# Research Papers — 2025-11 · bundle page 101 of 197

> Full-text markdown of papers #5001–5050 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/101
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/100.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/102.md)

### Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting

Authors: Zuqi Huang, Mengxin Tian, Huan Liu, Wentao Li, Baobao Liang, Jie Wu, Fang Yan, Zhaoqing Tang, Zhongyu Li
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12588v1

Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to the chromogen overlap, variable biomarker staining, and diverse cellular morphologies. Regression-based counting methods offer advantages over detection-based ones in handling overlapped cells, yet rarely support end-to-end multi-class counting. Moreover, the potential of foundation models remains largely underexplored in this paradigm. To address these limitations, we propose a rank-aware agglomeration framework that selectively distills knowledge from multiple strong foundation models, leveraging their complementary representations to handle IHC heterogeneity and obtain a compact yet effective student model, CountIHC. Unlike prior task-agnostic agglomeration strategies that either treat all teachers equally or rely on feature similarity, we design a Rank-Aware Teacher Selecting (RATS) strategy that models global-to-local patch rankings to assess each teacher's inherent counting capacity and enable sample-wise teacher selection. For multi-class cell counting, we introduce a fine-tuning stage that reformulates the task as vision-language alignment. Discrete semantic anchors derived from structured text prompts encode both category and quantity information, guiding the regression of class-specific density maps and improving counting for overlapping cells. Extensive experiments demonstrate that CountIHC surpasses state-of-the-art methods across 12 IHC biomarkers and 5 tissue types, while exhibiting high agreement with pathologists' assessments. Its effectiveness on H&E-stained data further confirms the scalability of the proposed method.

---

### MMWOZ: Building Multimodal Agent for Task-oriented Dialogue

Authors: Pu-Hai Yang, Heyan Huang, Heng-Da Xu, Fanshu Sun, Xian-Ling Mao, Chaoxu Mu
Published: 2025-11-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.12586v1

Task-oriented dialogue systems have garnered significant attention due to their conversational ability to accomplish goals, such as booking airline tickets for users. Traditionally, task-oriented dialogue systems are conceptualized as intelligent agents that interact with users using natural language and have access to customized back-end APIs. However, in real-world scenarios, the widespread presence of front-end Graphical User Interfaces (GUIs) and the absence of customized back-end APIs create a significant gap for traditional task-oriented dialogue systems in practical applications. In this paper, to bridge the gap, we collect MMWOZ, a new multimodal dialogue dataset that is extended from MultiWOZ 2.3 dataset. Specifically, we begin by developing a web-style GUI to serve as the front-end. Next, we devise an automated script to convert the dialogue states and system actions from the original dataset into operation instructions for the GUI. Lastly, we collect snapshots of the web pages along with their corresponding operation instructions. In addition, we propose a novel multimodal model called MATE (Multimodal Agent for Task-oriEnted dialogue) as the baseline model for the MMWOZ dataset. Furthermore, we conduct comprehensive experimental analysis using MATE to investigate the construction of a practical multimodal agent for task-oriented dialogue.

---

### LMM-IR: Large-Scale Netlist-Aware Multimodal Framework for Static IR-Drop Prediction

Authors: Kai Ma, Zhen Wang, Hongquan He, Qi Xu, Tinghuan Chen, Hao Geng
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12581v2

Static IR drop analysis is a fundamental and critical task in the field of chip design. Nevertheless, this process can be quite time-consuming, potentially requiring several hours. Moreover, addressing IR drop violations frequently demands iterative analysis, thereby causing the computational burden. Therefore, fast and accurate IR drop prediction is vital for reducing the overall time invested in chip design. In this paper, we firstly propose a novel multimodal approach that efficiently processes SPICE files through large-scale netlist transformer (LNT). Our key innovation is representing and processing netlist topology as 3D point cloud representations, enabling efficient handling of netlist with up to hundreds of thousands to millions nodes. All types of data, including netlist files and image data, are encoded into latent space as features and fed into the model for static voltage drop prediction. This enables the integration of data from multiple modalities for complementary predictions. Experimental results demonstrate that our proposed algorithm can achieve the best F1 score and the lowest MAE among the winning teams of the ICCAD 2023 contest and the state-of-the-art algorithms.

---

### Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models

Authors: Yongwen Ren, Chao Wang, Peng Du, Chuan Qin, Dazhong Shen, Hui Xiong
Published: 2025-11-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.12579v1

Recent advances in pretrained language models (PLMs) have significantly improved conversational recommender systems (CRS), enabling more fluent and context-aware interactions. To further enhance accuracy and mitigate hallucination, many methods integrate PLMs with knowledge graphs (KGs), but face key challenges: failing to fully exploit PLM reasoning over graph relationships, indiscriminately incorporating retrieved knowledge without context filtering, and neglecting collaborative preferences in multi-turn dialogues. To this end, we propose PCRS-TKA, a prompt-based framework employing retrieval-augmented generation to integrate PLMs with KGs. PCRS-TKA constructs dialogue-specific knowledge trees from KGs and serializes them into texts, enabling structure-aware reasoning while capturing rich entity semantics. Our approach selectively filters context-relevant knowledge and explicitly models collaborative preferences using specialized supervision signals. A semantic alignment module harmonizes heterogeneous inputs, reducing noise and enhancing accuracy. Extensive experiments demonstrate that PCRS-TKA consistently outperforms all baselines in both recommendation and conversational quality.

---

### TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction

Authors: Yukuo Ma, Cong Liu, Junke Wang, Junqi Liu, Haibin Huang, Zuxuan Wu, Chi Zhang, Xuelong Li
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12578v3

We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then progressively increase the frame rate to refine visual details and motion continuity. During generation, TempoMaster employs bidirectional attention within each frame-rate level while performing autoregression across frame rates, thus achieving long-range temporal coherence while enabling efficient and parallel synthesis. Extensive experiments demonstrate that TempoMaster establishes a new state-of-the-art in long video generation, excelling in both visual and temporal quality.

---

### Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection

Authors: Jiayi Zhu, Yihao Huang, Yue Cao, Xiaojun Jia, Qing Guo, Felix Juefei-Xu, Geguang Pu, Bin Wang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12575v1

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image perturbations provide a potential direction for geo-privacy protection, they require relatively strong distortions to be effective against LVLMs, which noticeably degrade visual quality and diminish an image's value for sharing. To overcome this limitation, we identify typographical attacks as a promising direction for protecting geo-privacy by adding text extension outside the visual content. We further investigate which textual semantics are effective in disrupting geolocation inference and design a two-stage, semantics-aware typographical attack that generates deceptive text to protect user privacy. Extensive experiments across three datasets demonstrate that our approach significantly reduces geolocation prediction accuracy of five state-of-the-art commercial LVLMs, establishing a practical and visually-preserving protection strategy against emerging geo-privacy threats.

---

### Mitigating Length Bias in RLHF through a Causal Lens

Authors: Hyeonji Kim, Sujeong Oh, Sanghack Lee
Published: 2025-11-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.12573v1

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF-trained reward models often exhibit length bias -- a systematic tendency to favor longer responses by conflating verbosity with quality. We propose a causal framework for analyzing and mitigating length bias in RLHF reward modeling. Central to our approach is a counterfactual data augmentation method that generates response pairs designed to isolate content quality from verbosity. These counterfactual examples are then used to train the reward model, enabling it to assess responses based on content quality independently of verbosity. Specifically, we construct (1) length-divergent pairs with similar content and (2) content-divergent pairs of similar length. Empirical evaluations show that our method reduces length bias in reward assignment and leads to more concise, content-focused outputs from the policy model. These findings demonstrate that the proposed approach effectively reduces length bias and improves the robustness and content sensitivity of reward modeling in RLHF pipelines.

---

### Through-Foliage Surface-Temperature Reconstruction for Early Wildfire Detection

Authors: Mohamed Youssef, Lukas Brunner, Klaus Rundhammer, Gerald Czech, Oliver Bimber
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12572v2

We present a method to reconstruct surface temperatures through forest vegetation by combining signal processing and machine learning, enabling fully automated aerial wildfire monitoring with drones for early fire detection. Synthetic aperture (SA) sensing reduces canopy occlusion but introduces thermal blur. To overcome this, we train a visual state space model to recover subtle thermal signals of partially occluded soil and fire hotspots from blurred data. To address limited real-world training data, we generate realistic surface temperature simulations using a latent diffusion model, temperature augmentation, and procedural thermal forest modeling. On simulated datasets, our method reduces RMSE by 2-2.5 versus conventional thermal and uncorrected SA imaging; in field experiments on hotspots, RMSE improved by 12.8-fold and 2.6-fold, respectively. Our approach also generalizes to other thermal signals, including human signatures, capturing morphology and extent -- critical where simple thresholding fails -- while conventional imaging struggles with partial occlusion.

---

### Enhancing Machine Learning Model Efficiency through Quantization and Bit Depth Optimization: A Performance Analysis on Healthcare Data

Authors: Mitul Goswami, Romit Chatterjee
Published: 2025-11-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.12568v1

This research aims to optimize intricate learning models by implementing quantization and bit-depth optimization techniques. The objective is to significantly cut time complexity while preserving model efficiency, thus addressing the challenge of extended execution times in intricate models. Two medical datasets were utilized as case studies to apply a Logistic Regression (LR) machine learning model. Using efficient quantization and bit depth optimization strategies the input data is downscaled from float64 to float32 and int32. The results demonstrated a significant reduction in time complexity, with only a minimal decrease in model accuracy post-optimization, showcasing the state-of-the-art optimization approach. This comprehensive study concludes that the impact of these optimization techniques varies depending on a set of parameters.

---

### A Content-Preserving Secure Linguistic Steganography

Authors: Lingyun Xiang, Chengfu Ou, Xu He, Zhongliang Yang, Yuling Liu
Published: 2025-11-16
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2511.12565v2

Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks in real-world applications. To address this challenge, we propose a content-preserving linguistic steganography paradigm for perfectly secure covert communication without modifying the cover text. Based on this paradigm, we introduce CLstega (\textit{C}ontent-preserving \textit{L}inguistic \textit{stega}nography), a novel method that embeds secret messages through controllable distribution transformation. CLstega first applies an augmented masking strategy to locate and mask embedding positions, where MLM(masked language model)-predicted probability distributions are easily adjustable for transformation. Subsequently, a dynamic distribution steganographic coding strategy is designed to encode secret messages by deriving target distributions from the original probability distributions. To achieve this transformation, CLstega elaborately selects target words for embedding positions as labels to construct a masked sentence dataset, which is used to fine-tune the original MLM, producing a target MLM capable of directly extracting secret messages from the cover text. This approach ensures perfect security of secret messages while fully preserving the integrity of the original cover text. Experimental results show that CLstega can achieve a 100\% extraction success rate, and outperforms existing methods in security, effectively balancing embedding capacity and security.

---

### Linear time small coresets for k-mean clustering of segments with applications

Authors: David Denisov, Shlomi Dolev, Dan Felmdan, Michael Segal
Published: 2025-11-16
Categories: cs.LG, cs.CG, cs.CV
arXiv: https://arxiv.org/abs/2511.12564v2

We study the $k$-means problem for a set $\mathcal{S} \subseteq \mathbb{R}^d$ of $n$ segments, aiming to find $k$ centers $X \subseteq \mathbb{R}^d$ that minimize $D(\mathcal{S},X) := \sum_{S \in \mathcal{S}} \min_{x \in X} D(S,x)$, where $D(S,x) := \int_{p \in S} |p - x| dp$ measures the total distance from each point along a segment to a center. Variants of this problem include handling outliers, employing alternative distance functions such as M-estimators, weighting distances to achieve balanced clustering, or enforcing unique cluster assignments. For any $\varepsilon > 0$, an $\varepsilon$-coreset is a weighted subset $C \subseteq \mathbb{R}^d$ that approximates $D(\mathcal{S},X)$ within a factor of $1 \pm \varepsilon$ for any set of $k$ centers, enabling efficient streaming, distributed, or parallel computation. We propose the first coreset construction that provably handles arbitrary input segments. For constant $k$ and $\varepsilon$, it produces a coreset of size $O(\log^2 n)$ computable in $O(nd)$ time. Experiments, including a real-time video tracking application, demonstrate substantial speedups with minimal loss in clustering accuracy, confirming both the practical efficiency and theoretical guarantees of our method.

---

### LOBERT: Generative AI Foundation Model for Limit Order Book Messages

Authors: Eljas Linna, Kestutis Baltakys, Alexandros Iosifidis, Juho Kanniainen
Published: 2025-11-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.12563v2

Modeling the dynamics of financial Limit Order Books (LOB) at the message level is challenging due to irregular event timing, rapid regime shifts, and the reactions of high-frequency traders to visible order flow. Previous LOB models require cumbersome data representations and lack adaptability outside their original tasks, leading us to introduce LOBERT, a general-purpose encoder-only foundation model for LOB data suitable for downstream fine-tuning. LOBERT adapts the original BERT architecture for LOB data by using a novel tokenization scheme that treats complete multi-dimensional messages as single tokens while retaining continuous representations of price, volume, and time. With these methods, LOBERT achieves leading performance in tasks such as predicting mid-price movements and next messages, while reducing the required context length compared to previous methods.

---

### SEMC: Structure-Enhanced Mixture-of-Experts Contrastive Learning for Ultrasound Standard Plane Recognition

Authors: Qing Cai, Guihao Yan, Fan Zhang, Cheng Zhang, Zhi Liu
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12559v1

Ultrasound standard plane recognition is essential for clinical tasks such as disease screening, organ evaluation, and biometric measurement. However, existing methods fail to effectively exploit shallow structural information and struggle to capture fine-grained semantic differences through contrastive samples generated by image augmentations, ultimately resulting in suboptimal recognition of both structural and discriminative details in ultrasound standard planes. To address these issues, we propose SEMC, a novel Structure-Enhanced Mixture-of-Experts Contrastive learning framework that combines structure-aware feature fusion with expert-guided contrastive learning. Specifically, we first introduce a novel Semantic-Structure Fusion Module (SSFM) to exploit multi-scale structural information and enhance the model's ability to perceive fine-grained structural details by effectively aligning shallow and deep features. Then, a novel Mixture-of-Experts Contrastive Recognition Module (MCRM) is designed to perform hierarchical contrastive learning and classification across multi-level features using a mixture-of-experts (MoE) mechanism, further improving class separability and recognition performance. More importantly, we also curate a large-scale and meticulously annotated liver ultrasound dataset containing six standard planes. Extensive experimental results on our in-house dataset and two public datasets demonstrate that SEMC outperforms recent state-of-the-art methods across various metrics.

---

### Training Instabilities Induce Flatness Bias in Gradient Descent

Authors: Lawrence Wang, Stephen J. Roberts
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12558v1

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss decreases monotonically. Yet, modern deep networks often achieve their best performance beyond this regime. We demonstrate that such instabilities induce an implicit bias in GD, driving parameters toward flatter regions of the loss landscape and thereby improving generalization. The key mechanism is the Rotational Polarity of Eigenvectors (RPE), a geometric phenomenon in which the leading eigenvectors of the Hessian rotate during training instabilities. These rotations, which increase with learning rates, promote exploration and provably lead to flatter minima. This theoretical framework extends to stochastic GD, where instability-driven flattening persists and its empirical effects outweigh minibatch noise. Finally, we show that restoring instabilities in Adam further improves generalization. Together, these results establish and understand the constructive role of training instabilities in deep learning.

---

### DLMMPR:Deep Learning-based Measurement Matrix for Phase Retrieval

Authors: Jing Liu, Bing Guo, Ren Zhu
Published: 2025-11-16
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2511.12556v1

This paper pioneers the integration of learning optimization into measurement matrix design for phase retrieval. We introduce the Deep Learning-based Measurement Matrix for Phase Retrieval (DLMMPR) algorithm, which parameterizes the measurement matrix within an end-to-end deep learning architecture. Synergistically augmented with subgradient descent and proximal mapping modules for robust recovery, DLMMPR's efficacy is decisively confirmed through comprehensive empirical validation across diverse noise regimes. Benchmarked against DeepMMSE and PrComplex, our method yields substantial gains in PSNR and SSIM, underscoring its superiority.

---

### EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis

Authors: Yijie Guo, Dexiang Hong, Weidong Chen, Zihan She, Cheng Ye, Xiaojun Chang, Zhendong Mao
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12554v2

Visual Emotion Analysis (VEA) aims to bridge the affective gap between visual content and human emotional responses. Despite its promise, progress in this field remains limited by the lack of open-source and interpretable datasets. Most existing studies assign a single discrete emotion label to an entire image, offering limited insight into how visual elements contribute to emotion. In this work, we introduce EmoVerse, a large-scale open-source dataset that enables interpretable visual emotion analysis through multi-layered, knowledge-graph-inspired annotations. By decomposing emotions into Background-Attribute-Subject (B-A-S) triplets and grounding each element to visual regions, EmoVerse provides word-level and subject-level emotional reasoning. With over 219k images, the dataset further includes dual annotations in Categorical Emotion States (CES) and Dimensional Emotion Space (DES), facilitating unified discrete and continuous emotion representation. A novel multi-stage pipeline ensures high annotation reliability with minimal human effort. Finally, we introduce an interpretable model that maps visual cues into DES representations and provides detailed attribution explanations. Together, the dataset, pipeline, and model form a comprehensive foundation for advancing explainable high-level emotion understanding.

---

### EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis

Authors: Yijie Guo, Dexiang Hong, Weidong Chen, Zihan She, Cheng Ye, Xiaojun Chang, Zhendong Mao
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12554v1

Visual Emotion Analysis (VEA) aims to bridge the affective gap between visual content and human emotional responses. Despite its promise, progress in this field remains limited by the lack of open-source and interpretable datasets. Most existing studies assign a single discrete emotion label to an entire image, offering limited insight into how visual elements contribute to emotion. In this work, we introduce EmoVerse, a large-scale open-source dataset that enables interpretable visual emotion analysis through multi-layered, knowledge-graph-inspired annotations. By decomposing emotions into Background-Attribute-Subject (B-A-S) triplets and grounding each element to visual regions, EmoVerse provides word-level and subject-level emotional reasoning. With over 219k images, the dataset further includes dual annotations in Categorical Emotion States (CES) and Dimensional Emotion Space (DES), facilitating unified discrete and continuous emotion representation. A novel multi-stage pipeline ensures high annotation reliability with minimal human effort. Finally, we introduce an interpretable model that maps visual cues into DES representations and provides detailed attribution explanations. Together, the dataset, pipeline, and model form a comprehensive foundation for advancing explainable high-level emotion understanding.

---

### CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching

Authors: Wenzhang Du
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12548v1

First-order optimizers are reliable but slow in sharp, anisotropic regions. We study a curvature-adaptive method that periodically sketches a low-rank Hessian subspace via Hessian--vector products and preconditions gradients only in that subspace, leaving the orthogonal complement first-order. For L-smooth non-convex objectives, we recover the standard O(1/T) stationarity guarantee with a widened stable stepsize range; under a Polyak--Lojasiewicz (PL) condition with bounded residual curvature outside the sketch, the loss contracts at refresh steps. On CIFAR-10/100 with ResNet-18/34, the method enters the low-loss region substantially earlier: measured by epochs to a pre-declared train-loss threshold (0.75), it reaches the threshold 2.95x faster than Adam on CIFAR-100/ResNet-18, while matching final test accuracy. The approach is one-knob: performance is insensitive to the sketch rank k across {1,3,5}, and k=0 yields a principled curvature-free ablation. We release anonymized logs and scripts that regenerate all figures and tables.

---

### HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models

Authors: Zhiguang Lu, Qianqian Xu, Peisong Wen, Siran Dai, Qingming Huang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12547v4

Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately capture the subtle, category-defining features critical for high fidelity. Standard approaches, such as text-based Classifier-Free Guidance (CFG), often lack the required specificity, potentially generating misleading examples that degrade fine-grained classifier performance. To address this, we propose Hierarchically Guided Fine-grained Augmentation (HiGFA). HiGFA leverages the temporal dynamics of the diffusion sampling process. It employs strong text and transformed contour guidance with fixed strengths in the early-to-mid sampling stages to establish overall scene, style, and structure. In the final sampling stages, HiGFA activates a specialized fine-grained classifier guidance and dynamically modulates the strength of all guidance signals based on prediction confidence. This hierarchical, confidence-driven orchestration enables HiGFA to generate diverse yet faithful synthetic images by intelligently balancing global structure formation with precise detail refinement. Experiments on several FGVC datasets demonstrate the effectiveness of HiGFA.

---

### HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models

Authors: Zhiguang Lu, Qianqian Xu, Peisong Wen, Siran Da, Qingming Huang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12547v1

Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately capture the subtle, category-defining features critical for high fidelity. Standard approaches, such as text-based Classifier-Free Guidance (CFG), often lack the required specificity, potentially generating misleading examples that degrade fine-grained classifier performance. To address this, we propose Hierarchically Guided Fine-grained Augmentation (HiGFA). HiGFA leverages the temporal dynamics of the diffusion sampling process. It employs strong text and transformed contour guidance with fixed strengths in the early-to-mid sampling stages to establish overall scene, style, and structure. In the final sampling stages, HiGFA activates a specialized fine-grained classifier guidance and dynamically modulates the strength of all guidance signals based on prediction confidence. This hierarchical, confidence-driven orchestration enables HiGFA to generate diverse yet faithful synthetic images by intelligently balancing global structure formation with precise detail refinement. Experiments on several FGVC datasets demonstrate the effectiveness of HiGFA.

---

### Center-Outward q-Dominance: A Sample-Computable Proxy for Strong Stochastic Dominance in Multi-Objective Optimisation

Authors: Robin van der Laag, Hao Wang, Thomas Bäck, Yingjie Fan
Published: 2025-11-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.12545v1

Stochastic multi-objective optimization (SMOOP) requires ranking multivariate distributions; yet, most empirical studies perform scalarization, which loses information and is unreliable. Based on the optimal transport theory, we introduce the center-outward q-dominance relation and prove it implies strong first-order stochastic dominance (FSD). Also, we develop an empirical test procedure based on q-dominance, and derive an explicit sample size threshold, $n^*(δ)$, to control the Type I error. We verify the usefulness of our approach in two scenarios: (1) as a ranking method in hyperparameter tuning; (2) as a selection method in multi-objective optimization algorithms. For the former, we analyze the final stochastic Pareto sets of seven multi-objective hyperparameter tuners on the YAHPO-MO benchmark tasks with q-dominance, which allows us to compare these tuners when the expected hypervolume indicator (HVI, the most common performance metric) of the Pareto sets becomes indistinguishable. For the latter, we replace the mean value-based selection in the NSGA-II algorithm with $q$-dominance, which shows a superior convergence rate on noise-augmented ZDT benchmark problems. These results establish center-outward q-dominance as a principled, tractable foundation for seeking truly stochastically dominant solutions for SMOOPs.

---

### FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration

Authors: Mukul Lokhande, Akash Sankhe, S. V. Jaya Chand, Santosh Kumar Vishvakarma
Published: 2025-11-16
Categories: cs.AR, cs.ET, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2511.12544v1

The growing demand for low-power and area-efficient TinyML inference on AIoT devices necessitates memory architectures that minimise data movement while sustaining high computational efficiency. This paper presents FERMI-ML, a Flexible and Resource-Efficient Memory-In-Situ (MIS) SRAM macro designed for TinyML acceleration. The proposed 9T XNOR-based RX9T bit-cell integrates a 5T storage cell with a 4T XNOR compute unit, enabling variable-precision MAC and CAM operations within the same array. A 22-transistor (C22T) compressor-tree-based accumulator facilitates logarithmic 1-64-bit MAC computation with reduced delay and power compared to conventional adder trees. The 4 KB macro achieves dual functionality for in-situ computation and CAM-based lookup operations, supporting Posit-4 or FP-4 precision. Post-layout results at 65 nm show operation at 350 MHz with 0.9 V, delivering a throughput of 1.93 TOPS and an energy efficiency of 364 TOPS/W, while maintaining a Quality-of-Result (QoR) above 97.5% with InceptionV4 and ResNet-18. FERMI-ML thus demonstrates a compact, reconfigurable, and energy-aware digital Memory-In-Situ macro capable of supporting mixed-precision TinyML workloads.

---

### Regret Guarantees for Linear Contextual Stochastic Shortest Path

Authors: Dor Polikar, Alon Cohen
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12534v1

We define the problem of linear Contextual Stochastic Shortest Path (CSSP), where at the beginning of each episode, the learner observes an adversarially chosen context that determines the MDP through a fixed but unknown linear function. The learner's objective is to reach a designated goal state with minimal expected cumulative loss, despite having no prior knowledge of the transition dynamics, loss functions, or the mapping from context to MDP. In this work, we propose LR-CSSP, an algorithm that achieves a regret bound of $\widetilde{O}(K^{2/3} d^{2/3} |S| |A|^{1/3} B_\star^2 T_\star \log (1/ δ))$, where $K$ is the number of episodes, $d$ is the context dimension, $S$ and $A$ are the sets of states and actions respectively, $B_\star$ bounds the optimal cumulative loss and $T_\star$, unknown to the learner, bounds the expected time for the optimal policy to reach the goal. In the case where all costs exceed $\ell_{\min}$, LR-CSSP attains a regret of $\widetilde O(\sqrt{K \cdot d^2 |S|^3 |A| B_\star^3 \log(1/δ)/\ell_{\min}})$. Unlike in contextual finite-horizon MDPs, where limited knowledge primarily leads to higher losses and regret, in the CSSP setting, insufficient knowledge can also prolong episodes and may even lead to non-terminating episodes. Our analysis reveals that LR-CSSP effectively handles continuous context spaces, while ensuring all episodes terminate within a reasonable number of time steps.

---

### ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding

Authors: Yuan Zhou, Litao Hua, Shilong Jin, Wentao Huang, Haoran Duan
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12530v1

Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on effective keyframes that are not only informative but also causally decisive. To this end, we propose Reinforced Causal Search with Information Bottleneck (ReaSon), a framework that formulates keyframe selection as an optimization problem with the help of a novel Causal Information Bottleneck (CIB), which explicitly defines keyframes as those satisfying both predictive sufficiency and causal necessity. Specifically, ReaSon employs a learnable policy network to select keyframes from a visually relevant pool of candidate frames to capture predictive sufficiency, and then assesses causal necessity via counterfactual interventions. Finally, a composite reward aligned with the CIB principle is designed to guide the selection policy through reinforcement learning. Extensive experiments on NExT-QA, EgoSchema, and Video-MME demonstrate that ReaSon consistently outperforms existing state-of-the-art methods under limited-frame settings, validating its effectiveness and generalization ability.

---

### Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing

Authors: Sanchaita Hazra, Doeun Lee, Bodhisattwa Prasad Majumder, Sachin Kumar
Published: 2025-11-16
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.12529v2

Large Language Models have seen expanding application across domains, yet their effectiveness as assistive tools for scientific writing - an endeavor requiring precision, multimodal synthesis, and domain expertise - remains insufficiently understood. We examine the potential of LLMs to support domain experts in scientific writing, with a focus on abstract composition. We design an incentivized randomized controlled trial with a hypothetical conference setup where participants with relevant expertise are split into an author and reviewer pool. Inspired by methods in behavioral science, our novel incentive structure encourages authors to edit the provided abstracts to an acceptable quality for a peer-reviewed submission. Our 2 x 2 between-subject design expands into two dimensions: the implicit source of the provided abstract and the disclosure of it. We find authors make most edits when editing human-written abstracts compared to AI-generated abstracts without source attribution, often guided by higher perceived readability in AI generation. Upon disclosure of source information, the volume of edits converges in both source treatments. Reviewer decisions remain unaffected by the source of the abstract, but bear a significant correlation with the number of edits made. Careful stylistic edits, especially in the case of AI-generated abstracts, in the presence of source information, improve the chance of acceptance. We find that AI-generated abstracts hold potential to reach comparable levels of acceptability to human-written ones with minimal revision, and that perceptions of AI authorship, rather than objective quality, drive much of the observed editing behavior. Our findings reverberate the significance of source disclosure in collaborative scientific writing.

---

### Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing

Authors: Sanchaita Hazra, Doeun Lee, Bodhisattwa Prasad Majumder, Sachin Kumar
Published: 2025-11-16
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.12529v1

Large Language Models have seen expanding application across domains, yet their effectiveness as assistive tools for scientific writing -- an endeavor requiring precision, multimodal synthesis, and domain expertise -- remains insufficiently understood. We examine the potential of LLMs to support domain experts in scientific writing, with a focus on abstract composition. We design an incentivized randomized controlled trial with a hypothetical conference setup where participants with relevant expertise are split into an author and reviewer pool. Inspired by methods in behavioral science, our novel incentive structure encourages authors to edit the provided abstracts to an acceptable quality for a peer-reviewed submission. Our 2x2 between-subject design expands into two dimensions: the implicit source of the provided abstract and the disclosure of it. We find authors make most edits when editing human-written abstracts compared to AI-generated abstracts without source attribution, often guided by higher perceived readability in AI generation. Upon disclosure of source information, the volume of edits converges in both source treatments. Reviewer decisions remain unaffected by the source of the abstract, but bear a significant correlation with the number of edits made. Careful stylistic edits, especially in the case of AI-generated abstracts, in the presence of source information, improve the chance of acceptance. We find that AI-generated abstracts hold potential to reach comparable levels of acceptability to human-written ones with minimal revision, and that perceptions of AI authorship, rather than objective quality, drive much of the observed editing behavior. Our findings reverberate the significance of source disclosure in collaborative scientific writing.

---

### D$^{2}$-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation

Authors: Zheyuan Zhang, Jiwei Zhang, Boyu Zhou, Linzhimeng Duan, Hong Chen
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12528v5

Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a geo-tagged reference database. Recently, the emergence of the powerful visual foundation model, DINOv2, trained in a self-supervised manner on massive datasets, has significantly improved VPR performance. This improvement stems from DINOv2's exceptional feature generalization capabilities but is often accompanied by increased model complexity and computational overhead that impede deployment on resource-constrained devices. To address this challenge, we propose $D^{2}$-VPR, a $D$istillation- and $D$eformable-based framework that retains the strong feature extraction capabilities of visual foundation models while significantly reducing model parameters and achieving a more favorable performance-efficiency trade-off. Specifically, first, we employ a two-stage training strategy that integrates knowledge distillation and fine-tuning. Additionally, we introduce a Distillation Recovery Module (DRM) to better align the feature spaces between the teacher and student models, thereby minimizing knowledge transfer losses to the greatest extent possible. Second, we design a Top-Down-attention-based Deformable Aggregator (TDDA) that leverages global semantic features to dynamically and adaptively adjust the Regions of Interest (ROI) used for aggregation, thereby improving adaptability to irregular structures. Extensive experiments demonstrate that our method achieves competitive performance compared to state-of-the-art approaches. Meanwhile, it reduces the parameter count by approximately 64.2% (compared to CricaVPR).Code is available at https://github.com/tony19980810/D2VPR.

---

### D$^{2}$-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation

Authors: Zheyuan Zhang, Jiwei Zhang, Boyu Zhou, Linzhimeng Duan, Hong Chen
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12528v1

Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a geo-tagged reference database. Recently, the emergence of the powerful visual foundation model, DINOv2, trained in a self-supervised manner on massive datasets, has significantly improved VPR performance. This improvement stems from DINOv2's exceptional feature generalization capabilities but is often accompanied by increased model complexity and computational overhead that impede deployment on resource-constrained devices. To address this challenge, we propose $D^{2}$-VPR, a $D$istillation- and $D$eformable-based framework that retains the strong feature extraction capabilities of visual foundation models while significantly reducing model parameters and achieving a more favorable performance-efficiency trade-off. Specifically, first, we employ a two-stage training strategy that integrates knowledge distillation and fine-tuning. Additionally, we introduce a Distillation Recovery Module (DRM) to better align the feature spaces between the teacher and student models, thereby minimizing knowledge transfer losses to the greatest extent possible. Second, we design a Top-Down-attention-based Deformable Aggregator (TDDA) that leverages global semantic features to dynamically and adaptively adjust the Regions of Interest (ROI) used for aggregation, thereby improving adaptability to irregular structures. Extensive experiments demonstrate that our method achieves competitive performance compared to state-of-the-art approaches. Meanwhile, it reduces the parameter count by approximately 64.2% and FLOPs by about 62.6% (compared to CricaVPR).Code is available at https://github.com/tony19980810/D2VPR.

---

### MdaIF: Robust One-Stop Multi-Degradation-Aware Image Fusion with Language-Driven Semantics

Authors: Jing Li, Yifan Wang, Jiafeng Yan, Renlong Zhang, Bin Yang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12525v1

Infrared and visible image fusion aims to integrate complementary multi-modal information into a single fused result. However, existing methods 1) fail to account for the degradation visible images under adverse weather conditions, thereby compromising fusion performance; and 2) rely on fixed network architectures, limiting their adaptability to diverse degradation scenarios. To address these issues, we propose a one-stop degradation-aware image fusion framework for multi-degradation scenarios driven by a large language model (MdaIF). Given the distinct scattering characteristics of different degradation scenarios (e.g., haze, rain, and snow) in atmospheric transmission, a mixture-of-experts (MoE) system is introduced to tackle image fusion across multiple degradation scenarios. To adaptively extract diverse weather-aware degradation knowledge and scene feature representations, collectively referred to as the semantic prior, we employ a pre-trained vision-language model (VLM) in our framework. Guided by the semantic prior, we propose degradation-aware channel attention module (DCAM), which employ degradation prototype decomposition to facilitate multi-modal feature interaction in channel domain. In addition, to achieve effective expert routing, the semantic prior and channel-domain modulated features are utilized to guide the MoE, enabling robust image fusion in complex degradation scenarios. Extensive experiments validate the effectiveness of our MdaIF, demonstrating superior performance over SOTA methods.

---

### Perturbing Best Responses in Zero-Sum Games

Authors: Adam Dziwoki, Rostislav Horcik
Published: 2025-11-16
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2511.12523v1

This paper investigates the impact of perturbations on the best-response-based algorithms approximating Nash equilibria in zero-sum games, namely Double Oracle and Fictitious Play. More precisely, we assume that the oracle computing the best responses perturbs the utilities before selecting the best response. We show that using such an oracle reduces the number of iterations for both algorithms. For some cases, suitable perturbations ensure the expected number of iterations is logarithmic. Although the utility perturbation is computationally demanding as it requires iterating through all pure strategies, we demonstrate that one can efficiently perturb the utilities in games where pure strategies have further inner structure.

---

### TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction

Authors: Jie Zhang, Bo Tang, Wanzi Shao, Wenqiang Wei, Jihao Zhao, Jianqing Zhu, Zhiyu li, Wen Xi, Zehao Lin, Feiyu Xiong, Yanchao Tan
Published: 2025-11-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.12520v1

Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations and broken reasoning chains. Moreover, traditional RAG retrieves unstructured knowledge, introducing irrelevant details that hinder accurate reasoning. To address these issues, we propose TAdaRAG, a novel RAG framework for on-the-fly task-adaptive knowledge graph construction from external sources. Specifically, we design an intent-driven routing mechanism to a domain-specific extraction template, followed by supervised fine-tuning and a reinforcement learning-based implicit extraction mechanism, ensuring concise, coherent, and non-redundant knowledge integration. Evaluations on six public benchmarks and a real-world business benchmark (NowNewsQA) across three backbone models demonstrate that TAdaRAG outperforms existing methods across diverse domains and long-text tasks, highlighting its strong generalization and practical effectiveness.

---

### xLSTM-PINN: Memory-Gated Spectral Remodeling for Physics-Informed Learning

Authors: Ze Tao, Darui Zhao, Fujun Liu, Ke Xu, Xiangsheng Hu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12512v2

Physics-informed neural networks (PINN) face significant challenges from spectral bias, which impedes their ability to model high-frequency phenomena and limits extrapolation performance. To address this, we introduce xLSTM-PINN, a novel architecture that performs representation-level spectral remodeling through memory gating and residual micro-steps. Our method consistently achieves markedly lower spectral error and root mean square error (RMSE) across four diverse partial differential equation (PDE) benchmarks, along withhhh a broader stable learning-rate window. Frequency-domain analysis confirms that xLSTM-PINN elevates high-frequency kernel weights, shifts the resolvable bandwidth rightward, and shortens the convergence time for high-wavenumber components. Without modifying automatic differentiation or physics loss constraints, this work provides a robust pathway to suppress spectral bias, thereby improving accuracy, reproducibility, and transferability in physics-informed learning.

---

### Spectral Bias Mitigation via xLSTM-PINN: Memory-Gated Representation Refinement for Physics-Informed Learning

Authors: Ze Tao, Darui Zhao, Fujun Liu, Ke Xu, Xiangsheng Hu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12512v1

Physics-informed learning for PDEs is surging across scientific computing and industrial simulation, yet prevailing methods face spectral bias, residual-data imbalance, and weak extrapolation. We introduce a representation-level spectral remodeling xLSTM-PINN that combines gated-memory multiscale feature extraction with adaptive residual-data weighting to curb spectral bias and strengthen extrapolation. Across four benchmarks, we integrate gated cross-scale memory, a staged frequency curriculum, and adaptive residual reweighting, and verify with analytic references and extrapolation tests, achieving markedly lower spectral error and RMSE and a broader stable learning-rate window. Frequency-domain benchmarks show raised high-frequency kernel weights and a right-shifted resolvable bandwidth, shorter high-k error decay and time-to-threshold, and narrower error bands with lower MSE, RMSE, MAE, and MaxAE. Compared with the baseline PINN, we reduce MSE, RMSE, MAE, and MaxAE across all four benchmarks and deliver cleaner boundary transitions with attenuated high-frequency ripples in both frequency and field maps. This work suppresses spectral bias, widens the resolvable band and shortens the high-k time-to-threshold under the same budget, and without altering AD or physics losses improves accuracy, reproducibility, and transferability.

---

### DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection

Authors: Jialiang Shen, Jiyang Zheng, Yunqi Xue, Huajie Chen, Yu Yao, Hui Kang, Ruiqi Liu, Helin Gong, Yang Yang, Dadong Wang, Tongliang Liu
Published: 2025-11-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.12511v2

With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection.

---

### DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection

Authors: Jialiang Shen, Jiyang Zheng, Yunqi Xue, Huajie Chen, Yu Yao, Hui Kang, Ruiqi Liu, Helin Gong, Yang Yang, Dadong Wang, Tongliang Liu
Published: 2025-11-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.12511v1

With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection.

---

### Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning

Authors: Jingtian Ma, Jingyuan Wang, Leong Hou U
Published: 2025-11-16
Categories: cs.LG, cs.GR
arXiv: https://arxiv.org/abs/2511.12507v1

Road networks are critical infrastructures underpinning intelligent transportation systems and their related applications. Effective representation learning of road networks remains challenging due to the complex interplay between spatial structures and frequency characteristics in traffic patterns. Existing graph neural networks for modeling road networks predominantly fall into two paradigms: spatial-based methods that capture local topology but tend to over-smooth representations, and spectral-based methods that analyze global frequency components but often overlook localized variations. This spatial-spectral misalignment limits their modeling capacity for road networks exhibiting both coarse global trends and fine-grained local fluctuations. To bridge this gap, we propose HiFiNet, a novel hierarchical frequency-decomposition graph neural network that unifies spatial and spectral modeling. HiFiNet constructs a multi-level hierarchy of virtual nodes to enable localized frequency analysis, and employs a decomposition-updating-reconstruction framework with a topology-aware graph transformer to separately model and fuse low- and high-frequency signals. Theoretically justified and empirically validated on multiple real-world datasets across four downstream tasks, HiFiNet demonstrates superior performance and generalization ability in capturing effective road network representations.

---

### QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs

Authors: Maria Tseytlin, Paul Roit, Omri Abend, Ido Dagan, Ayal Klein
Published: 2025-11-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.12504v1

Decomposing sentences into fine-grained meaning units is increasingly used to model semantic alignment. While QA-based semantic approaches have shown effectiveness for representing predicate-argument relations, they have so far left noun-centered semantics largely unaddressed. We introduce QA-Noun, a QA-based framework for capturing noun-centered semantic relations. QA-Noun defines nine question templates that cover both explicit syntactical and implicit contextual roles for nouns, producing interpretable QA pairs that complement verbal QA-SRL. We release detailed guidelines, a dataset of over 2,000 annotated noun mentions, and a trained model integrated with QA-SRL to yield a unified decomposition of sentence meaning into individual, highly fine-grained, facts. Evaluation shows that QA-Noun achieves near-complete coverage of AMR's noun arguments while surfacing additional contextually implied relations, and that combining QA-Noun with QA-SRL yields over 130\% higher granularity than recent fact-based decomposition methods such as FactScore and DecompScore. QA-Noun thus complements the broader QA-based semantic framework, forming a comprehensive and scalable approach to fine-grained semantic decomposition for cross-text alignment.

---

### Visible Structure Retrieval for Lightweight Image-Based Relocalisation

Authors: Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12503v1

Accurate camera pose estimation from an image observation in a previously mapped environment is commonly done through structure-based methods: by finding correspondences between 2D keypoints on the image and 3D structure points in the map. In order to make this correspondence search tractable in large scenes, existing pipelines either rely on search heuristics, or perform image retrieval to reduce the search space by comparing the current image to a database of past observations. However, these approaches result in elaborate pipelines or storage requirements that grow with the number of past observations. In this work, we propose a new paradigm for making structure-based relocalisation tractable. Instead of relying on image retrieval or search heuristics, we learn a direct mapping from image observations to the visible scene structure in a compact neural network. Given a query image, a forward pass through our novel visible structure retrieval network allows obtaining the subset of 3D structure points in the map that the image views, thus reducing the search space of 2D-3D correspondences. We show that our proposed method enables performing localisation with an accuracy comparable to the state of the art, while requiring lower computational and storage footprint.

---

### BSO: Binary Spiking Online Optimization Algorithm

Authors: Yu Liang, Yu Yang, Wenjie Wei, Ammar Belatreche, Shuai Wang, Malu Zhang, Yang Yang
Published: 2025-11-16
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.12502v1

Binary Spiking Neural Networks (BSNNs) offer promising efficiency advantages for resource-constrained computing. However, their training algorithms often require substantial memory overhead due to latent weights storage and temporal processing requirements. To address this issue, we propose Binary Spiking Online (BSO) optimization algorithm, a novel online training algorithm that significantly reduces training memory. BSO directly updates weights through flip signals under the online training framework. These signals are triggered when the product of gradient momentum and weights exceeds a threshold, eliminating the need for latent weights during training. To enhance performance, we propose T-BSO, a temporal-aware variant that leverages the inherent temporal dynamics of BSNNs by capturing gradient information across time steps for adaptive threshold adjustment. Theoretical analysis establishes convergence guarantees for both BSO and T-BSO, with formal regret bounds characterizing their convergence rates. Extensive experiments demonstrate that both BSO and T-BSO achieve superior optimization performance compared to existing training methods for BSNNs. The codes are available at https://github.com/hamings1/BSO.

---

### Iris: First-Class Multi-GPU Programming Experience in Triton

Authors: Muhammad Awad, Muhammad Osama, Brandon Potter
Published: 2025-11-16
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2511.12500v1

Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on low-level HIP/CUDA communication libraries that demand substantial engineering effort for even basic overlap patterns, while simpler abstractions often sacrifice performance. We present Iris, a multi-GPU communication library implemented entirely in Python and Triton that eliminates this trade-off. Iris provides tile-based symmetric memory abstractions that naturally align with Triton's programming model, enabling developers to write single-source kernels that seamlessly interleave computation and communication. We demonstrate a taxonomy of compute-communication overlap patterns--from bulk-synchronous to fine-grained workgroup specialization--that can be implemented with minimal code changes in Iris, often requiring just a few additional lines within the same Triton kernel. Our evaluation shows that Iris achieves near-optimal bandwidth utilization in microbenchmarks and delivers up to 1.79x speedup over PyTorch and RCCL for GEMM+All-Scatter workloads, demonstrating that high-level implementations can match or exceed heavily-optimized libraries while dramatically simplifying multi-GPU programming.

---

### Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion

Authors: Jongseong Bae, Junwoo Ha, Jinnyeong Heo, Yeongin Lee, Ha Young Kim
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12498v2

Recent camera-based 3D semantic scene completion (SSC) methods have increasingly explored leveraging temporal cues to enrich the features of the current frame. However, while these approaches primarily focus on enhancing in-frame regions, they often struggle to reconstruct critical out-of-frame areas near the sides of the ego-vehicle, although previous frames commonly contain valuable contextual information about these unseen regions. To address this limitation, we propose the Current-Centric Contextual 3D Fusion (C3DFusion) module, which generates hidden region-aware 3D feature geometry by explicitly aligning 3D-lifted point features from both current and historical frames. C3DFusion performs enhanced temporal fusion through two complementary techniques-historical context blurring and current-centric feature densification-which suppress noise from inaccurately warped historical point features by attenuating their scale, and enhance current point features by increasing their volumetric contribution. Simply integrated into standard SSC architectures, C3DFusion demonstrates strong effectiveness, significantly outperforming state-of-the-art methods on the SemanticKITTI and SSCBench-KITTI-360 datasets. Furthermore, it exhibits robust generalization, achieving notable performance gains when applied to other baseline models.

---

### Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion

Authors: Jongseong Bae, Junwoo Ha, Jinnyeong Heo, Yeongin Lee, Ha Young Kim
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12498v1

Recent camera-based 3D semantic scene completion (SSC) methods have increasingly explored leveraging temporal cues to enrich the features of the current frame. However, while these approaches primarily focus on enhancing in-frame regions, they often struggle to reconstruct critical out-of-frame areas near the sides of the ego-vehicle, although previous frames commonly contain valuable contextual information about these unseen regions. To address this limitation, we propose the Current-Centric Contextual 3D Fusion (C3DFusion) module, which generates hidden region-aware 3D feature geometry by explicitly aligning 3D-lifted point features from both current and historical frames. C3DFusion performs enhanced temporal fusion through two complementary techniques-historical context blurring and current-centric feature densification-which suppress noise from inaccurately warped historical point features by attenuating their scale, and enhance current point features by increasing their volumetric contribution. Simply integrated into standard SSC architectures, C3DFusion demonstrates strong effectiveness, significantly outperforming state-of-the-art methods on the SemanticKITTI and SSCBench-KITTI-360 datasets. Furthermore, it exhibits robust generalization, achieving notable performance gains when applied to other baseline models.

---

### SGuard-v1: Safety Guardrail for Large Language Models

Authors: JoonHo Lee, HyeonMin Cho, Jaewoong Yun, Hyunjae Lee, JunKyu Lee, Juree Seok
Published: 2025-11-16
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.12497v1

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component, ContentFilter, is trained to identify safety risks in LLM prompts and responses in accordance with the MLCommons hazard taxonomy, a comprehensive framework for trust and safety assessment of AI. The second component, JailbreakFilter, is trained with a carefully designed curriculum over integrated datasets and findings from prior work on adversarial prompting, covering 60 major attack types while mitigating false-unsafe classification. SGuard-v1 is built on the 2B-parameter Granite-3.3-2B-Instruct model that supports 12 languages. We curate approximately 1.4 million training instances from both collected and synthesized data and perform instruction tuning on the base model, distributing the curated data across the two component according to their designated functions. Through extensive evaluation on public and proprietary safety benchmarks, SGuard-v1 achieves state-of-the-art safety performance while remaining lightweight, thereby reducing deployment overhead. SGuard-v1 also improves interpretability for downstream use by providing multi-class safety predictions and their binary confidence scores. We release the SGuard-v1 under the Apache-2.0 License to enable further research and practical deployment in AI safety.

---

### Towards Better IncomLDL: We Are Unaware of Hidden Labels in Advance

Authors: Jiecheng Jiang, Jiawei Tang, Jiahao Jiang, Hui Liu, Junhui Hou, Yuheng Jia
Published: 2025-11-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.12494v1

Label distribution learning (LDL) is a novel paradigm that describe the samples by label distribution of a sample. However, acquiring LDL dataset is costly and time-consuming, which leads to the birth of incomplete label distribution learning (IncomLDL). All the previous IncomLDL methods set the description degrees of "missing" labels in an instance to 0, but remains those of other labels unchanged. This setting is unrealistic because when certain labels are missing, the degrees of the remaining labels will increase accordingly. We fix this unrealistic setting in IncomLDL and raise a new problem: LDL with hidden labels (HidLDL), which aims to recover a complete label distribution from a real-world incomplete label distribution where certain labels in an instance are omitted during annotation. To solve this challenging problem, we discover the significance of proportional information of the observed labels and capture it by an innovative constraint to utilize it during the optimization process. We simultaneously use local feature similarity and the global low-rank structure to reveal the mysterious veil of hidden labels. Moreover, we theoretically give the recovery bound of our method, proving the feasibility of our method in learning from hidden labels. Extensive recovery and predictive experiments on various datasets prove the superiority of our method to state-of-the-art LDL and IncomLDL methods.

---

### Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation

Authors: Ponhvoan Srey, Yaxin Shi, Hangwei Qian, Jing Li, Ivor W. Tsang
Published: 2025-11-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.12491v1

Fully Test-Time Adaptation (FTTA) addresses domain shifts without access to source data and training protocols of the pre-trained models. Traditional strategies that align source and target feature distributions are infeasible in FTTA due to the absence of training data and unpredictable target domains. In this work, we exploit a dual perspective on FTTA, and propose Agnostic FTTA (AFTTA) as a novel formulation that enables the usage of off-the-shelf domain transformations during test-time to enable direct generalization to unforeseeable target data. To address this, we develop an uncover-and-unlearn approach. First, we uncover potential unwanted shifts between source and target domains by simulating them through predefined mappings and consider them as nuisances. Then, during test-time prediction, the model is enforced to unlearn these nuisances by regularizing the consequent shifts in latent representations and label predictions. Specifically, a mutual information-based criterion is devised and applied to guide nuisances unlearning in the feature space and encourage confident and consistent prediction in label space. Our proposed approach explicitly addresses agnostic domain shifts, enabling superior model generalization under FTTA constraints. Extensive experiments on various tasks, involving corruption and style shifts, demonstrate that our method consistently outperforms existing approaches.

---

### SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design

Authors: Qingsong Zhong, Haomin Yu, Yan Lin, Wangmeng Shen, Long Zeng, Jilin Hu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12489v2

Structure-Based drug design (SBDD) has emerged as a popular approach in drug discovery, leveraging three-dimensional protein structures to generate drug ligands. However, existing generative models encounter several key challenges: (1) incorporating boundary condition constraints, (2) integrating hierarchical structural conditions, and (3) ensuring spatial modeling fidelity. To address these limitations, we propose SculptDrug, a spatial condition-aware generative model based on Bayesian flow networks (BFNs). First, SculptDrug follows a BFN-based framework and employs a progressive denoising strategy to ensure spatial modeling fidelity, iteratively refining atom positions while enhancing local interactions for precise spatial alignment. Second, we introduce a Boundary Awareness Block that incorporates protein surface constraints into the generative process to ensure that generated ligands are geometrically compatible with the target protein. Third, we design a Hierarchical Encoder that captures global structural context while preserving fine-grained molecular interactions, ensuring overall consistency and accurate ligand-protein conformations. We evaluate SculptDrug on the CrossDocked dataset, and experimental results demonstrate that SculptDrug outperforms state-of-the-art baselines, highlighting the effectiveness of spatial condition-aware modeling.

---

### SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design

Authors: Qingsong Zhong, Haomin Yu, Yan Lin, Wangmeng Shen, Long Zeng, Jilin Hu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12489v1

Structure-Based drug design (SBDD) has emerged as a popular approach in drug discovery, leveraging three-dimensional protein structures to generate drug ligands. However, existing generative models encounter several key challenges: (1) incorporating boundary condition constraints, (2) integrating hierarchical structural conditions, and (3) ensuring spatial modeling fidelity. To address these limitations, we propose SculptDrug, a spatial condition-aware generative model based on Bayesian flow networks (BFNs). First, SculptDrug follows a BFN-based framework and employs a progressive denoising strategy to ensure spatial modeling fidelity, iteratively refining atom positions while enhancing local interactions for precise spatial alignment. Second, we introduce a Boundary Awareness Block that incorporates protein surface constraints into the generative process to ensure that generated ligands are geometrically compatible with the target protein. Third, we design a Hierarchical Encoder that captures global structural context while preserving fine-grained molecular interactions, ensuring overall consistency and accurate ligand-protein conformations. We evaluate SculptDrug on the CrossDocked dataset, and experimental results demonstrate that SculptDrug outperforms state-of-the-art baselines, highlighting the effectiveness of spatial condition-aware modeling.

---

### ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models

Authors: Onkar Shelar, Travis Desell
Published: 2025-11-16
Categories: cs.NE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.12487v2

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous steady-state loop. The system employs a diverse set of operators, including lexical substitutions, negation, back-translation, paraphrasing, and two semantic crossover operators, while a moderation oracle provides fitness guidance. Operator-level analysis shows heterogeneous behavior: lexical substitutions offer the best yield-variance trade-off, semantic-similarity crossover acts as a precise low-throughput inserter, and global rewrites exhibit high variance with elevated refusal costs. Using elite prompts evolved on LLaMA 3.1 8B, we observe practically meaningful but attenuated cross-model transfer, with toxicity roughly halving on most targets, smaller LLaMA 3.2 variants showing the strongest resistance, and some cross-architecture models retaining higher toxicity. These results suggest that small, controllable perturbations are effective vehicles for systematic red-teaming and that defenses should anticipate cross-model reuse of adversarial prompts rather than focusing only on single-model hardening.

---

### Evolving Prompts for Toxicity Search in Large Language Models

Authors: Onkar Shelar, Travis Desell
Published: 2025-11-16
Categories: cs.NE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.12487v1

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous steady-state loop. The system employs a diverse set of operators, including lexical substitutions, negation, back-translation, paraphrasing, and two semantic crossover operators, while a moderation oracle provides fitness guidance. Operator-level analysis shows heterogeneous behavior: lexical substitutions offer the best yield-variance trade-off, semantic-similarity crossover acts as a precise low-throughput inserter, and global rewrites exhibit high variance with elevated refusal costs. Using elite prompts evolved on LLaMA 3.1 8B, we observe practically meaningful but attenuated cross-model transfer, with toxicity roughly halving on most targets, smaller LLaMA 3.2 variants showing the strongest resistance, and some cross-architecture models retaining higher toxicity. These results suggest that small, controllable perturbations are effective vehicles for systematic red-teaming and that defenses should anticipate cross-model reuse of adversarial prompts rather than focusing only on single-model hardening.

---

### ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction

Authors: Pengze Li, Jiaqi Liu, Junchi Yu, Lihao Liu, Mingyu Ding, Wanli Ouyang, Shixiang Tang, Xi Chen
Published: 2025-11-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.12485v1

Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether models truly understand the fundamental reasoning paradigms that underpin scientific inference. To address this, we introduce a novel task named Latent Reasoning Chain Extraction (ARCHE), in which models must decompose complex reasoning arguments into combinations of standard reasoning paradigms in the form of a Reasoning Logic Tree (RLT). In RLT, all reasoning steps are explicitly categorized as one of three variants of Peirce's fundamental inference modes: deduction, induction, or abduction. To facilitate this task, we release ARCHE Bench, a new benchmark derived from 70 Nature Communications articles, including more than 1,900 references and 38,000 viewpoints. We propose two logic-aware evaluation metrics: Entity Coverage (EC) for content completeness and Reasoning Edge Accuracy (REA) for step-by-step logical validity. Evaluations on 10 leading LLMs on ARCHE Bench reveal that models exhibit a trade-off between REA and EC, and none are yet able to extract a complete and standard reasoning chain. These findings highlight a substantial gap between the abilities of current reasoning models and the rigor required for scientific argumentation.

---