# Research Papers — 2025-12 · bundle page 32 of 175

> Full-text markdown of papers #1551–1600 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/32
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/31.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/33.md)

### ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design

Authors: R Yadunandan, Nimisha Ghosh
Published: 2025-12-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.20958v1

De novo drug design is a crucial component of modern drug development, yet navigating the vast chemical space to find synthetically accessible, high-affinity candidates remains a significant challenge. Reinforcement Learning (RL) enhances this process by enabling multi-objective optimization and exploration of novel chemical space - capabilities that traditional supervised learning methods lack. In this work, we introduce \textbf{ReACT-Drug}, a fully integrated, target-agnostic molecular design framework based on Reinforcement Learning. Unlike models requiring target-specific fine-tuning, ReACT-Drug utilizes a generalist approach by leveraging ESM-2 protein embeddings to identify similar proteins for a given target from a knowledge base such as Protein Data Base (PDB). Thereafter, the known drug ligands corresponding to such proteins are decomposed to initialize a fragment-based search space, biasing the agent towards biologically relevant subspaces. For each such fragment, the pipeline employs a Proximal Policy Optimization (PPO) agent guiding a ChemBERTa-encoded molecule through a dynamic action space of chemically valid, reaction-template-based transformations. This results in the generation of \textit{de novo} drug candidates with competitive binding affinities and high synthetic accessibility, while ensuring 100\% chemical validity and novelty as per MOSES benchmarking. This architecture highlights the potential of integrating structural biology, deep representation learning, and chemical synthesis rules to automate and accelerate rational drug design. The dataset and code are available at https://github.com/YadunandanRaman/ReACT-Drug/.

---

### One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

Authors: Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang, Yiming Xu, Zhixiang Wang, Kun Liang, Weikang Li, Jiahui Liang, Deguo Xia, Jizhou Huang, Jiyan He, Yunfang Wu
Published: 2025-12-24
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.20957v6

Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complicate model control. We propose RepoNavigator, an LLM agent equipped with a single execution-aware tool: jumping to the definition of an invoked symbol. This unified design reflects the actual flow of code execution while simplifying tool manipulation. RepoNavigator is trained end-to-end via Reinforcement Learning (RL) directly from a base pretrained model, without relying on closed-source distillation. Experiments demonstrate that RL-trained RepoNavigator achieves state-of-the-art performance, with the 7B model outperforming 14B baselines, the 14B model surpassing 32B competitors, and the 32B model exceeding closed-source models such as GPT-5 on most metrics. These results confirm that integrating a single, structurally grounded tool with RL training provides an efficient and scalable solution for repository-level issue localization.

---

### Solving Functional PDEs with Gaussian Processes and Applications to Functional Renormalization Group Equations

Authors: Xianjin Yang, Matthieu Darcy, Matthew Hudes, Francis J. Alexander, Gregory Eyink, Houman Owhadi
Published: 2025-12-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.20956v1

We present an operator learning framework for solving non-perturbative functional renormalization group equations, which are integro-differential equations defined on functionals. Our proposed approach uses Gaussian process operator learning to construct a flexible functional representation formulated directly on function space, making it independent of a particular equation or discretization. Our method is flexible, and can apply to a broad range of functional differential equations while still allowing for the incorporation of physical priors in either the prior mean or the kernel design. We demonstrate the performance of our method on several relevant equations, such as the Wetterich and Wilson--Polchinski equations, showing that it achieves equal or better performance than existing approximations such as the local-potential approximation, while being significantly more flexible. In particular, our method can handle non-constant fields, making it promising for the study of more complex field configurations, such as instantons.

---

### Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models

Authors: Xiang Zhang, Jiaqi Wei, Yuejin Yang, Zijie Qiu, Yuhan Chen, Zhiqiang Gao, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Wanli Ouyang, Chenyu You, Siqi Sun
Published: 2025-12-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.20954v1

Chain-of-Thought (CoT) prompting has significantly advanced task-solving capabilities in natural language processing with large language models. Unlike standard prompting, CoT encourages the model to generate intermediate reasoning steps, non-answer tokens, that help guide the model toward more accurate final outputs. These intermediate steps enable more complex reasoning processes such as error correction, memory management, future planning, and self-reflection. However, applying CoT to non-natural language domains, such as protein and RNA language models, is not yet possible, primarily due to the limited expressiveness of their token spaces (e.g., amino acid tokens). In this work, we propose and define the concept of language expressiveness: the ability of a given language, using its tokens and grammar, to encode information. We show that the limited expressiveness of protein language severely restricts the applicability of CoT-style reasoning. To overcome this, we introduce reflection pretraining, for the first time in a biological sequence model, which enables the model to engage in intermediate reasoning through the generation of auxiliary "thinking tokens" beyond simple answer tokens. Theoretically, we demonstrate that our augmented token set significantly enhances biological language expressiveness, thereby improving the overall reasoning capacity of the model. Experimentally, our pretraining approach teaches protein models to self-correct and leads to substantial performance gains compared to standard pretraining.

---

### MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment

Authors: Mohammad Mahdi Abootorabi, Alireza Ghahramani Kure, Mohammadali Mohammadkhani, Sina Elahimanesh, Mohammad Ali Ali Panah
Published: 2025-12-24
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2512.20950v1

This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a novel approach that leverages a dual-encoder architecture with contrastive learning and incorporates both native and English translations across different modalities. Our method effectively retrieves claims across multiple languages by learning the relative importance of different sources in alignment. To enhance robustness, we employ efficient data preprocessing and augmentation using large language models while incorporating hard negative sampling to improve representation learning. We evaluate our approach on monolingual and crosslingual benchmarks, demonstrating significant improvements in retrieval accuracy and fact-checking performance over baselines.

---

### Neural Probe-Based Hallucination Detection for Large Language Models

Authors: Shize Liang, Hongzhi Wang
Published: 2025-12-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.20949v1

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection methods based on uncertainty estimation and external knowledge retrieval suffer from the limitation that they still produce erroneous content at high confidence levels and rely heavily on retrieval efficiency and knowledge coverage. In contrast, probe methods that leverage the model's hidden-layer states offer real-time and lightweight advantages. However, traditional linear probes struggle to capture nonlinear structures in deep semantic spaces.To overcome these limitations, we propose a neural network-based framework for token-level hallucination detection. By freezing language model parameters, we employ lightweight MLP probes to perform nonlinear modeling of high-level hidden states. A multi-objective joint loss function is designed to enhance detection stability and semantic disambiguity. Additionally, we establish a layer position-probe performance response model, using Bayesian optimization to automatically search for optimal probe insertion layers and achieve superior training results.Experimental results on LongFact, HealthBench, and TriviaQA demonstrate that MLP probes significantly outperform state-of-the-art methods in accuracy, recall, and detection capability under low false-positive conditions.

---

### Foundation Model-based Evaluation of Neuropsychiatric Disorders: A Lifespan-Inclusive, Multi-Modal, and Multi-Lingual Study

Authors: Zhongren Dong, Haotian Guo, Weixiang Xu, Huan Zhao, Zixing Zhang
Published: 2025-12-24
Categories: cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2512.20948v1

Neuropsychiatric disorders, such as Alzheimer's disease (AD), depression, and autism spectrum disorder (ASD), are characterized by linguistic and acoustic abnormalities, offering potential biomarkers for early detection. Despite the promise of multi-modal approaches, challenges like multi-lingual generalization and the absence of a unified evaluation framework persist. To address these gaps, we propose FEND (Foundation model-based Evaluation of Neuropsychiatric Disorders), a comprehensive multi-modal framework integrating speech and text modalities for detecting AD, depression, and ASD across the lifespan. Leveraging 13 multi-lingual datasets spanning English, Chinese, Greek, French, and Dutch, we systematically evaluate multi-modal fusion performance. Our results show that multi-modal fusion excels in AD and depression detection but underperforms in ASD due to dataset heterogeneity. We also identify modality imbalance as a prevalent issue, where multi-modal fusion fails to surpass the best mono-modal models. Cross-corpus experiments reveal robust performance in task- and language-consistent scenarios but noticeable degradation in multi-lingual and task-heterogeneous settings. By providing extensive benchmarks and a detailed analysis of performance-influencing factors, FEND advances the field of automated, lifespan-inclusive, and multi-lingual neuropsychiatric disorder assessment. We encourage researchers to adopt the FEND framework for fair comparisons and reproducible research.

---

### AirGS: Real-Time 4D Gaussian Streaming for Free-Viewpoint Video Experiences

Authors: Zhe Wang, Jinghang Li, Yifei Zhu
Published: 2025-12-24
Categories: cs.GR, cs.DC, cs.LG, cs.MM, cs.NI, eess.IV
arXiv: https://arxiv.org/abs/2512.20943v1

Free-viewpoint video (FVV) enables immersive viewing experiences by allowing users to view scenes from arbitrary perspectives. As a prominent reconstruction technique for FVV generation, 4D Gaussian Splatting (4DGS) models dynamic scenes with time-varying 3D Gaussian ellipsoids and achieves high-quality rendering via fast rasterization. However, existing 4DGS approaches suffer from quality degradation over long sequences and impose substantial bandwidth and storage overhead, limiting their applicability in real-time and wide-scale deployments. Therefore, we present AirGS, a streaming-optimized 4DGS framework that rearchitects the training and delivery pipeline to enable high-quality, low-latency FVV experiences. AirGS converts Gaussian video streams into multi-channel 2D formats and intelligently identifies keyframes to enhance frame reconstruction quality. It further combines temporal coherence with inflation loss to reduce training time and representation size. To support communication-efficient transmission, AirGS models 4DGS delivery as an integer linear programming problem and design a lightweight pruning level selection algorithm to adaptively prune the Gaussian updates to be transmitted, balancing reconstruction quality and bandwidth consumption. Extensive experiments demonstrate that AirGS reduces quality deviation in PSNR by more than 20% when scene changes, maintains frame-level PSNR consistently above 30, accelerates training by 6 times, reduces per-frame transmission size by nearly 50% compared to the SOTA 4DGS approaches.

---

### A Multi-fidelity Double-Delta Wing Dataset and Empirical Scaling Laws for GNN-based Aerodynamic Field Surrogate

Authors: Yiren Shen, Juan J. Alonso
Published: 2025-12-24
Categories: cs.LG, cs.AI, physics.flu-dyn
arXiv: https://arxiv.org/abs/2512.20941v1

Data-driven surrogate models are increasingly adopted to accelerate vehicle design. However, open-source multi-fidelity datasets and empirical guidelines linking dataset size to model performance remain limited. This study investigates the relationship between training data size and prediction accuracy for a graph neural network (GNN) based surrogate model for aerodynamic field prediction. We release an open-source, multi-fidelity aerodynamic dataset for double-delta wings, comprising 2448 flow snapshots across 272 geometries evaluated at angles of attack from 11 (degree) to 19 (degree) at Ma=0.3 using both Vortex Lattice Method (VLM) and Reynolds-Averaged Navier-Stokes (RANS) solvers. The geometries are generated using a nested Saltelli sampling scheme to support future dataset expansion and variance-based sensitivity analysis. Using this dataset, we conduct a preliminary empirical scaling study of the MF-VortexNet surrogate by constructing six training datasets with sizes ranging from 40 to 1280 snapshots and training models with 0.1 to 2.4 million parameters under a fixed training budget. We find that the test error decreases with data size with a power-law exponent of -0.6122, indicating efficient data utilization. Based on this scaling law, we estimate that the optimal sampling density is approximately eight samples per dimension in a d-dimensional design space. The results also suggest improved data utilization efficiency for larger surrogate models, implying a potential trade-off between dataset generation cost and model training budget.

---

### Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection

Authors: Ruiqi Liu, Yi Han, Zhengbo Zhang, Liwei Yao, Zhiyuan Yan, Jialiang Shen, ZhiJin Chen, Boyi Sun, Lubin Weng, Jing Dong, Yan Wang, Shu Wu
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20937v1

The rapid progress of generative models has intensified the need for reliable and robust detection under real-world conditions. However, existing detectors often overfit to generator-specific artifacts and remain highly sensitive to real-world degradations. As generative architectures evolve and images undergo multi-round cross-platform sharing and post-processing (chain degradations), these artifact cues become obsolete and harder to detect. To address this, we propose Real-centric Envelope Modeling (REM), a new paradigm that shifts detection from learning generator artifacts to modeling the robust distribution of real images. REM introduces feature-level perturbations in self-reconstruction to generate near-real samples, and employs an envelope estimator with cross-domain consistency to learn a boundary enclosing the real image manifold. We further build RealChain, a comprehensive benchmark covering both open-source and commercial generators with simulated real-world degradation. Across eight benchmark evaluations, REM achieves an average improvement of 7.5% over state-of-the-art methods, and notably maintains exceptional generalization on the severely degraded RealChain benchmark, establishing a solid foundation for synthetic image detection under real-world conditions. The code and the RealChain benchmark will be made publicly available upon acceptance of the paper.

---

### Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation

Authors: Hongxing Fan, Shuyu Zhao, Jiayang Ao, Lu Sheng
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20936v1

Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and error accumulation. To tackle these limitations, we present a Collaborative Multi-Agent Reasoning Framework that explicitly decouples Semantic Planning from Visual Synthesis. By employing specialized agents for upfront reasoning, our method generates a structured, explicit plan before pixel generation, enabling visually and semantically coherent single-pass synthesis. We integrate this framework with two critical mechanisms: (1) a self-correcting Verification Agent that employs Chain-of-Thought reasoning to rectify visible region segmentation and identify residual occluders strictly within the Semantic Planning phase, and (2) a Diverse Hypothesis Generator that addresses the ambiguity of invisible regions by offering diverse, plausible semantic interpretations, surpassing the limited pixel-level variations of standard random seed sampling. Furthermore, addressing the limitations of traditional metrics in assessing inferred invisible content, we introduce the MAC-Score (MLLM Amodal Completion Score), a novel human-aligned evaluation metric. Validated against human judgment and ground truth, these metrics establish a robust standard for assessing structural completeness and semantic consistency with visible context. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods across multiple datasets. Our project is available at: https://fanhongxing.github.io/remac-page.

---

### Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning

Authors: Shengguang Wu, Xiaohan Wang, Yuhui Zhang, Hao Zhu, Serena Yeung-Levy
Published: 2025-12-24
Categories: cs.CV, cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2512.20934v1

Spatial reasoning in 3D scenes requires precise geometric calculations that challenge vision-language models. Visual programming addresses this by decomposing problems into steps calling specialized tools, yet existing methods rely on either fixed toolsets or speculative tool induction before solving problems, resulting in suboptimal programs and poor utilization of induced tools. We present Transductive Visual Programming (TVP), a novel framework that builds new tools from its own experience rather than speculation. TVP first solves problems using basic tools while accumulating experiential solutions into an Example Library, then abstracts recurring patterns from these programs into reusable higher-level tools for an evolving Tool Library. This allows TVP to tackle new problems with increasingly powerful tools learned from experience. On Omni3D-Bench, TVP achieves state-of-the-art performance, outperforming GPT-4o by 22% and the previous best visual programming system by 11%. Our transductively learned tools are used 5x more frequently as core program dependency than inductively created ones, demonstrating more effective tool discovery and reuse. The evolved tools also show strong generalization to unseen spatial tasks, achieving superior performance on benchmarks from SpatialScore-Hard collection without any testset-specific modification. Our work establishes experience-driven transductive tool creation as a powerful paradigm for building self-evolving visual programming agents that effectively tackle challenging spatial reasoning tasks. We release our code at https://transductive-visualprogram.github.io/.

---

### Guardrailed Elasticity Pricing: A Churn-Aware Forecasting Playbook for Subscription Strategy

Authors: Deepit Sapru
Published: 2025-12-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.20932v2

This paper presents a marketing analytics framework that operationalizes subscription pricing as a dynamic, guardrailed decision system, uniting multivariate demand forecasting, segment-level price elasticity, and churn propensity to optimize revenue, margin, and retention. The approach blends seasonal time-series models with tree-based learners, runs Monte Carlo scenario tests to map risk envelopes, and solves a constrained optimization that enforces business guardrails on customer experience, margin floors, and allowable churn. Validated across heterogeneous SaaS portfolios, the method consistently outperforms static tiers and uniform uplifts by reallocating price moves toward segments with higher willingness-to-pay while protecting price-sensitive cohorts. The system is designed for real-time recalibration via modular APIs and includes model explainability for governance and compliance. Managerially, the framework functions as a strategy playbook that clarifies when to shift from flat to dynamic pricing, how to align pricing with CLV and MRR targets, and how to embed ethical guardrails, enabling durable growth without eroding customer trust.

---

### Decoding Predictive Inference in Visual Language Processing via Spatiotemporal Neural Coherence

Authors: Sean C. Borneman, Julia Krebs, Ronnie B. Wilbur, Evie A. Malaia
Published: 2025-12-24
Categories: q-bio.NC, cs.CL
arXiv: https://arxiv.org/abs/2512.20929v1

Human language processing relies on the brain's capacity for predictive inference. We present a machine learning framework for decoding neural (EEG) responses to dynamic visual language stimuli in Deaf signers. Using coherence between neural signals and optical flow-derived motion features, we construct spatiotemporal representations of predictive neural dynamics. Through entropy-based feature selection, we identify frequency-specific neural signatures that differentiate interpretable linguistic input from linguistically disrupted (time-reversed) stimuli. Our results reveal distributed left-hemispheric and frontal low-frequency coherence as key features in language comprehension, with experience-dependent neural signatures correlating with age. This work demonstrates a novel multimodal approach for probing experience-driven generative models of perception in the brain.

---

### Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting

Authors: Yoonwoo Jeong, Cheng Sun, Frank Wang, Minsu Cho, Jaesung Choe
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20927v1

Recent advancements in computer vision have successfully extended Open-vocabulary segmentation (OVS) to the 3D domain by leveraging 3D Gaussian Splatting (3D-GS). Despite this progress, efficiently rendering the high-dimensional features required for open-vocabulary queries poses a significant challenge. Existing methods employ codebooks or feature compression, causing information loss, thereby degrading segmentation quality. To address this limitation, we introduce Quantile Rendering (Q-Render), a novel rendering strategy for 3D Gaussians that efficiently handles high-dimensional features while maintaining high fidelity. Unlike conventional volume rendering, which densely samples all 3D Gaussians intersecting each ray, Q-Render sparsely samples only those with dominant influence along the ray. By integrating Q-Render into a generalizable 3D neural network, we also propose Gaussian Splatting Network (GS-Net), which predicts Gaussian features in a generalizable manner. Extensive experiments on ScanNet and LeRF demonstrate that our framework outperforms state-of-the-art methods, while enabling real-time rendering with an approximate ~43.7x speedup on 512-D feature maps. Code will be made publicly available.

---

### Clever Hans in Chemistry: Chemist Style Signals Confound Activity Prediction on Public Benchmarks

Authors: Andrew D. Blevins, Ian K. Quigley
Published: 2025-12-24
Categories: q-bio.BM, cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2512.20924v1

Can machine learning models identify which chemist made a molecule from structure alone? If so, models trained on literature data may exploit chemist intent rather than learning causal structure-activity relationships. We test this by linking CHEMBL assays to publication authors and training a 1,815-class classifier to predict authors from molecular fingerprints, achieving 60% top-5 accuracy under scaffold-based splitting. We then train an activity model that receives only a protein identifier and an author-probability vector derived from structure, with no direct access to molecular descriptors. This author-only model achieves predictive power comparable to a simple baseline that has access to structure. This reveals a "Clever Hans" failure mode: models can predict bioactivity largely by inferring chemist goals and favorite targets without requiring a lab-independent understanding of chemistry. We analyze the sources of this leakage, propose author-disjoint splits, and recommend dataset practices to decouple chemist intent from biological outcomes.

---

### Self-supervised Multiplex Consensus Mamba for General Image Fusion

Authors: Yingying Wang, Rongjin Zhuang, Hui Zheng, Xuanhua He, Ke Cao, Xiaotong Tu, Xinghao Ding
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20921v1

Image fusion integrates complementary information from different modalities to generate high-quality fused images, thereby enhancing downstream tasks such as object detection and semantic segmentation. Unlike task-specific techniques that primarily focus on consolidating inter-modal information, general image fusion needs to address a wide range of tasks while improving performance without increasing complexity. To achieve this, we propose SMC-Mamba, a Self-supervised Multiplex Consensus Mamba framework for general image fusion. Specifically, the Modality-Agnostic Feature Enhancement (MAFE) module preserves fine details through adaptive gating and enhances global representations via spatial-channel and frequency-rotational scanning. The Multiplex Consensus Cross-modal Mamba (MCCM) module enables dynamic collaboration among experts, reaching a consensus to efficiently integrate complementary information from multiple modalities. The cross-modal scanning within MCCM further strengthens feature interactions across modalities, facilitating seamless integration of critical information from both sources. Additionally, we introduce a Bi-level Self-supervised Contrastive Learning Loss (BSCL), which preserves high-frequency information without increasing computational overhead while simultaneously boosting performance in downstream tasks. Extensive experiments demonstrate that our approach outperforms state-of-the-art (SOTA) image fusion algorithms in tasks such as infrared-visible, medical, multi-focus, and multi-exposure fusion, as well as downstream visual tasks.

---

### RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks

Authors: Ningyuan Liu, Jing Yang, Kaitong Cai, Keze Wang
Published: 2025-12-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.20920v1

Full parameter fine tuning is a key technique for adapting large language models (LLMs) to downstream tasks, but it incurs substantial memory overhead due to the need to cache extensive intermediate activations for backpropagation. This bottleneck makes full fine tuning of contemporary large scale LLMs challenging in practice. Existing distributed training frameworks such as DeepSpeed alleviate this issue using techniques like ZeRO and FSDP, which rely on multi GPU memory or CPU offloading, but often require additional hardware resources and reduce training speed. We introduce RevFFN, a memory efficient fine tuning paradigm for mixture of experts (MoE) LLMs. RevFFN employs carefully designed reversible Transformer blocks that allow reconstruction of layer input activations from outputs during backpropagation, eliminating the need to store most intermediate activations in memory. While preserving the expressive capacity of MoE architectures, this approach significantly reduces peak memory consumption for full parameter fine tuning. As a result, RevFFN enables efficient full fine tuning on a single consumer grade or server grade GPU.

---

### Towards a General Framework for Predicting and Explaining the Hardness of Graph-based Combinatorial Optimization Problems using Machine Learning and Association Rule Mining

Authors: Bharat Sharman, Elkafi Hassini
Published: 2025-12-24
Categories: cs.LG, math.CO
arXiv: https://arxiv.org/abs/2512.20915v1

This study introduces GCO-HPIF, a general machine-learning-based framework to predict and explain the computational hardness of combinatorial optimization problems that can be represented on graphs. The framework consists of two stages. In the first stage, a dataset is created comprising problem-agnostic graph features and hardness classifications of problem instances. Machine-learning-based classification algorithms are trained to map graph features to hardness categories. In the second stage, the framework explains the predictions using an association rule mining algorithm. Additionally, machine-learning-based regression models are trained to predict algorithmic computation times. The GCO-HPIF framework was applied to a dataset of 3287 maximum clique problem instances compiled from the COLLAB, IMDB, and TWITTER graph datasets using five state-of-the-art algorithms, namely three exact branch-and-bound-based algorithms (Gurobi, CliSAT, and MOMC) and two graph-neural-network-based algorithms (EGN and HGS). The framework demonstrated excellent performance in predicting instance hardness, achieving a weighted F1 score of 0.9921, a minority-class F1 score of 0.878, and an ROC-AUC score of 0.9083 using only three graph features. The best association rule found by the FP-Growth algorithm for explaining the hardness predictions had a support of 0.8829 for hard instances and an overall accuracy of 87.64 percent, underscoring the framework's usefulness for both prediction and explanation. Furthermore, the best-performing regression model for predicting computation times achieved a percentage RMSE of 5.12 and an R2 value of 0.991.

---

### Invariant Feature Extraction Through Conditional Independence and the Optimal Transport Barycenter Problem: the Gaussian case

Authors: Ian Bounos, Pablo Groisman, Mariela Sued, Esteban Tabak
Published: 2025-12-24
Categories: math.ST, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2512.20914v2

A methodology is developed to extract $d$ invariant features $W=f(X)$ that predict a response variable $Y$ without being confounded by variables $Z$ that may influence both $X$ and $Y$. The methodology's main ingredient is the penalization of any statistical dependence between $W$ and $Z$ conditioned on $Y$, replaced by the more readily implementable plain independence between $W$ and the random variable $Z_Y = T(Z,Y)$ that solves the (Monge) Optimal Transport Barycenter Problem for $Z\mid Y$. In the Gaussian case considered in this article, the two statements are equivalent. When the true confounders $Z$ are unknown, other measurable contextual variables $S$ can be used as surrogates, a replacement that involves no relaxation in the Gaussian case if the covariance matrix $Σ_{ZS}$ has full range. The resulting linear feature extractor adopts a closed form in terms of the first $d$ eigenvectors of a known matrix. The procedure extends with little change to more general, non-Gaussian / non-linear cases.

---

### Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

Authors: Kaiyuan Liu, Shaotian Yan, Rui Miao, Bing Wang, Chen Shen, Jun Zhang, Jieping Ye
Published: 2025-12-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.20908v2

Reasoning distillation has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in training contexts. However, previous approaches have lacked a detailed analysis of the origins of the distilled model's capabilities. It remains unclear whether the student can maintain consistent behaviors with the teacher in novel test-time contexts, or whether it regresses to its original output patterns, raising concerns about the generalization of distillation models. To analyse this question, we introduce a cross-model Reasoning Distillation Provenance Tracing framework. For each action (e.g., a sentence) produced by the distilled model, we obtain the predictive probabilities assigned by the teacher, the original student, and the distilled model under the same context. By comparing these probabilities, we classify each action into different categories. By systematically disentangling the provenance of each action, we experimentally demonstrate that, in test-time contexts, the distilled model can indeed generate teacher-originated actions, which correlate with and plausibly explain observed performance on distilled model. Building on this analysis, we further propose a teacher-guided data selection method. Unlike prior approach that rely on heuristics, our method directly compares teacher-student divergences on the training data, providing a principled selection criterion. We validate the effectiveness of our approach across multiple representative teacher models and diverse student models. The results highlight the utility of our provenance-tracing framework and underscore its promise for reasoning distillation. We hope to share Reasoning Distillation Provenance Tracing and our insights into reasoning distillation with the community.

---

### PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding

Authors: Seongmin Jung, Seongho Choi, Gunwoo Jeon, Minsu Cho, Jongwoo Lim
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20907v2

3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose a generalizable 3DVG framework, PanoGrounder, that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3D semantic and geometric features, serve as an intermediate representation between 2D and 3D, and offer two major benefits: (i) they can be directly fed to VLMs with minimal adaptation and (ii) they retain long-range object-to-object relations thanks to their 360-degree field of view. We devise a three-stage pipeline that places a compact set of panoramic viewpoints considering the scene layout and geometry, grounds a text query on each panoramic rendering with a VLM, and fuses per-view predictions into a single 3D bounding box via lifting. Our approach achieves state-of-the-art results on ScanRefer and Nr3D, and demonstrates strong generalization to unseen 3D datasets and text rephrasings.

---

### DiEC: Diffusion Embedded Clustering

Authors: Haidong Hu, Xiaoyu Zheng, Jin Zhou, Yingxu Wang, Rui Wang, Pei Dong, Shiyuan Han, Lin Wang, C. L. Philip Chen, Tong Zhang, Yuehui Chen
Published: 2025-12-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.20905v4

Deep clustering methods typically rely on a single, well-defined representation for clustering. In contrast, pretrained diffusion models provide abundant and diverse multi-scale representations across network layers and noise timesteps. However, a key challenge is how to efficiently identify the most clustering-friendly representation in the layer*timestep space. To address this issue, we propose Diffusion Embedded Clustering (DiEC), an unsupervised framework that performs clustering by leveraging optimal intermediate representations from pretrained diffusion models. DiEC systematically evaluates the clusterability of representations along the trajectory of network depth and noise timesteps. Meanwhile, an unsupervised search strategy is designed for recognizing the Clustering-optimal Layer (COL) and Clustering-optimal Timestep (COT) in the layer*timestep space of pretrained diffusion models, aiming to promote clustering performance and reduce computational overhead. DiEC is fine-tuned primarily with a structure-preserving DEC-style KL-divergence objective at the fixed COL + COT, together with a random-timestep diffusion denoising objective to maintain the generative capability of the pretrained model. Without relying on augmentation-based consistency constraints or contrastive learning, DiEC achieves excellent clustering performance across multiple benchmark datasets.

---

### Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction

Authors: Siqi Mu, Shuo Wen, Yang Lu, Ruihong Jiang, Bo Ai
Published: 2025-12-24
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2512.20902v1

Due to their inherent flexibility and autonomous operation, unmanned aerial vehicles (UAVs) have been widely used in Internet of Medical Things (IoMT) to provide real-time biomedical edge computing service for wireless body area network (WBAN) users. In this paper, considering the time-varying task criticality characteristics of diverse WBAN users and the dual mobility between WBAN users and UAV, we investigate the dynamic task offloading and UAV flight trajectory optimization problem to minimize the weighted average task completion time of all the WBAN users, under the constraint of UAV energy consumption. To tackle the problem, an embodied AI-enhanced IoMT edge computing framework is established. Specifically, we propose a novel hierarchical multi-scale Transformer-based user trajectory prediction model based on the users' historical trajectory traces captured by the embodied AI agent (i.e., UAV). Afterwards, a prediction-enhanced deep reinforcement learning (DRL) algorithm that integrates predicted users' mobility information is designed for intelligently optimizing UAV flight trajectory and task offloading decisions. Real-word movement traces and simulation results demonstrate the superiority of the proposed methods in comparison with the existing benchmarks.

---

### Benchmarking and Enhancing VLM for Compressed Image Understanding

Authors: Zifu Zhang, Tongda Xu, Siqi Li, Shengxi Li, Yue Zhang, Mai Xu, Yan Wang
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20901v2

With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs has become increasingly important. Existing VLMs predominantly digest and understand high-bitrate compressed images, while their ability to interpret low-bitrate compressed images has yet to be explored by far. In this paper, we introduce the first comprehensive benchmark to evaluate the ability of VLM against compressed images, varying existing widely used image codecs and diverse set of tasks, encompassing over one million compressed images in our benchmark. Next, we analyse the source of performance gap, by categorising the gap from a) the information loss during compression and b) generalisation failure of VLM. We visualize these gaps with concrete examples and identify that for compressed images, only the generalization gap can be mitigated. Finally, we propose a universal VLM adaptor to enhance model performance on images compressed by existing codecs. Consequently, we demonstrate that a single adaptor can improve VLM performance across images with varying codecs and bitrates by 10%-30%. We believe that our benchmark and enhancement method provide valuable insights and contribute toward bridging the gap between VLMs and compressed images. The source code is available at https://github.com/bblgbr/CompressVLMBench.

---

### DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction

Authors: Xiao Yu, Zhaojie Fang, Guanyu Zhou, Yin Shen, Huoling Luo, Ye Li, Ahmed Elazab, Xiang Wan, Ruiquan Ge, Changmiao Wang
Published: 2025-12-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.20898v1

Lung cancer continues to be the leading cause of cancer-related deaths globally. Early detection and diagnosis of pulmonary nodules are essential for improving patient survival rates. Although previous research has integrated multimodal and multi-temporal information, outperforming single modality and single time point, the fusion methods are limited to inefficient vector concatenation and simple mutual attention, highlighting the need for more effective multimodal information fusion. To address these challenges, we introduce a Dual-Graph Spatiotemporal Attention Network, which leverages temporal variations and multimodal data to enhance the accuracy of predictions. Our methodology involves developing a Global-Local Feature Encoder to better capture the local, global, and fused characteristics of pulmonary nodules. Additionally, a Dual-Graph Construction method organizes multimodal features into inter-modal and intra-modal graphs. Furthermore, a Hierarchical Cross-Modal Graph Fusion Module is introduced to refine feature integration. We also compiled a novel multimodal dataset named the NLST-cmst dataset as a comprehensive source of support for related research. Our extensive experiments, conducted on both the NLST-cmst and curated CSTL-derived datasets, demonstrate that our DGSAN significantly outperforms state-of-the-art methods in classifying pulmonary nodules with exceptional computational efficiency.

---

### Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks

Authors: Runqi Lin
Published: 2025-12-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.20893v1

With deep neural networks (DNNs) increasingly embedded in modern society, ensuring their safety has become a critical and urgent issue. In response, substantial efforts have been dedicated to the red-blue adversarial framework, where the red team focuses on identifying vulnerabilities in DNNs and the blue team on mitigating them. However, existing approaches from both teams remain computationally intensive, constraining their applicability to large-scale models. To overcome this limitation, this thesis endeavours to provide time-efficient methods for the evaluation and enhancement of adversarial robustness in DNNs.

---

### Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification

Authors: Tingfeng Xian, Wenlve Zhou, Zhiheng Zhou, Zhelin Li
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20892v1

Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking, yet it is fundamentally challenged by significant modality discrepancies. Mainstream solutions typically rely on explicit modality alignment strategies; however, this paradigm heavily depends on constructing large-scale paired datasets for pre-training. To address this, grounded in the Platonic Representation Hypothesis, we explore the potential of Vision Foundation Models (VFMs) in bridging modality gaps. Recognizing the suboptimal performance of existing generic Parameter-Efficient Fine-Tuning (PEFT) methods that operate within the weight space, particularly on limited-capacity models, we shift the optimization perspective to the feature space and propose a novel PEFT strategy termed Domain Representation Injection (DRI). Specifically, while keeping the VFM fully frozen to maximize the preservation of general knowledge, we design a lightweight, learnable Offset Encoder to extract domain-specific representations rich in modality and identity attributes from raw inputs. Guided by the contextual information of intermediate features at different layers, a Modulator adaptively transforms these representations. Subsequently, they are injected into the intermediate layers via additive fusion, dynamically reshaping the feature distribution to adapt to the downstream task without altering the VFM's pre-trained weights. Extensive experimental results demonstrate the superiority of our method, achieving State-of-the-Art (SOTA) performance with minimal trainable parameters. For instance, on the HOSS-ReID dataset, we attain 57.9\% and 60.5\% mAP using only 1.54M and 7.05M parameters, respectively. The code is available at https://github.com/TingfengXian/DRI.

---

### From GNNs to Symbolic Surrogates via Kolmogorov-Arnold Networks for Delay Prediction

Authors: Sami Marouani, Kamal Singh, Baptiste Jeudy, Amaury Habrard
Published: 2025-12-24
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2512.20885v2

Accurate prediction of flow delay is essential for optimizing and managing modern communication networks. We investigate three levels of modeling for this task. First, we implement a heterogeneous GNN with attention-based message passing, establishing a strong neural baseline. Second, we propose FlowKANet in which Kolmogorov-Arnold Networks replace standard MLP layers, reducing trainable parameters while maintaining competitive predictive performance. FlowKANet integrates KAMP-Attn (Kolmogorov-Arnold Message Passing with Attention), embedding KAN operators directly into message-passing and attention computation. Finally, we distill the model into symbolic surrogate models using block-wise regression, producing closed-form equations that eliminate trainable weights while preserving graph-structured dependencies. The results show that KAN layers provide a favorable trade-off between efficiency and accuracy and that symbolic surrogates emphasize the potential for lightweight deployment and enhanced transparency.

---

### The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents

Authors: Zan-Kai Chong, Hiroyuki Ohsaki, Bryan Ng
Published: 2025-12-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.20884v1

Autonomous agents powered by LLMs and Retrieval-Augmented Generation (RAG) are proficient consumers of digital content but remain unidirectional, a limitation we term epistemic asymmetry. This isolation leads to redundant reasoning and stagnates collective intelligence. Current self-reflection frameworks remain largely heuristic and private, lacking a probabilistic foundation to quantify certainty or justify external interaction.To bridge this gap, we propose a formal probabilistic framework that provides agents with a non-altruistic motive for bidirectional knowledge exchange. We model an agent's belief in a proposition using a Beta-Bernoulli distribution with a forgetting factor ($γ$). This allows us to isolate epistemic uncertainty as the variance of belief, establishing a dual drive for interaction: A homeostatic motive: The need to maintain certainty against the temporal decay introduced by $γ$. An optimal learning strategy: Targeting points of maximum ambiguity ($\mathbb{E}(θ)=0.5$) to maximize information gain. Under this framework, public contribution is reframed as optimal active learning: sharing solutions to elicit feedback is the most efficient method for an agent to reduce its own uncertainty. To ensure scalability, we introduce epistemic caching, which leverages the forgetting factor to dynamically prioritize resources for the active head of non-stationary knowledge distributions. Finally, we demonstrate how these accumulated belief states serve as verifiable reward signals for Reinforcement Learning from Human Feedback (RLHF) and high-quality data filters for Supervised Fine-Tuning (SFT). Simulation results validate that this uncertainty-driven strategy significantly outperforms random baselines in heterogeneous (Zipfian) environments, maintaining high adaptability to concept drift.

---

### Architectural Trade-offs in Small Language Models Under Compute Constraints

Authors: Shivraj Singh Bhatti
Published: 2025-12-24
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.20877v1

We present a systematic empirical study of small language models under strict compute constraints, analyzing how architectural choices and training budget interact to determine performance. Starting from a linear next-token predictor, we progressively introduce nonlinearities, self-attention, and multi-layer transformer architectures, evaluating each on character-level modeling of Tiny Shakespeare and word-level modeling of Penn Treebank (PTB) and WikiText-2. We compare models using test negative log-likelihood (NLL), parameter count, and approximate training FLOPs to characterize accuracy-efficiency trade-offs. Our results show that attention-based models dominate MLPs in per-FLOP efficiency even at small scale, while increasing depth or context without sufficient optimization can degrade performance. We further examine rotary positional embeddings (RoPE), finding that architectural techniques successful in large language models do not necessarily transfer to small-model regimes.

---

### Better Call Graphs: A New Dataset of Function Call Graphs for Malware Classification

Authors: Jakir Hossain, Jue Guo, Gurvinder Singh, Lukasz Ziarek, Ahmet Erdem Sarıyüce
Published: 2025-12-24
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.20872v2

Function call graphs (FCGs) have emerged as a powerful abstraction for malware detection, capturing the behavioral structure of applications beyond surface-level signatures. Their utility in traditional program analysis has been well established, enabling effective classification and analysis of malicious software. In the mobile domain, especially in the Android ecosystem, FCG-based malware classification is particularly critical due to the platform's widespread adoption and the complex, component-based structure of Android apps. However, progress in this direction is hindered by the lack of large-scale, high-quality Android-specific FCG datasets. Existing datasets are often outdated, dominated by small or redundant graphs resulting from app repackaging, and fail to reflect the diversity of real-world malware. These limitations lead to overfitting and unreliable evaluation of graph-based classification methods. To address this gap, we introduce Better Call Graphs (BCG), a comprehensive dataset of large and unique FCGs extracted from recent Android application packages (APKs). BCG includes both benign and malicious samples spanning various families and types, along with graph-level features for each APK. Through extensive experiments using baseline classifiers, we demonstrate the necessity and value of BCG compared to existing datasets. BCG is publicly available at https://erdemub.github.io/BCG-dataset.

---

### NeRV360: Neural Representation for 360-Degree Videos with a Viewport Decoder

Authors: Daichi Arai, Kyohei Unno, Yasuko Sugito, Yuichi Kusakabe
Published: 2025-12-24
Categories: cs.CV, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2512.20871v2

Implicit neural representations for videos (NeRV) have shown strong potential for video compression. However, applying NeRV to high-resolution 360-degree videos causes high memory usage and slow decoding, making real-time applications impractical. We propose NeRV360, an end-to-end framework that decodes only the user-selected viewport instead of reconstructing the entire panoramic frame. Unlike conventional pipelines, NeRV360 integrates viewport extraction into decoding and introduces a spatial-temporal affine transform module for conditional decoding based on viewpoint and time. Experiments on 6K-resolution videos show that NeRV360 achieves a 7-fold reduction in memory consumption and a 2.5-fold increase in decoding speed compared to HNeRV, a representative prior work, while delivering better image quality in terms of objective metrics.

---

### Lightweight framework for underground pipeline recognition and spatial localization based on multi-view 2D GPR images

Authors: Haotian Lv, Chao Li, Jiangbo Dai, Yuhui Zhang, Zepeng Fan, Yiqiu Tan, Dawei Wang, Binglei Xie
Published: 2025-12-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.20866v1

To address the issues of weak correlation between multi-view features, low recognition accuracy of small-scale targets, and insufficient robustness in complex scenarios in underground pipeline detection using 3D GPR, this paper proposes a 3D pipeline intelligent detection framework. First, based on a B/C/D-Scan three-view joint analysis strategy, a three-dimensional pipeline three-view feature evaluation method is established by cross-validating forward simulation results obtained using FDTD methods with actual measurement data. Second, the DCO-YOLO framework is proposed, which integrates DySample, CGLU, and OutlookAttention cross-dimensional correlation mechanisms into the original YOLOv11 algorithm, significantly improving the small-scale pipeline edge feature extraction capability. Furthermore, a 3D-DIoU spatial feature matching algorithm is proposed, which integrates three-dimensional geometric constraints and center distance penalty terms to achieve automated association of multi-view annotations. The three-view fusion strategy resolves inherent ambiguities in single-view detection. Experiments based on real urban underground pipeline data show that the proposed method achieves accuracy, recall, and mean average precision of 96.2%, 93.3%, and 96.7%, respectively, in complex multi-pipeline scenarios, which are 2.0%, 2.1%, and 0.9% higher than the baseline model. Ablation experiments validated the synergistic optimization effect of the dynamic feature enhancement module and Grad-CAM++ heatmap visualization demonstrated that the improved model significantly enhanced its ability to focus on pipeline geometric features. This study integrates deep learning optimization strategies with the physical characteristics of 3D GPR, offering an efficient and reliable novel technical framework for the intelligent recognition and localization of underground pipelines.

---

### Robustness Certificates for Neural Networks Against Data Poisoning and Evasion Attacks

Authors: Sara Taheri, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Majid Zamani
Published: 2025-12-24
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.20865v3

The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing defenses lack formal guarantees or rely on restrictive assumptions about the model class, attack type, extent of poisoning, or point-wise certification, limiting their practical reliability. This paper introduces a principled formal robustness certification framework that models gradient-based training as a discrete-time dynamical system (dt-DS) and formulates poisoning robustness as a formal safety verification problem. By adapting the concept of barrier certificates (BCs) from control theory, we introduce sufficient conditions to certify a robust radius ensuring that the terminal model remains safe under worst-case ${\ell}_p$-norm-based poisoning. To make this practical, we parameterize BCs as neural networks trained on finite sets of poisoned trajectories. We further derive probably approximately correct (PAC) bounds by solving a scenario convex program (SCP), which yields a confidence lower bound on the certified robustness radius generalizing beyond the training set. Importantly, our framework also extends to certification against test-time attacks, making it the first unified framework to provide formal guarantees in both training and test-time attack settings. Experiments on MNIST, SVHN, CIFAR-10, and CIFAR-100 show that our approach certifies non-trivial perturbation budgets while being model-agnostic and requiring no prior knowledge of the attack or contamination level.

---

### Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

Authors: Pierre Abillama, Changwoo Lee, Juechu Dong, David Blaauw, Dennis Sylvester, Hun-Seok Kim
Published: 2025-12-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.20861v2

Recent advances in transformer-based foundation models have made them the default choice for many tasks, but their rapidly growing size makes fitting a full model on a single GPU increasingly difficult and their computational cost prohibitive. Block low-rank (BLR) compression techniques address this challenge by learning compact representations of weight matrices. While traditional low-rank (LR) methods often incur sharp accuracy drops, BLR approaches such as Monarch and BLAST can better capture the underlying structure, thus preserving accuracy while reducing computations and memory footprints. In this work, we use roofline analysis to show that, although BLR methods achieve theoretical savings and practical speedups for single-token inference, multi-token inference often becomes memory-bound in practice, increasing latency despite compiler-level optimizations in PyTorch. To address this, we introduce custom Triton kernels with partial fusion and memory layout optimizations for both Monarch and BLAST. On memory-constrained NVIDIA GPUs such as Jetson Orin Nano and A40, our kernels deliver up to $3.76\times$ speedups and $3\times$ model size compression over PyTorch dense baselines using CUDA backend and compiler-level optimizations, while supporting various models including Llama-7/1B, GPT2-S, DiT-XL/2, and ViT-B. Our code is available at https://github.com/pabillam/mem-efficient-blr.

---

### ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction

Authors: Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang
Published: 2025-12-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.20858v1

Traditional lecture videos offer flexibility but lack mechanisms for real-time clarification, forcing learners to search externally when confusion arises. Recent advances in large language models and neural avatars provide new opportunities for interactive learning, yet existing systems typically lack lecture awareness, rely on cloud-based services, or fail to integrate retrieval and avatar-delivered explanations in a unified, privacy-preserving pipeline. We present ALIVE, an Avatar-Lecture Interactive Video Engine that transforms passive lecture viewing into a dynamic, real-time learning experience. ALIVE operates fully on local hardware and integrates (1) Avatar-delivered lecture generated through ASR transcription, LLM refinement, and neural talking-head synthesis; (2) A content-aware retrieval mechanism that combines semantic similarity with timestamp alignment to surface contextually relevant lecture segments; and (3) Real-time multimodal interaction, enabling students to pause the lecture, ask questions through text or voice, and receive grounded explanations either as text or as avatar-delivered responses. To maintain responsiveness, ALIVE employs lightweight embedding models, FAISS-based retrieval, and segmented avatar synthesis with progressive preloading. We demonstrate the system on a complete medical imaging course, evaluate its retrieval accuracy, latency characteristics, and user experience, and show that ALIVE provides accurate, content-aware, and engaging real-time support. ALIVE illustrates how multimodal AI-when combined with content-aware retrieval and local deployment-can significantly enhance the pedagogical value of recorded lectures, offering an extensible pathway toward next-generation interactive learning environments.

---

### NVIDIA Nemotron 3: Efficient and Open Intelligence

Authors: NVIDIA, :, Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek et al.
Published: 2025-12-24
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.20856v1

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to 1M tokens. Super and Ultra models are trained with NVFP4 and incorporate LatentMoE, a novel approach that improves model quality. The two larger models also include MTP layers for faster text generation. All Nemotron 3 models are post-trained using multi-environment reinforcement learning enabling reasoning, multi-step tool use, and support granular reasoning budget control. Nano, the smallest model, outperforms comparable models in accuracy while remaining extremely cost-efficient for inference. Super is optimized for collaborative agents and high-volume workloads such as IT ticket automation. Ultra, the largest model, provides state-of-the-art accuracy and reasoning performance. Nano is released together with its technical report and this white paper, while Super and Ultra will follow in the coming months. We will openly release the model weights, pre- and post-training software, recipes, and all data for which we hold redistribution rights.

---

### How important is Recall for Measuring Retrieval Quality?

Authors: Shelly Schwartz, Oleg Vasilyev, Randy Sawaya
Published: 2025-12-24
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2512.20854v2

In realistic retrieval settings with large and evolving knowledge bases, the total number of documents relevant to a query is typically unknown, and recall cannot be computed. In this paper, we evaluate several established strategies for handling this limitation by measuring the correlation between retrieval quality metrics and LLM-based judgments of response quality, where responses are generated from the retrieved documents. We conduct experiments across multiple datasets with a relatively low number of relevant documents (2-15). We also introduce a simple retrieval quality measure that performs well without requiring knowledge of the total number of relevant documents.

---

### Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India

Authors: Rakshita Goel, S Pranav Kumar, Anmol Agrawal, Divyan Poddar, Pratik Narang, Dhruv Kumar
Published: 2025-12-23
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.23371v1

Legal research in India involves navigating long and heterogeneous documents spanning statutes, constitutional provisions, penal codes, and judicial precedents, where purely keyword-based or embedding-only retrieval systems often fail to support structured legal reasoning. Recent retrieval augmented generation (RAG) approaches improve grounding but struggle with multi-hop reasoning, citation chaining, and cross-domain dependencies inherent to legal texts. We propose a domain partitioned hybrid RAG and Knowledge Graph architecture designed specifically for Indian legal research. The system integrates three specialized RAG pipelines covering Supreme Court case law, statutory and constitutional texts, and the Indian Penal Code, each optimized for domain specific retrieval. To enable relational reasoning beyond semantic similarity, we construct a Neo4j based Legal Knowledge Graph capturing structured relationships among cases, statutes, IPC sections, judges, and citations. An LLM driven agentic orchestrator dynamically routes queries across retrieval modules and the knowledge graph, fusing evidence into grounded and citation aware responses. We evaluate the system using a 40 question synthetic legal question answer benchmark curated from authoritative Indian legal sources and assessed via an LLM as a Judge framework. Results show that the hybrid architecture achieves a 70 percent pass rate, substantially outperforming a RAG only baseline at 37.5 percent, with marked improvements in completeness and legal reasoning quality. These findings demonstrate that combining domain partitioned retrieval with structured relational knowledge provides a scalable and interpretable foundation for advanced legal AI systems in the Indian judicial context.

---

### Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents

Authors: Kaifeng Wu, Junyan Wu, Qiang Liu, Jiarui Zhang, Wen Xu
Published: 2025-12-23
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.23370v1

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained by fixed windows and cannot model document-level semantics; generative large language models can output paragraph boundaries, but inference is expensive and long inputs are difficult to support. To address these issues, we propose a discriminative segmentation model based on Qwen3-0.6B. On top of the backbone network, we add a cross-window context fusion layer and a boundary classification head, and combine them with an overlapping sliding-window strategy. Our model supports single-pass inputs of up to 13k tokens and can be extended to ultra-long documents for paragraph boundary detection. To further enhance downstream retrieval efficiency, we derive a vector fusion method with scalar correction, which compresses the representation of ultra-long segments into a single vector without semantic loss. Experiments on the Wikipedia long-document topic segmentation dataset WIKI-727K show that, compared with three generative models based on Qwen2-0.5B released by Jina, our method achieves a better macro-averaged F1 and delivers two orders of magnitude faster inference, substantially improving the practicality and scalability of long-document processing.

---

### From Textbook to Talkbot: A Case Study of a Greek-Language RAG-Based Chatbot in Higher Education

Authors: Maria Eleni Koutsiaki, Marina Delianidi, Chaido Mizeli, Konstantinos Diamantaras, Iraklis Grigoropoulos, Nikolaos Koutlianos
Published: 2025-12-23
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.14265v1

The integration of AI chatbots into educational settings has opened new pathways for transforming teaching and learning, offering enhanced support to both educators and learners. This study investigates the design and application of an AI chatbot as an educational tool in higher education. Designed to operate in the Greek language, the chatbot addresses linguistic challenges unique to Greek while delivering accurate, context grounded support aligned with the curriculum. The AI chatbot is built on the Retrieval Augmented Generation (RAG) framework by grounding its responses in specific course content. RAG architecture significantly enhances the chatbots reliability by providing accurate, context-aware responses while mitigating common challenges associated with large language models (LLMs), such as hallucinations and misinformation. The AI chatbot serves a dual purpose: it enables students to access accurate, ondemand academic support and assists educators in the rapid creation of relevant educational materials. This dual functionality promotes learner autonomy and streamlines the instructional design process. The study aims to evaluate the effectiveness, reliability, and perceived usability of RAG based chatbots in higher education, exploring their potential to enhance educational practices and outcomes as well as supporting the broader adoption of AI technologies in language specific educational contexts. Findings from this research are expected to contribute to the emerging field of AI driven education by demonstrating how intelligent systems can be effectively aligned with pedagogical goals.

---

### DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research

Authors: Zifeng Wang, Zheng Chen, Ziwei Yang, Xuan Wang, Qiao Jin, Yifan Peng, Zhiyong Lu, Jimeng Sun
Published: 2025-12-23
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.11560v1

Biomedical knowledge graphs (KGs) encode vast, heterogeneous information spanning literature, genes, pathways, drugs, diseases, and clinical trials, but leveraging them collectively for scientific discovery remains difficult. Their structural differences, continual evolution, and limited cross-resource alignment require substantial manual integration, limiting the depth and scale of knowledge exploration. We introduce DeepEvidence, an AI-agent framework designed to perform Deep Research across various heterogeneous biomedical KGs. Unlike generic Deep Research systems that rely primarily on internet-scale text, DeepEvidence incorporates specialized knowledge-graph tooling and coordinated exploration strategies to systematically bridge heterogeneous resources. At its core is an orchestrator that directs two complementary agents: Breadth-First ReSearch (BFRS) for broad, multi-graph entity search, and Depth-First ReSearch (DFRS) for multi-hop, evidence-focused reasoning. An internal, incrementally built evidence graph provides a structured record of retrieved entities, relations, and supporting evidence. To operate at scale, DeepEvidence includes unified interfaces for querying diverse biomedical APIs and an execution sandbox that enables programmatic data retrieval, extraction, and analysis. Across established deep-reasoning benchmarks and four key stages of the biomedical discovery lifecycle: drug discovery, pre-clinical experimentation, clinical trial development, and evidence-based medicine, DeepEvidence demonstrates substantial gains in systematic exploration and evidence synthesis. These results highlight the potential of knowledge-graph-driven Deep Research to accelerate biomedical discovery.

---

### Multi-Level Embedding Conformer Framework for Bengali Automatic Speech Recognition

Authors: Md. Nazmus Sakib, Golam Mahmud, Md. Maruf Bangabashi, Umme Ara Mahinur Istia, Md. Jahidul Islam, Partha Sarker, Afra Yeamini Prity
Published: 2025-12-23
Categories: eess.AS, cs.CL
arXiv: https://arxiv.org/abs/2601.09710v1

Bengali, spoken by over 300 million people, is a morphologically rich and lowresource language, posing challenges for automatic speech recognition (ASR). This research presents an end-to-end framework for Bengali ASR, building on a Conformer-CTC backbone with a multi-level embedding fusion mechanism that incorporates phoneme, syllable, and wordpiece representations. By enriching acoustic features with these linguistic embeddings, the model captures fine-grained phonetic cues and higher-level contextual patterns. The architecture employs early and late Conformer stages, with preprocessing steps including silence trimming, resampling, Log-Mel spectrogram extraction, and SpecAugment augmentation. The experimental results demonstrate the strong potential of the model, achieving a word error rate (WER) of 10.01% and a character error rate (CER) of 5.03%. These results demonstrate the effectiveness of combining multi-granular linguistic information with acoustic modeling, providing a scalable approach for low-resource ASR development.

---

### Más contexto no es mejor. Paradoja de la dilución vectorial en RAG corporativos

Authors: Alex Dantart
Published: 2025-12-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.08851v1

Técnicas recientes de "Contextualized Chunking" inyectan resúmenes para mejorar el contexto en RAG, pero introducen una "dilución vectorial" que opaca el contenido local. Evaluando distintos ratios de inyección, demostramos una curva en "U invertida": una inyección moderada mejora el "Recall" (+18%), pero superar un umbral crítico (CIR > 0.4) reduce la precisión en un 22% para consultas específicas. Proponemos un marco teórico para calcular el ratio óptimo de inyección. -- Recent "Contextualized Chunking" techniques inject summaries to improve RAG context but introduce "vector dilution" drowning out local content. Evaluating various injection ratios, we demonstrate an "inverted U" curve: moderate injection boosts Recall (+18%), but exceeding a critical threshold (CIR > 0.4) drops precision by 22% for specific queries. We propose a theoretical framework to calculate the optimal injection ratio.

---

### AI Application Operations -- A Socio-Technical Framework for Data-driven Organizations

Authors: Daniel Jönsson, Mattias Tiger, Stefan Ekberg, Daniel Jakobsson, Mattias Jonhede, Fredrik Viksten
Published: 2025-12-23
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.06061v1

We outline a comprehensive framework for artificial intelligence (AI) Application Operations (AIAppOps), based on real-world experiences from diverse organizations. Data-driven projects pose additional challenges to organizations due to their dependency on data across the development and operations cycles. To aid organizations in dealing with these challenges, we present a framework outlining the main steps and roles involved in going from idea to production for data-driven solutions. The data dependency of these projects entails additional requirements on continuous monitoring and feedback, as deviations can emerge in any process step. Therefore, the framework embeds monitoring not merely as a safeguard, but as a unifying feedback mechanism that drives continuous improvement, compliance, and sustained value realization-anchored in both statistical and formal assurance methods that extend runtime verification concepts from safety-critical AI to organizational operations. The proposed framework is structured across core technical processes and supporting services to guide both new initiatives and maturing AI programs.

---

### Why Slop Matters

Authors: Cody Kommers, Eamon Duede, Julia Gordon, Ari Holtzman, Tess McNulty, Spencer Stewart, Lindsay Thomas, Richard Jean So, Hoyt Long
Published: 2025-12-23
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06060v1

AI-generated "slop" is often seen as digital pollution. We argue that this dismissal of the topic risks missing important aspects of AI Slop that deserve rigorous study. AI Slop serves a social function: it offers a supply-side solution to a variety of problems in cultural and economic demand - that, collectively, people want more content than humans can supply. We also argue that AI Slop is not mere digital detritus but has its own aesthetic value. Like other "low" cultural forms initially dismissed by critics, it nonetheless offers a legitimate means of collective sense-making, with the potential to express meaning and identity. We identify three key features of family resemblance for prototypical AI Slop: superficial competence (its veneer of quality is belied by a deeper lack of substance), asymmetry effort (it takes vastly less effort to generate than would be the case without AI), and mass producibility (it is part of a digital ecosystem of widespread generation and consumption). While AI Slop is heterogeneous and depends crucially on its medium, it tends to vary across three dimensions: instrumental utility, personalization, and surrealism. AI Slop will be an increasingly prolific and impactful part of our creative, information, and cultural economies; we should take it seriously as an object of study in its own right.

---

### Context Video Semantic Transmission with Variable Length and Rate Coding over MIMO Channels

Authors: Bingyan Xie, Yongpeng Wu, Wenjun Zhang, Derrick Wing Kwan Ng, Merouane Debbah
Published: 2025-12-23
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2601.06059v1

The evolution of semantic communications has profoundly impacted wireless video transmission, whose applications dominate driver of modern bandwidth consumption. However, most existing schemes are predominantly optimized for simple additive white Gaussian noise or Rayleigh fading channels, neglecting the ubiquitous multiple-input multiple-output (MIMO) environments that critically hinder practical deployment. To bridge this gap, we propose the context video semantic transmission (CVST) framework under MIMO channels. Building upon an efficient contextual video transmission backbone, CVST effectively learns a context-channel correlation map to explicitly formulate the relationships between feature groups and MIMO subchannels. Leveraging these channel-aware features, we design a multi-reference entropy coding mechanism, enabling channel state-aware variable length coding. Furthermore, CVST incorporates a checkerboard-based feature modulation strategy to achieve multiple rate points within a single trained model, thereby enhancing deployment flexibility. These innovations constitute our multi-reference variable length and rate coding (MR-VLRC) scheme. By integrating contextual transmission with MR-VLRC, CVST demonstrates substantial performance gains over various standardized separated coding methods and recent wireless video semantic communication approaches. The code is available at https://github.com/xie233333/CVST.

---

### Base Station Deployment under EMF constrain by Deep Reinforcement learning

Authors: Mohammed Mallik, Guillaume Villemaud
Published: 2025-12-23
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2601.02385v1

As 5G networks rapidly expand and 6G technologies emerge, characterized by dense deployments, millimeter-wave communications, and dynamic beamforming, the need for scalable simulation tools becomes increasingly critical. These tools must support efficient evaluation of key performance metrics such as coverage and radio-frequency electromagnetic field (RF-EMF) exposure, inform network design decisions, and ensure compliance with safety regulations. Moreover, base station (BS) placement is a crucial task in the network design, where satisfying coverage requirements is essential. To address these, based on our previous work, we first propose a conditional generative adversarial network (cGAN) that predicts location specific received signal strength (RSS), and EMF exposure simultaneously from the network topology, as images. As a network designing application, we propose a Deep Q Network (DQN) framework, using the trained cGAN, for optimal base station (BS) deployment in the network. Compared to conventional ray tracing simulations, the proposed cGAN reduces inference and deployment time from several hours to seconds. Unlike a standalone cGAN, which provides static performance maps, the proposed GAN-DQN framework enables sequential decision making under coverage and exposure constraints, learning effective deployment strategies that directly solve the BS placement problem. Thus making it well suited for real time design and adaptation in dynamic scenarios in order to satisfy pre defined network specific heterogeneous performance goals.

---

### Energy-Aware Routing to Large Reasoning Models

Authors: Austin R. Ellis-Mohr, Max Hartman, Lav R. Varshney
Published: 2025-12-23
Categories: cs.AI, cs.IT, eess.SY
arXiv: https://arxiv.org/abs/2601.00823v2

Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it is important to choose the right LRM and operate it in the right way. As a result, the performance of systems that dispatch tasks to different individual LRMs depend on the balance between mean energy provisioning and stochastic fluctuations. The critical regime is the unique operating point at which neither auxiliary energy nor baseline energy is systematically wasted. Increasing baseline supply shifts the system toward persistent over-supply and baseline-energy waste, while reducing supply induces persistent reliance on auxiliary energy. Yet in this regime, performance remains volatility-limited and so a second-order characterization provides further insights that we develop. Here, performance is governed by how variability is absorbed across time, models, and execution choices. This perspective highlights variance-aware routing and dispatch as a principled design axis, and provides a theoretical basis for developing energy-aware model routing policies. Routing behavior is characterized when dispatch policies are based on training-compute and inference-compute scaling laws for LRMs.

---