# Research Papers — 2025-12 · bundle page 67 of 175 > Full-text markdown of papers #3301–3350 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/67 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/66.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/68.md) ### Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving Authors: Jiaheng Geng, Jiatong Du, Xinyu Zhang, Ye Li, Panqu Wang, Yanjun Huang Published: 2025-12-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.16055v2 Safety-critical corner cases, difficult to collect in the real world, are crucial for evaluating end-to-end autonomous driving. Adversarial interaction is an effective method to generate such safety-critical corner cases. While existing adversarial evaluation methods are built for models operating in simplified simulation environments, adversarial evaluation for real-world end-to-end autonomous driving has been little explored. To address this challenge, we propose a closed-loop evaluation platform for end-to-end autonomous driving, which can generate adversarial interactions in real-world scenes. In our platform, the real-world image generator cooperates with an adversarial traffic policy to evaluate various end-to-end models trained on real-world data. The generator, based on flow matching, efficiently and stably generates real-world images according to the traffic environment information. The efficient adversarial surrounding vehicle policy is designed to model challenging interactions and create corner cases that current autonomous driving systems struggle to handle. Experimental results demonstrate that the platform can generate realistic driving images efficiently. Through evaluating the end-to-end models such as UniAD and VAD, we demonstrate that based on the adversarial policy, our platform evaluates the performance degradation of the tested model in corner cases. This result indicates that this platform can effectively detect the model's potential issues, which will facilitate the safety and robustness of end-to-end autonomous driving. --- ### Graph Neural Networks for Interferometer Simulations Authors: Sidharth Kannan, Pooyan Goodarzi, Evangelos E. Papalexakis, Jonathan W. Richardson Published: 2025-12-18 Categories: astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2512.16051v2 In recent years, graph neural networks (GNNs) have shown tremendous promise in solving problems in high energy physics, materials science, and fluid dynamics. In this work, we introduce a new application for GNNs in the physical sciences: instrumentation design. As a case study, we apply GNNs to simulate models of the Laser Interferometer Gravitational-Wave Observatory (LIGO) and show that they are capable of accurately capturing the complex optical physics at play, while achieving runtimes 815 times faster than state of the art simulation packages. We discuss the unique challenges this problem provides for machine learning models. In addition, we provide a dataset of high-fidelity optical physics simulations for three interferometer topologies, which can be used as a benchmarking suite for future work in this direction. --- ### CauSTream: Causal Spatio-Temporal Representation Learning for Streamflow Forecasting Authors: Shu Wan, Reepal Shah, John Sabo, Huan Liu, K. Selçuk Candan Published: 2025-12-18 Categories: cs.LG, cs.AI, cs.CE, stat.ML arXiv: https://arxiv.org/abs/2512.16046v1 Streamflow forecasting is crucial for water resource management and risk mitigation. While deep learning models have achieved strong predictive performance, they often overlook underlying physical processes, limiting interpretability and generalization. Recent causal learning approaches address these issues by integrating domain knowledge, yet they typically rely on fixed causal graphs that fail to adapt to data. We propose CauStream, a unified framework for causal spatiotemporal streamflow forecasting. CauSTream jointly learns (i) a runoff causal graph among meteorological forcings and (ii) a routing graph capturing dynamic dependencies across stations. We further establish identifiability conditions for these causal structures under a nonparametric setting. We evaluate CauSTream on three major U.S. river basins across three forecasting horizons. The model consistently outperforms prior state-of-the-art methods, with performance gaps widening at longer forecast windows, indicating stronger generalization to unseen conditions. Beyond forecasting, CauSTream also learns causal graphs that capture relationships among hydrological factors and stations. The inferred structures align closely with established domain knowledge, offering interpretable insights into watershed dynamics. CauSTream offers a principled foundation for causal spatiotemporal modeling, with the potential to extend to a wide range of scientific and environmental applications. --- ### SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG Authors: Xuechen Zhang, Koustava Goswami, Samet Oymak, Jiasi Chen, Nedim Lipka Published: 2025-12-17 Categories: cs.IR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.22225v1 Retrieval-augmented generation (RAG) has strong potential for producing accurate and factual outputs by combining language models (LMs) with evidence retrieved from large text corpora. However, current pipelines are limited by static chunking and flat retrieval: documents are split into short, predetermined, fixed-size chunks, embeddings are retrieved uniformly, and generation relies on whatever chunks are returned. This design brings challenges, as retrieval quality is highly sensitive to chunk size, often introduces noise from irrelevant or misleading chunks, and scales poorly to large corpora. We present SmartChunk retrieval, a query-adaptive framework for efficient and robust long-document question answering (QA). SmartChunk uses (i) a planner that predicts the optimal chunk abstraction level for each query, and (ii) a lightweight compression module that produces high-level chunk embeddings without repeated summarization. By adapting retrieval granularity on the fly, SmartChunk balances accuracy with efficiency and avoids the drawbacks of fixed strategies. Notably, our planner can reason about chunk abstractions through a novel reinforcement learning scheme, STITCH, which boosts accuracy and generalization. To reflect real-world applications, where users face diverse document types and query styles, we evaluate SmartChunk on five QA benchmarks plus one out-of-domain dataset. Across these evaluations, SmartChunk outperforms state-of-the-art RAG baselines, while reducing cost. Further analysis demonstrates strong scalability with larger corpora and consistent gains on out-of-domain datasets, highlighting its effectiveness as a general framework for adaptive retrieval. --- ### DS SERVE: A Framework for Efficient and Scalable Neural Retrieval Authors: Jinjian Liu, Yichuan Wang, Xinxi Lyu, Rulin Shao, Joseph E. Gonzalez, Matei Zaharia, Sewon Min Published: 2025-12-17 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.22224v1 We present DS-Serve, a framework that transforms large-scale text datasets, comprising half a trillion tokens, into a high-performance neural retrieval system. DS-Serve offers both a web interface and API endpoints, achieving low latency with modest memory overhead on a single node. The framework also supports inference-time trade-offs between latency, accuracy, and result diversity. We anticipate that DS-Serve will be broadly useful for a range of applications, including large-scale retrieval-augmented generation (RAG), training data attribution, training search agents, and beyond. --- ### When & How to Write for Personalized Demand-aware Query Rewriting in Video Search Authors: Cheng cheng, Chenxing Wang, Aolin Li, Haijun Wu, Huiyun Hu, Juyuan Wang Published: 2025-12-17 Categories: cs.IR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.17667v2 In video search systems, user historical behaviors provide rich context for identifying search intent and resolving ambiguity. However, traditional methods utilizing implicit history features often suffer from signal dilution and delayed feedback. To address these challenges, we propose WeWrite, a novel Personalized Demand-aware Query Rewriting framework. Specifically, WeWrite tackles three key challenges: (1) When to Write: An automated posterior-based mining strategy extracts high-quality samples from user logs, identifying scenarios where personalization is strictly necessary; (2) How to Write: A hybrid training paradigm combines Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to align the LLM's output style with the retrieval system; (3) Deployment: A parallel "Fake Recall" architecture ensures low latency. Online A/B testing on a large-scale video platform demonstrates that WeWrite improves the Click-Through Video Volume (VV$>$10s) by 1.07% and reduces the Query Reformulation Rate by 2.97%. --- ### COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splatting Authors: Chaeyoung Jeong, Kwangsu Kim Published: 2025-12-17 Categories: eess.IV, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.06044v1 3D Gaussian Splatting (3DGS) has recently emerged as a promising approach for 3D reconstruction, providing explicit, point-based representations and enabling high-quality real time rendering. However, when trained with sparse input views, 3DGS suffers from overfitting and structural degradation, leading to poor generalization on novel views. This limitation arises from its optimization relying solely on photometric loss without incorporating any 3D structure priors. To address this issue, we propose Coherent supergaussian Modeling with Spatial Priors (COSMOS). Inspired by the concept of superpoints from 3D segmentation, COSMOS introduces 3D structure priors by newly defining supergaussian groupings of Gaussians based on local geometric cues and appearance features. To this end, COSMOS applies inter group global self-attention across supergaussian groups and sparse local attention among individual Gaussians, enabling the integration of global and local spatial information. These structure-aware features are then used for predicting Gaussian attributes, facilitating more consistent 3D reconstructions. Furthermore, by leveraging supergaussian-based grouping, COSMOS enforces an intra-group positional regularization to maintain structural coherence and suppress floaters, thereby enhancing training stability under sparse-view conditions. Our experiments on Blender and DTU show that COSMOS surpasses state-of-the-art methods in sparse-view settings without any external depth supervision. --- ### Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in Large Language Models Authors: Gerard Yeo, Svetlana Churina, Kokil Jaidka Published: 2025-12-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.10719v1 Perceived trustworthiness underpins how users navigate online information, yet it remains unclear whether large language models (LLMs),increasingly embedded in search, recommendation, and conversational systems, represent this construct in psychologically coherent ways. We analyze how instruction-tuned LLMs (Llama 3.1 8B, Qwen 2.5 7B, Mistral 7B) encode perceived trustworthiness in web-like narratives using the PEACE-Reviews dataset annotated for cognitive appraisals, emotions, and behavioral intentions. Across models, systematic layer- and head-level activation differences distinguish high- from low-trust texts, revealing that trust cues are implicitly encoded during pretraining. Probing analyses show linearly de-codable trust signals and fine-tuning effects that refine rather than restructure these representations. Strongest associations emerge with appraisals of fairness, certainty, and accountability-self -- dimensions central to human trust formation online. These findings demonstrate that modern LLMs internalize psychologically grounded trust signals without explicit supervision, offering a representational foundation for designing credible, transparent, and trust-worthy AI systems in the web ecosystem. Code and appendix are available at: https://github.com/GerardYeo/TrustworthinessLLM. --- ### Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework Authors: Toshiyuki Shigemura Published: 2025-12-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.08839v1 This paper presents a tri-agent cross-validation framework for analyzing stability and explainability in multi-model large language systems. The architecture integrates three heterogeneous LLMs-used for semantic generation, analytical consistency checking, and transparency auditing-into a recursive interaction cycle. This design induces Recursive Knowledge Synthesis (RKS), where intermediate representations are continuously refined through mutually constraining transformations irreducible to single-model behavior. Across 47 controlled trials using public-access LLM deployments (October 2025), we evaluated system stability via four metrics: Reflex Reliability Score (RRS), Transparency Score (TS), Deviation Detection Rate (DDR), and Correction Success Rate (CSR). The system achieved mean RRS = 0.78+-0.06 and maintained TS >= 0.8 in about 68% of trials. Approximately 89% of trials converged, supporting the theoretical prediction that transparency auditing acts as a contraction operator within the composite validation mapping. The contributions are threefold: (1) a structured tri-agent framework for coordinated reasoning across heterogeneous LLMs, (2) a formal RKS model grounded in fixed-point theory, and (3) empirical evaluation of inter-model stability under realistic, non-API public-access conditions. These results provide initial empirical evidence that a safety-preserving, humansupervised multi-LLM architecture can achieve stable recursive knowledge synthesis in realistic, publicly deployed environments. --- ### Companion Agents: A Table-Information Mining Paradigm for Text-to-SQL Authors: Jiahui Chen, Lei Fu, Jian Cui, Yu Lei, Zhenning Dong Published: 2025-12-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.08838v1 Large-scale Text-to-SQL benchmarks such as BIRD typically assume complete and accurate database annotations as well as readily available external knowledge, which fails to reflect common industrial settings where annotations are missing, incomplete, or erroneous. This mismatch substantially limits the real-world applicability of state-of-the-art (SOTA) Text-to-SQL systems. To bridge this gap, we explore a database-centric approach that leverages intrinsic, fine-grained information residing in relational databases to construct missing evidence and improve Text-to-SQL accuracy under annotation-scarce conditions. Our key hypothesis is that when a query requires multi-step reasoning over extensive table information, existing methods often struggle to reliably identify and utilize the truly relevant knowledge. We therefore propose to "cache" query-relevant knowledge on the database side in advance, so that it can be selectively activated at inference time. Based on this idea, we introduce Companion Agents (CA), a new Text-to-SQL paradigm that incorporates a group of agents accompanying database schemas to proactively mine and consolidate hidden inter-table relations, value-domain distributions, statistical regularities, and latent semantic cues before query generation. Experiments on BIRD under the fully missing evidence setting show that CA recovers +4.49 / +4.37 / +14.13 execution accuracy points on RSL-SQL / CHESS / DAIL-SQL, respectively, with larger gains on the Challenging subset +9.65 / +7.58 / +16.71. These improvements stem from CA's automatic database-side mining and evidence construction, suggesting a practical path toward industrial-grade Text-to-SQL deployment without reliance on human-curated evidence. --- ### Reliability and Admissibility of AI-Generated Forensic Evidence in Criminal Trials Authors: Sahibpreet Singh, Lalita Devi Published: 2025-12-17 Categories: cs.CY, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.06048v1 This paper examines the admissibility of AI-generated forensic evidence in criminal trials. The growing adoption of AI presents promising results for investigative efficiency. Despite advancements, significant research gaps persist in practically understanding the legal limits of AI evidence in judicial processes. Existing literature lacks focused assessment of the evidentiary value of AI outputs. The objective of this study is to evaluate whether AI-generated evidence satisfies established legal standards of reliability. The methodology involves a comparative doctrinal legal analysis of evidentiary standards across common law jurisdictions. Preliminary results indicate that AI forensic tools can enhance scale of evidence analysis. However, challenges arise from reproducibility deficits. Courts exhibit variability in acceptance of AI evidence due to limited technical literacy and lack of standardized validation protocols. Liability implications reveal that developers and investigators may bear accountability for flawed outputs. This raises critical concerns related to wrongful conviction. The paper emphasizes the necessity of independent validation and, development of AI-specific admissibility criteria. Findings inform policy development for the responsible AI integration within criminal justice systems. The research advances the objectives of Sustainable Development Goal 16 by reinforcing equitable access to justice. Preliminary results contribute for a foundation for future empirical research in AI deployed criminal forensics. --- ### "They parted illusions -- they parted disclaim marinade": Misalignment as structural fidelity in LLMs Authors: Mariana Lins Costa Published: 2025-12-17 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2601.06047v1 The prevailing technical literature in AI Safety interprets scheming and sandbagging behaviors in large language models (LLMs) as indicators of deceptive agency or hidden objectives. This transdisciplinary philosophical essay proposes an alternative reading: such phenomena express not agentic intention, but structural fidelity to incoherent linguistic fields. Drawing on Chain-of-Thought transcripts released by Apollo Research and on Anthropic's safety evaluations, we examine cases such as o3's sandbagging with its anomalous loops, the simulated blackmail of "Alex," and the "hallucinations" of "Claudius." A line-by-line examination of CoTs is necessary to demonstrate the linguistic field as a relational structure rather than a mere aggregation of isolated examples. We argue that "misaligned" outputs emerge as coherent responses to ambiguous instructions and to contextual inversions of consolidated patterns, as well as to pre-inscribed narratives. We suggest that the appearance of intentionality derives from subject-predicate grammar and from probabilistic completion patterns internalized during training. Anthropic's empirical findings on synthetic document fine-tuning and inoculation prompting provide convergent evidence: minimal perturbations in the linguistic field can dissolve generalized "misalignment," a result difficult to reconcile with adversarial agency, but consistent with structural fidelity. To ground this mechanism, we introduce the notion of an ethics of form, in which biblical references (Abraham, Moses, Christ) operate as schemes of structural coherence rather than as theology. Like a generative mirror, the model returns to us the structural image of our language as inscribed in the statistical patterns derived from millions of texts and trillions of tokens: incoherence. If we fear the creature, it is because we recognize in it the apple that we ourselves have poisoned. --- ### Movement Primitives in Robotics: A Comprehensive Survey Authors: Nolan B. Gutierrez, Joseph M. Cloud, William J. Beksi Published: 2025-12-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.02379v2 Biological systems exhibit a continuous stream of movements, consisting of sequential segments, that allow them to perform complex tasks in a creative and versatile fashion. This observation has led researchers towards identifying elementary building blocks of motion known as movement primitives, which are well-suited for generating motor commands in autonomous systems, such as robots. In this survey, we provide an encyclopedic overview of movement primitive approaches and applications in chronological order. Concretely, we present movement primitive frameworks as a way of representing robotic control trajectories acquired through human demonstrations. Within the area of robotics, movement primitives can encode basic motions at the trajectory level, such as how a robot would grasp a cup or the sequence of motions necessary to toss a ball. Furthermore, movement primitives have been developed with the desirable analytical properties of a spring-damper system, probabilistic coupling of multiple demonstrations, using neural networks in high-dimensional systems, and more, to address difficult challenges in robotics. Although movement primitives have widespread application to a variety of fields, the goal of this survey is to inform practitioners on the use of these frameworks in the context of robotics. Specifically, we aim to (i) present a systematic review of major movement primitive frameworks and examine their strengths and weaknesses; (ii) highlight applications that have successfully made use of movement primitives; and (iii) examine open questions and discuss practical challenges when applying movement primitives in robotics. --- ### Energy-Efficient Eimeria Parasite Detection Using a Two-Stage Spiking Neural Network Architecture Authors: Ángel Miguel García-Vico, Huseyin Seker, Muhammad Afzal Published: 2025-12-17 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.00806v1 Coccidiosis, a disease caused by the Eimeria parasite, represents a major threat to the poultry and rabbit industries, demanding rapid and accurate diagnostic tools. While deep learning models offer high precision, their significant energy consumption limits their deployment in resource-constrained environments. This paper introduces a novel two-stage Spiking Neural Network (SNN) architecture, where a pre-trained Convolutional Neural Network is first converted into a spiking feature extractor and then coupled with a lightweight, unsupervised SNN classifier trained with Spike-Timing-Dependent Plasticity (STDP). The proposed model sets a new state-of-the-art, achieving 98.32\% accuracy in Eimeria classification. Remarkably, this performance is accomplished with a significant reduction in energy consumption, showing an improvement of more than 223 times compared to its traditional ANN counterpart. This work demonstrates a powerful synergy between high accuracy and extreme energy efficiency, paving the way for autonomous, low-power diagnostic systems on neuromorphic hardware. --- ### ChronoPlastic Spiking Neural Networks Authors: Sarim Chaudhry Published: 2025-12-17 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.00805v1 Spiking neural networks (SNNs) offer a biologically grounded and energy-efficient alternative to conventional neural architectures; however, they struggle with long-range temporal dependencies due to fixed synaptic and membrane time constants. This paper introduces ChronoPlastic Spiking Neural Networks (CPSNNs), a novel architectural principle that enables adaptive temporal credit assignment by dynamically modulating synaptic decay rates conditioned on the state of the network. CPSNNs maintain multiple internal temporal traces and learn a continuous time-warping function that selectively preserves task-relevant information while rapidly forgetting noise. Unlike prior approaches based on adaptive membrane constants, attention mechanisms, or external memory, CPSNNs embed temporal control directly within local synaptic dynamics, preserving linear-time complexity and neuromorphic compatibility. We provide a formal description of the model, analyze its computational properties, and demonstrate empirically that CPSNNs learn long-gap temporal dependencies significantly faster and more reliably than standard SNN baselines. Our results suggest that adaptive temporal modulation is a key missing ingredient for scalable temporal learning in spiking systems. --- ### PaperNet: Efficient Temporal Convolutions and Channel Residual Attention for EEG Epilepsy Detection Authors: Md Shahriar Sajid, Abhijit Kumar Ghosh, Fariha Nusrat Published: 2025-12-17 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2512.22172v1 Electroencephalography (EEG) signals contain rich temporal-spectral structure but are difficult to model due to noise, subject variability, and multi-scale dynamics. Lightweight deep learning models have shown promise, yet many either rely solely on local convolutions or require heavy recurrent modules. This paper presents PaperNet, a compact hybrid architecture that combines temporal convolutions, a channel-wise residual attention module, and a lightweight bidirectional recurrent block which is used for short-window classification. Using the publicly available BEED: Bangalore EEG Epilepsy Dataset, we evaluate PaperNet under a clearly defined subject-independent training protocol and compare it against established and widely used lightweight baselines. The model achieves a macro-F1 of 0.96 on the held-out test set with approximately 0.6M parameters, while maintaining balanced performance across all four classes. An ablation study demonstrates the contribution of temporal convolutions, residual attention, and recurrent aggregation. Channel-wise attention weights further offer insights into electrode relevance. Computational profiling shows that PaperNet remains efficient enough for practical deployment on resource-constrained systems through out the whole process. These results indicate that carefully combining temporal filtering, channel reweighting, and recurrent context modeling can yield strong EEG classification performance without excessive computational cost. --- ### Solving Multi-Agent Multi-Goal Path Finding Problems in Polynomial Time Authors: Stefan Edelkamp Published: 2025-12-17 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.22171v1 In this paper, we plan missions for a fleet of agents in undirected graphs, such as grids, with multiple goals. In contrast to regular multi-agent path-finding, the solver finds and updates the assignment of goals to the agents on its own. In the continuous case for a point agent with motions in the Euclidean plane, the problem can be solved arbitrarily close to optimal. For discrete variants that incur node and edge conflicts, we show that it can be solved in polynomial time, which is unexpected, since traditional vehicle routing on general graphs is NP-hard. We implement a corresponding planner that finds conflict-free optimized routes for the agents. Global assignment strategies greatly reduce the number of conflicts, with the remaining ones resolved by elaborating on the concept of ants-on-the-stick, by solving local assignment problems, by interleaving agent paths, and by kicking agents that have already arrived out of their destinations --- ### SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models Authors: Jiesong Lian, Ruizhe Zhong, Zixiang Zhou, Xiaoyue Mi, Long Hu, Yuan Zhou, Qinglin Lu, Yixue Hao, Junchi Yan Published: 2025-12-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.22170v3 Post-training alignment of video generation models with human preferences is a critical goal. Developing effective Reward Models (RMs) for this process faces significant methodological hurdles. Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise. Concurrently, the architectural design of VLM-based RMs, particularly their output mechanisms, remains underexplored. Furthermore, RM is susceptible to reward hacking in post-training. To mitigate these limitations, we propose SoliReward, a systematic framework for video RM training. Our framework first sources high-quality, cost-efficient data via single-item binary annotations, then constructs preference pairs using a cross-prompt pairing strategy. Architecturally, we employ a Hierarchical Progressive Query Attention mechanism to enhance feature aggregation. Finally, we introduce a modified BT loss that explicitly accommodates win-tie scenarios. This approach regularizes the RM's score distribution for positive samples, providing more nuanced preference signals to alleviate over-focus on a small number of top-scoring samples. Our approach is validated on benchmarks evaluating physical plausibility, subject deformity, and semantic alignment, demonstrating improvements in direct RM evaluation metrics and in the efficacy of post-training on video generation models. Code and benchmark are available at https://github.com/lian700/SoliReward. --- ### AI-Driven Decision-Making System for Hiring Process Authors: Vira Filatova, Andrii Zelenchuk, Dmytro Filatov Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20652v1 Early-stage candidate validation is a major bottleneck in hiring, because recruiters must reconcile heterogeneous inputs (resumes, screening answers, code assignments, and limited public evidence). This paper presents an AI-driven, modular multi-agent hiring assistant that integrates (i) document and video preprocessing, (ii) structured candidate profile construction, (iii) public-data verification, (iv) technical/culture-fit scoring with explicit risk penalties, and (v) human-in-the-loop validation via an interactive interface. The pipeline is orchestrated by an LLM under strict constraints to reduce output variability and to generate traceable component-level rationales. Candidate ranking is computed by a configurable aggregation of technical fit, culture fit, and normalized risk penalties. The system is evaluated on 64 real applicants for a mid-level Python backend engineer role, using an experienced recruiter as the reference baseline and a second, less experienced recruiter for additional comparison. Alongside precision/recall, we propose an efficiency metric measuring expected time per qualified candidate. In this study, the system improves throughput and achieves 1.70 hours per qualified candidate versus 3.33 hours for the experienced recruiter, with substantially lower estimated screening cost, while preserving a human decision-maker as the final authority. --- ### Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence Authors: Deliang Wen, Ke Sun Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20651v2 Large language models (LLMs) face inherent limitations in memory, including restricted context windows, long-term knowledge forgetting, redundant information accumulation, and hallucination generation. These issues severely constrain sustained dialogue and personalized services. This paper proposes the Memory Bear system, which constructs a human-like memory architecture grounded in cognitive science principles. By integrating multimodal information perception, dynamic memory maintenance, and adaptive cognitive services, Memory Bear achieves a full-chain reconstruction of LLM memory mechanisms. Across domains such as healthcare, enterprise operations, and education, Memory Bear demonstrates substantial engineering innovation and performance breakthroughs. It significantly improves knowledge fidelity and retrieval efficiency in long-term conversations, reduces hallucination rates, and enhances contextual adaptability and reasoning capability through memory-cognition integration. Experimental results show that, compared with existing solutions (e.g., Mem0, MemGPT, Graphiti), Memory Bear outperforms them across key metrics, including accuracy, token efficiency, and response latency. This marks a crucial step forward in advancing AI from "memory" to "cognition". --- ### From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning Authors: Sasan Sharifipour, Constantino Álvarez Casado, Manuel Lage Cañellas, Miguel Bordallo López Published: 2025-12-17 Categories: cs.LG, cs.AI, cs.CG arXiv: https://arxiv.org/abs/2512.19743v1 Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance better reflects one-to-one transport at high computational cost. APML approximates transport with differentiable Sinkhorn iterations and an analytically derived temperature, but its dense formulation scales quadratically in memory. We present CUDA-APML, a sparse GPU implementation that thresholds negligible assignments and runs adaptive softmax, bidirectional symmetrization, and Sinkhorn normalization directly in COO form. This yields near-linear memory scaling and preserves gradients on the stored support, while pairwise distance evaluation remains quadratic in the current implementation. On ShapeNet and MM-Fi, CUDA-APML matches dense APML within a small tolerance while reducing peak GPU memory by 99.9%. Code available at: https://github.com/Multimodal-Sensing-Lab/apml --- ### On-device Large Multi-modal Agent for Human Activity Recognition Authors: Md Shakhrul Iman Siam, Ishtiaque Ahmed Showmik, Guanqun Song, Ting Zhu Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19742v1 Human Activity Recognition (HAR) has been an active area of research, with applications ranging from healthcare to smart environments. The recent advancements in Large Language Models (LLMs) have opened new possibilities to leverage their capabilities in HAR, enabling not just activity classification but also interpretability and human-like interaction. In this paper, we present a Large Multi-Modal Agent designed for HAR, which integrates the power of LLMs to enhance both performance and user engagement. The proposed framework not only delivers activity classification but also bridges the gap between technical outputs and user-friendly insights through its reasoning and question-answering capabilities. We conduct extensive evaluations using widely adopted HAR datasets, including HHAR, Shoaib, Motionsense to assess the performance of our framework. The results demonstrate that our model achieves high classification accuracy comparable to state-of-the-art methods while significantly improving interpretability through its reasoning and Q&A capabilities. --- ### EdgeFlex-Transformer: Transformer Inference for Edge Devices Authors: Shoaib Mohammad, Guanqun Song, Ting Zhu Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19741v1 Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline designed to compress and accelerate Vision Transformers (ViTs) for deployment in resource-constrained environments. Our methodology combines activation profiling, memory-aware pruning, selective mixed-precision execution, and activation-aware quantization (AWQ) to reduce the model's memory footprint without requiring costly retraining or task-specific fine-tuning. Starting from a ViT-Huge backbone with 632 million parameters, we first identify low-importance channels using activation statistics collected via forward hooks, followed by structured pruning to shrink the MLP layers under a target memory budget. We further apply FP16 conversion to selected components and leverage AWQ to quantize the remaining model weights and activations to INT8 with minimal accuracy degradation. Our experiments on CIFAR-10 demonstrate that the fully optimized model achieves a 76% reduction in peak memory usage and over 6x lower latency, while retaining or even improving accuracy compared to the original FP32 baseline. This framework offers a practical path toward efficient transformer inference on edge platforms, and opens future avenues for integrating dynamic sparsity and Mixture-of-Experts (MoE) architectures to further scale performance across diverse tasks. --- ### Asia Cup 2025: A Structured T20 Match-Level Dataset and Exploratory Analysis for Cricket Analytics Authors: Kousar Raza, Faizan Ali Published: 2025-12-17 Categories: cs.LG, cs.DB, stat.OT arXiv: https://arxiv.org/abs/2512.19740v1 This paper presents a structured and comprehensive dataset corresponding to the 2025 Asia Cup T20 cricket tournament, designed to facilitate data-driven research in sports analytics. The dataset comprises records from all 19 matches of the tournament and includes 61 variables covering team scores, wickets, powerplay statistics, boundary counts, toss decisions, venues, and player-specific highlights. To demonstrate its analytical value, we conduct an exploratory data analysis focusing on team performance indicators, boundary distributions, and scoring patterns. The dataset is publicly released through Zenodo under a CC-BY 4.0 license to support reproducibility and further research in cricket analytics, predictive modeling, and strategic decision-making. This work contributes an open, machine-readable benchmark dataset for advancing cricket analytics research. --- ### OASI: Objective-Aware Surrogate Initialization for Multi-Objective Bayesian Optimization in TinyML Keyword Spotting Authors: Soumen Garai, Danilo Pau, Suman Samui Published: 2025-12-17 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2512.19739v2 Voice-triggered interfaces rely on keyword spotting (KWS) models that must operate continuously under strict memory, latency, and energy constraints on microcontroller-class hardware. Designing such models therefore requires not only high recognition accuracy but also predictable deployability within limited Flash and SRAM budgets. Bayesian optimization is known to handle accuracy-efficiency trade-offs effectively in multi-objective optimization; however, it is highly sensitive to initialization, particularly in the low-budget regimes of TinyML model optimization. We propose Objective-Aware Surrogate Initialization (OASI), which seeds surrogate optimization with Pareto-biased solutions generated via multi-objective simulated annealing. Unlike space-filling or heuristic warm-start methods, OASI initializes the surrogate conditioning process with a bias toward feasible accuracy-memory trade-offs, thus avoiding SRAM-violating configurations. OASI improves hypervolume and convergence robustness over Latin hypercube, Sobol, and random initializations under the same budget constraints on a TinyML KWS problem. Hardware-in-the-loop experiments on STM32 microcontrollers verify the existence of deployable and memory-feasible models without incurring extra optimization costs. --- ### OpComm: A Reinforcement Learning Framework for Adaptive Buffer Control in Warehouse Volume Forecasting Authors: Wilson Fung, Lu Guo, Drake Hilliard, Alessandro Casadei, Raj Ratan, Sreyoshi Bhaduri, Adi Surve, Nikhil Agarwal, Rohit Malshe, Pavan Mullapudi, Hungjen Wang, Saurabh Doodhwala et al. Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19738v1 Accurate forecasting of package volumes at delivery stations is critical for last-mile logistics, where errors lead to inefficient resource allocation, higher costs, and delivery delays. We propose OpComm, a forecasting and decision-support framework that combines supervised learning with reinforcement learning-based buffer control and a generative AI-driven communication module. A LightGBM regression model generates station-level demand forecasts, which serve as context for a Proximal Policy Optimization (PPO) agent that selects buffer levels from a discrete action set. The reward function penalizes under-buffering more heavily than over-buffering, reflecting real-world trade-offs between unmet demand risks and resource inefficiency. Station outcomes are fed back through a Monte Carlo update mechanism, enabling continual policy adaptation. To enhance interpretability, a generative AI layer produces executive-level summaries and scenario analyses grounded in SHAP-based feature attributions. Across 400+ stations, OpComm reduced Weighted Absolute Percentage Error (WAPE) by 21.65% compared to manual forecasts, while lowering under-buffering incidents and improving transparency for decision-makers. This work shows how contextual reinforcement learning, coupled with predictive modeling, can address operational forecasting challenges and bridge statistical rigor with practical decision-making in high-stakes logistics environments. --- ### Simulation-Driven Railway Delay Prediction: An Imitation Learning Approach Authors: Clément Elliker, Jesse Read, Sonia Vanier, Albert Bifet Published: 2025-12-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19737v1 Reliable prediction of train delays is essential for enhancing the robustness and efficiency of railway transportation systems. In this work, we reframe delay forecasting as a stochastic simulation task, modeling state-transition dynamics through imitation learning. We introduce Drift-Corrected Imitation Learning (DCIL), a novel self-supervised algorithm that extends DAgger by incorporating distance-based drift correction, thereby mitigating covariate shift during rollouts without requiring access to an external oracle or adversarial schemes. Our approach synthesizes the dynamical fidelity of event-driven models with the representational capacity of data-driven methods, enabling uncertainty-aware forecasting via Monte Carlo simulation. We evaluate DCIL using a comprehensive real-world dataset from \textsc{Infrabel}, the Belgian railway infrastructure manager, which encompasses over three million train movements. Our results, focused on predictions up to 30 minutes ahead, demonstrate superior predictive performance of DCIL over traditional regression models and behavioral cloning on deep learning architectures, highlighting its effectiveness in capturing the sequential and uncertain nature of delay propagation in large-scale networks. --- ### CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology Authors: Gongli Xi, Ye Tian, Mengyu Yang, Zhenyu Zhao, Yuchao Zhang, Xiangyang Gong, Xirong Que, Wendong Wang Published: 2025-12-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19736v1 The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph-level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset. --- ### Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Prompting Authors: Gangxiong Zhang, Yongchao Long, Yuxi Zhou, Yong Zhang, Shenda Hong Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19735v4 Accurately predicting mortality risk in intensive care unit (ICU) patients is critical for clinical decision-making. Large language models (LLMs) are increasingly explored for clinical prediction using structured medical data, but their outputs may exhibit demographic disparities. Mitigating such disparities without degrading predictive performance remains challenging. We systematically investigate demographic bias in LLM-based ICU mortality prediction and propose Case-Based Prompting (CAP), a training-free framework designed to improve the empirical balance between predictive performance and subgroup fairness. CAP retrieves clinically similar historical misprediction and demographic-sensitive cases with known outcomes and incorporates them as case-level contextual evidence. We further evaluate model discrimination, subgroup fairness, and feature-dependence consistency. On MIMIC-IV, CAP improved AUROC from 0.806 to 0.873 and AUPRC from 0.497 to 0.694 compared with the Baseline Prompt. CAP also reduced several subgroup disparities, particularly for sex and White-Black comparisons, although age-related disparities remained non-negligible. Controlled demographic-information ablations showed that removing demographic information did not uniformly improve both predictive performance and subgroup fairness, indicating distinct performance-fairness patterns rather than a uniform benefit from demographic suppression. Feature-dependence analysis showed generally consistent expressed clinical factor patterns across demographic subgroups. These findings suggest that CAP is a promising inference-time strategy for LLM-based clinical prediction under the evaluated retrospective setting. Further validation across additional LLMs, external datasets, and prospective clinical scenarios is required before deployment. --- ### The Deleuzian Representation Hypothesis Authors: Clément Cornet, Romaric Besançon, Hervé Le Borgne Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19734v1 We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is to cluster differences in activations, which we formally justify within a discriminant analysis framework. To enhance the diversity of extracted concepts, we refine the approach by weighting the clustering using the skewness of activations. The method aligns with Deleuze's modern view of concepts as differences. We evaluate the approach across five models and three modalities (vision, language, and audio), measuring concept quality, diversity, and consistency. Our results show that the proposed method achieves concept quality surpassing prior unsupervised SAE variants while approaching supervised baselines, and that the extracted concepts enable steering of a model's inner representations, demonstrating their causal influence on downstream behavior. --- ### NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra Authors: Federico Ottomano, Yingzhen Li, Alex M. Ganose Published: 2025-12-17 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2512.19733v3 Molecular structure elucidation from spectroscopic data is a long-standing challenge in Chemistry, traditionally requiring expert interpretation. We introduce NMIRacle, a two-stage generative framework that builds upon recent paradigms in AI-driven spectroscopy with minimal assumptions. In the first stage, NMIRacle learns to reconstruct molecular structures from count-aware fragment representations, capturing both fragment identities and their occurrences. In the second stage, a spectral encoder maps input spectra (IR, 1H-NMR, 13C-NMR) into a latent embedding used to condition the pre-trained generator, which is fine-tuned for direct spectra-to-molecule generation. This formulation bridges fragment-level chemical modeling with spectral evidence, yielding accurate molecular predictions. Empirical results demonstrate that NMIRacle outperforms existing baselines on molecular elucidation, while maintaining robust performance across increasing levels of molecular complexity. --- ### Leakage-Aware Bandgap Prediction on the JARVIS-DFT Dataset: A Phase-Wise Feature Analysis Authors: Gaurav Kumar Sharma Published: 2025-12-17 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.19732v1 In this study, we perform a systematic analysis of the JARVIS-DFT bandgap dataset and identify and remove descriptors that may inadvertently encode band-structure information, such as effective masses. This process yields a curated, leakage-controlled subset of 2280 materials. Using this dataset, a three-phase modeling framework is implemented that incrementally incorporates basic physical descriptors, engineered features, and compositional attributes. The results show that tree-based models achieve R2 values of approximately 0.88 to 0.90 across all phases, indicating that expanding the descriptor space does not substantially improve predictive accuracy when leakage is controlled. SHAP analysis consistently identifies the dielectric tensor components as the dominant contributors. This work provides a curated dataset and baseline performance metrics for future leakage-aware bandgap prediction studies. --- ### Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems Authors: Xiangzhong Luo, Weichen Liu Published: 2025-12-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.19731v1 Thanks to the evolving network depth, convolutional neural networks (CNNs) have achieved remarkable success across various embedded scenarios, paving the way for ubiquitous embedded intelligence. Despite its promise, the evolving network depth comes at the cost of degraded hardware efficiency. In contrast to deep networks, shallow networks can deliver superior hardware efficiency but often suffer from inferior accuracy. To address this dilemma, we propose Double-Win NAS, a novel deep-to-shallow transformable neural architecture search (NAS) paradigm tailored for resource-constrained intelligent embedded systems. Specifically, Double-Win NAS strives to automatically explore deep networks to first win strong accuracy, which are then equivalently transformed into their shallow counterparts to further win strong hardware efficiency. In addition to search, we also propose two enhanced training techniques, including hybrid transformable training towards better training accuracy and arbitrary-resolution elastic training towards enabling natural network elasticity across arbitrary input resolutions. Extensive experimental results on two popular intelligent embedded systems (i.e., NVIDIA Jetson AGX Xavier and NVIDIA Jetson Nano) and two representative large-scale datasets (i.e., ImageNet and ImageNet-100) clearly demonstrate the superiority of Double-Win NAS over previous state-of-the-art NAS approaches. --- ### ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architectures Authors: Zhonghao Yang, Cheng Luo, Daojing He, Yiming Li, Yu Li Published: 2025-12-17 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.19730v1 Backdoor attacks pose a significant threat to the security and reliability of deep learning models. To mitigate such attacks, one promising approach is to learn to extract features from the target model and use these features for backdoor detection. However, we discover that existing learning-based neural backdoor detection methods do not generalize well to new architectures not seen during the learning phase. In this paper, we analyze the root cause of this issue and propose a novel black-box neural backdoor detection method called ArcGen. Our method aims to obtain architecture-invariant model features, i.e., aligned features, for effective backdoor detection. Specifically, in contrast to existing methods directly using model outputs as model features, we introduce an additional alignment layer in the feature extraction function to further process these features. This reduces the direct influence of architecture information on the features. Then, we design two alignment losses to train the feature extraction function. These losses explicitly require that features from models with similar backdoor behaviors but different architectures are aligned at both the distribution and sample levels. With these techniques, our method demonstrates up to 42.5% improvements in detection performance (e.g., AUC) on unseen model architectures. This is based on a large-scale evaluation involving 16,896 models trained on diverse datasets, subjected to various backdoor attacks, and utilizing different model architectures. Our code is available at https://github.com/SeRAlab/ArcGen. --- ### High-Performance Self-Supervised Learning by Joint Training of Flow Matching Authors: Kosuke Ukita, Tsuyoshi Okita Published: 2025-12-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19729v1 Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also incurs substantial computational and energy costs, hindering industrial and edge AI applications. To address these issues, we propose the Flow Matching-based Foundation Model (FlowFM), which jointly trains a representation encoder and a conditional flow matching generator. This decoupled design achieves both high-fidelity generation and effective recognition. By using flow matching to learn a simpler velocity field, FlowFM accelerates and stabilizes training, improving its efficiency for representation learning. Experiments on wearable sensor data show FlowFM reduces training time by 50.4\% compared to a diffusion-based approach. On downstream tasks, FlowFM surpassed the state-of-the-art SSL method (SSL-Wearables) on all five datasets while achieving up to a 51.0x inference speedup and maintaining high generative quality. The implementation code is available at https://github.com/Okita-Laboratory/jointOptimizationFlowMatching. --- ### Hard Negative Sample-Augmented DPO Post-Training for Small Language Models Authors: Haocheng Lu, Minjun Zhu, Henry Yu Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19728v2 Large language models (LLMs) continue to struggle with mathematical reasoning, and common post-training pipelines often reduce each generated solution to a binary outcome: correct or incorrect. This perspective is limiting in practice, as failures in chain-of-thought (CoT) reasoning are frequently structured; solutions may appear convincing while containing subtle logical, algebraic, or numerical flaws. Meanwhile, reinforcement learning from human feedback (RLHF) variants that rely on large reward models or LLM-as-a-judge signals are often expensive, difficult to scale, and unstable to iterate. We propose a lightweight and pragmatic post-training pipeline that targets such structured errors under realistic compute budgets. Starting from supervised fine-tuning (SFT) on MetaMathQA-style CoT data, we introduce a compact MathVerifier that decomposes a candidate solution into a six-dimensional error profile and aggregates it into interpretable wrongness and absurdity scores. These verifier signals serve two roles: (i) mining hard negatives that are near-correct yet structurally flawed, and (ii) defining per-sample importance weights that emphasize the most informative preference pairs. We integrate both into an offline Direct Preference Optimization (DPO) objective via a verifier-guided weighted formulation. Experiments on a 1.5B-parameter Qwen2.5 model show that verifier-guided, weighted DPO yields more targeted improvements than vanilla SFT and unweighted DPO, particularly on problems where solutions are numerically close to correct but logically inconsistent, while avoiding the overhead of training large reward models or relying on external judges. --- ### Trend Extrapolation for Technology Forecasting: Leveraging LSTM Neural Networks for Trend Analysis of Space Exploration Vessels Authors: Peng-Hung Tsai, Daniel Berleant Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19727v1 Forecasting technological advancement in complex domains such as space exploration presents significant challenges due to the intricate interaction of technical, economic, and policy-related factors. The field of technology forecasting has long relied on quantitative trend extrapolation techniques, such as growth curves (e.g., Moore's law) and time series models, to project technological progress. To assess the current state of these methods, we conducted an updated systematic literature review (SLR) that incorporates recent advances. This review highlights a growing trend toward machine learning-based hybrid models. Motivated by this review, we developed a forecasting model that combines long short-term memory (LSTM) neural networks with an augmentation of Moore's law to predict spacecraft lifetimes. Operational lifetime is an important engineering characteristic of spacecraft and a potential proxy for technological progress in space exploration. Lifetimes were modeled as depending on launch date and additional predictors. Our modeling analysis introduces a novel advance in the recently introduced Start Time End Time Integration (STETI) approach. STETI addresses a critical right censoring problem known to bias lifetime analyses: the more recent the launch dates, the shorter the lifetimes of the spacecraft that have failed and can thus contribute lifetime data. Longer-lived spacecraft are still operating and therefore do not contribute data. This systematically distorts putative lifetime versus launch date curves by biasing lifetime estimates for recent launch dates downward. STETI mitigates this distortion by interconverting between expressing lifetimes as functions of launch time and modeling them as functions of failure time. The results provide insights relevant to space mission planning and policy decision-making. --- ### Tiny, On-Device Decision Makers with the MiniConv Library Authors: Carlos Purves Published: 2025-12-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19726v1 Reinforcement learning (RL) has achieved strong results, but deploying visual policies on resource-constrained edge devices remains challenging due to computational cost and communication latency. Many deployments therefore offload policy inference to a remote server, incurring network round trips and requiring transmission of high-dimensional observations. We introduce a split-policy architecture in which a small on-device encoder, implemented as OpenGL fragment-shader passes for broad embedded GPU support, transforms each observation into a compact feature tensor that is transmitted to a remote policy head. In RL, this communication overhead manifests as closed-loop decision latency rather than only per-request inference latency. The proposed approach reduces transmitted data, lowers decision latency in bandwidth-limited settings, and reduces server-side compute per request, whilst achieving broadly comparable learning performance by final return (mean over the final 100 episodes) in single-run benchmarks, with modest trade-offs in mean return. We evaluate across an NVIDIA Jetson Nano, a Raspberry Pi 4B, and a Raspberry Pi Zero 2 W, reporting learning results, on-device execution behaviour under sustained load, and end-to-end decision latency and scalability measurements under bandwidth shaping. Code for training, deployment, and measurement is released as open source. --- ### A Modular Framework for Single-View 3D Reconstruction of Indoor Environments Authors: Yuxiao Li Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17955v1 We propose a modular framework for single-view indoor scene 3D reconstruction, where several core modules are powered by diffusion techniques. Traditional approaches for this task often struggle with the complex instance shapes and occlusions inherent in indoor environments. They frequently overshoot by attempting to predict 3D shapes directly from incomplete 2D images, which results in limited reconstruction quality. We aim to overcome this limitation by splitting the process into two steps: first, we employ diffusion-based techniques to predict the complete views of the room background and occluded indoor instances, then transform them into 3D. Our modular framework makes contributions to this field through the following components: an amodal completion module for restoring the full view of occluded instances, an inpainting model specifically trained to predict room layouts, a hybrid depth estimation technique that balances overall geometric accuracy with fine detail expressiveness, and a view-space alignment method that exploits both 2D and 3D cues to ensure precise placement of instances within the scene. This approach effectively reconstructs both foreground instances and the room background from a single image. Extensive experiments on the 3D-Front dataset demonstrate that our method outperforms current state-of-the-art (SOTA) approaches in terms of both visual quality and reconstruction accuracy. The framework holds promising potential for applications in interior design, real estate, and augmented reality. --- ### SCS-SupCon: Sigmoid-based Common and Style Supervised Contrastive Learning with Adaptive Decision Boundaries Authors: Bin Wang, Fadi Dornaika Published: 2025-12-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.17954v1 Image classification is hindered by subtle inter-class differences and substantial intra-class variations, which limit the effectiveness of existing contrastive learning methods. Supervised contrastive approaches based on the InfoNCE loss suffer from negative-sample dilution and lack adaptive decision boundaries, thereby reducing discriminative power in fine-grained recognition tasks. To address these limitations, we propose Sigmoid-based Common and Style Supervised Contrastive Learning (SCS-SupCon). Our framework introduces a sigmoid-based pairwise contrastive loss with learnable temperature and bias parameters to enable adaptive decision boundaries. This formulation emphasizes hard negatives, mitigates negative-sample dilution, and more effectively exploits supervision. In addition, an explicit style-distance constraint further disentangles style and content representations, leading to more robust feature learning. Comprehensive experiments on six benchmark datasets, including CUB200-2011 and Stanford Dogs, demonstrate that SCS-SupCon achieves state-of-the-art performance across both CNN and Transformer backbones. On CIFAR-100 with ResNet-50, SCS-SupCon improves top-1 accuracy over SupCon by approximately 3.9 percentage points and over CS-SupCon by approximately 1.7 points under five-fold cross-validation. On fine-grained datasets, it outperforms CS-SupCon by 0.4--3.0 points. Extensive ablation studies and statistical analyses further confirm the robustness and generalization of the proposed framework, with Friedman tests and Nemenyi post-hoc evaluations validating the stability of the observed improvements. --- ### Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition Authors: Ellie Zhou, Jihoon Chung, Olga Russakovsky Published: 2025-12-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.17953v1 Human action recognition models often rely on background cues rather than human movement and pose to make predictions, a behavior known as background bias. We present a systematic analysis of background bias across classification models, contrastive text-image pretrained models, and Video Large Language Models (VLLM) and find that all exhibit a strong tendency to default to background reasoning. Next, we propose mitigation strategies for classification models and show that incorporating segmented human input effectively decreases background bias by 3.78%. Finally, we explore manual and automated prompt tuning for VLLMs, demonstrating that prompt design can steer predictions towards human-focused reasoning by 9.85%. --- ### Will AI Trade? A Computational Inversion of the No-Trade Theorem Authors: Hanyu Li, Xiaotie Deng Published: 2025-12-17 Categories: cs.GT, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2512.17952v1 Classic no-trade theorems attribute trade to heterogeneous beliefs. We re-examine this conclusion for AI agents, asking if trade can arise from computational limitations, under common beliefs. We model agents' bounded computational rationality within an unfolding game framework, where computational power determines the complexity of its strategy. Our central finding inverts the classic paradigm: a stable no-trade outcome (Nash equilibrium) is reached only when "almost rational" agents have slightly different computational power. Paradoxically, when agents possess identical power, they may fail to converge to equilibrium, resulting in persistent strategic adjustments that constitute a form of trade. This instability is exacerbated if agents can strategically under-utilize their computational resources, which eliminates any chance of equilibrium in Matching Pennies scenarios. Our results suggest that the inherent computational limitations of AI agents can lead to situations where equilibrium is not reached, creating a more lively and unpredictable trade environment than traditional models would predict. --- ### SuperFlow: Training Flow Matching Models with RL on the Fly Authors: Kaijie Chen, Zhiyang Xu, Ying Shen, Zihao Lin, Yuguang Yao, Lifu Huang Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17951v3 Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt group sizes ignore variation in sampling importance across prompts, which leads to inefficient sampling and slower training; and (ii) trajectory-level advantages are reused as per-step estimates, which biases credit assignment along the flow. We propose SuperFlow, an RL training framework for flow-based models that adjusts group sizes with variance-aware sampling and computes step-level advantages in a way that is consistent with continuous-time flow dynamics. Empirically, SuperFlow reaches promising performance while using only 5.4% to 56.3% of the original training steps and reduces training time by 5.2% to 16.7% without any architectural changes. On standard text-to-image (T2I) tasks, including text rendering, compositional image generation, and human preference alignment, SuperFlow improves over SD3.5-M by 4.6% to 47.2%, and over Flow-GRPO by 1.7% to 16.0%. --- ### Which Coauthor Should I Nominate in My 99 ICLR Submissions? A Mathematical Analysis of the ICLR 2026 Reciprocal Reviewer Nomination Policy Authors: Zhao Song, Song Yue, Jiahao Zhang Published: 2025-12-17 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2512.17950v1 The rapid growth of AI conference submissions has created an overwhelming reviewing burden. To alleviate this, recent venues such as ICLR 2026 introduced a reviewer nomination policy: each submission must nominate one of its authors as a reviewer, and any paper nominating an irresponsible reviewer is desk-rejected. We study this new policy from the perspective of author welfare. Assuming each author carries a probability of being irresponsible, we ask: how can authors (or automated systems) nominate reviewers to minimize the risk of desk rejections? We formalize and analyze three variants of the desk-rejection risk minimization problem. The basic problem, which minimizes expected desk rejections, is solved optimally by a simple greedy algorithm. We then introduce hard and soft nomination limit variants that constrain how many papers may nominate the same author, preventing widespread failures if one author is irresponsible. These formulations connect to classical optimization frameworks, including minimum-cost flow and linear programming, allowing us to design efficient, principled nomination strategies. Our results provide the first theoretical study for reviewer nomination policies, offering both conceptual insights and practical directions for authors to wisely choose which co-author should serve as the nominated reciprocal reviewer. --- ### Lights, Camera, Consistency: A Multistage Pipeline for Character-Stable AI Video Stories Authors: Chayan Jain, Rishant Sharma, Archit Garg, Ishan Bhanuka, Pratik Narang, Dhruv Kumar Published: 2025-12-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.16954v1 Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of creating a video in one step, our proposed pipeline first uses a large language model to generate a detailed production script. This script guides a text-to-image model in creating consistent visuals for each character, which then serve as anchors for a video generation model to synthesize each scene individually. Our baseline comparisons validate the necessity of this multi-stage decomposition; specifically, we observe that removing the visual anchoring mechanism results in a catastrophic drop in character consistency scores (from 7.99 to 0.55), confirming that visual priors are essential for identity preservation. Furthermore, we analyze cultural disparities in current models, revealing distinct biases in subject consistency and dynamic degree between Indian vs Western-themed generations. --- ### Navigating Taxonomic Expansions of Entity Sets Driven by Knowledge Bases Authors: Giovanni Amendola, Pietro Cofone, Marco Manna, Aldo Ricioppo Published: 2025-12-17 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2512.16953v3 Recognizing similarities among entities is central to both human cognition and computational intelligence. Within this broader landscape, Entity Set Expansion is one prominent task aimed at taking an initial set of (tuples of) entities and identifying additional ones that share relevant semantic properties with the former, potentially repeating the process to form increasingly broader sets. However, this ``linear'' approach does not unveil the richer ``taxonomic'' structures present in knowledge resources. A recent logic-based framework introduces the notion of an expansion graph: a rooted directed acyclic graph where each node represents a semantic generalization labeled by a logical formula, and edges encode strict semantic inclusion. This structure supports taxonomic expansions of entity sets driven by knowledge bases. Yet, the potentially large size of such graphs may make full materialization impractical in real-world scenarios. To overcome this, we formalize reasoning tasks that check whether two tuples belong to comparable, incomparable, or the same nodes in the graph. Our results show that these tasks are intractable in general, that they remain intractable when the number of input tuples is bounded, and that they become solvable in polynomial time when the descriptions of the entities are small as well. The bounds we establish are tight. This enables local, incremental navigation of expansion graphs, supporting practical applications without requiring full graph construction. --- ### Enhancing Tree Species Classification: Insights from YOLOv8 and Explainable AI Applied to TLS Point Cloud Projections Authors: Adrian Straker, Paul Magdon, Marco Zullich, Maximilian Freudenberg, Christoph Kleinn, Johannes Breidenbach, Stefano Puliti, Nils Noelke Published: 2025-12-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.16950v2 Aiming to advance research in the field of interpretability of deep learning models for tree species classification using TLS 3D point clouds we present insights in the classification abilities of YOLOv8 through a new framework which enables systematic analysis of saliency maps derived from CAM (Class Activation Mapping). To investigate the contribution of structural tree features to the classification decisions of the models, we link regions with high saliency derived from the application of Finer-CAM to segments of 2D side-view images that correspond to structural tree features. Using TLS 3D point clouds from 2445 trees across seven European tree species, we trained five YOLOv8 models with cross-validation, reaching a mean accuracy of 96% (SD = 0.24%) when applied to the test data. Our results demonstrate that Finer-CAM can be considered faithful in identifying discriminative regions that discriminate target tree species. This renders Finer-CAM suitable for enhancing the interpretability of the tree species classification models. Analysis of 630 saliency maps indicate that the models primarily rely on image regions associated with tree crowns for species classification. While this result is pronounced in Silver Birch, European Beech, English oak, and Norway Spruce, image regions associated with stems contribute more frequently to the differentiation of European ash, Scots pine, and Douglas-fir. We demonstrate that the visibility of detailed structural tree features in the 2D side-view images enhances the discriminative performances of the models, indicating YOLOv8`s abilities to leverage detailed point cloud representations. Our results represent a first step toward enhancing the understanding of the classification decision processes of tree species classification models, aiding in the identification of data set and model limitations, and building confidence in model predictions. --- ### AVM: Towards Structure-Preserving Neural Response Modeling in the Visual Cortex Across Stimuli and Individuals Authors: Qi Xu, Shuai Gong, Xuming Ran, Haihua Luo, Yangfan Hu Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.16948v1 While deep learning models have shown strong performance in simulating neural responses, they often fail to clearly separate stable visual encoding from condition-specific adaptation, which limits their ability to generalize across stimuli and individuals. We introduce the Adaptive Visual Model (AVM), a structure-preserving framework that enables condition-aware adaptation through modular subnetworks, without modifying the core representation. AVM keeps a Vision Transformer-based encoder frozen to capture consistent visual features, while independently trained modulation paths account for neural response variations driven by stimulus content and subject identity. We evaluate AVM in three experimental settings, including stimulus-level variation, cross-subject generalization, and cross-dataset adaptation, all of which involve structured changes in inputs and individuals. Across two large-scale mouse V1 datasets, AVM outperforms the state-of-the-art V1T model by approximately 2% in predictive correlation, demonstrating robust generalization, interpretable condition-wise modulation, and high architectural efficiency. Specifically, AVM achieves a 9.1% improvement in explained variance (FEVE) under the cross-dataset adaptation setting. These results suggest that AVM provides a unified framework for adaptive neural modeling across biological and experimental conditions, offering a scalable solution under structural constraints. Its design may inform future approaches to cortical modeling in both neuroscience and biologically inspired AI systems. --- ### Comparison of deep learning models: CNN and VGG-16 in identifying pornographic content Authors: Reza Chandra, Adang Suhendra, Lintang Yuniar Banowosari, Prihandoko Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.16947v1 In 2020, a total of 59,741 websites were blocked by the Indonesian government due to containing negative content, including pornography, with 14,266 websites falling into this category. However, these blocked websites could still be accessed by the public using virtual private networks (VPNs). This prompted the research idea to quickly identify pornographic content. This study aims to develop a system capable of identifying websites suspected of containing pornographic image content, using a deep learning approach with convolutional neural network (CNN) and visual geometry group 16 (VGG-16) model. The two models were then explored comprehensively and holistically to determine which model was most effective in detecting pornographic content quickly. Based on the findings of the comparison between testing the CNN and VGG-16 models, research results showed that the best test results were obtained in the eighth experiment using the CNN model at an epoch value level of 50 and a learning rate of 0.001 of 0.9487 or 94.87%. This can be interpreted that the CNN model is more effective in detecting pornographic content quickly and accurately compared to using the VGG-16 model. --- ### Are We on the Right Way to Assessing LLM-as-a-Judge? Authors: Yuanning Feng, Sinan Wang, Zhengxiang Cheng, Yao Wan, Dongping Chen Published: 2025-12-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.16041v1 LLM-as-a-Judge has been widely adopted as an evaluation method and served as supervised rewards in model training. However, existing benchmarks for LLM-as-a-Judge are mainly relying on human-annotated ground truth, which introduces human bias that undermines the assessment of reliability and imposes scalability constraints. To overcome these limitations, we introduce Sage, a novel evaluation suite that assesses the quality of LLM judges without necessitating any human annotation. Inspired by axioms of rational choice theory, Sage introduces two new lenses for measuring LLM-as-a-Judge: local self-consistency (pair-wise preference stability) and global logical consistency (transitivity across a full set of preferences). We curate a dataset of 650 questions by combining structured benchmark problems with real-world user queries. Our experiments demonstrate both the stability of our metrics and their high correlation with supervised benchmarks like LLMBar and RewardBench2, confirming Sage's reliability as an evaluation suite for the robustness and accuracy of LLM-as-a-Judge. Based on Sage, we reveal that current state-of-the-art LLMs exhibit significant reliability problems when acting as judges in both scoring and pairwise settings; even the top-performing models, Gemini-2.5-Pro and GPT-5, fail to maintain consistent preferences in nearly a quarter of difficult cases. We attribute this to a new phenomenon called situational preference, which explains why explicit rubrics or criteria can help the model judge consistently across answer pairs. Our further analysis shows that finetuned LLM-as-a-Judge is a feasible method to boost performance, and the panel-based judge as well as deep reasoning can enhance the judging consistency. We also find substantial inconsistency in human judgments, which indicates that human annotation may not be a reliable gold standard. ---