3) exploratory evidence of increased social presence in AI-mediated co-viewing. We discuss challenges and future directions for applying this approach to diverse viewing contexts including entertainment, education, and collaborative watching experiences.

---

### Hermitian Yang--Mills connections on general vector bundles: geometry and physical Yukawa couplings

Authors: Challenger Mishra, Justin Tan
Published: 2025-12-11
Categories: hep-th, cs.LG
arXiv: https://arxiv.org/abs/2512.10907v1

We compute solutions to the Hermitian Yang-Mills equations on holomorphic vector bundles $V$ via an alternating optimisation procedure founded on geometric machine learning. The proposed method is fully general with respect to the rank and structure group of $V$, requiring only the ability to enumerate a basis of global sections for a given bundle. This enables us to compute the physically normalised Yukawa couplings in a broad class of heterotic string compactifications. Using this method, we carry out this computation in full for a heterotic compactification incorporating a gauge bundle with non-Abelian structure group.

---

### Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets

Authors: Feras Al Taha, Eilyan Bitar
Published: 2025-12-11
Categories: math.OC, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.10906v2

We consider a class of finite-horizon, linear-quadratic stochastic control problems, where the probability distribution governing the noise process is unknown but assumed to belong to an ambiguity set consisting of all distributions whose mean and covariance lie within norm balls centered at given nominal values. To cope with this ambiguity, we design causal affine control policies to minimize the worst-case expected regret over all distributions in the ambiguity set. The resulting minimax optimal control problem is shown to admit an equivalent reformulation as a tractable convex program, which can be interpreted as a regularized version of the nominal linear-quadratic stochastic control problem. Based on the dual of this convex reformulation, we develop a scalable projected subgradient method for computing optimal controllers to arbitrary accuracy. Numerical experiments are provided to compare the proposed method with state-of-the-art data-driven control design methods.

---

### Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets

Authors: Feras Al Taha, Eilyan Bitar
Published: 2025-12-11
Categories: math.OC, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.10906v1

In this paper, we consider a class of finite-horizon, linear-quadratic stochastic control problems, where the probability distribution governing the noise process is unknown but assumed to belong to an ambiguity set consisting of all distributions whose mean and covariance lie within norm balls centered at given nominal values. To address the distributional ambiguity, we explore the design of causal affine control policies to minimize the worst-case expected regret over all distributions in the given ambiguity set. The resulting minimax optimal control problem is shown to admit an equivalent reformulation as a tractable convex program that corresponds to a regularized version of the nominal linear-quadratic stochastic control problem. While this convex program can be recast as a semidefinite program, semidefinite programs are typically solved using primal-dual interior point methods that scale poorly with the problem size in practice. To address this limitation, we propose a scalable dual projected subgradient method to compute optimal controllers to an arbitrary accuracy. Numerical experiments are presented to benchmark the proposed method against state-of-the-art data-driven and distributionally robust control design approaches.

---

### Multi-Granular Node Pruning for Causal Circuit Discovery

Authors: Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad, A. B. Siddique
Published: 2025-12-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.10903v3

Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited to coarse-grained units such as attention heads or MLP blocks, overlooking finer structures like individual neurons. We propose a node-level pruning framework for circuit discovery that addresses both scalability and granularity limitations. Our method introduces learnable masks across multiple levels of granularity, from entire blocks to individual neurons, within a unified optimization objective. Granularity-specific sparsity penalties guide the pruning process, allowing a comprehensive compression in a single fine-tuning run. Empirically, our approach identifies circuits that are smaller in nodes than those discovered by prior methods; moreover, we demonstrate that many neurons deemed important by coarse methods are actually irrelevant, while still maintaining task performance. Furthermore, our method has a significantly lower memory footprint, 5-10x, as it does not require keeping intermediate activations in the memory to work.

---

### Multi-Granular Node Pruning for Circuit Discovery

Authors: Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad, A. B. Siddique
Published: 2025-12-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.10903v1

Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited to coarse-grained units such as attention heads or MLP blocks, overlooking finer structures like individual neurons. We propose a node-level pruning framework for circuit discovery that addresses both scalability and granularity limitations. Our method introduces learnable masks across multiple levels of granularity, from entire blocks to individual neurons, within a unified optimization objective. Granularity-specific sparsity penalties guide the pruning process, allowing a comprehensive compression in a single fine-tuning run. Empirically, our approach identifies circuits that are smaller in nodes than those discovered by prior methods; moreover, we demonstrate that many neurons deemed important by coarse methods are actually irrelevant, while still maintaining task performance. Furthermore, our method has a significantly lower memory footprint, 5-10x, as it does not require keeping intermediate activations in the memory to work.

---

### LLMs Can Assist with Proposal Selection at Large User Facilities

Authors: Lijie Ding, Janell Thomson, Jon Taylor, Changwoo Do
Published: 2025-12-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.10895v1

We explore how large language models (LLMs) can enhance the proposal selection process at large user facilities, offering a scalable, consistent, and cost-effective alternative to traditional human review. Proposal selection depends on assessing the relative strength among submitted proposals; however, traditional human scoring often suffers from weak inter-proposal correlations and is subject to reviewer bias and inconsistency. A pairwise preference-based approach is logically superior, providing a more rigorous and internally consistent basis for ranking, but its quadratic workload makes it impractical for human reviewers. We address this limitation using LLMs. Leveraging the uniquely well-curated proposals and publication records from three beamlines at the Spallation Neutron Source (SNS), Oak Ridge National Laboratory (ORNL), we show that the LLM rankings correlate strongly with the human rankings (Spearman $ρ\simeq 0.2-0.8$, improving to $\geq 0.5$ after 10\% outlier removal). Moreover, LLM performance is no worse than that of human reviewers in identifying proposals with high publication potential, while costing over two orders of magnitude less. Beyond ranking, LLMs enable advanced analyses that are challenging for humans, such as quantitative assessment of proposal similarity via embedding models, which provides information crucial for review committees.

---

### DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance

Authors: Peiying Zhang, Nanxuan Zhao, Matthew Fisher, Yiran Xu, Jing Liao, Difan Liu
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10894v1

Recent vision-language model (VLM)-based approaches have achieved impressive results on SVG generation. However, because they generate only text and lack visual signals during decoding, they often struggle with complex semantics and fail to produce visually appealing or geometrically coherent SVGs. We introduce DuetSVG, a unified multimodal model that jointly generates image tokens and corresponding SVG tokens in an end-to-end manner. DuetSVG is trained on both image and SVG datasets. At inference, we apply a novel test-time scaling strategy that leverages the model's native visual predictions as guidance to improve SVG decoding quality. Extensive experiments show that our method outperforms existing methods, producing visually faithful, semantically aligned, and syntactically clean SVGs across a wide range of applications.

---

### Iterative Compositional Data Generation for Robot Control

Authors: Anh-Quan Pham, Marcel Hussing, Shubhankar P. Patankar, Dani S. Bassett, Jorge Mendez-Mendez, Eric Eaton
Published: 2025-12-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.10891v5

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative models can synthesize useful data for individual tasks, they do not exploit the compositional structure of robotic domains and struggle to generalize to unseen task combinations. We propose a semantic compositional diffusion transformer that factorizes transitions into robot-, object-, obstacle-, and objective-specific components and learns their interactions through attention. Once trained on a limited subset of tasks, we show that our model can zero-shot generate high-quality transitions from which we can learn control policies for unseen task combinations. Then, we introduce an iterative self-improvement procedure in which synthetic data is validated via offline reinforcement learning and incorporated into subsequent training rounds. Our approach substantially improves zero-shot performance over monolithic and hard-coded compositional baselines, ultimately solving nearly all held-out tasks and demonstrating the emergence of meaningful compositional structure in the learned representations.

---

### Iterative Compositional Data Generation for Robot Control

Authors: Anh-Quan Pham, Marcel Hussing, Shubhankar P. Patankar, Dani S. Bassett, Jorge Mendez-Mendez, Eric Eaton
Published: 2025-12-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.10891v1

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative models can synthesize useful data for individual tasks, they do not exploit the compositional structure of robotic domains and struggle to generalize to unseen task combinations. We propose a semantic compositional diffusion transformer that factorizes transitions into robot-, object-, obstacle-, and objective-specific components and learns their interactions through attention. Once trained on a limited subset of tasks, we show that our model can zero-shot generate high-quality transitions from which we can learn control policies for unseen task combinations. Then, we introduce an iterative self-improvement procedure in which synthetic data is validated via offline reinforcement learning and incorporated into subsequent training rounds. Our approach substantially improves zero-shot performance over monolithic and hard-coded compositional baselines, ultimately solving nearly all held-out tasks and demonstrating the emergence of meaningful compositional structure in the learned representations.

---

### PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction

Authors: Brandon Smock, Valerie Faucon-Morin, Max Sokolov, Libin Liang, Tayyibah Khanam, Amrit Ramesh, Maury Courtland
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10888v3

Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), to extract tables directly in their full page or document context. However, a lack of annotated data has made progress difficult to demonstrate. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 unifies TE across various levels of surrounding context and, notably, is the first benchmark for multi-page TE. Our evaluations reveal that while current frontier models strongly outperform ($+0.354\ \textrm{GriTS}_\textrm{Con}$) small models on the most complex task (full-document multi-page TE), this gap can be closed or even reversed ($-0.056\ \textrm{GriTS}_\textrm{Con}$) on narrower tasks (cropped table extraction) with targeted training. Data is available at https://huggingface.co/datasets/kensho/PubTables-v2. Code and models will be released.

---

### PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction

Authors: Brandon Smock, Valerie Faucon-Morin, Max Sokolov, Libin Liang, Tayyibah Khanam, Maury Courtland
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10888v1

Table extraction (TE) is a key challenge in visual document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), that can extract tables directly in their full page or document context. However, progress has been difficult to demonstrate due to a lack of annotated data. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 supports a number of current challenging table extraction tasks. Notably, it is the first large-scale benchmark for multi-page table structure recognition. We demonstrate its usefulness by evaluating domain-specialized VLMs on these tasks and highlighting current progress. Finally, we use PubTables-v2 to create the Page-Object Table Transformer (POTATR), an image-to-graph extension of the Table Transformer to comprehensive page-level TE. Data, code, and trained models will be released.

---

### Physics-Informed Learning of Flow Distribution and Receiver Heat Losses in Parabolic Trough Solar Fields

Authors: Stefan Matthes, Markus Schramm
Published: 2025-12-11
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2512.10886v1

Parabolic trough Concentrating Solar Power (CSP) plants operate large hydraulic networks of collector loops that must deliver a uniform outlet temperature despite spatially heterogeneous optical performance, heat losses, and pressure drops. While loop temperatures are measured, loop-level mass flows and receiver heat-loss parameters are unobserved, making it impossible to diagnose hydraulic imbalances or receiver degradation using standard monitoring tools. We present a physics-informed learning framework that infers (i) loop-level mass-flow ratios and (ii) time-varying receiver heat-transfer coefficients directly from routine operational data. The method exploits nocturnal homogenization periods -- when hot oil is circulated through a non-irradiated field -- to isolate hydraulic and thermal-loss effects. A differentiable conjugate heat-transfer model is discretized and embedded into an end-to-end learning pipeline optimized using historical plant data from the 50 MW Andasol 3 solar field. The model accurately reconstructs loop temperatures (RMSE $<2^\circ$C) and produces physically meaningful estimates of loop imbalances and receiver heat losses. Comparison against drone-based infrared thermography (QScan) shows strong correspondence, correctly identifying all areas with high-loss receivers. This demonstrates that noisy real-world CSP operational data contain enough information to recover latent physical parameters when combined with appropriate modeling and differentiable optimization.

---

### Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity

Authors: Hauke Licht
Published: 2025-12-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.10882v4

Research increasingly leverages audio-visual materials to analyze emotions in political communication. Multimodal large language models (mLLMs) promise to enable such analyses through in-context learning. However, we lack systematic evidence on whether current mLLMs can reliably measure emotions in real-world political settings. This paper closes this gap by evaluating open- and closed-weights mLLMs available as of early 2026 in video-based emotional arousal measurement using two complementary human-labeled datasets: speech actor recordings created under laboratory conditions and real-world parliamentary debates. I find a critical lab-vs-field performance gap. In videos created under laboratory conditions, the examined mLLMs arousal scores approach human-level reliability. However, in parliamentary debate recordings, all examined models' arousal scores correlate at best moderately with average human ratings. Moreover, in each dataset, all but one of the examined mLLMs exhibit systematic gender-differential bias, consistently underestimating arousal more for male than for female speakers, resulting in a net-positive intensity bias. These findings reveal important limitations of current mLLMs for real-world political video analysis and establish a rigorous evaluation framework for tracking future developments.

---

### Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity

Authors: Hauke Licht
Published: 2025-12-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.10882v1

Emotions are central to politics and analyzing their role in political communication has a long tradition. As research increasingly leverages audio-visual materials to analyze the display of emotions, the emergence of multimodal generative AI promises great advances. However, we lack evidence about the effectiveness of multimodal AI in emotion analysis. This paper addresses this gap by evaluating current multimodal large language models (mLLMs) in video-based analysis of emotional arousal in two complementary data sets of human-labeled video recordings. I find that under ideal circumstances, mLLMs' emotional arousal ratings are highly reliable and show little to know indication of demographic bias. However, in recordings of speakers in real-world parliamentary debates, mLLMs' arousal ratings fail to deliver on this promise with potential negative consequences for downstream statistical inferences. This study therefore underscores the need for continued, thorough evaluation of emerging generative AI methods in political analysis and contributes a suitable replicable framework.

---

### MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

Authors: Kehong Gong, Zhengyu Wen, Weixia He, Mingxi Xu, Qi Wang, Ning Zhang, Zhengyu Li, Dongze Lian, Wei Zhao, Xiaoyu He, Mingyuan Zhang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10881v2

Motion capture now underpins content creation far beyond digital humans, yet most existing pipelines remain species- or template-specific. We formalize this gap as Category-Agnostic Motion Capture (CAMoCap): given a monocular video and an arbitrary rigged 3D asset as a prompt, the goal is to reconstruct a rotation-based animation such as BVH that directly drives the specific asset. We present MoCapAnything, a reference-guided, factorized framework that first predicts 3D joint trajectories and then recovers asset-specific rotations via constraint-aware inverse kinematics. The system contains three learnable modules and a lightweight IK stage: (1) a Reference Prompt Encoder that extracts per-joint queries from the asset's skeleton, mesh, and rendered images; (2) a Video Feature Extractor that computes dense visual descriptors and reconstructs a coarse 4D deforming mesh to bridge the gap between video and joint space; and (3) a Unified Motion Decoder that fuses these cues to produce temporally coherent trajectories. We also curate Truebones Zoo with 1038 motion clips, each providing a standardized skeleton-mesh-render triad. Experiments on both in-domain benchmarks and in-the-wild videos show that MoCapAnything delivers high-quality skeletal animations and exhibits meaningful cross-species retargeting across heterogeneous rigs, enabling scalable, prompt-driven 3D motion capture for arbitrary assets. Project page: https://animotionlab.github.io/MoCapAnything/

---

### MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

Authors: Kehong Gong, Zhengyu Wen, Weixia He, Mingxi Xu, Qi Wang, Ning Zhang, Zhengyu Li, Dongze Lian, Wei Zhao, Xiaoyu He, Mingyuan Zhang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10881v1

Motion capture now underpins content creation far beyond digital humans, yet most existing pipelines remain species- or template-specific. We formalize this gap as Category-Agnostic Motion Capture (CAMoCap): given a monocular video and an arbitrary rigged 3D asset as a prompt, the goal is to reconstruct a rotation-based animation such as BVH that directly drives the specific asset. We present MoCapAnything, a reference-guided, factorized framework that first predicts 3D joint trajectories and then recovers asset-specific rotations via constraint-aware inverse kinematics. The system contains three learnable modules and a lightweight IK stage: (1) a Reference Prompt Encoder that extracts per-joint queries from the asset's skeleton, mesh, and rendered images; (2) a Video Feature Extractor that computes dense visual descriptors and reconstructs a coarse 4D deforming mesh to bridge the gap between video and joint space; and (3) a Unified Motion Decoder that fuses these cues to produce temporally coherent trajectories. We also curate Truebones Zoo with 1038 motion clips, each providing a standardized skeleton-mesh-render triad. Experiments on both in-domain benchmarks and in-the-wild videos show that MoCapAnything delivers high-quality skeletal animations and exhibits meaningful cross-species retargeting across heterogeneous rigs, enabling scalable, prompt-driven 3D motion capture for arbitrary assets. Project page: https://animotionlab.github.io/MoCapAnything/

---

### Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes

Authors: Xuan Zhao, Zhuo Cao, Arya Bangun, Hanno Scharr, Ira Assent
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10878v1

Counterfactual explanations provide actionable insights by identifying minimal input changes required to achieve a desired model prediction. Beyond their interpretability benefits, counterfactuals can also be leveraged for model reconstruction, where a surrogate model is trained to replicate the behavior of a target model. In this work, we demonstrate that model reconstruction can be significantly improved by recognizing that counterfactuals, which typically lie close to the decision boundary, can serve as informative though less representative samples for both classes. This is particularly beneficial in settings with limited access to labeled data. We propose a method that integrates original data samples with counterfactuals to approximate class prototypes using the Wasserstein barycenter, thereby preserving the underlying distributional structure of each class. This approach enhances the quality of the surrogate model and mitigates the issue of decision boundary shift, which commonly arises when counterfactuals are naively treated as ordinary training instances. Empirical results across multiple datasets show that our method improves fidelity between the surrogate and target models, validating its effectiveness.

---

### Guided Transfer Learning for Discrete Diffusion Models

Authors: Julian Kleutgens, Claudio Battiloro, Lingkai Kong, Benjamin Grewe, Francesca Dominici, Mauricio Tec
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10877v4

Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autoregressive modeling. Yet this performance typically depends on large training datasets, challenging the performance of DMs in small-data regimes -- common under real-world constraints. Aimed at this challenge, recent work in continuous DMs suggests that transfer learning via classifier ratio-based guidance can adapt a pretrained DM to a related target distribution, often outperforming alternatives such as full-weight fine-tuning on the target data. By contrast, transfer learning for discrete DMs remains unexplored. We address this gap by exploring practical analogues of ratio-based transfer learning for discrete DMs. Our theoretical analysis shows that a direct extension of existing ratio-based guidance is computationally prohibitive, scaling with vocabulary size. To overcome this limitation, we introduce a scheduling mechanism that yields a practical algorithm, Guided Transfer Learning for discrete diffusion models (GTL). GTL enables sampling from a target distribution without modifying the pretrained denoiser and reduces the cost to linear scaling in vocabulary size, which in turn supports longer sequence generation. We evaluate GTL on sequential data, including synthetic Markov chains and language modeling tasks, and provide a detailed empirical analysis of its behavior. The results highlight a clear trade-off: when target datasets are large, weight fine-tuning is often preferable, whereas GTL becomes increasingly effective as target data shrinks. Finally, we experimentally demonstrate a key failure mode of GTL: when the source and target distributions overlap poorly, the ratio-based classifier required for guidance becomes unreliable, limiting transfer performance.

---

### Guided Transfer Learning for Discrete Diffusion Models

Authors: Julian Kleutgens, Claudio Battiloro, Lingkai Kong, Benjamin Grewe, Francesca Dominici, Mauricio Tec
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10877v1

Discrete diffusion models achieve strong performance across language and other discrete domains, providing a powerful alternative to autoregressive models. However, their strong performance relies on large training datasets, which are costly or risky to obtain, especially when adapting to new domains. Transfer learning is the natural way to adapt pretrained discrete diffusion models, but current methods require fine-tuning large diffusion models, which is computationally expensive and often impractical. Building on ratio-based transfer learning for continuous diffusion, we provide Guided Transfer Learning for discrete diffusion models (GTL). This enables sampling from a target distribution without modifying the pretrained denoiser. The same guidance formulation applies to both discrete-time diffusion and continuous-time score-based discrete diffusion, yielding a unified treatment. Guided discrete diffusion often requires many forward passes of the guidance network, which becomes impractical for large vocabularies and long sequences. To address this, we further present an efficient guided sampler that concentrates evaluations on planner-selected positions and top candidate tokens, thus lowering sampling time and computation. This makes guided language modeling practical at scale for large vocabularies and long sequences. We evaluate GTL on sequential data, including synthetic Markov chains and language modeling, and provide empirical analyses of its behavior.

---

### A Differentiable Digital Twin of Distributed Link Scheduling for Contention-Aware Networking

Authors: Zhongyuan Zhao, Yujun Ming, Kevin Chan, Ananthram Swami, Santiago Segarra
Published: 2025-12-11
Categories: cs.NI, cs.LG, eess.SP, eess.SY
arXiv: https://arxiv.org/abs/2512.10874v1

Many routing and flow optimization problems in wired networks can be solved efficiently using minimum cost flow formulations. However, this approach does not extend to wireless multi-hop networks, where the assumptions of fixed link capacity and linear cost structure collapse due to contention for shared spectrum resources. The key challenge is that the long-term capacity of a wireless link becomes a non-linear function of its network context, including network topology, link quality, and the traffic assigned to neighboring links. In this work, we pursue a new direction of modeling wireless network under randomized medium access control by developing an analytical network digital twin (NDT) that predicts link duty cycles from network context. We generalize randomized contention as finding a Maximal Independent Set (MIS) on the conflict graph using weighted Luby's algorithm, derive an analytical model of link duty cycles, and introduce an iterative procedure that resolves the circular dependency among duty cycle, link capacity, and contention probability. Our numerical experiments show that the proposed NDT accurately predicts link duty cycles and congestion patterns with up to a 5000x speedup over packet-level simulation, and enables us to optimize link scheduling using gradient descent for reduced congestion and radio footprint.

---

### Physics-informed Polynomial Chaos Expansion with Enhanced Constrained Optimization Solver and D-optimal Sampling

Authors: Qitian Lu, Himanshu Sharma, Michael D. Shields, Lukáš Novák
Published: 2025-12-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.10873v1

Physics-informed polynomial chaos expansions (PC$^2$) provide an efficient physically constrained surrogate modeling framework by embedding governing equations and other physical constraints into the standard data-driven polynomial chaos expansions (PCE) and solving via the Karush-Kuhn-Tucker (KKT) conditions. This approach improves the physical interpretability of surrogate models while achieving high computational efficiency and accuracy. However, the performance and efficiency of PC$^2$ can still be degraded with high-dimensional parameter spaces, limited data availability, or unrepresentative training data. To address this problem, this study explores two complementary enhancements to the PC$^2$ framework. First, a numerically efficient constrained optimization solver, straightforward updating of Lagrange multipliers (SULM), is adopted as an alternative to the conventional KKT solver. The SULM method significantly reduces computational cost when solving physically constrained problems with high-dimensionality and derivative boundary conditions that require a large number of virtual points. Second, a D-optimal sampling strategy is utilized to select informative virtual points to improve the stability and achieve the balance of accuracy and efficiency of the PC$^2$. The proposed methods are integrated into the PC$^2$ framework and evaluated through numerical examples of representative physical systems governed by ordinary or partial differential equations. The results demonstrate that the enhanced PC$^2$ has better comprehensive capability than standard PC$^2$, and is well-suited for high-dimensional uncertainty quantification tasks.

---

### From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

Authors: Zongzhao Li, Xiangzhe Kong, Jiahui Su, Zongyang Ma, Mingze Li, Songyou Li, Yuelin Zhang, Yu Rong, Tingyang Xu, Deli Zhao, Wenbing Huang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10867v2

This paper introduces the concept of Microscopic Spatial Intelligence (MiSI), the capability to perceive and reason about the spatial relationships of invisible microscopic entities, which is fundamental to scientific discovery. To assess the potential of Vision-Language Models (VLMs) in this domain, we propose a systematic benchmark framework MiSI-Bench. This framework features over 163,000 question-answer pairs and 587,000 images derived from approximately 4,000 molecular structures, covering nine complementary tasks that evaluate abilities ranging from elementary spatial transformations to complex relational identifications. Experimental results reveal that current state-of-the-art VLMs perform significantly below human level on this benchmark. However, a fine-tuned 7B model demonstrates substantial potential, even surpassing humans in spatial transformation tasks, while its poor performance in scientifically-grounded tasks like hydrogen bond recognition underscores the necessity of integrating explicit domain knowledge for progress toward scientific AGI. The datasets are available at https://huggingface.co/datasets/zongzhao/MiSI-bench.

---

### From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

Authors: Zongzhao Li, Xiangzhe Kong, Jiahui Su, Zongyang Ma, Mingze Li, Songyou Li, Yuelin Zhang, Yu Rong, Tingyang Xu, Deli Zhao, Wenbing Huang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10867v1

This paper introduces the concept of Microscopic Spatial Intelligence (MiSI), the capability to perceive and reason about the spatial relationships of invisible microscopic entities, which is fundamental to scientific discovery. To assess the potential of Vision-Language Models (VLMs) in this domain, we propose a systematic benchmark framework MiSI-Bench. This framework features over 163,000 question-answer pairs and 587,000 images derived from approximately 4,000 molecular structures, covering nine complementary tasks that evaluate abilities ranging from elementary spatial transformations to complex relational identifications. Experimental results reveal that current state-of-the-art VLMs perform significantly below human level on this benchmark. However, a fine-tuned 7B model demonstrates substantial potential, even surpassing humans in spatial transformation tasks, while its poor performance in scientifically-grounded tasks like hydrogen bond recognition underscores the necessity of integrating explicit domain knowledge for progress toward scientific AGI. The datasets are available at https://huggingface.co/datasets/zongzhao/MiSI-bench.

---

### UrbanAI 2025 Challenge: Linear vs Transformer Models for Long-Horizon Exogenous Temperature Forecasting

Authors: Ruslan Gokhman
Published: 2025-12-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.10866v1

We study long-horizon exogenous-only temperature forecasting - a challenging univariate setting where only the past values of the indoor temperature are used for prediction - using linear and Transformer-family models. We evaluate Linear, NLinear, DLinear, Transformer, Informer, and Autoformer under standardized train, validation, and test splits. Results show that linear baselines (Linear, NLinear, DLinear) consistently outperform more complex Transformer-family architectures, with DLinear achieving the best overall accuracy across all splits. These findings highlight that carefully designed linear models remain strong baselines for time series forecasting in challenging exogenous-only settings.

---

### Quantifying Emotional Tone in Tolkien's The Hobbit: Dialogue Sentiment Analysis with RegEx, NRC-VAD, and Python

Authors: Lilin Qiu
Published: 2025-12-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.10865v1

This study analyzes the emotional tone of dialogue in J. R. R. Tolkien's The Hobbit (1937) using computational text analysis. Dialogue was extracted with regular expressions, then preprocessed, and scored using the NRC-VAD lexicon to quantify emotional dimensions. The results show that the dialogue maintains a generally positive (high valence) and calm (low arousal) tone, with a gradually increasing sense of agency (dominance) as the story progresses. These patterns reflect the novel's emotional rhythm: moments of danger and excitement are regularly balanced by humor, camaraderie, and relief. Visualizations -- including emotional trajectory graphs and word clouds -- highlight how Tolkien's language cycles between tension and comfort. By combining computational tools with literary interpretation, this study demonstrates how digital methods can uncover subtle emotional structures in literature, revealing the steady rhythm and emotional modulation that shape the storytelling in The Hobbit.

---

### MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence

Authors: Jingli Lin, Runsen Xu, Shaohao Zhu, Sihan Yang, Peizhou Cao, Yunlong Ran, Miao Hu, Chenming Zhu, Yiman Xie, Yilin Long, Wenbo Hu, Dahua Lin et al.
Published: 2025-12-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.10863v1

Spatial understanding over continuous visual input is crucial for MLLMs to evolve into general-purpose assistants in physical environments. Yet there is still no comprehensive benchmark that holistically assesses the progress toward this goal. In this work, we introduce MMSI-Video-Bench, a fully human-annotated benchmark for video-based spatial intelligence in MLLMs. It operationalizes a four-level framework, Perception, Planning, Prediction, and Cross-Video Reasoning, through 1,106 questions grounded in 1,278 clips from 25 datasets and in-house videos. Each item is carefully designed and reviewed by 3DV experts with explanatory rationales to ensure precise, unambiguous grounding. Leveraging its diverse data sources and holistic task coverage, MMSI-Video-Bench also supports three domain-oriented sub-benchmarks (Indoor Scene Perception Bench, Robot Bench and Grounding Bench) for targeted capability assessment. We evaluate 25 strong open-source and proprietary MLLMs, revealing a striking human--AI gap: many models perform near chance, and the best reasoning model lags humans by nearly 60%. We further find that spatially fine-tuned models still fail to generalize effectively on our benchmark. Fine-grained error analysis exposes systematic failures in geometric reasoning, motion grounding, long-horizon prediction, and cross-video correspondence. We also show that typical frame-sampling strategies transfer poorly to our reasoning-intensive benchmark, and that neither 3D spatial cues nor chain-of-thought prompting yields meaningful gains. We expect our benchmark to establish a solid testbed for advancing video-based spatial intelligence.

---

### SWiT-4D: Sliding-Window Transformer for Lossless and Parameter-Free Temporal 4D Generation

Authors: Kehong Gong, Zhengyu Wen, Mingxi Xu, Weixia He, Qi Wang, Ning Zhang, Zhengyu Li, Chenbin Li, Dongze Lian, Wei Zhao, Xiaoyu He, Mingyuan Zhang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10860v1

Despite significant progress in 4D content generation, the conversion of monocular videos into high-quality animated 3D assets with explicit 4D meshes remains considerably challenging. The scarcity of large-scale, naturally captured 4D mesh datasets further limits the ability to train generalizable video-to-4D models from scratch in a purely data-driven manner. Meanwhile, advances in image-to-3D generation, supported by extensive datasets, offer powerful prior models that can be leveraged. To better utilize these priors while minimizing reliance on 4D supervision, we introduce SWiT-4D, a Sliding-Window Transformer for lossless, parameter-free temporal 4D mesh generation. SWiT-4D integrates seamlessly with any Diffusion Transformer (DiT)-based image-to-3D generator, adding spatial-temporal modeling across video frames while preserving the original single-image forward process, enabling 4D mesh reconstruction from videos of arbitrary length. To recover global translation, we further introduce an optimization-based trajectory module tailored for static-camera monocular videos. SWiT-4D demonstrates strong data efficiency: with only a single short (<10s) video for fine-tuning, it achieves high-fidelity geometry and stable temporal consistency, indicating practical deployability under extremely limited 4D supervision. Comprehensive experiments on both in-domain zoo-test sets and challenging out-of-domain benchmarks (C4D, Objaverse, and in-the-wild videos) show that SWiT-4D consistently outperforms existing baselines in temporal smoothness. Project page: https://animotionlab.github.io/SWIT4D/

---

### Scaling Behavior of Discrete Diffusion Language Models

Authors: Dimitri von Rütte, Janis Fluri, Omead Pooladzandi, Bernhard Schölkopf, Thomas Hofmann, Antonio Orvieto
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10858v3

Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishing factor. Discrete diffusion language models (DLMs) have been proposed as an alternative to autoregressive language models (ALMs). However, their scaling behavior has not yet been fully explored, with prior work suggesting that they require more data and compute to match the performance of ALMs. We study the scaling behavior of DLMs on different noise types by smoothly interpolating between masked and uniform diffusion while paying close attention to crucial hyperparameters such as batch size and learning rate. Our experiments reveal that the scaling behavior of DLMs strongly depends on the noise type and is considerably different from ALMs. While all noise types converge to similar loss values in compute-bound scaling, we find that uniform diffusion requires more parameters and less data for compute-efficient training compared to masked diffusion, making them a promising candidate in data-bound settings. We scale our uniform diffusion model up to 10B parameters trained for $10^{22}$ FLOPs, confirming the predicted scaling behavior and making it the largest publicly known uniform diffusion model to date.

---

### Scaling Behavior of Discrete Diffusion Language Models

Authors: Dimitri von Rütte, Janis Fluri, Omead Pooladzandi, Bernhard Schölkopf, Thomas Hofmann, Antonio Orvieto
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10858v1

Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishing factor. Discrete diffusion language models (DLMs) have been proposed as an alternative to autoregressive language models (ALMs). However, their scaling behavior has not yet been fully explored, with prior work suggesting that they require more data and compute to match the performance of ALMs. We study the scaling behavior of DLMs on different noise types by smoothly interpolating between masked and uniform diffusion while paying close attention to crucial hyperparameters such as batch size and learning rate. Our experiments reveal that the scaling behavior of DLMs strongly depends on the noise type and is considerably different from ALMs. While all noise types converge to similar loss values in compute-bound scaling, we find that uniform diffusion requires more parameters and less data for compute-efficient training compared to masked diffusion, making them a promising candidate in data-bound settings. We scale our uniform diffusion model up to 10B parameters trained for $10^{22}$ FLOPs, confirming the predicted scaling behavior and making it the largest publicly known uniform diffusion model to date.

---

### Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

Authors: Chirag Modi, Jiequn Han, Eric Vanden-Eijnden, Joan Bruna
Published: 2025-12-11
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2512.10857v2

Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A generative model for the original data thus requires solving an inverse problem at the level of distributions. In this work, we introduce a novel approach to this task based on Stochastic Interpolants: we iteratively update a transport map between corrupted and clean data samples using only access to the corrupted dataset as well as black box access to the corruption channel. Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data. We refer to the resulting method as the self-consistent stochastic interpolant (SCSI). It (i) is computationally efficient compared to variational alternatives, (ii) highly flexible, handling arbitrary nonlinear forward models with only black-box access, and (iii) enjoys theoretical guarantees. We demonstrate superior performance on inverse problems in natural image processing and scientific reconstruction, and establish convergence guarantees of the scheme under appropriate assumptions. Our source code is publicly available at https://github.com/modichirag/SCSI

---

### Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

Authors: Chirag Modi, Jiequn Han, Eric Vanden-Eijnden, Joan Bruna
Published: 2025-12-11
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2512.10857v1

Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A generative model for the original data thus requires solving an inverse problem at the level of distributions. In this work, we introduce a novel approach to this task based on Stochastic Interpolants: we iteratively update a transport map between corrupted and clean data samples using only access to the corrupted dataset as well as black box access to the corruption channel. Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data. We refer to the resulting method as the self-consistent stochastic interpolant (SCSI). It (i) is computationally efficient compared to variational alternatives, (ii) highly flexible, handling arbitrary nonlinear forward models with only black-box access, and (iii) enjoys theoretical guarantees. We demonstrate superior performance on inverse problems in natural image processing and scientific reconstruction, and establish convergence guarantees of the scheme under appropriate assumptions.

---

### Bayesian Symbolic Regression via Posterior Sampling

Authors: Geoffrey F. Bomarito, Patrick E. Leser
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10849v1

Symbolic regression is a powerful tool for discovering governing equations directly from data, but its sensitivity to noise hinders its broader application. This paper introduces a Sequential Monte Carlo (SMC) framework for Bayesian symbolic regression that approximates the posterior distribution over symbolic expressions, enhancing robustness and enabling uncertainty quantification for symbolic regression in the presence of noise. Differing from traditional genetic programming approaches, the SMC-based algorithm combines probabilistic selection, adaptive tempering, and the use of normalized marginal likelihood to efficiently explore the search space of symbolic expressions, yielding parsimonious expressions with improved generalization. When compared to standard genetic programming baselines, the proposed method better deals with challenging, noisy benchmark datasets. The reduced tendency to overfit and enhanced ability to discover accurate and interpretable equations paves the way for more robust symbolic regression in scientific discovery and engineering design applications.

---

### PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

Authors: Jianqi Chen, Biao Zhang, Xiangjun Tang, Peter Wonka
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10840v2

6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects. Project page: https://windvchen.github.io/PoseGAM/ .

---

### PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

Authors: Jianqi Chen, Biao Zhang, Xiangjun Tang, Peter Wonka
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10840v1

6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects. Project page: https://windvchen.github.io/PoseGAM/ .

---

### UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors

Authors: Atahan Cilan, Atay Özgövde
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10835v2

This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models for different player types, or provide no direct mapping between interpretable behavioral parameters and the learned policy, limiting their scalability and controllability. We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses the subset representing real human styles. During training, each agent receives both its current and target behavior vectors as input, and the reward is based on the normalized reduction in distance between them. This allows the policy to learn how actions influence behavioral statistics, enabling smooth control over attributes such as aggressiveness, mobility, and cooperativeness. A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining. Experiments conducted in a custom multi-player Unity game show that the proposed framework produces significantly greater behavioral diversity than a win-only baseline and reliably matches specified behavior vectors across diverse targets. The method offers a scalable solution for automated playtesting, game balancing, human-like behavior simulation, and replacing disconnected players in online games.

---

### Learning Controllable and Diverse Player Behaviors in Multi-Agent Environments

Authors: Atahan Cilan, Atay Özgövde
Published: 2025-12-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.10835v1

This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models for different player types, or provide no direct mapping between interpretable behavioral parameters and the learned policy, limiting their scalability and controllability. We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses the subset representing real human styles. During training, each agent receives both its current and target behavior vectors as input, and the reward is based on the normalized reduction in distance between them. This allows the policy to learn how actions influence behavioral statistics, enabling smooth control over attributes such as aggressiveness, mobility, and cooperativeness. A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining. Experiments conducted in a custom multi-player Unity game show that the proposed framework produces significantly greater behavioral diversity than a win-only baseline and reliably matches specified behavior vectors across diverse targets. The method offers a scalable solution for automated playtesting, game balancing, human-like behavior simulation, and replacing disconnected players in online games.

---

### An Elementary Proof of the Near Optimality of LogSumExp Smoothing

Authors: Thabo Samakhoana, Benjamin Grimmer
Published: 2025-12-11
Categories: math.ST, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.10825v3

We consider the design of smoothings of the (coordinate-wise) max function in $\mathbb{R}^d$ in the infinity norm. The LogSumExp function $f(x)=\ln(\sum^d_i\exp(x_i))$ provides a classical smoothing, differing from the max function in value by at most $\ln(d)$. We provide an elementary construction of a lower bound, establishing that every overestimating smoothing of the max function must differ by at least $\sim 0.8145\ln(d)$. Hence, LogSumExp is optimal up to small constant factors. However, we provide strictly stronger smoothings showing the entropy-based LogSumExp approach is not exactly optimal. In small dimensions, we propose exactly optimal smoothings, attaining our lower bound.

---

### An Elementary Proof of the Near Optimality of LogSumExp Smoothing

Authors: Thabo Samakhoana, Benjamin Grimmer
Published: 2025-12-11
Categories: math.ST, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.10825v1

We consider the design of smoothings of the (coordinate-wise) max function in $\mathbb{R}^d$ in the infinity norm. The LogSumExp function $f(x)=\ln(\sum^d_i\exp(x_i))$ provides a classical smoothing, differing from the max function in value by at most $\ln(d)$. We provide an elementary construction of a lower bound, establishing that every overestimating smoothing of the max function must differ by at least $\sim 0.8145\ln(d)$. Hence, LogSumExp is optimal up to constant factors. However, in small dimensions, we provide stronger, exactly optimal smoothings attaining our lower bound, showing that the entropy-based LogSumExp approach to smoothing is not exactly optimal.

---

### V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions

Authors: Mumuksh Tayal, Manan Tayal, Aditya Singh, Shishir Kolathaya, Ravi Prakash
Published: 2025-12-11
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.10822v2

Ensuring safety in autonomous systems requires controllers that aim to satisfy state-wise constraints without relying on online interaction.While existing Safe Offline RL methods typically enforce soft expected-cost constraints, they struggle to ensure strict state-wise safety. Conversely, Control Barrier Functions (CBFs) offer a principled mechanism to enforce forward invariance, but often rely on expert-designed barrier functions or knowledge of the system dynamics. We introduce Value-Guided Offline Control Barrier Functions (V-OCBF), a framework that learns a neural CBF entirely from offline demonstrations. Unlike prior approaches, V-OCBF does not assume access to the dynamics model; instead, it derives a recursive finite-difference barrier update, enabling model-free learning of a barrier that propagates safety information over time. Moreover, V-OCBF incorporates an expectile-based objective that avoids querying the barrier on out-of-distribution actions and restricts updates to the dataset-supported action set. The learned barrier is then used with a Quadratic Program (QP) formulation to synthesize real-time safe control. Across multiple case studies, V-OCBF yields substantially fewer safety violations than baseline methods while maintaining strong task performance, highlighting its scalability for offline synthesis of safety-critical controllers without online interaction or hand-engineered barriers.

---

### V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions

Authors: Mumuksh Tayal, Manan Tayal, Aditya Singh, Shishir Kolathaya, Ravi Prakash
Published: 2025-12-11
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.10822v1

Ensuring safety in autonomous systems requires controllers that satisfy hard, state-wise constraints without relying on online interaction. While existing Safe Offline RL methods typically enforce soft expected-cost constraints, they do not guarantee forward invariance. Conversely, Control Barrier Functions (CBFs) provide rigorous safety guarantees but usually depend on expert-designed barrier functions or full knowledge of the system dynamics. We introduce Value-Guided Offline Control Barrier Functions (V-OCBF), a framework that learns a neural CBF entirely from offline demonstrations. Unlike prior approaches, V-OCBF does not assume access to the dynamics model; instead, it derives a recursive finite-difference barrier update, enabling model-free learning of a barrier that propagates safety information over time. Moreover, V-OCBF incorporates an expectile-based objective that avoids querying the barrier on out-of-distribution actions and restricts updates to the dataset-supported action set. The learned barrier is then used with a Quadratic Program (QP) formulation to synthesize real-time safe control. Across multiple case studies, V-OCBF yields substantially fewer safety violations than baseline methods while maintaining strong task performance, highlighting its scalability for offline synthesis of safety-critical controllers without online interaction or hand-engineered barriers.

---

### Agile Deliberation: Concept Deliberation for Subjective Visual Classification

Authors: Leijie Wang, Otilia Stretcu, Wei Qiao, Thomas Denby, Krishnamurthy Viswanathan, Enming Luo, Chun-Ta Lu, Tushar Dogra, Ranjay Krishna, Ariel Fuxman
Published: 2025-12-11
Categories: cs.AI, cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2512.10821v2

From content moderation to content curation, applications requiring vision classifiers for visual concepts are rapidly expanding. Existing human-in-the-loop approaches typically assume users begin with a clear, stable concept understanding to be able to provide high-quality supervision. In reality, users often start with a vague idea and must iteratively refine it through "concept deliberation", a practice we uncovered through structured interviews with content moderation experts. We operationalize the common strategies in deliberation used by real content moderators into a human-in-the-loop framework called "Agile Deliberation" that explicitly supports evolving and subjective concepts. The system supports users in defining the concept for themselves by exposing them to borderline cases. The system does this with two deliberation stages: (1) concept scoping, which decomposes the initial concept into a structured hierarchy of sub-concepts, and (2) concept iteration, which surfaces semantically borderline examples for user reflection and feedback to iteratively align an image classifier with the user's evolving intent. Since concept deliberation is inherently subjective and interactive, we painstakingly evaluate the framework through 18 user sessions, each 1.5h long, rather than standard benchmarking datasets. We find that Agile Deliberation achieves 7.5% higher F1 scores than automated decomposition baselines and more than 3% higher than manual deliberation, while participants reported clearer conceptual understanding and lower cognitive effort.

---

### Agile Deliberation: Concept Deliberation for Subjective Visual Classification

Authors: Leijie Wang, Otilia Stretcu, Wei Qiao, Thomas Denby, Krishnamurthy Viswanathan, Enming Luo, Chun-Ta Lu, Tushar Dogra, Ranjay Krishna, Ariel Fuxman
Published: 2025-12-11
Categories: cs.AI, cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2512.10821v1

From content moderation to content curation, applications requiring vision classifiers for visual concepts are rapidly expanding. Existing human-in-the-loop approaches typically assume users begin with a clear, stable concept understanding to be able to provide high-quality supervision. In reality, users often start with a vague idea and must iteratively refine it through "concept deliberation", a practice we uncovered through structured interviews with content moderation experts. We operationalize the common strategies in deliberation used by real content moderators into a human-in-the-loop framework called "Agile Deliberation" that explicitly supports evolving and subjective concepts. The system supports users in defining the concept for themselves by exposing them to borderline cases. The system does this with two deliberation stages: (1) concept scoping, which decomposes the initial concept into a structured hierarchy of sub-concepts, and (2) concept iteration, which surfaces semantically borderline examples for user reflection and feedback to iteratively align an image classifier with the user's evolving intent. Since concept deliberation is inherently subjective and interactive, we painstakingly evaluate the framework through 18 user sessions, each 1.5h long, rather than standard benchmarking datasets. We find that Agile Deliberation achieves 7.5% higher F1 scores than automated decomposition baselines and more than 3% higher than manual deliberation, while participants reported clearer conceptual understanding and lower cognitive effort.

---

### Deep sets and event-level maximum-likelihood estimation for fast pile-up jet rejection in ATLAS

Authors: Mohammed Aboelela
Published: 2025-12-11
Categories: hep-ex, cs.LG
arXiv: https://arxiv.org/abs/2512.10819v1

Multiple proton-proton collisions (pile-up) occur at every bunch crossing at the LHC, with the mean number of interactions expected to reach 80 during Run 3 and up to 200 at the High-Luminosity LHC. As a direct consequence, events with multijet signatures will occur at increasingly high rates. To cope with the increased luminosity, being able to efficiently group jets according to their origin along the beamline is crucial, particularly at the trigger level. In this work, a novel uncertainty-aware jet regression model based on a Deep Sets architecture is introduced, DIPz, to regress on a jet origin position along the beamline. The inputs to the DIPz algorithm are the charged particle tracks associated to each jet. An event-level discriminant, the Maximum Log Product of Likelihoods (MLPL), is constructed by combining the DIPz per-jet predictions. MLPL is cut-optimized to select events compatible with targeted multi-jet signature selection. This combined approach provides a robust and computationally efficient method for pile-up rejection in multi-jet final states, applicable to real-time event selections at the ATLAS High Level Trigger.

---

### Self-Ensemble Post Learning for Noisy Domain Generalization

Authors: Wang Lu, Jindong Wang
Published: 2025-12-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.10818v1

While computer vision and machine learning have made great progress, their robustness is still challenged by two key issues: data distribution shift and label noise. When domain generalization (DG) encounters noise, noisy labels further exacerbate the emergence of spurious features in deep layers, i.e. spurious feature enlargement, leading to a degradation in the performance of existing algorithms. This paper, starting from domain generalization, explores how to make existing methods rework when meeting noise. We find that the latent features inside the model have certain discriminative capabilities, and different latent features focus on different parts of the image. Based on these observations, we propose the Self-Ensemble Post Learning approach (SEPL) to diversify features which can be leveraged. Specifically, SEPL consists of two parts: feature probing training and prediction ensemble inference. It leverages intermediate feature representations within the model architecture, training multiple probing classifiers to fully exploit the capabilities of pre-trained models, while the final predictions are obtained through the integration of outputs from these diverse classification heads. Considering the presence of noisy labels, we employ semi-supervised algorithms to train probing classifiers. Given that different probing classifiers focus on different areas, we integrate their predictions using a crowdsourcing inference approach. Extensive experimental evaluations demonstrate that the proposed method not only enhances the robustness of existing methods but also exhibits significant potential for real-world applications with high flexibility.

---

### Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

Authors: Brian P. Powell, Jordan A. Caraballo-Vega, Mark L. Carroll, Thomas Maxwell, Andrew Ptak, Greg Olmschenk, Jorge Martinez-Palomera
Published: 2025-12-11
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2512.10817v1

We report the discovery that binary encoding allows neural networks to extrapolate periodic functions beyond their training bounds. We introduce Normalized Base-2 Encoding (NB2E) as a method for encoding continuous numerical values and demonstrate that, using this input encoding, vanilla multi-layer perceptrons (MLP) successfully extrapolate diverse periodic signals without prior knowledge of their functional form. Internal activation analysis reveals that NB2E induces bit-phase representations, enabling MLPs to learn and extrapolate signal structure independently of position.

---