# Research Papers — 2026-01 · bundle page 56 of 189 > Full-text markdown of papers #2751–2800 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/56 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/55.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/57.md) ### MV-SAM: Multi-view Promptable Segmentation using Pointmap Guidance Authors: Yoonwoo Jeong, Cheng Sun, Yu-Chiang Frank Wang, Minsu Cho, Jaesung Choe Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17866v1 Promptable segmentation has emerged as a powerful paradigm in computer vision, enabling users to guide models in parsing complex scenes with prompts such as clicks, boxes, or textual cues. Recent advances, exemplified by the Segment Anything Model (SAM), have extended this paradigm to videos and multi-view images. However, the lack of 3D awareness often leads to inconsistent results, necessitating costly per-scene optimization to enforce 3D consistency. In this work, we introduce MV-SAM, a framework for multi-view segmentation that achieves 3D consistency using pointmaps -- 3D points reconstructed from unposed images by recent visual geometry models. Leveraging the pixel-point one-to-one correspondence of pointmaps, MV-SAM lifts images and prompts into 3D space, eliminating the need for explicit 3D networks or annotated 3D data. Specifically, MV-SAM extends SAM by lifting image embeddings from its pretrained encoder into 3D point embeddings, which are decoded by a transformer using cross-attention with 3D prompt embeddings. This design aligns 2D interactions with 3D geometry, enabling the model to implicitly learn consistent masks across views through 3D positional embeddings. Trained on the SA-1B dataset, our method generalizes well across domains, outperforming SAM2-Video and achieving comparable performance with per-scene optimization baselines on NVOS, SPIn-NeRF, ScanNet++, uCo3D, and DL3DV benchmarks. Code will be released. --- ### D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models Authors: Jia Gu, Liang Pang, Huawei Shen, Xueqi Cheng Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17865v2 The predictive probability of the next token (P_token) in large language models (LLMs) is inextricably linked to the probability of relevance for the next piece of information, the purchase probability of the next product, and the execution probability of the next action-all of which fall under the scope of the task-level target distribution (P_task). While LLMs are known to generate samples that approximate real-world distributions, whether their fine-grained sampling probabilities faithfully align with task requirements remains an open question. Through controlled distribution-sampling simulations, we uncover a striking dichotomy in LLM behavior, distinguishing two model types: D-models (e.g. Qwen-2.5), whose P_token exhibits large step-to-step variability and poor alignment with P_task; and E-models (e.g. Mistral-Small), whose P_token is more stable and better aligned with P_task. We further evaluate these two model types in downstream tasks such as code generation and recommendation, revealing systematic trade-offs between diversity and stability that shape task outcomes. Finally, we analyze the internal properties of both model families to probe their underlying mechanisms. These findings offer foundational insights into the probabilistic sampling behavior of LLMs and provide practical guidance on when to favor D- versus E-models. For web-scale applications, including recommendation, search, and conversational agents, our results inform model selection and configuration to balance diversity with reliability under real-world uncertainty, providing a better level of interpretation. --- ### Domain Generalization with Quantum Enhancement for Medical Image Classification: A Lightweight Approach for Cross-Center Deployment Authors: Jingsong Xia, Siqi Wang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17862v1 Medical image artificial intelligence models often achieve strong performance in single-center or single-device settings, yet their effectiveness frequently deteriorates in real-world cross-center deployment due to domain shift, limiting clinical generalizability. To address this challenge, we propose a lightweight domain generalization framework with quantum-enhanced collaborative learning, enabling robust generalization to unseen target domains without relying on real multi-center labeled data. Specifically, a MobileNetV2-based domain-invariant encoder is constructed and optimized through three key components: (1) multi-domain imaging shift simulation using brightness, contrast, sharpening, and noise perturbations to emulate heterogeneous acquisition conditions; (2) domain-adversarial training with gradient reversal to suppress domain-discriminative features; and (3) a lightweight quantum feature enhancement layer that applies parameterized quantum circuits for nonlinear feature mapping and entanglement modeling. In addition, a test-time adaptation strategy is employed during inference to further alleviate distribution shifts. Experiments on simulated multi-center medical imaging datasets demonstrate that the proposed method significantly outperforms baseline models without domain generalization or quantum enhancement on unseen domains, achieving reduced domain-specific performance variance and improved AUC and sensitivity. These results highlight the clinical potential of quantum-enhanced domain generalization under constrained computational resources and provide a feasible paradigm for hybrid quantum--classical medical imaging systems. --- ### MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging Authors: Jiapeng Wang, Changxin Tian, Kunlong Chen, Ziqi Liu, Jiaxin Mao, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou Published: 2026-01-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.17858v1 Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy training. To address this, we introduce \textbf{MergeMix}, a novel approach that efficiently determines optimal data mixing ratios by repurposing model merging weights as a high-fidelity, low-cost performance proxy. By training domain-specific experts on minimal tokens and optimizing their merging weights against downstream benchmarks, MergeMix effectively optimizes the performance of data mixtures without incurring the cost of full-scale training. Extensive experiments on models with 8B and 16B parameters validate that MergeMix achieves performance comparable to or surpassing exhaustive manual tuning while drastically reducing search costs. Furthermore, MergeMix exhibits high rank consistency (Spearman $ρ> 0.9$) and strong cross-scale transferability, offering a scalable, automated solution for data mixture optimization. --- ### SynMind: Reducing Semantic Hallucination in fMRI-Based Image Reconstruction Authors: Lan Yang, Minghan Yang, Ke Li, Honggang Zhang, Kaiyue Pang, Yi-Zhe Song Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17857v1 Recent advances in fMRI-based image reconstruction have achieved remarkable photo-realistic fidelity. Yet, a persistent limitation remains: while reconstructed images often appear naturalistic and holistically similar to the target stimuli, they frequently suffer from severe semantic misalignment -- salient objects are often replaced or hallucinated despite high visual quality. In this work, we address this limitation by rethinking the role of explicit semantic interpretation in fMRI decoding. We argue that existing methods rely too heavily on entangled visual embeddings which prioritize low-level appearance cues -- such as texture and global gist -- over explicit semantic identity. To overcome this, we parse fMRI signals into rich, sentence-level semantic descriptions that mirror the hierarchical and compositional nature of human visual understanding. We achieve this by leveraging grounded VLMs to generate synthetic, human-like, multi-granularity textual representations that capture object identities and spatial organization. Built upon this foundation, we propose SynMind, a framework that integrates these explicit semantic encodings with visual priors to condition a pretrained diffusion model. Extensive experiments demonstrate that SynMind outperforms state-of-the-art methods across most quantitative metrics. Notably, by offloading semantic reasoning to our text-alignment module, SynMind surpasses competing methods based on SDXL while using the much smaller Stable Diffusion 1.4 and a single consumer GPU. Large-scale human evaluations further confirm that SynMind produces reconstructions more consistent with human visual perception. Neurovisualization analyses reveal that SynMind engages broader and more semantically relevant brain regions, mitigating the over-reliance on high-level visual areas. --- ### A Universal Load Balancing Principle and Its Application to Large Language Model Serving Authors: Zixi Chen, Tianci Bu, Chendong Song, Xin Lu, Yinyu Ye, Zijie Zhou Published: 2026-01-25 Categories: cs.DC, stat.ML arXiv: https://arxiv.org/abs/2601.17855v2 Over 40% of computational power in Large Language Model (LLM) serving systems can be systematically wasted - not from hardware limits, but from load imbalance in barrier-synchronized parallel processing. When progress is gated by the slowest worker at each step, heterogeneous and evolving workloads create persistent stragglers; faster workers idle while drawing power, producing nothing. In large language model inference alone, this translates to gigawatt-hours of wasted electricity daily. Here we develop a universal load-balancing principle for barrier-synchronized systems with non-migratable state. We prove worst-case theoretical guarantees: imbalance reduction grows with system scale, and the resulting energy savings can exceed 52% for modern hardware at fleet scale. Experiments corroborate the theory, demonstrating 28% energy reduction alongside substantial throughput and latency improvements. Formulated as an online integer optimization with provable guarantees, the principle extends beyond LLM serving to broad classes of barrier-synchronized parallel systems, establishing a theoretical foundation for sustainable high-performance computing. --- ### RAICL: Retrieval-Augmented In-Context Learning for Vision-Language-Model Based EEG Seizure Detection Authors: Siyang Li, Zhuoya Wang, Xiyan Gui, Xiaoqing Chen, Ziwei Wang, Yaozhi Wen, Dongrui Wu Published: 2026-01-25 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.17844v1 Electroencephalogram (EEG) decoding is a critical component of medical diagnostics, rehabilitation engineering, and brain-computer interfaces. However, contemporary decoding methodologies remain heavily dependent on task-specific datasets to train specialized neural network architectures. Consequently, limited data availability impedes the development of generalizable large brain decoding models. In this work, we propose a paradigm shift from conventional signal-based decoding by leveraging large-scale vision-language models (VLMs) to analyze EEG waveform plots. By converting multivariate EEG signals into stacked waveform images and integrating neuroscience domain expertise into textual prompts, we demonstrate that foundational VLMs can effectively differentiate between different patterns in the human brain. To address the inherent non-stationarity of EEG signals, we introduce a Retrieval-Augmented In-Context Learning (RAICL) approach, which dynamically selects the most representative and relevant few-shot examples to condition the autoregressive outputs of the VLM. Experiments on EEG-based seizure detection indicate that state-of-the-art VLMs under RAICL achieved better or comparable performance with traditional time series based approaches. These findings suggest a new direction in physiological signal processing that effectively bridges the modalities of vision, language, and neural activities. Furthermore, the utilization of off-the-shelf VLMs, without the need for retraining or downstream architecture construction, offers a readily deployable solution for clinical applications. --- ### EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapy Authors: Lanqing Du, Yunong Li, YuJie Long, Shihong Chen Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17842v2 The use of large language models (LLMs) for Mental Health Question Answering (MHQA) offers a promising way to alleviate shortages in mental health resources. However, prior work has mainly relied on Cognitive Behavioral Therapy (CBT) and predominantly follows a top-down strategy centered on rational cognitive restructuring, providing limited support for embodied experience and primary emotion processing. To address this gap, we propose EFT-CoT, a multi-agent chain-of-thought framework grounded in Emotion-Focused Therapy (EFT). EFT-CoT operationalizes intervention as a three-stage workflow: Embodied Perception, Cognitive Exploration, and Narrative Intervention. The framework employs eight specialized agents to model key processes including somatic awareness mapping, adaptive evaluation, core belief extraction, and narrative restructuring. Based on this framework, we construct EFT-Instruct, a high-quality instruction-tuning dataset built from process-level augmentation of about 67,000 real help-seeking texts, and further fine-tune a dedicated model, EFT-LLM. Experiments show that EFT-LLM consistently outperforms strong baselines and human responses in empathic depth and structural professionalism. Ablation studies further verify the contribution of key mechanisms, while white-box auditing demonstrates the consistency and traceability of critical intermediate states. Overall, this work provides a reproducible framework-data-model pipeline for embedding EFT mechanisms into LLM-based mental health support. --- ### Geometry-Grounded Gaussian Splatting Authors: Baowen Zhang, Chenxing Jiang, Heng Li, Shaojie Shen, Ping Tan Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17835v2 Gaussian Splatting (GS) has demonstrated impressive quality and efficiency in novel view synthesis. However, shape extraction from Gaussian primitives remains an open problem. Due to inadequate geometry parameterization and approximation, existing shape reconstruction methods suffer from poor multi-view consistency and are sensitive to floaters. In this paper, we present a rigorous theoretical derivation that establishes Gaussian primitives as a specific type of stochastic solids. This theoretical framework provides a principled foundation for Geometry-Grounded Gaussian Splatting by enabling the direct treatment of Gaussian primitives as explicit geometric representations. Using the volumetric nature of stochastic solids, our method efficiently renders high-quality depth maps for fine-grained geometry extraction. Experiments show that our method achieves the best shape reconstruction results among all Gaussian Splatting-based methods on public datasets. --- ### SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training Authors: Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li, Yucheng Lin, Guojiang Shen, Xiangjie Kong, Yong Liu, Guang Dai, Jingdong Wang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17830v2 Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA (requiring dual-model setups), inevitably incur heavy computational overhead during training due to external dependencies. To tackle these challenges, this paper proposes SRA 2, a lightweight intrinsic guidance framework for efficient diffusion training. SRA 2 leverages off-the-shelf pre-trained Variational Autoencoder (VAE) features: their reconstruction property ensures inherent encoding of visual priors like rich texture details, structural patterns, and basic semantic information. Specifically, SRA 2 aligns the intermediate latent features of diffusion transformers with VAE features via a lightweight projection layer, supervised by a feature alignment loss. This design accelerates training without extra representation encoders or dual-model maintenance, resulting in a simple yet effective pipeline. Extensive experiments demonstrate that SRA 2 improves both generation quality and training convergence speed compared to vanilla diffusion transformers, matches or outperforms state-of-the-art acceleration methods, and incurs merely 4% extra GFLOPs with zero additional cost for external guidance models. --- ### Linguistic and Argument Diversity in Synthetic Data for Function-Calling Agents Authors: Dan Greenstein, Zohar Karnin, Chen Amiraz, Oren Somekh Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17829v1 The construction of function calling agents has emerged as a promising avenue for extending model capabilities. A major challenge for this task is obtaining high quality diverse data for training. Prior work emphasizes diversity in functions, invocation patterns, and interaction turns, yet linguistic diversity of requests and coverage of arguments (e.g., \texttt{city\_name}, \texttt{stock\_ticker}) remain underexplored. We propose a method that generates synthetic datasets via optimizing general-purpose diversity metrics across both queries and arguments, without relying on hand-crafted rules or taxonomies, making it robust to different usecases. We demonstrate the effectiveness of our technique via both intrinsic and extrinsic testing, comparing it to SoTA data generation methods. We show a superiority over baselines in terms of diversity, while keeping comparable correctness. Additionally, when used as a training set, the model resulting from our dataset exhibits superior performance compared to analogous models based on the baseline data generation methods in out-of-distribution performance. In particular, we achieve an $7.4\%$ increase in accuracy on the BFCL benchmark compared to similar counterparts. --- ### Aligning Medical Conversational AI through Online Reinforcement Learning with Information-Theoretic Rewards Authors: Tanvi Verma, Yang Zhou, Rick Siow Mong Goh, Yong Liu Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17828v1 We present Information Gain Fine-Tuning (IGFT), a novel approach for training medical conversational AI to conduct effective patient interviews and generate comprehensive History of Present Illness (HPI) without requiring pre-collected human conversations. IGFT combines online Group Relative Policy Optimization (GRPO) with information-theoretic rewards, enabling models to learn from self-generated conversations with simulated patients. Unlike existing approaches that rely on expensive expert-annotated conversations or static datasets, our online RL framework allows models to discover effective questioning strategies through exploration. Our key innovation is an information gain reward function that tracks which clinical entities such as symptoms, temporal patterns, and medical history, are revealed during conversation. Each question's reward is computed based on its expected information gain combined with GPT-4o-mini quality assessments across dimensions including clinical relevance, patient engagement, and specificity. This hybrid approach ensures models learn to ask targeted, clinically appropriate questions that efficiently gather diagnostic information. We fine-tune two models using LoRA: Llama-3.1-8B-Instruct and DeepSeek-R1-Distill-Qwen-7B (a reasoning-optimized model). Training exclusively on Avey data containing concise HPIs, we evaluate generalization to MIMIC data with longer, more elaborate HPIs. DeepSeek-R1-Distill-Qwen-7B (IGFT) achieves F1 scores of 0.408 on Avey (10.9% improvement over base) and 0.289 on MIMIC (12.9% improvement), while Llama-3.1-8B-Instruct (IGFT) reaches 0.384 and 0.336 respectively. Both models outperform OpenAI's model on MIMIC and surpass medical domain-specific baselines like HuatuoGPT and UltraMedical, which were optimized for single-turn medical QA rather than multi-turn conversations. --- ### RegGuard: AI-Powered Retrieval-Enhanced Assistant for Pharmaceutical Regulatory Compliance Authors: Siyuan Yang, Xihan Bian, Jiayin Tang Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17826v1 The increasing frequency and complexity of regulatory updates present a significant burden for multinational pharmaceutical companies. Compliance teams must interpret evolving rules across jurisdictions, formats, and agencies, often manually, at high cost and risk of error. We introduce RegGuard, an industrial-scale AI assistant designed to automate the interpretation of heterogeneous regulatory texts and align them with internal corporate policies. The system ingests heterogeneous document sources through a secure pipeline and enhances retrieval and generation quality with two novel components: HiSACC (Hierarchical Semantic Aggregation for Contextual Chunking) semantically segments long documents into coherent units while maintaining consistency across non-contiguous sections. ReLACE (Regulatory Listwise Adaptive Cross-Encoder for Reranking), a domain-adapted cross-encoder built on an open-source model, jointly models user queries and retrieved candidates to improve ranking relevance. Evaluations in enterprise settings demonstrate that RegGuard improves answer quality specifically in terms of relevance, groundedness, and contextual focus, while significantly mitigating hallucination risk. The system architecture is built for auditability and traceability, featuring provenance tracking, access control, and incremental indexing, making it highly responsive to evolving document sources and relevant for any domain with stringent compliance demands. --- ### DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation Authors: Pranav Kasela, Marco Braga, Alessandro Ghiotto, Andrea Pilzer, Marco Viviani, Alessandro Raganato Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17823v1 In this paper, we present DIETA, a small, decoder-only Transformer model with 0.5 billion parameters, specifically designed and trained for Italian-English machine translation. We collect and curate a large parallel corpus consisting of approximately 207 million Italian-English sentence pairs across diverse domains, including parliamentary proceedings, legal texts, web-crawled content, subtitles, news, literature and 352 million back-translated data using pretrained models. Additionally, we create and release a new small-scale evaluation set, consisting of 450 sentences, based on 2025 WikiNews articles, enabling assessment of translation quality on contemporary text. Comprehensive evaluations show that DIETA achieves competitive performance on multiple Italian-English benchmarks, consistently ranking in the second quartile of a 32-system leaderboard and outperforming most other sub-3B models on four out of five test suites. The training script, trained models, curated corpus, and newly introduced evaluation set are made publicly available, facilitating further research and development in specialized Italian-English machine translation. https://github.com/pkasela/DIETA-Machine-Translation --- ### ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning Authors: Wen Luo, Peng Chen, Xiaotao Huang, LiQun Huang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17818v1 Large Vision-Language Models (LVLMs) incur high computational costs due to significant redundancy in their visual tokens. To effectively reduce this cost, researchers have proposed various visual token pruning methods. However, existing methods are generally limited, either losing critical visual information prematurely due to pruning in the vision encoder, or leading to information redundancy among the selected tokens due to pruning in the Large Language Models (LLMs). To address these challenges, we propose a Visual and Textual Semantic Collaborative Pruning framework (ViTCoP) that combines redundancy filtering in the vision encoder with step-wise co-pruning within the LLM based on its hierarchical characteristics, to efficiently preserve critical and informationally diverse visual tokens. Meanwhile, to ensure compatibility with acceleration techniques like FlashAttention, we introduce the L2 norm of K-vectors as the token saliency metric in the LLM. Extensive experiments on various Large Vision-Language Models demonstrate that ViTCoP not only achieves state-of-the-art performance surpassing existing methods on both image and video understanding tasks, but also significantly reduces model inference latency and GPU memory consumption. Notably, its performance advantage over other methods becomes even more pronounced under extreme pruning rates. --- ### MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing Authors: Haoxuan Ma, Guannan Lai, Han-Jia Ye Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17814v1 Multimodal large language models (MLLMs) have advanced rapidly, yet heterogeneity in architecture, alignment strategies, and efficiency means that no single model is uniformly superior across tasks. In practical deployments, workloads span lightweight OCR to complex multimodal reasoning; using one MLLM for all queries either over-provisions compute on easy instances or sacrifices accuracy on hard ones. Query-level model selection (routing) addresses this tension, but extending routing from text-only LLMs to MLLMs is nontrivial due to modality fusion, wide variation in computational cost across models, and the absence of a standardized, budget-aware evaluation. We present MMR-Bench, a unified benchmark that isolates the multimodal routing problem and enables comparison under fixed candidate sets and cost models. MMR-Bench provides (i) a controlled environment with modality-aware inputs and variable compute budgets, (ii) a broad suite of vision-language tasks covering OCR, general VQA, and multimodal math reasoning, and (iii) strong single-model reference, oracle upper bounds, and representative routing policies. Using MMR-Bench, we show that incorporating multimodal signals improves routing quality. Empirically, these cues improve the cost-accuracy frontier and enable the routed system to exceed the strongest single model's accuracy at roughly 33% of its cost. Furthermore, policies trained on a subset of models and tasks generalize zero-shot to new datasets and text-only benchmarks without retuning, establishing MMR-Bench as a foundation for studying adaptive multimodal model selection and efficient MLLM deployment. The code will be available at: https://github.com/Hunter-Wrynn/MMR-Bench. --- ### Motif Diversity in Human Liver ChIP-seq Data Using MAP-Elites Authors: Alejandro Medina, Mary Lauren Benton Published: 2026-01-25 Categories: cs.NE, q-bio.GN arXiv: https://arxiv.org/abs/2601.17808v2 Motif discovery is a core problem in computational biology, traditionally formulated as a likelihood optimization task that returns a single dominant motif from a DNA sequence dataset. However, regulatory sequence data admit multiple plausible motif explanations, reflecting underlying biological heterogeneity. In this work, we frame motif discovery as a quality-diversity problem and apply the MAP-Elites algorithm to evolve position weight matrix motifs under a likelihood-based fitness objective while explicitly preserving diversity across biologically meaningful dimensions. We evaluate MAP-Elites using three complementary behavioral characterizations that capture trade-offs between motif specificity, compositional structure, coverage, and robustness. Experiments on human CTCF liver ChIP-seq data aligned to the human reference genome compare MAP-Elites against a standard motif discovery tool, MEME, under matched evaluation criteria across stratified dataset subsets. Results show that MAP-Elites recovers multiple high-quality motif variants with fitness comparable to MEME's strongest solutions while revealing structured diversity obscured by single-solution approaches. --- ### An autonomous living database for perovskite photovoltaics Authors: Sherjeel Shabih, Hampus Näsström, Sharat Patil, Asmin Askin, Keely Dodd-Clements, Jessica Helisa Hautrive Rossato, Hugo Gajardoni de Lemos, Yuxin Liu, Florian Mathies, Natalia Maticiuc, Rico Meitzner, Edgar Nandayapa et al. Published: 2026-01-25 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2601.17807v1 Scientific discovery is severely bottlenecked by the inability of manual curation to keep pace with exponential publication rates. This creates a widening knowledge gap. This is especially stark in photovoltaics, where the leading database for perovskite solar cells has been stagnant since 2021 despite massive ongoing research output. Here, we resolve this challenge by establishing an autonomous, self-updating living database (PERLA). Our pipeline integrates large language models with physics-aware validation to extract complex device data from the continuous literature stream, achieving human-level precision (>90%) and eliminating annotator variance. By employing this system on the previously inaccessible post-2021 literature, we uncover critical evolutionary trends hidden by data lag: the field has decisively shifted toward inverted architectures employing self-assembled monolayers and formamidinium-rich compositions, driving a clear trajectory of sustained voltage loss reduction. PERLA transforms static publications into dynamic knowledge resources that enable data-driven discovery to operate at the speed of publication. --- ### Robust Computational Extraction of Non-Enhancing Hypercellular Tumor Regions from Clinical Imaging Data Authors: A. Brawanski, Th. Schaffer, F. Raab, K. -M. Schebesch, M. Schrey, Chr. Doenitz, A. M. Tomé, E. W. Lang Published: 2026-01-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17802v1 Accurate identification of non-enhancing hypercellular (NEH) tumor regions is an unmet need in neuro-oncological imaging, with significant implications for patient management and treatment planning. We present a robust computational framework that generates probability maps of NEH regions from routine MRI data, leveraging multiple network architectures to address the inherent variability and lack of clear imaging boundaries. Our approach was validated against independent clinical markers -- relative cerebral blood volume (rCBV) and enhancing tumor recurrence location (ETRL) -- demonstrating both methodological robustness and biological relevance. This framework enables reliable, non-invasive mapping of NEH tumor compartments, supporting their integration as imaging biomarkers in clinical workflows and advancing precision oncology for brain tumor patients. --- ### Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem Authors: Thanawat Sornwanee Published: 2026-01-25 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2601.17800v2 We show how the differentiability method employed in the paper ``Differentiable Integer Linear Programming'', Geng, et al., 2025 as shown in its theorem 5 is incorrect. Moreover, there already exists some downstream work that inherits the same error. The underlying reason comes from that, though being continuous in expectation, the surrogate loss is discontinuous in almost every realization of the randomness, for the stochastic gradient descent. --- ### Agreement-Driven Multi-View 3D Reconstruction for Live Cattle Weight Estimation Authors: Rabin Dulal, Wenfeng Jia, Lihong Zheng, Jane Quinn Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17791v1 Accurate cattle live weight estimation is vital for livestock management, welfare, and productivity. Traditional methods, such as manual weighing using a walk-over weighing system or proximate measurements using body condition scoring, involve manual handling of stock and can impact productivity from both a stock and economic perspective. To address these issues, this study investigated a cost-effective, non-contact method for live weight calculation in cattle using 3D reconstruction. The proposed pipeline utilized multi-view RGB images with SAM 3D-based agreement-guided fusion, followed by ensemble regression. Our approach generates a single 3D point cloud per animal and compares classical ensemble models with deep learning models under low-data conditions. Results show that SAM 3D with multi-view agreement fusion outperforms other 3D generation methods, while classical ensemble models provide the most consistent performance for practical farm scenarios (R$^2$ = 0.69 $\pm$ 0.10, MAPE = 2.22 $\pm$ 0.56 \%), making this practical for on-farm implementation. These findings demonstrate that improving reconstruction quality is more critical than increasing model complexity for scalable deployment on farms where producing a large volume of 3D data is challenging. --- ### Neuro-Symbolic Verification on Instruction Following of LLMs Authors: Yiming Su, Kunzhao Xu, Yanjie Gao, Fan Yang, Cheng Li, Mao Yang, Tianyin Xu Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17789v1 A fundamental problem of applying Large Language Models (LLMs) to important applications is that LLMs do not always follow instructions, and violations are often hard to observe or check. In LLM-based agentic workflows, such violations can propagate and amplify along reasoning chains, causing task failures and system incidents. This paper presents NSVIF, a neuro-symbolic framework for verifying whether an LLM's output follows the instructions used to prompt the LLM. NSVIF is a universal, general-purpose verifier; it makes no assumption about the instruction or the LLM. NSVIF formulates instruction-following verification as a constraint-satisfaction problem by modeling user instructions as constraints. NSVIF models both logical and semantic constraints; constraint solving is done by a unified solver that orchestrates logical reasoning and semantic analysis. To evaluate NSVIF, we develop VIFBENCH, a new benchmark for instruction-following verifiers with fine-grained data labels. Experiments show that NSVIF significantly outperforms LLM-based approaches and provides interpretable feedback. We also show that feedback from NSVIF helps improve LLMs' instruction-following capability without post-training. --- ### Beyond a Single Perspective: Text Anomaly Detection with Multi-View Language Representations Authors: Yixin Liu, Kehan Yan, Shiyuan Li, Qingfeng Chen, Shirui Pan Published: 2026-01-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.17786v1 Text anomaly detection (TAD) plays a critical role in various language-driven real-world applications, including harmful content moderation, phishing detection, and spam review filtering. While two-step "embedding-detector" TAD methods have shown state-of-the-art performance, their effectiveness is often limited by the use of a single embedding model and the lack of adaptability across diverse datasets and anomaly types. To address these limitations, we propose to exploit the embeddings from multiple pretrained language models and integrate them into $MCA^2$, a multi-view TAD framework. $MCA^2$ adopts a multi-view reconstruction model to effectively extract normal textual patterns from multiple embedding perspectives. To exploit inter-view complementarity, a contrastive collaboration module is designed to leverage and strengthen the interactions across different views. Moreover, an adaptive allocation module is developed to automatically assign the contribution weight of each view, thereby improving the adaptability to diverse datasets. Extensive experiments on 10 benchmark datasets verify the effectiveness of $MCA^2$ against strong baselines. The source code of $MCA^2$ is available at https://github.com/yankehan/MCA2. --- ### Shortcut Learning in Binary Classifier Black Boxes: Applications to Voice Anti-Spoofing and Biometrics Authors: Md Sahidullah, Hye-jin Shim, Rosa Gonzalez Hautamäki, Tomi H. Kinnunen Published: 2026-01-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.17782v1 The widespread adoption of deep-learning models in data-driven applications has drawn attention to the potential risks associated with biased datasets and models. Neglected or hidden biases within datasets and models can lead to unexpected results. This study addresses the challenges of dataset bias and explores ``shortcut learning'' or ``Clever Hans effect'' in binary classifiers. We propose a novel framework for analyzing the black-box classifiers and for examining the impact of both training and test data on classifier scores. Our framework incorporates intervention and observational perspectives, employing a linear mixed-effects model for post-hoc analysis. By evaluating classifier performance beyond error rates, we aim to provide insights into biased datasets and offer a comprehensive understanding of their influence on classifier behavior. The effectiveness of our approach is demonstrated through experiments on audio anti-spoofing and speaker verification tasks using both statistical models and deep neural networks. The insights gained from this study have broader implications for tackling biases in other domains and advancing the field of explainable artificial intelligence. --- ### Controlling Reading Ease with Gaze-Guided Text Generation Authors: Andreas Säuberli, Darja Jepifanova, Diego Frassinelli, Barbara Plank Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17781v1 The way our eyes move while reading can tell us about the cognitive effort required to process the text. In the present study, we use this fact to generate texts with controllable reading ease. Our method employs a model that predicts human gaze patterns to steer language model outputs towards eliciting certain reading behaviors. We evaluate the approach in an eye-tracking experiment with native and non-native speakers of English. The results demonstrate that the method is effective at making the generated texts easier or harder to read, measured both in terms of reading times and perceived difficulty of the texts. A statistical analysis reveals that the changes in reading behavior are mostly due to features that affect lexical processing. Possible applications of our approach include text simplification for information accessibility and generation of personalized educational material for language learning. --- ### DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning Authors: Xiaoyu Liu, Xiaoyu Guan, Di Liang, Xianjie Wu Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17777v1 Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often induce the "seesaw effect": optimizing for one task may degrade performance on others, particularly when model parameters are updated indiscriminately. In this paper, we propose a principled approach to disentangle and isolate task-specific parameter regions, motivated by the hypothesis that parameter heterogeneity underlies cross-task interference. Specifically, we first independently fine-tune LLMs on diverse SFT tasks and identify each task's core parameter region as the subset of parameters exhibiting the largest updates. Tasks with highly overlapping core parameter regions are merged for joint training, while disjoint tasks are organized into different stages. During multi-stage SFT, core parameters acquired in prior tasks are frozen, thereby preventing overwriting by subsequent tasks. To verify the effectiveness of our method, we conducted intensive experiments on multiple public datasets. The results showed that our dynamic parameter isolation strategy consistently reduced data conflicts and achieved consistent performance improvements compared to multi-stage and multi-task tuning baselines. --- ### MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks Authors: Jeonggyu Huh, Seungwon Jeong, Hyun-Gyoon Kim, Hyeng Keun Koo, Byung Hwa Lim Published: 2026-01-25 Categories: q-fin.ST, cs.LG, econ.EM arXiv: https://arxiv.org/abs/2601.17773v1 This paper introduces MarketGAN, a factor-based generative framework for high-dimensional asset return generation under severe data scarcity. We embed an explicit asset-pricing factor structure as an economic inductive bias and generate returns as a single joint vector, thereby preserving cross-sectional dependence and tail co-movement alongside inter-temporal dynamics. MarketGAN employs generative adversarial learning with a temporal convolutional network (TCN) backbone, which models stochastic, time-varying factor loadings and volatilities and captures long-range temporal dependence. Using daily returns of large U.S. equities, we find that MarketGAN more closely matches empirical stylized facts of asset returns, including heavy-tailed marginal distributions, volatility clustering, leverage effects, and, most notably, high-dimensional cross-sectional correlation structures and tail co-movement across assets, than conventional factor-model-based bootstrap approaches. In portfolio applications, covariance estimates derived from MarketGAN-generated samples outperform those derived from other methods when factor information is at least weakly informative, demonstrating tangible economic value. --- ### Context-Aware Iterative Token Detection and Masked Transmission for Wireless Token Communication Authors: Junyong Shin, Joohyuk Park, Jihong Park, Jinho Choi, Yo-Seb Jeon Published: 2026-01-25 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2601.17770v1 The success of large-scale language models has established tokens as compact and meaningful units for natural-language representation, which motivates token communication over wireless channels, where tokens are considered fundamental units for wireless transmission. We propose a context-aware token communication framework that uses a pretrained masked language model (MLM) as a shared contextual probability model between the transmitter (Tx) and receiver (Rx). At Rx, we develop an iterative token detection method that jointly exploits MLM-guided contextual priors and channel observations based on a Bayesian perspective. At Tx, we additionally introduce a context-aware masking strategy which skips highly predictable token transmission to reduce transmission rate. Simulation results demonstrate that the proposed framework substantially improves reconstructed sentence quality and supports effective rate adaptation under various channel conditions. --- ### LLM-42: Enabling Determinism in LLM Inference with Verified Speculation Authors: Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar Published: 2026-01-25 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2601.17768v2 In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined with dynamic batching and GPU kernels whose reduction orders vary with batch size. A straightforward way to eliminate non-determinism is to disable dynamic batching during inference, but doing so severely degrades throughput. Another approach is to make kernels batch-invariant; however, this tightly couples determinism to kernel design, requiring new implementations. This coupling also imposes fixed runtime overheads, regardless of how much of the workload actually requires determinism. Inspired by ideas from speculative decoding, we present LLM-42, a scheduling-based approach to enable determinism in LLM inference. Our key observation is that if a sequence is in a consistent state, the next emitted token is likely to be consistent even with dynamic batching. Moreover, most GPU kernels use shape-consistent reductions. Leveraging these insights, LLM-42 decodes tokens using a non-deterministic fast path and enforces determinism via a lightweight verify-rollback loop. The verifier replays candidate tokens under a fixed-shape reduction schedule, commits those that are guaranteed to be consistent across runs, and rolls back those violating determinism. LLM-42 mostly re-uses existing kernels unchanged and incurs overhead only in proportion to the traffic that requires determinism. --- ### HyCARD-Net: A Synergistic Hybrid Intelligence Framework for Cardiovascular Disease Diagnosis Authors: Rajan Das Gupta, Xiaobin Wu, Xun Liu, Jiaqi He Published: 2026-01-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.17767v1 Cardiovascular disease (CVD) remains the foremost cause of mortality worldwide, underscoring the urgent need for intelligent and data-driven diagnostic tools. Traditional predictive models often struggle to generalize across heterogeneous datasets and complex physiological patterns. To address this, we propose a hybrid ensemble framework that integrates deep learning architectures, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), with classical machine learning algorithms, including K-Nearest Neighbor (KNN) and Extreme Gradient Boosting (XGB), using an ensemble voting mechanism. This approach combines the representational power of deep networks with the interpretability and efficiency of traditional models. Experiments on two publicly available Kaggle datasets demonstrate that the proposed model achieves superior performance, reaching 82.30 percent accuracy on Dataset I and 97.10 percent on Dataset II, with consistent gains in precision, recall, and F1-score. These findings underscore the robustness and clinical potential of hybrid AI frameworks for predicting cardiovascular disease and facilitating early intervention. Furthermore, this study directly supports the United Nations Sustainable Development Goal 3 (Good Health and Well-being) by promoting early diagnosis, prevention, and management of non-communicable diseases through innovative, data-driven healthcare solutions. --- ### Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali Authors: Md Asgor Hossain Reaj, Rajan Das Gupta, Jui Saha Pritha, Abdullah Al Noman, Abir Ahmed, Golam Md Mohiuddin, Tze Hui Liew Published: 2026-01-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.17764v1 Large Language Models (LLMs) have achieved significant success in recent years; yet, issues of intrinsic gender bias persist, especially in non-English languages. Although current research mostly emphasizes English, the linguistic and cultural biases inherent in Global South languages, like Bengali, are little examined. This research seeks to examine the characteristics and magnitude of gender bias in Bengali, evaluating the efficacy of current approaches in identifying and alleviating bias. We use several methods to extract gender-biased utterances, including lexicon-based mining, computational classification models, translation-based comparison analysis, and GPT-based bias creation. Our research indicates that the straight application of English-centric bias detection frameworks to Bengali is severely constrained by language disparities and socio-cultural factors that impact implicit biases. To tackle these difficulties, we executed two field investigations inside rural and low-income areas, gathering authentic insights on gender bias. The findings demonstrate that gender bias in Bengali presents distinct characteristics relative to English, requiring a more localized and context-sensitive methodology. Additionally, our research emphasizes the need of integrating community-driven research approaches to identify culturally relevant biases often neglected by automated systems. Our research enhances the ongoing discussion around gender bias in AI by illustrating the need to create linguistic tools specifically designed for underrepresented languages. This study establishes a foundation for further investigations into bias reduction in Bengali and other Indic languages, promoting the development of more inclusive and fair NLP systems. --- ### AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation Authors: Dongjie Cheng, Ruifeng Yuan, Yongqi Li, Runyang You, Wenjie Wang, Liqiang Nie, Lei Zhang, Wenjie Li Published: 2026-01-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.17761v1 Real-world perception and interaction are inherently multimodal, encompassing not only language but also vision and speech, which motivates the development of "Omni" MLLMs that support both multimodal inputs and multimodal outputs. While a sequence of omni MLLMs has emerged, most existing systems still rely on additional expert components to achieve multimodal generation, limiting the simplicity of unified training and inference. Autoregressive (AR) modeling, with a single token stream, a single next-token objective, and a single decoder, is an elegant and scalable foundation in the text domain. Motivated by this, we present AR-Omni, a unified any-to-any model in the autoregressive paradigm without any expert decoders. AR-Omni supports autoregressive text and image generation, as well as streaming speech generation, all under a single Transformer decoder. We further address three practical issues in unified AR modeling: modality imbalance via task-aware loss reweighting, visual fidelity via a lightweight token-level perceptual alignment loss for image tokens, and stability-creativity trade-offs via a finite-state decoding mechanism. Empirically, AR-Omni achieves strong quality across three modalities while remaining real-time, achieving a 0.88 real-time factor for speech generation. --- ### MV-S2V: Multi-View Subject-Consistent Video Generation Authors: Ziyang Song, Xinyu Gong, Bangya Liu, Zelin Zhao Published: 2026-01-25 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2601.17756v3 Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V pipeline, failing to exploit the full potential of video subject control. In this work, we propose and address the challenging Multi-View S2V (MV-S2V) task, which synthesizes videos from multiple reference views to enforce 3D-level subject consistency. Regarding the scarcity of training data, we first develop a synthetic data curation pipeline to generate highly customized synthetic data, complemented by a small-scale real-world captured dataset to boost the training of MV-S2V. Another key issue lies in the potential confusion between cross-subject and cross-view references in conditional generation. To overcome this, we further introduce Temporally Shifted RoPE (TS-RoPE) to distinguish between different subjects and distinct views of the same subject in reference conditioning. Our framework achieves superior 3D subject consistency w.r.t. multi-view reference images and high-quality visual outputs, establishing a new meaningful direction for subject-driven video generation. Code and data are available at: https://szy-young.github.io/mv-s2v --- ### HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG Authors: Jinyoung Park, Sanghyeok Lee, Omar Zia Khan, Hyunwoo J. Kim, Joo-Kyung Kim Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17755v2 Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning beyond text-chunk retrieval. Recent advances have integrated reinforcement learning (RL) into agentic GraphRAG approaches, enabling iterative interactions with knowledge graphs during training. However, existing RL-based methods suffer from two key limitations: (1) they primarily depend on semantic similarity for retrieval, often overlooking the underlying graph topology, and (2) they rely on sparse, outcome-level rewards that fail to capture the quality of intermediate retrieval steps and their dependencies. To address these limitations, we propose HyperGraphPro, a progress-aware agentic framework for graph-based retrieval and multi-step reasoning. HyperGraphPro introduces a structure-aware hypergraph retrieval mechanism that jointly considers semantic relevance and graph connectivity, promoting coherent traversal along multi-hop reasoning paths. Furthermore, we design a progress-based stepwise policy optimization that provides dense learning signals by modulating advantages according to intermediate reasoning progress within a graph, rather than relying solely on final outcomes. Experiments on multi-hop question answering benchmarks demonstrate that HyperGraphPro consistently improves reasoning accuracy and generation quality over existing GraphRAG methods. --- ### Hylog: A Hybrid Approach to Logging Text Production in Non-alphabetic Scripts Authors: Roberto Crotti, Giovanni Denaro, Zhiqiang Du, Ricardo Muñoz Martín Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17753v2 Research keyloggers are essential for cognitive studies of text production, yet most fail to capture the on-screen transformations performed by Input Method Editors (IMEs) for non-alphabetic scripts. To address this methodological gap, we present Hylog, a novel hybrid logging system that combines analytical keylogging with ecological text logging for a more complete and finer-grained analysis. Our modular, open-source system uses plug-ins for standard applications (Microsoft Word, Google Chrome) to capture both keyboard output and rendered text, which a hybridizer module then synchronizes into a dual trace. To validate the system's technical feasibility and demonstrate its analytical capabilities, we conducted a proof-of-concept study where two volunteers translated a text into simplified Chinese. Hylog successfully captured keypresses and temporal intervals between Latin letters, Chinese characters, and IME confirmations -- some measurements invisible to traditional keyloggers. The resulting data enable the formulation of new, testable hypotheses about the cognitive restrictions and affordances at different linguistic layers in IME-mediated typing. Our plug-in architecture enables extension to other IME systems and fosters more inclusive multilingual text-production research. --- ### Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces Authors: Kyriakos Stylianopoulos, Mattia Fabiani, Giulia Torcolacci, Davide Dardari, George C. Alexandropoulos Published: 2026-01-25 Categories: eess.SP, cs.ET, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2601.17749v2 The recently envisioned goal-oriented communications paradigm calls for the application of inference on wirelessly transferred data via Machine Learning (ML) tools. An emerging research direction deals with the realization of inference ML models directly in the physical layer of Multiple-Input Multiple-Output (MIMO) systems, which, however, entails certain significant challenges. In this paper, leveraging the technology of programmable MetaSurfaces (MSs), we present an eXtremely Large (XL) MIMO system that acts as an Extreme Learning Machine (ELM) performing binary classification tasks completely Over-The-Air (OTA), which can be trained in closed form. The proposed system comprises a receiver architecture consisting of densely parallel placed diffractive layers of XL MSs, also known as Stacked Intelligent Metasurfaces (SIM), followed by a single reception radio-frequency chain. The front layer facing the XL MIMO channel consists of identical unit cells of a fixed NonLinear (NL) response, whereas the remaining layers of elements of tunable linear responses are utilized to approximate OTA the trained ELM weights. Our numerical investigations showcase that, in the XL regime of MS elements, the proposed XL-MIMO-ELM system achieves performance comparable to that of digital and idealized ML models across diverse datasets and wireless scenarios, thereby demonstrating the feasibility of embedding OTA learning capabilities into future wireless systems. --- ### Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection Authors: Kaixuan Jiang, Chen Wu, Zhenghui Zhao, Chengxi Han, Haonan Guo, Hongruixuan Chen Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17747v2 Change detection (CD) aims to identify surface changes from multi-temporal remote sensing imagery. In real-world scenarios, Pixel-level change labels are expensive to acquire, and existing models struggle to adapt to scenarios with diverse annotation availability. To tackle this challenge, we propose a unified change detection framework (UniCD), which collaboratively handles supervised, weakly-supervised, and unsupervised tasks through a coupled architecture. UniCD eliminates architectural barriers through a shared encoder and multi-branch collaborative learning mechanism, achieving deep coupling of heterogeneous supervision signals. Specifically, UniCD consists of three supervision-specific branches. In the supervision branch, UniCD introduces the spatial-temporal awareness module (STAM), achieving efficient synergistic fusion of bi-temporal features. In the weakly-supervised branch, we construct change representation regularization (CRR), which steers model convergence from coarse-grained activations toward coherent and separable change modeling. In the unsupervised branch, we propose semantic prior-driven change inference (SPCI), which transforms unsupervised tasks into controlled weakly-supervised path optimization. Experiments on mainstream datasets demonstrate that UniCD achieves optimal performance across three tasks. It exhibits significant accuracy improvements in weakly and unsupervised scenarios, surpassing current state-of-the-art by 12.72% and 12.37% on LEVIR-CD, respectively. --- ### Faramesh: A Protocol-Agnostic Execution Control Plane for Autonomous Agent Systems Authors: Amjad Fatmi Published: 2026-01-25 Categories: cs.AI, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2601.17744v1 Autonomous agent systems increasingly trigger real-world side effects: deploying infrastructure, modifying databases, moving money, and executing workflows. Yet most agent stacks provide no mandatory execution checkpoint where organizations can deterministically permit, deny, or defer an action before it changes reality. This paper introduces Faramesh, a protocol-agnostic execution control plane that enforces execution-time authorization for agent-driven actions via a non-bypassable Action Authorization Boundary (AAB). Faramesh canonicalizes agent intent into a Canonical Action Representation (CAR), evaluates actions deterministically against policy and state, and issues a decision artifact (PERMIT/DEFER/DENY) that executors must validate prior to execution. The system is designed to be framework- and model-agnostic, supports multi-agent and multi-tenant deployments, and remains independent of transport protocols (e.g., MCP). Faramesh further provides decision-centric, append-only provenance logging keyed by canonical action hashes, enabling auditability, verification, and deterministic replay without re-running agent reasoning. We show how these primitives yield enforceable, predictable governance for autonomous execution while avoiding hidden coupling to orchestration layers or observability-only approaches. --- ### Video Compression with Hierarchical Temporal Neural Representation Authors: Jun Zhu, Xinfeng Zhang, Lv Tang, Junhao Jiang, Gai Zhang, Jia Wang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17743v1 Video compression has recently benefited from implicit neural representations (INRs), which model videos as continuous functions. INRs offer compact storage and flexible reconstruction, providing a promising alternative to traditional codecs. However, most existing INR-based methods treat the temporal dimension as an independent input, limiting their ability to capture complex temporal dependencies. To address this, we propose a Hierarchical Temporal Neural Representation for Videos, TeNeRV. TeNeRV integrates short- and long-term dependencies through two key components. First, an Inter-Frame Feature Fusion (IFF) module aggregates features from adjacent frames, enforcing local temporal coherence and capturing fine-grained motion. Second, a GoP-Adaptive Modulation (GAM) mechanism partitions videos into Groups-of-Pictures and learns group-specific priors. The mechanism modulates network parameters, enabling adaptive representations across different GoPs. Extensive experiments demonstrate that TeNeRV consistently outperforms existing INR-based methods in rate-distortion performance, validating the effectiveness of our proposed approach. --- ### Frequency-aware Neural Representation for Videos Authors: Jun Zhu, Xinfeng Zhang, Lv Tang, Junhao Jiang, Gai Zhang, Jia Wang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17741v1 Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bias, which favors low-frequency components and leads to over-smoothed reconstructions and suboptimal rate-distortion performance. In this paper, we propose FaNeRV, a Frequency-aware Neural Representation for videos, which explicitly decouples low- and high-frequency components to enable efficient and faithful video reconstruction. FaNeRV introduces a multi-resolution supervision strategy that guides the network to progressively capture global structures and fine-grained textures through staged supervision . To further enhance high-frequency reconstruction, we propose a dynamic high-frequency injection mechanism that adaptively emphasizes challenging regions. In addition, we design a frequency-decomposed network module to improve feature modeling across different spectral bands. Extensive experiments on standard benchmarks demonstrate that FaNeRV significantly outperforms state-of-the-art INR methods and achieves competitive rate-distortion performance against traditional codecs. --- ### Learning Sewing Patterns via Latent Flow Matching of Implicit Fields Authors: Cong Cao, Ren Li, Corentin Dumery, Hao Li Published: 2026-01-25 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2601.17740v2 Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements. In this work, we introduce a sewing pattern modeling method based on an implicit representation. We represent each panel using a signed distance field that defines its boundary and an unsigned distance field that identifies seam endpoints, and encode these fields into a continuous latent space that enables differentiable meshing. A latent flow matching model learns distributions over panel combinations in this representation, and a stitching prediction module recovers seam relations from extracted edge segments. This formulation allows accurate modeling and generation of sewing patterns with complex structures. We further show that it can be used to estimate sewing patterns from images with improved accuracy relative to existing approaches, and supports applications such as pattern completion and refitting, providing a practical tool for digital fashion design. --- ### The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation Authors: Chenyu Mu, Xin He, Qu Yang, Wanshun Chen, Jiadi Yao, Huang Liu, Zihao Yi, Bo Zhao, Xingyu Chen, Ruotian Ma, Fanghua Ye, Erkun Yang et al. Published: 2026-01-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.17737v3 Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-form, coherent narratives from high-level concepts like dialogue, revealing a ``semantic gap'' between a creative idea and its cinematic execution. To bridge this gap, we introduce a novel, end-to-end agentic framework for dialogue-to-cinematic-video generation. Central to our framework is ScripterAgent, a model trained to translate coarse dialogue into a fine-grained, executable cinematic script. To enable this, we construct ScriptBench, a new large-scale benchmark with rich multimodal context, annotated via an expert-guided pipeline. The generated script then guides DirectorAgent, which orchestrates state-of-the-art video models using a cross-scene continuous generation strategy to ensure long-horizon coherence. Our comprehensive evaluation, featuring an AI-powered CriticAgent and a new Visual-Script Alignment (VSA) metric, shows our framework significantly improves script faithfulness and temporal fidelity across all tested video models. Furthermore, our analysis uncovers a crucial trade-off in current SOTA models between visual spectacle and strict script adherence, providing valuable insights for the future of automated filmmaking. --- ### From Static to Interactive: Authoring Interactive Visualizations via Natural Language Authors: Can Liu, Jaeuk Lee, Tianhe Chen, Zhibang Jiang, Xiaolin Wen, Yong Wang Published: 2026-01-25 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.17736v2 Interactivity is crucial for effective data visualizations. However, it is often challenging to implement interactions for existing static visualizations, since the underlying code and data for existing static visualizations are often not available, and it also takes significant time and effort to enable interactions for them even if the original code and data are available. To fill this gap, we propose Athanor, a novel approach to transform existing static visualizations into interactive ones using multimodal large language models (MLLMs) and natural language instructions. Our approach introduces three key innovations: (1) an action-modification interaction design space that maps visualization interactions into user actions and corresponding adjustments, (2) a multi-agent requirement analyzer that translates natural language instructions into an actionable operational space, and (3) a visualization abstraction transformer that converts static visualizations into flexible and interactive representations regardless of their underlying implementation. Athanor allows users to effortlessly author interactions through natural language instructions, eliminating the need for programming. We conducted two case studies and in-depth interviews with target users to evaluate our approach. The results demonstrate the effectiveness and usability of our approach in allowing users to conveniently enable flexible interactions for static visualizations. --- ### ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agents Authors: Kyungho Kim, Geon Lee, Juyeon Kim, Dongwon Choi, Shinhwan Kang, Kijung Shin Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17735v1 Relational databases (RDBs) play a crucial role in many real-world web applications, supporting data management across multiple interconnected tables. Beyond typical retrieval-oriented tasks, prediction tasks on RDBs have recently gained attention. In this work, we address this problem by generating informative relational features that enhance predictive performance. However, generating such features is challenging: it requires reasoning over complex schemas and exploring a combinatorially large feature space, all without explicit supervision. To address these challenges, we propose ReFuGe, an agentic framework that leverages specialized large language model agents: (1) a schema selection agent identifies the tables and columns relevant to the task, (2) a feature generation agent produces diverse candidate features from the selected schema, and (3) a feature filtering agent evaluates and retains promising features through reasoning-based and validation-based filtering. It operates within an iterative feedback loop until performance converges. Experiments on RDB benchmarks demonstrate that ReFuGe substantially improves performance on various RDB prediction tasks. Our code and datasets are available at https://github.com/K-Kyungho/REFUGE. --- ### Flatten The Complex: Joint B-Rep Generation via Compositional $k$-Cell Particles Authors: Junran Lu, Yuanqi Li, Hengji Li, Jie Guo, Yanwen Guo Published: 2026-01-25 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2601.17733v1 Boundary Representation (B-Rep) is the widely adopted standard in Computer-Aided Design (CAD) and manufacturing. However, generative modeling of B-Reps remains a formidable challenge due to their inherent heterogeneity as geometric cell complexes, which entangles topology with geometry across cells of varying orders (i.e., $k$-cells such as vertices, edges, faces). Previous methods typically rely on cascaded sequences to handle this hierarchy, which fails to fully exploit the geometric relationships between cells, such as adjacency and sharing, limiting context awareness and error recovery. To fill this gap, we introduce a novel paradigm that reformulates B-Reps into sets of compositional $k$-cell particles. Our approach encodes each topological entity as a composition of particles, where adjacent cells share identical latents at their interfaces, thereby promoting geometric coupling along shared boundaries. By decoupling the rigid hierarchy, our representation unifies vertices, edges, and faces, enabling the joint generation of topology and geometry with global context awareness. We synthesize these particle sets using a multi-modal flow matching framework to handle unconditional generation as well as precise conditional tasks, such as 3D reconstruction from single-view or point cloud. Furthermore, the explicit and localized nature of our representation naturally extends to downstream tasks like local in-painting and enables the direct synthesis of non-manifold structures (e.g., wireframes). Extensive experiments demonstrate that our method produces high-fidelity CAD models with superior validity and editability compared to state-of-the-art methods. --- ### Unsupervised Elicitation of Moral Values from Language Models Authors: Meysam Alizadeh, Fabrizio Gilardi, Zeynab Samei Published: 2026-01-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17728v1 As AI systems become pervasive, grounding their behavior in human values is critical. Prior work suggests that language models (LMs) exhibit limited inherent moral reasoning, leading to calls for explicit moral teaching. However, constructing ground truth data for moral evaluation is difficult given plural frameworks and pervasive biases. We investigate unsupervised elicitation as an alternative, asking whether pretrained (base) LMs possess intrinsic moral reasoning capability that can be surfaced without human supervision. Using the Internal Coherence Maximization (ICM) algorithm across three benchmark datasets and four LMs, we test whether ICM can reliably label moral judgments, generalize across moral frameworks, and mitigate social bias. Results show that ICM outperforms all pre-trained and chatbot baselines on the Norm Bank and ETHICS benchmarks, while fine-tuning on ICM labels performs on par with or surpasses those of human labels. Across theoretically motivated moral frameworks, ICM yields its largest relative gains on Justice and Commonsense morality. Furthermore, although chatbot LMs exhibit social bias failure rates comparable to their pretrained ones, ICM reduces such errors by more than half, with the largest improvements in race, socioeconomic status, and politics. These findings suggest that pretrained LMs possess latent moral reasoning capacities that can be elicited through unsupervised methods like ICM, providing a scalable path for AI alignment. --- ### Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark Authors: Tayyab Nasir, Daochang Liu, Ajmal Mian Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17723v3 Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic empirical study has examined the effectiveness of existing methods under consistent conditions, nor investigated the effects of different training recipes, such as objective design, optimization strategies, and scaling behavior. A rigorous empirical analysis is essential not only for benchmarking performance and revealing true gains but also for establishing the current state of ASSR, identifying saturation limits, and highlighting promising directions. We fill this gap by training 6 INR-based ASSR methods under 9 controlled training recipes and evaluating them across 7 datasets and 7 image quality assessment (IQA) metrics, presenting aggregated performance results through a unified ranking framework that enables more reliable interpretation of performance comparisons and evaluation claims. Furthermore, we investigate the impact of carefully controlled training configurations on perceptual image quality and analyze the role of auxiliary objectives in preserving edges, textures, and fine details during training. Our analysis yields the following insights, previously overlooked: (1) Recent, more complex INR methods provide only marginal improvements over earlier methods, indicating architectural saturation on existing benchmarks. (2) Model performance is strongly correlated with training configurations, a factor neglected in prior comparisons. (3) Auxiliary objectives consistently enhance texture fidelity across architectures compared to standard L1-Loss, emphasizing the role of objective design for targeted perceptual gains. (4) INR-based ASSR exhibits consistent, monotonic scaling behavior across model capacity, training compute, and data diversity, though with diminishing returns as complexity grows. --- ### EntWorld: A Holistic Environment and Benchmark for Verifiable Enterprise GUI Agents Authors: Ying Mo, Yu Bai, Dapeng Sun, Yuqian Shi, Yukai Miao, Li Chen, Dan Li Published: 2026-01-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.17722v1 Recent advances in Multimodal Large Language Models (MLLMs) have enabled agents to operate in open-ended web and operating system environments. However, existing benchmarks predominantly target consumer-oriented scenarios (e.g., e-commerce and travel booking), failing to capture the complexity and rigor of professional enterprise workflows. Enterprise systems pose distinct challenges, including high-density user interfaces, strict business logic constraints, and a strong reliance on precise, state-consistent information retrieval-settings in which current generalist agents often struggle. To address this gap, we introduce EntWorld, a large-scale benchmark consisting of 1,756 tasks across six representative enterprise domains, including customer relationship management (CRM), information technology infrastructure library (ITIL), and enterprise resource planning (ERP) systems. Unlike previous datasets that depend on fragile execution traces or extensive manual annotation, EntWorld adopts a schema-grounded task generation framework that directly reverse-engineers business logic from underlying database schemas, enabling the synthesis of realistic, long-horizon workflows. Moreover, we propose a SQL-based deterministic verification mechanism in building datasets that replaces ambiguous visual matching with rigorous state-transition validation. Experimental results demonstrate that state-of-the-art models (e.g., GPT-4.1) achieve 47.61% success rate on EntWorld, substantially lower than the human performance, highlighting a pronounced enterprise gap in current agentic capabilities and the necessity of developing domain-specific agents. We release EntWorld as a rigorous testbed to facilitate the development and evaluation of the next generation of enterprise-ready digital agents. --- ### Advancing Structured Priors for Sparse-Voxel Surface Reconstruction Authors: Ting-Hsun Chi, Chu-Rong Chen, Chi-Tun Hsu, Hsuan-Ting Lin, Sheng-Yu Huang, Cheng Sun, Yu-Chiang Frank Wang Published: 2026-01-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.17720v1 Reconstructing accurate surfaces with radiance fields has progressed rapidly, yet two promising explicit representations, 3D Gaussian Splatting and sparse-voxel rasterization, exhibit complementary strengths and weaknesses. 3D Gaussian Splatting converges quickly and carries useful geometric priors, but surface fidelity is limited by its point-like parameterization. Sparse-voxel rasterization provides continuous opacity fields and crisp geometry, but its typical uniform dense-grid initialization slows convergence and underutilizes scene structure. We combine the advantages of both by introducing a voxel initialization method that places voxels at plausible locations and with appropriate levels of detail, yielding a strong starting point for per-scene optimization. To further enhance depth consistency without blurring edges, we propose refined depth geometry supervision that converts multi-view cues into direct per-ray depth regularization. Experiments on standard benchmarks demonstrate improvements over prior methods in geometric accuracy, better fine-structure recovery, and more complete surfaces, while maintaining fast convergence. --- ### A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data Authors: Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le, Fariha Kabir Torsha, Zhimeng Jiang, Minh Khai Bui, Chia-Yuan Chang, Yu-Neng Chuang, Zhen Xiong, Ying Lin, Guanchu Wang, Na Zou Published: 2026-01-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.17717v3 Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality of LLM-generated synthetic data remains a critical challenge. Existing research primarily focuses on generation methodologies, with limited direct attention to the quality of the resulting data. Furthermore, most studies are restricted to single modalities, lacking a unified perspective across different data types. To bridge this gap, we propose the \textbf{LLM Data Auditor framework}. In this framework, we first describe how LLMs are utilized to generate data across six distinct modalities. More importantly, we systematically categorize intrinsic metrics for evaluating synthetic data from two dimensions: quality and trustworthiness. This approach shifts the focus from extrinsic evaluation, which relies on downstream task performance, to the inherent properties of the data itself. Using this evaluation system, we analyze the experimental evaluations of representative generation methods for each modality and identify substantial deficiencies in current evaluation practices. Based on these findings, we offer concrete recommendations for the community to improve the evaluation of data generation. Finally, the framework outlines methodologies for the practical application of synthetic data across different modalities. ---