# Research Papers — 2026-01 · bundle page 15 of 189

> Full-text markdown of papers #701–750 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/15
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/14.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/16.md)

### Is Task-Specific Training Necessary for Anomaly Detection?

Authors: Xingwu Zhang, Guanxuan Li, Paul Henderson, Gerardo Aragon-Camarasa, Zijun Long
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22763v3

Current state-of-the-art multi-class unsupervised anomaly detection (MUAD) methods rely on training encoder--decoder models to reconstruct anomaly-free features. However, we argue that such task-specific training is costly under distribution shifts, and that reconstruction-based residual scoring further faces a fidelity--stability dilemma. Existing training-free alternatives, in turn, remain prone to cross-category and cross-region mismatches in MUAD. Motivated by these limitations, we propose Retrieval-based Anomaly Detection (RAD), a task-specific training-free framework that stores anomaly-free features in a memory and detects anomalies through multi-level retrieval, matching test patches against the memory. Experiments demonstrate that RAD achieves state-of-the-art performance across four established benchmarks (MVTec-AD, VisA, Real-IAD, 3D-ADAM) under both standard and few-shot settings. On MVTec-AD, RAD reaches 96.7% Pixel AUROC with just a single anomaly-free image compared to 98.5% of RAD's full-data performance. Collectively, these findings overturn the assumption that MUAD requires task-specific training, showing that state-of-the-art anomaly detection is feasible with training-free memory-based retrieval. Our code is available at https://github.com/longkukuhi/RAD.

---

### AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation

Authors: Zhongzhen Wen, Shudi Shao, Zhong Li, Yu Ge, Tongtong Xu, Yuanyi Lin, Tian Zhang
Published: 2026-01-30
Categories: cs.DC, cs.LG, cs.PF, cs.SE
arXiv: https://arxiv.org/abs/2601.22760v1

The performance of deep learning models critically depends on efficient kernel implementations, yet developing high-performance kernels for specialized accelerators remains time-consuming and expertise-intensive. While recent work demonstrates that large language models (LLMs) can generate correct and performant GPU kernels, kernel generation for neural processing units (NPUs) remains largely underexplored due to domain-specific programming models, limited public examples, and sparse documentation. Consequently, directly generating AscendC kernels with LLMs yields extremely low correctness, highlighting a substantial gap between GPU and NPU kernel generation. We present AscendCraft, a DSL-guided approach for automatic AscendC kernel generation. AscendCraft introduces a lightweight DSL that abstracts non-essential complexity while explicitly modeling Ascend-specific execution semantics. Kernels are first generated in the DSL using category-specific expert examples and then transcompiled into AscendC through structured, constraint-driven LLM lowering passes. Evaluated on MultiKernelBench across seven operator categories, AscendCraft achieves 98.1% compilation success and 90.4% functional correctness. Moreover, 46.2% of generated kernels match or exceed PyTorch eager execution performance, demonstrating that DSL-guided transcompilation can enable LLMs to generate both correct and competitive NPU kernels. Beyond benchmarks, AscendCraft further demonstrates its generality by successfully generating two correct kernels for newly proposed mHC architecture, achieving performance that substantially surpasses PyTorch eager execution.

---

### Qualitative Evaluation of LLM-Designed GUI

Authors: Bartosz Sawicki, Tomasz Les, Dariusz Parzych, Aleksandra Wycisk-Ficek, Pawel Trebacz, Pawel Zawadzki
Published: 2026-01-30
Categories: cs.HC, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.22759v1

As generative artificial intelligence advances, Large Language Models (LLMs) are being explored for automated graphical user interface (GUI) design. This study investigates the usability and adaptability of LLM-generated interfaces by analysing their ability to meet diverse user needs. The experiments included utilization of three state-of-the-art models from January 2025 (OpenAI GPT o3-mini-high, DeepSeek R1, and Anthropic Claude 3.5 Sonnet) generating mockups for three interface types: a chat system, a technical team panel, and a manager dashboard. Expert evaluations revealed that while LLMs are effective at creating structured layouts, they face challenges in meeting accessibility standards and providing interactive functionality. Further testing showed that LLMs could partially tailor interfaces for different user personas but lacked deeper contextual understanding. The results suggest that while LLMs are promising tools for early-stage UI prototyping, human intervention remains critical to ensure usability, accessibility, and user satisfaction.

---

### AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts

Authors: Libin Qiu, Zhirong Gao, Junfu Chen, Yuhang Ye, Liangyu Li, Weizhi Huang, Xiaobo Xue, Wenkai Qiu, Shuo Tang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22758v2

Large language model agents repeatedly encounter related tasks, yet systems that learn from trajectories commit every lesson to one predefined artifact form. A local constraint, a reusable procedure, and a delegated objective require different amounts of runtime ownership, so one form either under-specifies the correction or wraps it in execution machinery it does not need. We present AutoRefine, which treats trajectory learning as typed artifact compilation. It contrasts failed against successful trajectories to derive a type-neutral, evidence-linked intervention specification, then compiles that specification into the first Rule, Skill, or bounded Subagent that closes it under a runtime-relative ownership order: the selected schema must own every specified observation, state variable, dependent decision, and completion condition. Validation is stated in the same terms: a type-specific contract gate tests whether the generated object realizes its declared boundary, and a replay gate admits it only when it improves the correction cases linked to its source failures without regression on preservation cases. With GPT-5.6-terra as the shared backbone, AutoRefine records the highest success on ALFWorld, ScienceWorld, TravelPlanner, and SpreadsheetBench, and ties the best result on SkillCraft; on TravelPlanner it reaches 80.56% success against 50.0% for the strongest baseline. Removing boundary closure or replay validation costs 15.00 and 16.11 percentage points, the two largest losses among our construction and admission policies. In a longitudinal TravelPlanner stream, the repository holds 89--91% held-out success after 60 learning tasks with no net loss on previously solved tasks, and frozen repositories improve all 25 evaluated source--target pairs, more within a domain (14.20 points on average) than across domains (6.99).

---

### Unveiling Scaling Behaviors in Molecular Language Models: Effects of Model Size, Data, and Representation

Authors: Dong Xu, Qihua Pan, Sisi Yuan, Jianqiang Li, Zexuan Zhu, Junkai Ji
Published: 2026-01-30
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2601.22757v1

Molecular generative models, often employing GPT-style language modeling on molecular string representations, have shown promising capabilities when scaled to large datasets and model sizes. However, it remains unclear and subject to debate whether these models adhere to predictable scaling laws under fixed computational budgets, which is a crucial understanding for optimally allocating resources between model size, data volume, and molecular representation. In this study, we systematically investigate the scaling behavior of molecular language models across both pretraining and downstream tasks. We train 300 models and conduct over 10,000 experiments, rigorously controlling compute budgets while independently varying model size, number of training tokens, and molecular representation. Our results demonstrate clear scaling laws in molecular models for both pretraining and downstream transfer, reveal the substantial impact of molecular representation on performance, and explain previously observed inconsistencies in scaling behavior for molecular generation. Additionally, we publicly release the largest library of molecular language models to date to facilitate future research and development. Code and models are available at https://github.com/SZU-ADDG/MLM-Scaling.

---

### Understanding Generalization from Embedding Dimension and Distributional Convergence

Authors: Junjie Yu, Zhuoli Ouyang, Haotian Deng, Chen Wei, Wenxiao Ma, Jianyu Zhang, Zihan Deng, Quanying Liu
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22756v1

Deep neural networks often generalize well despite heavy over-parameterization, challenging classical parameter-based analyses. We study generalization from a representation-centric perspective and analyze how the geometry of learned embeddings controls predictive performance for a fixed trained model. We show that population risk can be bounded by two factors: (i) the intrinsic dimension of the embedding distribution, which determines the convergence rate of empirical embedding distribution to the population distribution in Wasserstein distance, and (ii) the sensitivity of the downstream mapping from embeddings to predictions, characterized by Lipschitz constants. Together, these yield an embedding-dependent error bound that does not rely on parameter counts or hypothesis class complexity. At the final embedding layer, architectural sensitivity vanishes and the bound is dominated by embedding dimension, explaining its strong empirical correlation with generalization performance. Experiments across architectures and datasets validate the theory and demonstrate the utility of embedding-based diagnostics.

---

### Procedural Knowledge Extraction from Industrial Troubleshooting Guides Using Vision Language Models

Authors: Guillermo Gil de Avalle, Laura Maruster, Christos Emmanouilidis
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22754v2

Industrial troubleshooting guides encode diagnostic procedures in flowchart-like diagrams where spatial layout and technical language jointly convey meaning. To integrate this knowledge into operator support systems, which assist shop-floor personnel in diagnosing and resolving equipment issues, the information must first be extracted and structured for machine interpretation. However, when performed manually, this extraction is labor-intensive and error-prone. Vision Language Models offer potential to automate this process by jointly interpreting visual and textual meaning, yet their performance on such guides remains underexplored. This paper evaluates two VLMs on extracting structured knowledge, comparing two prompting strategies: standard instruction-guided versus an augmented approach that cues troubleshooting layout patterns. Results reveal model-specific trade-offs between layout sensitivity and semantic robustness, informing practical deployment decisions.

---

### OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space

Authors: Zhiyuan Cao, Zeyu Ma, Chenhao Yang, Han Zheng, Mingang Chen
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22752v1

We propose Obfuscated Semantic Null space Injection for Privacy (OSNIP), a lightweight client-side encryption framework for privacy-preserving LLM inference. Generalizing the geometric intuition of linear kernels to the high-dimensional latent space of LLMs, we formally define the ``Obfuscated Semantic Null Space'', a high-dimensional regime that preserves semantic fidelity while enforcing near-orthogonality to the original embedding. By injecting perturbations that project the original embedding into this space, OSNIP ensures privacy without any post-processing. Furthermore, OSNIP employs a key-dependent stochastic mapping that synthesizes individualized perturbation trajectories unique to each user. Evaluations on 12 generative and classification benchmarks show that OSNIP achieves state-of-the-art performance, sharply reducing attack success rates while maintaining strong model utility under strict security constraints.

---

### Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks

Authors: Gnankan Landry Regis N'guessan, Bum Jun Kim
Published: 2026-01-30
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.22751v1

Physical systems near singularities, interfaces, and critical points exhibit power-law scaling, yet standard neural networks leave the governing exponents implicit. We introduce physics-informed M"untz-Sz'asz Networks (MSN-PINN), a power-law basis network that treats scaling exponents as trainable parameters. The model outputs both the solution and its scaling structure. We prove identifiability, or unique recovery, and show that, under these conditions, the squared error between learned and true exponents scales as $O(|μ- α|^2)$. Across experiments, MSN-PINN achieves single-exponent recovery with 1--5% error under noise and sparse sampling. It recovers corner singularity exponents for the two-dimensional Laplace equation with 0.009% error, matches the classical result of Kondrat'ev (1967), and recovers forcing-induced exponents in singular Poisson problems with 0.03% and 0.05% errors. On a 40-configuration wedge benchmark, it reaches a 100% success rate with 0.022% mean error. Constraint-aware training encodes physical requirements such as boundary condition compatibility and improves accuracy by three orders of magnitude over naive training. By combining the expressiveness of neural networks with the interpretability of asymptotic analysis, MSN-PINN produces learned parameters with direct physical meaning.

---

### UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling

Authors: Pingping Liu, Jiamiao Liu, Zijian Zhang, Hao Miao, Qi Jiang, Qingliang Li, Qiuzhan Zhou, Irwin King
Published: 2026-01-30
Categories: cs.ET, cs.AI
arXiv: https://arxiv.org/abs/2601.22746v1

Urban region profiling, the task of characterizing geographical areas, is crucial for urban planning and resource allocation. However, existing research in this domain faces two significant limitations. First, most methods are confined to single-task prediction, failing to capture the interconnected, multi-faceted nature of urban environments where numerous indicators are deeply correlated. Second, the field lacks a standardized experimental benchmark, which severely impedes fair comparison and reproducible progress. To address these challenges, we first establish a comprehensive benchmark for multi-task urban region profiling, featuring multi-modal features and a diverse set of strong baselines to ensure a fair and rigorous evaluation environment. Concurrently, we propose UrbanMoE, the first sparse multi-modal, multi-expert framework specifically architected to solve the multi-task challenge. Leveraging a sparse Mixture-of-Experts architecture, it dynamically routes multi-modal features to specialized sub-networks, enabling the simultaneous prediction of diverse urban indicators. We conduct extensive experiments on three real-world datasets within our benchmark, where UrbanMoE consistently demonstrates superior performance over all baselines. Further in-depth analysis validates the efficacy and efficiency of our approach, setting a new state-of-the-art and providing the community with a valuable tool for future research in urban analytics

---

### Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss

Authors: Yuanhao Pu, Defu Lian, Enhong Chen
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22745v1

The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework situates it as a canonical instance within a broad family of surrogates. Concurrently, another line of research has addressed scalability when the number of classes is exceedingly large, in which numerous approximations have been proposed to retain the benefits of the exact objective while improving efficiency. Building on these two perspectives, we present a principled investigation of the Softmax-family losses. We examine whether different surrogates achieve consistency with classification and ranking metrics, and analyze their gradient dynamics to reveal distinct convergence behaviors. We also introduce a systematic bias-variance decomposition for approximate methods that provides convergence guarantees, and further derive a per-epoch complexity analysis, showing explicit trade-offs between effectiveness and efficiency. Extensive experiments on a representative task demonstrate a strong alignment between consistency, convergence, and empirical performance. Together, these results establish a principled foundation and offer practical guidance for loss selections in large-class machine learning applications.

---

### Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing

Authors: Yilong Huang, Songze Li
Published: 2026-01-30
Categories: cs.CV, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.22744v1

Diffusion-based face swapping achieves state-of-the-art performance, yet it also exacerbates the potential harm of malicious face swapping to violate portraiture right or undermine personal reputation. This has spurred the development of proactive defense methods. However, existing approaches face a core trade-off: large perturbations distort facial structures, while small ones weaken protection effectiveness. To address these issues, we propose FaceDefense, an enhanced proactive defense framework against diffusion-based face swapping. Our method introduces a new diffusion loss to strengthen the defensive efficacy of adversarial examples, and employs a directional facial attribute editing to restore perturbation-induced distortions, thereby enhancing visual imperceptibility. A two-phase alternating optimization strategy is designed to generate final perturbed face images. Extensive experiments show that FaceDefense significantly outperforms existing methods in both imperceptibility and defense effectiveness, achieving a superior trade-off.

---

### AR-BENCH: Benchmarking Legal Reasoning with Judgment Error Detection, Classification and Correction

Authors: Yifei Li, Richong Zhang, Wanyu Tu, Zhijie Nie, Haokun Luo, Chuantao Yin, Pengchong Li
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22742v1

Legal judgments may contain errors due to the complexity of case circumstances and the abstract nature of legal concepts, while existing appellate review mechanisms face efficiency pressures from a surge in case volumes. Although current legal AI research focuses on tasks like judgment prediction and legal document generation, the task of judgment review differs fundamentally in its objectives and paradigm: it centers on detecting, classifying, and correcting errors after a judgment is issued, constituting anomaly detection rather than prediction or generation. To address this research gap, we introduce a novel task APPELLATE REVIEW, aiming to assess models' diagnostic reasoning and reliability in legal practice. We also construct a novel dataset benchmark AR-BENCH, which comprises 8,700 finely annotated decisions and 34,617 supplementary corpora. By evaluating 14 large language models, we reveal critical limitations in existing models' ability to identify legal application errors, providing empirical evidence for future improvements.

---

### StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing

Authors: Han Wang, Deyi Ji, Lanyun Zhu, Jiebo Luo, Roy Ka-Wei Lee
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22738v1

Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming encoder with selective routing to a Vision-Language Model (VLM) expert. StreamSense handles most timestamps with the lightweight streaming encoder, escalates hard/ambiguous cases to the VLM, and defers decisions when context is insufficient. The encoder is trained using (i) a cross-modal contrastive term to align visual/audio cues with textual signals, and (ii) an IoU-weighted loss that down-weights poorly overlapping target segments, mitigating label interference across segment boundaries. We evaluate StreamSense on multiple social streaming detection tasks (e.g., sentiment classification and hate content moderation), and the results show that StreamSense achieves higher accuracy than VLM-only streaming while only occasionally invoking the VLM, thereby reducing average latency and compute. Our results indicate that selective escalation and deferral are effective primitives for understanding streaming social tasks. Code is publicly available on GitHub.

---

### Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models

Authors: Enyi Shi, Pengyang Shao, Yanxin Zhang, Chenhang Cui, Jiayi Lyu, Xiaobo Xia, Fei Shen, Tat-Seng Chua
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22737v2

The robust safety of Vision-Language Large Models (VLLMs) against joint multilingual and multimodal threats remains severely underexplored. Current benchmarks typically isolate these dimensions, being either multilingual but text-only, or multimodal but monolingual. While recent red-teaming efforts attempt to bridge this gap by rendering harmful prompts as images, their overreliance on typography-style visuals and lack of semantically grounded image-text pairs fail to capture realistic cross-modal interactions under multilingual and multimodal conditions. To address this, we introduce Lingua-SafetyBench, a comprehensive benchmark of 100,440 harmful image-text pairs spanning 10 languages. Crucially, Lingua-SafetyBench explicitly partitions data into image-dominant and text-dominant subsets to precisely disentangle sources of risk. Extensive evaluations reveal that current VLLMs retain non-negligible vulnerabilities under these joint inputs. Linguistically, requests in Non-High-Resource Languages (Non-HRLs) and non-Latin scripts generally pose greater threats. Furthermore, analyzing modality-language interactions uncovers a striking asymmetry: in High-Resource Languages (HRLs), models are most vulnerable to image-dominant risks, whereas in Non-HRLs, text-dominant risks severely degrade safety performance. Finally, a controlled study on the Qwen series demonstrates that while model scaling and iterative upgrades improve overall safety, they disproportionately benefit HRLs. This exacerbates the safety disparity between HRLs and Non-HRLs under text-dominant risks, highlighting that achieving robust safety requires dedicated language- and modality-aware alignment strategies beyond mere scaling. The code and dataset will be available at https://github.com/zsxr15/Lingua-SafetyBench.Warning: this paper contains examples with unsafe content.

---

### Uncertainty-aware Causal Decision Making via Effect Bound Decomposition

Authors: Md Musfiqur Rahman, Ziwei Jiang, Hilaf Hasson, Murat Kocaoglu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22736v3

Causal inference from observational data can provide strong evidence for finding the best action in a decision-making scenario without having to perform expensive randomized trials. The causal effect of an action is often not pointwise identifiable even with infinite data due to unobserved confounding factors. Furthermore, having only finitely many samples adds another layer of uncertainty to causal effect estimation. Several existing methods can be used to obtain upper and lower bounds to the causal effect, ranging from symbolic methods to the more recent neural network-based approaches, which implicitly incorporate both sources of uncertainty. However, these methods do not inform whether collecting more samples may or may not help identify the best action from observational data, leaving experts in the dark about their data collection strategies. We address this problem with a novel framework that can distinguish the range of causal effect values that might be eliminated by collecting more samples from the range of values that, with high probability, cannot be eliminated with more observational samples. We show that this partitioning can be obtained by solving max-min and min-max optimization problems. We leverage neural causal models to approximately recover this decomposition in practice. We demonstrate via experiments on synthetic and real-world datasets that our algorithm can determine when collecting more samples will not help determine the best action. Our framework can help practitioners decide when to resort to non-observational studies or seek to measure some of the unmeasured confounders for optimal decision-making.

---

### MM-THEBench: Do Reasoning MLLMs Think Reasonably?

Authors: Zhidian Huang, Zijun Yao, Ji Qi, Shangqing Tu, Junxian Ma, Jinxin Liu, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22735v1

Recent advances in multimodal large language models (MLLMs) mark a shift from non-thinking models to post-trained reasoning models capable of solving complex problems through thinking. However, whether such thinking mitigates hallucinations in multimodal perception and reasoning remains unclear. Self-reflective reasoning enhances robustness but introduces additional hallucinations, and subtle perceptual errors still result in incorrect or coincidentally correct answers. Existing benchmarks primarily focus on models before the emergence of reasoning MLLMs, neglecting the internal thinking process and failing to measure the hallucinations that occur during thinking. To address these challenges, we introduce MM-THEBench, a comprehensive benchmark for assessing hallucinations of intermediate CoTs in reasoning MLLMs. MM-THEBench features a fine-grained taxonomy grounded in cognitive dimensions, diverse data with verified reasoning annotations, and a multi-level automated evaluation framework. Extensive experiments on mainstream reasoning MLLMs reveal insights into how thinking affects hallucination and reasoning capability in various multimodal tasks.

---

### Active Learning-Driven Lightweight YOLOv9: Enhancing Efficiency in Smart Agriculture

Authors: Hung-Chih Tu, Bo-Syun Chen, Yun-Chien Cheng
Published: 2026-01-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.22732v1

This study addresses the demand for real-time detection of tomatoes and tomato flowers by agricultural robots deployed on edge devices in greenhouse environments. Under practical imaging conditions, object detection systems often face challenges such as large scale variations caused by varying camera distances, severe occlusion from plant structures, and highly imbalanced class distributions. These factors make conventional object detection approaches that rely on fully annotated datasets difficult to simultaneously achieve high detection accuracy and deployment efficiency. To overcome these limitations, this research proposes an active learning driven lightweight object detection framework, integrating data analysis, model design, and training strategy. First, the size distribution of objects in raw agricultural images is analyzed to redefine an operational target range, thereby improving learning stability under real-world conditions. Second, an efficient feature extraction module is incorporated to reduce computational cost, while a lightweight attention mechanism is introduced to enhance feature representation under multi-scale and occluded scenarios. Finally, an active learning strategy is employed to iteratively select high-information samples for annotation and training under a limited labeling budget, effectively improving the recognition performance of minority and small-object categories. Experimental results demonstrate that, while maintaining a low parameter count and inference cost suitable for edge-device deployment, the proposed method effectively improves the detection performance of tomatoes and tomato flowers in raw images. Under limited annotation conditions, the framework achieves an overall detection accuracy of 67.8% mAP, validating its practicality and feasibility for intelligent agricultural applications.

---

### ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model

Authors: Xiaoshu Chen, Sihang Zhou, Ke Liang, Taichun Zhou, Xinwang Liu
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22730v1

Compressing long chains of thought (CoT) into compact latent tokens is crucial for efficient reasoning with large language models (LLMs). Recent studies employ autoencoders to achieve this by reconstructing textual CoT from latent tokens, thus encoding CoT semantics. However, treating textual CoT as the reconstruction target forces latent tokens to preserve surface-level linguistic features (e.g., word choice and syntax), introducing a strong linguistic inductive bias that prioritizes linguistic form over reasoning structure and limits logical abstraction. Thus, we propose ImgCoT that replaces the reconstruction target from textual CoT to the visual CoT obtained by rendering CoT into images. This substitutes linguistic bias with spatial inductive bias, i.e., a tendency to model spatial layouts of the reasoning steps in visual CoT, enabling latent tokens to better capture global reasoning structure. Moreover, although visual latent tokens encode abstract reasoning structure, they may blur reasoning details. We thus propose a loose ImgCoT, a hybrid reasoning that augments visual latent tokens with a few key textual reasoning steps, selected based on low token log-likelihood. This design allows LLMs to retain both global reasoning structure and fine-grained reasoning details with fewer tokens than the complete CoT. Extensive experiments across multiple datasets and LLMs demonstrate the effectiveness of the two versions of ImgCoT.

---

### GaussianOcc3D: A Gaussian-Based Adaptive Multi-modal 3D Occupancy Prediction

Authors: A. Enes Doruk, Hasan F. Ates
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22729v1

3D semantic occupancy prediction is a pivotal task in autonomous driving, providing a dense and fine-grained understanding of the surrounding environment, yet single-modality methods face trade-offs between camera semantics and LiDAR geometry. Existing multi-modal frameworks often struggle with modality heterogeneity, spatial misalignment, and the representation crisis--where voxels are computationally heavy and BEV alternatives are lossy. We present GaussianOcc3D, a multi-modal framework bridging camera and LiDAR through a memory-efficient, continuous 3D Gaussian representation. We introduce four modules: (1) LiDAR Depth Feature Aggregation (LDFA), using depth-wise deformable sampling to lift sparse signals onto Gaussian primitives; (2) Entropy-Based Feature Smoothing (EBFS) to mitigate domain noise; (3) Adaptive Camera-LiDAR Fusion (ACLF) with uncertainty-aware reweighting for sensor reliability; and (4) a Gauss-Mamba Head leveraging Selective State Space Models for global context with linear complexity. Evaluations on Occ3D, SurroundOcc, and SemanticKITTI benchmarks demonstrate state-of-the-art performance, achieving mIoU scores of 49.4%, 28.9%, and 25.2% respectively. GaussianOcc3D exhibits superior robustness across challenging rainy and nighttime conditions.

---

### OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

Authors: Jin Li, Tao Chen, Kai Wen, Siqi Yin, Shuai Jiang, Weijie Wang, Jingwen Luo, Chenhui Wu
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22725v4

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and Gemini-powered dense captioning, ensuring a uniform distribution across 20 fine-grained garment categories. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Experimental results show strong agreement with human judgments (Kendall's $τ$ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.

---

### A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement

Authors: Chengchun Liu, Wendi Cai, Boxuan Zhao, Fanyang Mo
Published: 2026-01-30
Categories: physics.chem-ph, cs.AI, physics.atm-clus
arXiv: https://arxiv.org/abs/2601.22723v1

Accurate molecular geometries are a prerequisite for reliable quantum-chemical predictions, yet density functional theory (DFT) optimization remains a major bottleneck for high-throughput molecular screening. Here we present GeoOpt-Net, a multi-branch SE(3)-equivariant geometry refinement network that predicts DFT-quality structures at the B3LYP/TZVP level of theory in a single forward pass starting from inexpensive initial conformers generated at a low-cost force-field level. GeoOpt-Net is trained using a two-stage strategy in which a broadly pretrained geometric representation is subsequently fine-tuned to approach B3LYP/TZVP-level accuracy, with theory- and basis-set-aware calibration enabled by a fidelity-aware feature modulation (FAFM) mechanism. Benchmarking against representative approaches spanning classical conformer generation (RDKit), semiempirical quantum methods (xTB), data-driven geometry refinement pipelines (Auto3D), and machine-learning interatomic potentials (UMA) on external drug-like molecules demonstrates that GeoOpt-Net achieves sub-milli-Å all-atom RMSD with near-zero B3LYP/TZVP single-point energy deviations, indicating DFT-ready geometries that closely reproduce both structural and energetic references. Beyond geometric metrics, GeoOpt-Net generates initial guesses intrinsically compatible with DFT convergence criteria, yielding nonzero ``All-YES'' convergence rates (65.0\% under loose and 33.4\% under default thresholds), and substantially reducing re-optimization steps and wall-clock time. GeoOpt-Net further exhibits smooth and predictable energy scaling with molecular complexity while preserving key electronic observables such as dipole moments. Collectively, these results establish GeoOpt-Net as a scalable, physically consistent geometry refinement framework that enables efficient acceleration of DFT-based quantum-chemical workflows.

---

### Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain

Authors: Junjie Yu, Wenxiao Ma, Chen Wei, Jianyu Zhang, Haotian Deng, Zihan Deng, Quanying Liu
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22722v1

Recent work has found that neural networks with stronger generalization tend to exhibit higher representational alignment with one another across architectures and training paradigms. In this work, we show that models with stronger generalization also align more strongly with human neural activity. Moreover, generalization performance, model--model alignment, and model--brain alignment are all significantly correlated with each other. We further show that these relationships can be explained by a single geometric property of learned representations: the local intrinsic dimension of embeddings. Lower local dimension is consistently associated with stronger model--model alignment, stronger model--brain alignment, and better generalization, whereas global dimension measures fail to capture these effects. Finally, we find that increasing model capacity and training data scale systematically reduces local intrinsic dimension, providing a geometric account of the benefits of scaling. Together, our results identify local intrinsic dimension as a unifying descriptor of representational convergence in artificial and biological systems.

---

### AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises

Authors: Ivan K. Tung, Yu Xiang Shi, Alex Chien, Wenkai Liu, Lawrence Zheng
Published: 2026-01-30
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.22720v1

Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that generates attack paths using LLMs, white-box access, and Monte Carlo Tree Search over real exploit execution. LLM-based search discovers exploits dynamically without pre-existing vulnerability graphs, while white-box access enables validating exploits in isolation before committing to attack paths. Evaluation at CIDeX 2025, a large-scale exercise spanning 46 IT hosts, showed that AEGIS-generated paths are comparable to human-authored scenarios across four dimensions of training experience (perceived learning, engagement, believability, challenge). Results were measured with a validated questionnaire extensible to general simulation-based training. By automating exploit chain discovery and validation, AEGIS reduces scenario development from months to days, shifting expert effort from technical validation to scenario design.

---

### A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization

Authors: Shiye Lei, Zhihao Cheng, Dacheng Tao
Published: 2026-01-30
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22718v1

Reinforcement learning (RL) post-training has increasingly demonstrated strong ability to elicit reasoning behaviors in large language models (LLMs). For training efficiency, rollouts are typically generated in an off-policy manner using an older sampling policy and then used to update the current target policy. To correct the resulting discrepancy between the sampling and target policies, most existing RL objectives rely on a token-level importance sampling ratio, primarily due to its computational simplicity and numerical stability. However, we observe that token-level correction often leads to unstable training dynamics when the degree of off-policyness is large. In this paper, we revisit LLM policy optimization under off-policy conditions and show that the theoretically rigorous correction term is the prefix importance ratio, and that relaxing it to a token-level approximation can induce instability in RL post-training. To stabilize LLM optimization under large off-policy drift, we propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO). MinPRO replaces the unstable cumulative prefix ratio with a non-cumulative surrogate based on the minimum token-level ratio observed in the preceding prefix. Extensive experiments on both dense and mixture-of-experts LLMs, across multiple mathematical reasoning benchmarks, demonstrate that MinPRO substantially improves training stability and peak performance in off-policy regimes.

---

### Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation

Authors: Pingzhi Tang, Ruijie Zhou, Fanxu Meng, Wenjie Pei, Muhan Zhang
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22716v1

Current quantization methods for LLMs predominantly rely on block-wise structures to maintain efficiency, often at the cost of representational flexibility. In this work, we demonstrate that element-wise quantization can be made as efficient as block-wise scaling while providing strictly superior expressive power by modeling the scaling manifold as continuous low-rank matrices ($S = BA$). We propose Low-Rank Decomposed Scaling (LoRDS), a unified framework that rethinks quantization granularity through this low-rank decomposition. By "breaking the blocks" of spatial constraints, LoRDS establishes a seamless efficiency lifecycle: it provides high-fidelity PTQ initialization refined via iterative optimization, enables joint QAT of weights and scaling factors, and facilitates high-rank multiplicative PEFT adaptation. Unlike additive PEFT approaches such as QLoRA, LoRDS enables high-rank weight updates within a low-rank budget while incurring no additional inference overhead. Supported by highly optimized Triton kernels, LoRDS consistently outperforms state-of-the-art baselines across various model families in both quantization and downstream fine-tuning tasks. Notably, on Llama3-8B, our method achieves up to a 27.0% accuracy improvement at 3 bits over NormalFloat quantization and delivers a 1.5x inference speedup on NVIDIA RTX 4090 while enhancing PEFT performance by 9.6% on downstream tasks over 4bit QLoRA, offering a robust and integrated solution for unified compression and adaptation of LLMs.

---

### Vision-Language Models Unlock Task-Centric Latent Actions

Authors: Alexander Nikulin, Ilya Zisman, Albina Klepach, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.22714v1

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often encoding noise instead of meaningful latent actions. Humans, on the other hand, can effortlessly distinguish task-relevant motions from irrelevant details in any video given only a brief task description. In this work, we propose to utilize the common-sense reasoning abilities of Vision-Language Models (VLMs) to provide promptable representations, effectively separating controllable changes from the noise in unsupervised way. We use these representations as targets during LAM training and benchmark a wide variety of popular VLMs, revealing substantial variation in the quality of promptable representations as well as their robustness to different prompts and hyperparameters. Interestingly, we find that more recent VLMs may perform worse than older ones. Finally, we show that simply asking VLMs to ignore distractors can substantially improve latent action quality, yielding up to a six-fold increase in downstream success rates on Distracting MetaWorld.

---

### SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks

Authors: Matteo Gambella, Fabrizio Pittorino, Giuliano Casale, Manuel Roveri
Published: 2026-01-30
Categories: cs.LG, cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2601.22711v1

Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approaches typically rely on single-model confidence thresholds, which are frequently unreliable due to inherent calibration issues. To address this, we introduce SQUAD (Scalable Quorum Adaptive Decisions), the first inference scheme that integrates early-exit mechanisms with distributed ensemble learning, improving uncertainty estimation while reducing the inference time. Unlike traditional methods that depend on individual confidence scores, SQUAD employs a quorum-based stopping criterion on early-exit learners by collecting intermediate predictions incrementally in order of computational complexity until a consensus is reached and halting the computation at that exit if the consensus is statistically significant. To maximize the efficacy of this voting mechanism, we also introduce QUEST (Quorum Search Technique), a Neural Architecture Search method to select early-exit learners with optimized hierarchical diversity, ensuring learners are complementary at every intermediate layer. This consensus-driven approach yields statistically robust early exits, improving the test accuracy up to 5.95% compared to state-of-the-art dynamic solutions with a comparable computational cost and reducing the inference latency up to 70.60% compared to static ensembles while maintaining a good accuracy.

---

### AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs

Authors: Jaehee Kim, Pilsung Kang
Published: 2026-01-30
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2601.22710v2

Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a deployable API-only \cradd{exposure-reduction layer that reduces plaintext exposure} by translating text into an Alien Language via a vocabulary-scale bijection, enabling lossless recovery on the client side. Using only standard fine-tuning APIs, Alien Adaptation Training (AAT) adapts target models to operate directly on alienized inputs. Across four LLM backbones and seven benchmarks, AlienLM retains over 81\% of plaintext-oracle performance on average, substantially outperforming random-bijection and character-level baselines. Under adversaries with access to model weights, corpus statistics, and learning-based inverse translation, recovery attacks reconstruct fewer than 0.22\% of alienized tokens. Our results demonstrate a practical pathway for \cradd{privacy-aware} LLM deployment under API-only access, substantially reducing plaintext exposure while maintaining task performance. Code and data are available at https://github.com/KimJaehee0725/AlienLM.

---

### Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

Authors: Yanlong Chen, Amirhossein Habibian, Luca Benini, Yawei Li
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22709v5

Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its potential, quantization-aware training for VLMs remains underexplored. We propose GRACE, a framework unifying knowledge distillation and QAT under the Information Bottleneck principle: quantization constrains information capacity while distillation guides what to preserve within this budget. Treating the teacher as a proxy for task-relevant information, we introduce confidence-gated decoupled distillation to filter unreliable supervision, relational centered kernel alignment to transfer visual token structures, and an adaptive controller via Lagrangian relaxation to balance fidelity against capacity constraints. Across extensive benchmarks on LLaVA and Qwen families, our INT4 models consistently outperform FP16 baselines (e.g., LLaVA-1.5-7B: 70.1 vs. 66.8 on SQA; Qwen2-VL-2B: 76.9 vs. 72.6 on MMBench), nearly matching teacher performance. Using real INT4 kernel, we achieve 3$\times$ throughput with 54% memory reduction. This principled framework significantly outperforms existing quantization methods, making GRACE a compelling solution for resource-constrained deployment. Code and data are available at: https://github.com/ForeverBlue816/GRACE.

---

### A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation

Authors: Haonan He, Jingqi Ye, Minglei Li, Zhengbo Wang, Tao Chen, Lei Bai, Peng Ye
Published: 2026-01-30
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.22708v1

Low-Rank Adaptation (LoRA) is a fundamental parameter-efficient fine-tuning method that balances efficiency and performance in large-scale neural networks. However, the proliferation of LoRA variants has led to fragmentation in methodology, theory, code, and evaluation. To this end, this work presents the first unified study of LoRA variants, offering a systematic taxonomy, unified theoretical review, structured codebase, and standardized empirical assessment. First, we categorize LoRA variants along four principal axes: rank, optimization dynamics, initialization, and integration with Mixture-of-Experts. Then, we review their relationships and evolution within a common theoretical framework focused on low-rank update dynamics. Further, we introduce LoRAFactory, a modular codebase that implements variants through a unified interface, supporting plug-and-play experimentation and fine-grained analysis. Last, using this codebase, we conduct a large-scale evaluation across natural language generation, natural language understanding, and image classification tasks, systematically exploring key hyperparameters. Our results uncover several findings, notably: LoRA and its variants exhibit pronounced sensitivity to the choices of learning rate compared to other hyperparameters; moreover, with proper hyperparameter configurations, LoRA consistently matches or surpasses the performance of most of its variants.

---

### Deep Learning-Based Early-Stage IR-Drop Estimation via CNN Surrogate Modeling

Authors: Ritesh Bhadana
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.AR, eess.IV
arXiv: https://arxiv.org/abs/2601.22707v1

IR-drop is a critical power integrity challenge in modern VLSI designs that can cause timing degradation, reliability issues, and functional failures if not detected early in the design flow. Conventional IR-drop analysis relies on physics-based signoff tools, which provide high accuracy but incur significant computational cost and require near-final layout information, making them unsuitable for rapid early-stage design exploration. In this work, we propose a deep learning-based surrogate modeling approach for early-stage IR-drop estimation using a CNN. The task is formulated as a dense pixel-wise regression problem, where spatial physical layout features are mapped directly to IR-drop heatmaps. A U-Net-based encoder-decoder architecture with skip connections is employed to effectively capture both local and global spatial dependencies within the layout. The model is trained on a physics-inspired synthetic dataset generated by us, which incorporates key physical factors including power grid structure, cell density distribution, and switching activity. Model performance is evaluated using standard regression metrics such as Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). Experimental results demonstrate that the proposed approach can accurately predict IR-drop distributions with millisecond-level inference time, enabling fast pre-signoff screening and iterative design optimization. The proposed framework is intended as a complementary early-stage analysis tool, providing designers with rapid IR-drop insight prior to expensive signoff analysis. The implementation, dataset generation scripts, and the interactive inference application are publicly available at: https://github.com/riteshbhadana/IR-Drop-Predictor. The live application can be accessed at: https://ir-drop-predictor.streamlit.app/.

---

### DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation

Authors: Abid Hassan, Tuan Ngo, Saad Shafiq, Nenad Medvidovic
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22703v2

Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc detection methods operate on penultimate feature representations derived from global average pooling (GAP) -- a lossy operation that discards valuable distributional statistics from activation maps prior to global average pooling. We contend that these overlooked statistics, particularly channel-wise variance and dominant (maximum) activations, are highly discriminative for OOD detection. We introduce DAVIS, a simple and broadly applicable post-hoc technique that enriches feature vectors by incorporating these crucial statistics, directly addressing the information loss from GAP. Extensive evaluations show DAVIS sets a new benchmark across diverse architectures, including ResNet, DenseNet, and EfficientNet. It achieves significant reductions in the false positive rate (FPR95), with improvements of 48.26\% on CIFAR-10 using ResNet-18, 38.13\% on CIFAR-100 using ResNet-34, and 26.83\% on ImageNet-1k benchmarks using MobileNet-v2. Our analysis reveals the underlying mechanism for this improvement, providing a principled basis for moving beyond the mean in OOD detection.

---

### Metric Hub: A metric library and practical selection workflow for use-case-driven data quality assessment in medical AI

Authors: Katinka Becker, Maximilian P. Oppelt, Tobias S. Zech, Martin Seyferth, Sandie Cabon, Vanja Miskovic, Ivan Cimrak, Michal Kozubek, Giuseppe D'Avenio, Ilaria Campioni, Jana Fehr, Kanjar De et al.
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22702v1

Machine learning (ML) in medicine has transitioned from research to concrete applications aimed at supporting several medical purposes like therapy selection, monitoring and treatment. Acceptance and effective adoption by clinicians and patients, as well as regulatory approval, require evidence of trustworthiness. A major factor for the development of trustworthy AI is the quantification of data quality for AI model training and testing. We have recently proposed the METRIC-framework for systematically evaluating the suitability (fit-for-purpose) of data for medical ML for a given task. Here, we operationalize this theoretical framework by introducing a collection of data quality metrics - the metric library - for practically measuring data quality dimensions. For each metric, we provide a metric card with the most important information, including definition, applicability, examples, pitfalls and recommendations, to support the understanding and implementation of these metrics. Furthermore, we discuss strategies and provide decision trees for choosing an appropriate set of data quality metrics from the metric library given specific use cases. We demonstrate the impact of our approach exemplarily on the PTB-XL ECG-dataset. This is a first step to enable fit-for-purpose evaluation of training and test data in practice as the base for establishing trustworthy AI in medicine.

---

### Best-of-Q: Improving VLM agents with Q-function Action Ranking at Inference

Authors: Emilien Biré, María Santos, Kai Yuan
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22701v1

Vision-Language Models (VLMs) have become powerful backbones for agents to autonomously operate in digital environments like the web and operating systems. However, these models suffer from inadaptability to fast-changing environments like the web, which can be alleviated by fine-tuning requiring expansive model training and data collection. In this work, we introduce a novel paradigm for enhancing agentic VLM policies at inference without policy retraining. Fundamentally, our approach decouples the VLM's role as a high-capacity action proposer from the final action selection mechanism. We keep the VLM policy frozen and use it to generate a set of candidate actions for a given state. Then, a lightweight, offline-trained Q-function reranks these candidates, and the agent executes the action with the highest estimated value. The main contribution is to apply the Q-function directly during inference for immediate policy improvement, and not offline to relabel data for policy retraining. We demonstrate on the academic WebVoyager benchmark that our method significantly boosts agent success rates, improving a Qwen2.5-VL-7B agent from 38.8% to 55.7% and a proprietary GPT-4.1 agent from 82.4% to 88.8%.

---

### Models Know Models Best: Evaluation via Model-Preferred Formats

Authors: Joonhak Lee, Sungmok Jung, Jongyeon Park, Jaejin Lee
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22699v1

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural language continuation benefits from likelihood scoring, whereas explicit comparison is better suited to symbol-based selection. These trends are consistent across various decoder-based LLMs, indicating model-agnostic effects. To address these inconsistencies, a dynamic format-alignment strategy is introduced that employs a lightweight classifier trained on latent model-preference signals. In contrast to human-designed heuristics, which often degrade performance, this approach uses model-generated signals to determine the optimal format for each problem instance. The proposed method achieves substantial and consistent improvements in zero-shot accuracy across reasoning and knowledge benchmarks, better revealing the models' latent capabilities.

---

### Bi-MCQ: Reformulating Vision-Language Alignment for Negation Understanding

Authors: Tae Hun Kim, Hyun Gyu Lee
Published: 2026-01-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.22696v1

Recent vision-language models (VLMs) achieve strong zero-shot performance via large-scale image-text pretraining and have been widely adopted in medical image analysis. However, existing VLMs remain notably weak at understanding negated clinical statements, largely due to contrastive alignment objectives that treat negation as a minor linguistic variation rather than a meaning-inverting operator. In multi-label settings, prompt-based InfoNCE fine-tuning further reinforces easy-positive image-prompt alignments, limiting effective learning of disease absence. To overcome these limitations, we reformulate vision-language alignment as a conditional semantic comparison problem, which is instantiated through a bi-directional multiple-choice learning framework(Bi-MCQ). By jointly training Image-to-Text and Text-to-Image MCQ tasks with affirmative, negative, and mixed prompts, our method implements fine-tuning as conditional semantic comparison instead of global similarity maximization. We further introduce direction-specific Cross-Attention fusion modules to address asymmetric cues required by bi-directional reasoning and reduce alignment interference. Experiments on ChestXray14, Open-I, CheXpert, and PadChest show that Bi-MCQ improves negation understanding by up to 0.47 AUC over the zero-shot performance of the state-of-the-art CARZero model, while achieving up to a 0.08 absolute gain on positive-negative combined (PNC) evaluation. Additionally, Bi-MCQ reduces the affirmative-negative AUC gap by an average of 0.12 compared to InfoNCE-based fine-tuning, demonstrating that objective reformulation can substantially enhance negation understanding in medical VLMs.

---

### PEAR: Pixel-aligned Expressive humAn mesh Recovery

Authors: Jiahao Wu, Yunfei Liu, Lijian Lin, Ye Zhu, Lei Zhu, Jingyi Li, Yu Li
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22693v2

Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods often suffer from slow inference, produce only coarse body poses, and exhibit misalignments or unnatural artifacts in fine-grained regions such as the face and hands. These issues make current approaches difficult to apply to downstream tasks. To address these challenges, we propose PEAR-a fast and robust framework for pixel-aligned expressive human mesh recovery. PEAR explicitly tackles three major limitations of existing methods: slow inference, inaccurate localization of fine-grained human pose details, and insufficient facial expression capture. Specifically, to enable real-time SMPLX parameter inference, we depart from prior designs that rely on high resolution inputs or multi-branch architectures. Instead, we adopt a clean and unified ViT-based model capable of recovering coarse 3D human geometry. To compensate for the loss of fine-grained details caused by this simplified architecture, we introduce pixel-level supervision to optimize the geometry, significantly improving the reconstruction accuracy of fine-grained human details. To make this approach practical, we further propose a modular data annotation strategy that enriches the training data and enhances the robustness of the model. Overall, PEAR is a preprocessing-free framework that can simultaneously infer EHM-s (SMPLX and scaled-FLAME) parameters at over 100 FPS. Extensive experiments on multiple benchmark datasets demonstrate that our method achieves substantial improvements in pose estimation accuracy compared to previous SMPLX-based approaches. Project page: https://wujh2001.github.io/PEAR

---

### FNF: Functional Network Fingerprint for Large Language Models

Authors: Yiheng Liu, Junhao Ning, Sichen Xia, Haiyang Sun, Yang Yang, Hanyang Chi, Xiaohui Gao, Ning Qiang, Bao Ge, Junwei Han, Xintao Hu
Published: 2026-01-30
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.22692v1

The development of large language models (LLMs) is costly and has significant commercial value. Consequently, preventing unauthorized appropriation of open-source LLMs and protecting developers' intellectual property rights have become critical challenges. In this work, we propose the Functional Network Fingerprint (FNF), a training-free, sample-efficient method for detecting whether a suspect LLM is derived from a victim model, based on the consistency between their functional network activity. We demonstrate that models that share a common origin, even with differences in scale or architecture, exhibit highly consistent patterns of neuronal activity within their functional networks across diverse input samples. In contrast, models trained independently on distinct data or with different objectives fail to preserve such activity alignment. Unlike conventional approaches, our method requires only a few samples for verification, preserves model utility, and remains robust to common model modifications (such as fine-tuning, pruning, and parameter permutation), as well as to comparisons across diverse architectures and dimensionalities. FNF thus provides model owners and third parties with a simple, non-invasive, and effective tool for protecting LLM intellectual property. The code is available at https://github.com/WhatAboutMyStar/LLM_ACTIVATION.

---

### Do Transformers Have the Ability for Periodicity Generalization?

Authors: Huanyu Liu, Ge Li, Yihong Dong, Sihan Wu, Peixu Wang, Sihao Cheng, Taozhi Chen, Kechi Zhang, Hao Zhu, Tongxuan Liu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22690v1

Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit substantial limitations in out-of-distribution (OOD) generalization compared with humans. We investigate this gap through periodicity, one of the basic OOD scenarios. Periodicity captures invariance amid variation. Periodicity generalization represents a model's ability to extract periodic patterns from training data and generalize to OOD scenarios. We introduce a unified interpretation of periodicity from the perspective of abstract algebra and reasoning, including both single and composite periodicity, to explain why Transformers struggle to generalize periodicity. Then we construct Coper about composite periodicity, a controllable generative benchmark with two OOD settings, Hollow and Extrapolation. Experiments reveal that periodicity generalization in Transformers is limited, where models can memorize periodic data during training, but cannot generalize to unseen composite periodicity. We release the source code to support future research.

---

### TSLM: Tree-Structured Language Modeling for Divergent Thinking

Authors: Doyoung Kim, Jaehyeok Doo, Minjoon Seo
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22688v1

Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM), which uses special tokens to encode branching structure, enabling models to generate and selectively expand multiple search paths within a single generation process. By training on complete search trees including both successful and failed attempts, TSLM learns to internalize systematic exploration without redundant recomputation of shared prefixes. TSLM achieves robust performance and superior inference efficiency by avoiding the multiple independent forward passes required by external search methods. These results suggest a new paradigm of inference-time scaling for robust reasoning, demonstrating that supervised learning on complete tree-structured traces provides an efficient alternative for developing systematic exploration capabilities in language models.

---

### OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection

Authors: Binyi Su, Chenghao Huang, Haiyong Chen
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22685v1

Zero-shot out-of-vocabulary detection (ZS-OOVD) aims to accurately recognize objects of in-vocabulary (IV) categories provided at zero-shot inference, while simultaneously rejecting undefined ones (out-of-vocabulary, OOV) that lack corresponding category prompts. However, previous methods are prone to overfitting the IV classes, leading to the OOV or undefined classes being misclassified as IV ones with a high confidence score. To address this issue, this paper proposes a zero-shot OOV detector (OOVDet), a novel framework that effectively detects predefined classes while reliably rejecting undefined ones in zero-shot scenes. Specifically, due to the model's lack of prior knowledge about the distribution of OOV data, we synthesize region-level OOV prompts by sampling from the low-likelihood regions of the class-conditional Gaussian distributions in the hidden space, motivated by the assumption that unknown semantics are more likely to emerge in low-density areas of the latent space. For OOV images, we further propose a Dirichlet-based gradient attribution mechanism to mine pseudo-OOV image samples, where the attribution gradients are interpreted as Dirichlet evidence to estimate prediction uncertainty, and samples with high uncertainty are selected as pseudo-OOV images. Building on these synthesized OOV prompts and pseudo-OOV images, we construct the OOV decision boundary through a low-density prior constraint, which regularizes the optimization of OOV classes using Gaussian kernel density estimation in accordance with the above assumption. Experimental results show that our method significantly improves the OOV detection performance in zero-shot scenes. The code is available at https://github.com/binyisu/OOV-detector.

---

### Visual Personalization Turing Test

Authors: Rameen Abdal, James Burgess, Sergey Tulyakov, Kuan-Chieh Jackson Wang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22680v1

We introduce the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization based on perceptual indistinguishability, rather than identity replication. A model passes the VPTT if its output (image, video, 3D asset, etc.) is indistinguishable to a human or calibrated VLM judge from content a given person might plausibly create or share. To operationalize VPTT, we present the VPTT Framework, integrating a 10k-persona benchmark (VPTT-Bench), a visual retrieval-augmented generator (VPRAG), and the VPTT Score, a text-only metric calibrated against human and VLM judgments. We show high correlation across human, VLM, and VPTT evaluations, validating the VPTT Score as a reliable perceptual proxy. Experiments demonstrate that VPRAG achieves the best alignment-originality balance, offering a scalable and privacy-safe foundation for personalized generative AI.

---

### Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation

Authors: Youngjoong Kim, Duhoe Kim, Woosung Kim, Jaesik Park
Published: 2026-01-30
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2601.22679v2

Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch, motivating subsequent work to explain and stabilize these issues. While these efforts have provided valuable insights, the explanations remain fragmented, and the theoretical relationships remain unclear. In this work, we provide a theoretical examination of consistency models by analyzing them from a flow map-based perspective. This joint analysis clarifies how training stability and convergence behavior can give rise to degenerate solutions. Building on these insights, we revisit self-distillation as a practical remedy for certain forms of suboptimal convergence and reformulate it to avoid excessive gradient norms for stable optimization. We demonstrate that our strategy extends beyond image generation to diffusion-based policy learning, without reliance on pretrained diffusion models for initialization, illustrating its broader applicability.

---

### Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective

Authors: Mengfan Liu, Da Zheng, Junwei Su, Chuan Wu
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22678v3

Full-graph and mini-batch Graph Neural Network (GNN) training approaches have distinct system design demands, making it crucial to choose the appropriate approach to develop. A core challenge in comparing these two GNN training approaches lies in characterizing their model performance (i.e., convergence and generalization) and computational efficiency. While a batch size has been an effective lens in analyzing such behaviors in deep neural networks (DNNs), GNNs extend this lens by introducing a fan-out size, as full-graph training can be viewed as mini-batch training with the largest possible batch size and fan-out size. However, the impact of the batch and fan-out size for GNNs remains insufficiently explored. To this end, this paper systematically compares full-graph vs. mini-batch training of GNNs through empirical and theoretical analyses from the view points of the batch size and fan-out size. Our key contributions include: 1) We provide a novel generalization analysis using the Wasserstein distance to study the impact of the graph structure, especially the fan-out size. 2) We uncover the non-isotropic effects of the batch size and the fan-out size in GNN convergence and generalization, providing practical guidance for tuning these hyperparameters under resource constraints. Finally, full-graph training does not always yield better model performance or computational efficiency than well-tuned smaller mini-batch settings. The implementation can be found in the github link: https://github.com/LIUMENGFAN-gif/GNN_fullgraph_minibatch_training.

---

### Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition

Authors: Shuhan Ye, Yuanbin Qian, Yi Yu, Chong Wang, Yuqi Xie, Jiazhen Xu, Kun Wang, Xudong Jiang
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22675v1

Spiking neural networks (SNNs) have gained traction in vision due to their energy efficiency, bio-plausibility, and inherent temporal processing. Yet, despite this temporal capacity, most progress concentrates on static image benchmarks, and SNNs still underperform on dynamic video tasks compared to artificial neural networks (ANNs). In this work, we diagnose a fundamental pass-band mismatch: Standard spiking dynamics behave as a temporal low pass that emphasizes static content while attenuating motion bearing bands, where task relevant information concentrates in dynamic tasks. This phenomenon explains why SNNs can approach ANNs on static tasks yet fall behind on tasks that demand richer temporal understanding.To remedy this, we propose the Pass-Bands Optimizer (PBO), a plug-and-play module that optimizes the temporal pass-band toward task-relevant motion bands. PBO introduces only two learnable parameters, and a lightweight consistency constraint that preserves semantics and boundaries, incurring negligible computational overhead and requires no architectural changes. PBO deliberately suppresses static components that contribute little to discrimination, effectively high passing the stream so that spiking activity concentrates on motion bearing content. On UCF101, PBO yields over ten percentage points improvement. On more complex multi-modal action recognition and weakly supervised video anomaly detection, PBO delivers consistent and significant gains, offering a new perspective for SNN based video processing and understanding.

---

### VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

Authors: Hanxun Yu, Wentong Li, Xuan Qu, Song Wang, Junbo Chen, Jianke Zhu
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22674v3

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline components and often neglect textual alignment, leading to performance degradation. In this paper, we propose VisionTrim, a unified framework for training-free MLLM acceleration, integrating two effective plug-and-play modules: 1) the Dominant Vision Token Selection (DVTS) module, which preserves essential visual tokens via a global-local view, and 2) the Text-Guided Vision Complement (TGVC) module, which facilitates context-aware token merging guided by textual cues. Extensive experiments across diverse image and video multimodal benchmarks demonstrate the performance superiority of our VisionTrim, advancing practical MLLM deployment in real-world applications. The code is available at: https://github.com/hanxunyu/VisionTrim.

---

### Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning

Authors: Youngjoon Lee, Hyukjoon Lee, Seungrok Jung, Andy Luo, Jinu Gong, Yang Cao, Joonhyuk Kang
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22669v3

Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data. However, reliance on fixed global rounds or validation data for hyperparameter tuning hinders practical deployment by incurring high computational costs and privacy risks. To address this, we propose a data-free early stopping framework that determines the optimal stopping point by monitoring the task vector's growth rate using only server-side parameters. The numerical results on skin lesion/blood cell/colon pathology classification demonstrate that our approach is comparable to the validation-based early stopping across various state-of-the-art FL methods. In particular, the proposed framework requires an average of 45/12/31 (skin lesion/blood cell/colon pathology) additional rounds to achieve over 12.3%/8.9%/3.9% higher performance than early stopping based on validation data. Moreover, the proposed framework requires only 9/8/14 additional rounds to screen bad configurations, which is less than 3% of the fixed-round budget. To the best of our knowledge, this is the first work to propose a data-free early stopping framework for FL methods. Our code is available at this open repository.

---

### From Horizontal Layering to Vertical Integration: A Comparative Study of the AI-Driven Software Development Paradigm

Authors: Chi Zhang, Zehan Li, Ziqian Zhong, Haibing Ma, Dan Xiao, Chen Lin, Ming Dong
Published: 2026-01-30
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.22667v1

This paper examines the organizational implications of Generative AI adoption in software engineering through a multiple-case comparative study. We contrast two development environments: a traditional enterprise (brownfield) and an AI-native startup (greenfield). Our analysis reveals that transitioning from Horizontal Layering (functional specialization) to Vertical Integration (end-to-end ownership) yields 8-fold to 33-fold reductions in resource consumption. We attribute these gains to the emergence of Super Employees, AI-augmented engineers who span traditional role boundaries, and the elimination of inter-functional coordination overhead. Theoretically, we propose Human-AI Collaboration Efficacy as the primary optimization target for engineering organizations, supplanting individual productivity metrics. Our Total Factor Productivity analysis identifies an AI Distortion Effect that diminishes returns to labor scale while amplifying technological leverage. We conclude with managerial strategies for organizational redesign, including the reactivation of idle cognitive bandwidth in senior engineers and the suppression of blind scale expansion.

---

### ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding

Authors: Junyi Hu, Tian Bai, Fengyi Wu, Wenyan Li, Zhenming Peng, Yi Zhang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22666v1

Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with explicit supervision or heavy cross-attention designs. We propose ExpAlign, a theoretically grounded vision-language alignment framework built on a principled multiple instance learning formulation. ExpAlign introduces an Expectation Alignment Head that performs attention-based soft MIL pooling over token-region similarities, enabling implicit token and instance selection without additional annotations. To further stabilize alignment learning, we develop an energy-based multi-scale consistency regularization scheme, including a Top-K multi-positive contrastive objective and a Geometry-Aware Consistency Objective derived from a Lagrangian-constrained free-energy minimization. Extensive experiments show that ExpAlign consistently improves open-vocabulary detection and zero-shot instance segmentation, particularly on long-tail categories. Most notably, it achieves 36.2 AP$_r$ on the LVIS minival split, outperforming other state-of-the-art methods at comparable model scale, while remaining lightweight and inference-efficient.

---