paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter

Runyi Li, Bin CHEN, Jian Zhang, Radu Timofte

Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservation of facial identity. Although diffusion models like Stable Diffusion have shown promise in generating high-quality images, their VAE modules are typically trained on broad natural-image data dominated by HQ content; severely degraded LQ inputs therefore yield latents that fall in low-density regions of the diffusion prior, weakening the effectiveness of LQ conditions during the denoising process. Existing approaches often tackle this issue by retraining the VAE encoder, which is computationally expensive and memory intensive. To address this limitation efficiently, we propose LAFR, a codebook-based latent space adapter that aligns LQ latents to the in-distribution region the diffusion prior was trained to denoise, enabling sampling from a better matched latent condition without altering the original VAE. To further improve identity and structural consistency relative to OSEDiff-style baselines, we introduce a multilevel restoration loss combining constraints from semantic identity embeddings and facial structural priors. Furthermore, by leveraging the inherent structural regularity of facial images, we show that lightweight fine-tuning of a diffusion prior on just 0.9% of FFHQ can achieve competitive results while reducing training time by 70%. We also give a short analysis of why a codebook correction closes a mode-dependent latent gap that no global normalisation or affine map can. In summary, LAFR is a data and compute efficient one-step face-restoration method that improves perceptual quality, FID, landmark accuracy, and identity/structure consistency over OSEDiff-style baselines, without claiming uniform state of the art; it reaches this operating point while remaining competitive with far more expensive pipelines.

arXiv

DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates

Akash Jadhav, Michael Greenspan

We propose DLTPose, a novel method for 6DoF object pose estimation from RGBD images that combines the accuracy of sparse keypoint methods with the robustness of dense pixel-wise predictions. DLTPose predicts per-pixel radial distances to a set of minimally four keypoints, which are then fed into our novel Direct Linear Transform (DLT) formulation to produce accurate 3D object frame surface estimates, leading to better 6DoF pose estimation. Additionally, we introduce a novel symmetry-aware keypoint ordering approach, designed to handle object symmetries that otherwise cause inconsistencies in keypoint assignments.Previous keypoint-based methods relied on fixed keypoint orderings, which failed to account for the multiple valid configurations exhibited by symmetric objects, which our ordering approach exploits to enhance the model's ability to learn stable keypoint representations. Extensive experiments on the benchmark BOP-Classic-Core datasets show that DLTPose outperforms many recent methods, performing especially well for symmetric and occluded objects. The code is available at anonymous.4open.science/r/DLTPose.

arXiv

Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition

Koki Hirooka, Abu Saleh Musa Miah, Tatsuya Murakami, Md. Al Mehedi Hasan, Yong Seok Hwang, Jungpil Shin

Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between deaf and non-deaf individuals. While Graph Convolutional Networks (GCNs) are common, they are limited by their reliance on fixed skeletal graphs. To overcome this, we propose the Sequential Spatio-Temporal Attention Network (SSTAN), a novel Transformer-based architecture. Our model employs a hierarchical, stacked design that sequentially integrates Spatial Multi-Head Attention (MHA) to capture intra-frame joint relationships and Temporal MHA to model long-range inter-frame dependencies. This approach allows the model to efficiently learn complex spatio-temporal patterns without predefined graph structures. We validated our model through extensive experiments on diverse, large-scale datasets (WLASL, JSL, and KSL). A key finding is that our model, trained entirely from scratch, achieves state-of-the-art (SOTA) performance in the challenging fingerspelling categories (JSL and KSL). Furthermore, it establishes a new SOTA for skeleton-only methods on WLASL, outperforming several approaches that rely on complex self-supervised pre-training. These results demonstrate our model's high data efficiency and its effectiveness in capturing the intricate dynamics of sign language. The official implementation is available at our GitHub repository: \href{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}.

arXiv

Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization

Ganzhao Yuan

This paper proposes {\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing composite nonconvex finite-sum functions. It integrates three acceleration techniques: adaptive stepsizes, Nesterov's extrapolation, and the recursive stochastic path-integrated estimator SPIDER. Unlike existing methods that adjust the stepsize factor using historical gradients, {\sf AEPG-SPIDER} relies on past iterate differences for its update. While targeting stochastic finite-sum problems, {\sf AEPG-SPIDER} simplifies to {\sf AEPG} in the full-batch, non-stochastic setting, which is also of independent interest. To our knowledge, {\sf AEPG-SPIDER} and {\sf AEPG} are the first Lipschitz-free methods to achieve optimal iteration complexity for this class of \textit{composite} minimization problems. Specifically, {\sf AEPG} achieves the optimal iteration complexity of $\mathcal{O}(N ε^{-2})$, while {\sf AEPG-SPIDER} achieves $\mathcal{O}(N + \sqrt{N} ε^{-2})$ for finding $ε$-approximate stationary points, where $N$ is the number of component functions. Under the Kurdyka-Lojasiewicz (KL) assumption, we establish non-ergodic convergence rates for both methods. Preliminary experiments on sparse phase retrieval and linear eigenvalue problems demonstrate the superior performance of {\sf AEPG-SPIDER} and {\sf AEPG} compared to existing methods.

arXiv

Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers

Wenhao Liang, Liangwei Zheng, Wei Zhang, Weitong Chen

Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss (FCL), which adds a squared probability-error (multiclass Brier) anchor to the focal objective, $\mathcal{L}{\mathrm{FCL}}^{γ,λ} = \mathcal{L}{\mathrm{focal}}^γ + λ|\hat{p}(x) - e_y|_2^2$. Our analysis separates two properties that are easily conflated: FCL is classification-calibrated for every $γ, λ\ge 0$, preserving the Bayes decision rule, yet for $γ> 0$ it is generally not proper, so its Bayes-optimal probability vector is displaced from the true posterior. The main result quantifies that displacement and shows the anchor controls it: bounded by $\sqrt{\log K / λ}$ for every posterior and minimizer without regularity assumptions, improving to $O(1/λ)$ for interior posteriors, with an exact first-order expansion identifying the bias and corresponding population $\ell_2$ calibration guarantees. We verify these population statements directly, minimizing the conditional risk on the simplex with no network involved: the posterior-distortion rate matches its prediction to a median fitted slope of $-0.994$, and exact population squared calibration error follows the predicted $λ^{-2}$ law (slopes $\approx -1.99$). Across CIFAR-10/100, Tiny-ImageNet, text and medical multi-label tasks, FCL is competitive rather than dominant, and the picture is regime- and metric-dependent: under a common validation-split protocol the validation-adaptive AdaFocal attains lower binned calibration error, while FCL attains lower NLL, Brier and error on two of three settings. On transformers its calibration advantage is absent, and a from-scratch experiment tested and did not support the conjecture that pretraining explains this. We report both the gains and the failure regimes.

arXiv

Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition

Guanghao Zhu, Lin Liu, Yuhao Hu, Haixin Sun, Fang Liu, Xiaohui Du, Ruqian Hao, Juanxiu Liu, Yong Liu, Jing Zhang

Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including criminal analysis and psychotherapy. However, micro-expression recognition is challenging since micro-expressions have low intensity and public datasets are small in size. To this end, a three-stream temporal-shift attention network based on self-knowledge distillation is proposed in this paper. Firstly, to address the low intensity of muscle movements, we utilize learning-based motion magnification modules to enhance the intensity of muscle movements. Secondly, we employ efficient channel attention modules in the local-spatial stream to make the network focus on facial regions that are highly relevant to micro-expressions. In addition, temporal shift modules are used in the dynamic-temporal stream, which enables temporal modeling with no additional parameters by mixing motion information from two different temporal domains. Furthermore, we introduce self-knowledge distillation into the micro-expression recognition task by introducing auxiliary classifiers and using the deepest section of the network for supervision, encouraging all blocks to fully explore the features of the training set. Finally, extensive experiments are conducted on five publicly available micro-expression datasets. The experimental results demonstrate that our network outperforms other existing methods and achieves new state-of-the-art performance. Our code is available at https://github.com/GuanghaoZhu663/SKD-TSTSAN.

arXiv

Screening Autism Spectrum Disorder in children using Deep Learning Approach : Evaluating the classification model of YOLOv26s by comparing with other models

Subash Gautam, Sagar Pathak, Prabin Sharma, Bidhya Shrestha, Kisan Thapa, Shubham Joshi, Mala Deep Upadhaya, Dikshya Thapa, Chandiprasad Chintalapati, Sagar Duwal, Angela Upreti, Salik Ram Khanal

Autism spectrum disorder (ASD) is a developmental condition that presents significant challenges in social interac- tion, communication, and behavior. Early intervention plays a pivotal role in enhancing cognitive abilities and reducing autistic symptoms in children with ASD. Numerous clinical studies have highlighted distinctive facial characteristics that distinguish ASD children from typically developing (TD) children. In this study, we propose a practical solution for ASD screening using facial images using YOLOv26s model. By employing YOLOv26s, a deep learning technique, we achieved exceptional results. Our model achieved a remarkable 92.86% accuracy in classification and an F1-score of 0.9291. Our findings provide support for the clini- cal observations regarding facial feature discrepancies between children with ASD. The high F1-score obtained demonstrates the potential of deep learning models in screening children with ASD. We conclude that the newest version of YOLOv26s which is usually used for object detection can be used for classification problem of Austistic and Non-autistic images.

arXiv

Deep Feature Pyramid Convolutional Networks with In-Place Activated Batch Normalization for Automated Skin Lesion Boundary Segmentation

Glib Kechyn

Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant melanoma, but remains challenging due to fuzzy margins, occluding artifacts such as hair and blood vessels, low contrast, and high inter-patient variability. This work presents a memory-efficient deep convolutional neural network framework for lesion boundary segmentation, developed for the ISIC 2018 Challenge (Task 1: Lesion Boundary Segmentation). A U-Net-style encoder-decoder architecture is adapted using Wide ResNet38 and Dual Path Network (DPN) backbones with a Feature Pyramid Network (FPN) decoder, pretrained on ImageNet. In-Place Activated Batch Normalization (InPlace-ABN) reduces memory consumption during training, allowing higher-capacity ensembling under standard GPU memory constraints, combined with five-fold cross-validation, extensive augmentation, snapshot ensembling, and test-time augmentation. The best-performing model achieves a Thresholded Jaccard score of 0.752 on the ISIC 2018 Challenge evaluation, with single-model configurations scoring between 0.700 and 0.750; InPlace-ABN reduces memory consumption by approximately 25%. To contextualize this result against current practice, a simplified single-model U-Net baseline retrained in 2026 using standard modern tooling is also reported, achieving a Dice score of 0.8443 (IoU 0.7608, Thresholded Jaccard 0.6680), which highlights the substantial contribution of ensembling and pretraining to the original result. This work does not claim state-of-the-art segmentation accuracy; rather, it documents a memory-efficient training approach that enables higher-capacity ensembling under constrained GPU resources, a practical consideration for training high-capacity segmentation models in settings with limited computational budgets.

arXiv

Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning

Mingwen Zhang, Jisheng Dang, Minqiang Yang, Bimei Wang, Bin Hu, Tat-Seng Chua

Video reasoning tasks such as grounded video question answering and temporal grounding require selecting temporal evidence that supports the query. In many current training setups, temporal supervision is applied through local objectives such as boundary regression or span generation, while verification is used mainly to rerank candidate segments at inference time. We study whether a frozen verifier can also guide training. Our multi-agent framework couples a trainable \emph{Grounder} with a frozen \emph{Verifier}: the Grounder samples candidate trajectories and evidence segments, the Verifier assigns query-conditioned segment scores, a group-relative policy-gradient objective favors trajectories that outperform their within-input peers, and a bootstrapped calibration loss steers temporal predictions toward verifier-preferred spans. Trained on source tasks and evaluated without target-dataset fine-tuning, a two-billion-parameter instantiation transfers zero-shot across grounded question answering, temporal grounding, and long-video question answering, reaching 28.7\% intersection-over-union and 25.4\% answer-grounding accuracy on a grounded-question-answering benchmark, 46.1\% intersection-over-union on a temporal-grounding benchmark, and 54.1\% on a long-video question-answering benchmark. Relative to a strong same-scale baseline, the gains are modest but consistent, with the clearest improvements on relevance-oriented metrics such as intersection-over-union and moderate-overlap recall. Within the tested benchmarks and transfer setting, the results support frozen verification as a training signal for evidence selection, while showing that strict boundary precision remains comparatively weaker. Code and models are available at https://anonymous.4open.science/r/MASIRL-E50C/

arXiv

Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Making

Minda Zhao, XU HAN, Rishabh Goel, Maya Dagan, Noa Dagan, Adithya Madduri, Payal Chandak, Shilpa Nadimpalli Kobren, Isaac S. Kohane

Clinical decision-making often involves prioritizing ethical values, such as beneficence, non-maleficence, respecting a patient's autonomy, and justice. Recent work has begun to assess how large language models (LLMs) make such subjective, value-laden clinical judgments. However, evaluations of LLM decision-making in rare disease care contexts, where ethical tensions are ubiquitous and where scarce prior information likely impacts LLM behavior, are still lacking. Here, we present a benchmark of 208 clinically grounded rare disease vignettes, each of which presents genuine, high-stakes conflicts. When prompting 11 state-of-the-art LLMs to choose between clinically defensible yet ethically conflicting next steps embedded within these vignettes, we found that all evaluated models consistently prioritized justice over other core bioethical principles. Specifically, models overwhelmingly favor equal resource allocation over need-based considerations, indicating LLMs' limited responsiveness to differences in clinical severity or situational context. We also identify a strong authority-framing effect: models favor justice in committee-based contexts and shift toward beneficence and autonomy only when final decisions are framed as being made by clinicians or patients respectively. Our work suggests that institutional pressures surrounding rare disease resource utilization may be silently reflected in LLM-based decision support systems, with finer ethical considerations disregarded.

arXiv

Output Dilution: Redundant but Fragile Representations in MoE Models

Orion Reblitz-Richardson

Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-7B, linear probes recover moral valence from nearly every expert-layer combination, with mean peak-layer accuracy above 90%. But these representations collapse under levels of activation noise that a dense model of matched size easily tolerates, with a 4.2-fold difference in robustness. We trace this to output dilution. Because the MoE block averages across active experts before contributing to the residual stream, the feedforward signal reaching downstream layers is nearly two orders of magnitude smaller than in a dense MLP. Moral information, our interest, survives aggregation intact but at a scale trivially overwhelmed by perturbation. Routing itself remains stable under noise while the vulnerability originates entirely in the diluted aggregate. Checkpoint trajectories confirm this is architectural, not learned. Experts never specialize and accuracy saturates within the first few thousand steps. In sparse architectures, redundant encoding does not imply robust encoding.

arXiv

Trust the Mass: Forced Weights in KV-Cache Eviction

Jack Shi, Jerry Gu

Every deployed sparse-attention or KV-cache-eviction rule keeps a subset of the keys, discards the rest, and renormalizes the attention weights over the kept set. Enumerating the exact best subset under that constraint on $168{,}192$ attention rows from five models shows that keeping the largest weights is already near-optimal, since the best subset closes only a median $2$ to $5\%$ of the remaining gap to full attention. If selection closes this little, published margins between eviction methods must come from elsewhere, so we measure the bytes each method holds. In the shared evaluation pipeline, the strongest query-agnostic methods hold the full cache because their per-head selections are stored as masks, and only ragged per-head storage frees that memory. Enforcing a nominal budget on one fixed selection costs $14$ to $62$ benchmark points. We trace an $87.6$-point retrieval margin to rankings computed while the question is visible. ContourKV, a training-free allocator built from the dropped-mass statistic, wins $93$ of $160$ paired comparisons against that state of the art and loses $22$ at the byte count of the budget-enforcing baselines, and it ties the strongest of them.

arXiv

TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue

Freeman Jiang, Ramon Sanabria, Soham Deshmukh, Bandhav Veluri, Simon Michael Vuch Williams, Elliott K. Suen, Garreth Lee, Kevin Yoonho Choi, Takuya Umeki, Riku Kubo, Sathvik Udupa, Chien-yu Huang, Shih-Yun Shan Kuan, Zhuoyan Tao, Satyapriya Krishna, Sefik Emre Eskimez, Yu Tsao, Hung-yi Lee, Shinji Watanabe

Speakers in natural conversation take turns speaking and listening, deciding in real time when to take, hold, or yield the floor. However, turn-taking evaluation remains limited due to the lack of a consistent, linguistically grounded evaluation protocol and hand-annotated data covering diverse conversation types. To address this, we present TurnBench, a multi-domain benchmark that pairs a 30-hour, hand-labeled corpus of dyadic human conversation with a standardized evaluation protocol for end-of-turn and interruption detection. We set conversation type as a controllable experimental variable, covering six distinct interaction styles, and triple-annotate each conversation. Benchmarking 14 heterogeneous turn-taking systems, we find end-of-turn recall stable across types, while interruption false positives are strongly type-dependent and concentrated in backchannel-dense interaction styles. Although in smooth floor transfers human listeners begin speaking a median 151 ms before the current turn ends, no current system performs equivalently without incurring excessive false positives. We release our corpus, a 104-hour training set, and a public leaderboard with an interactive dataset viewer at https://turnbench.sesame.com

arXiv

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

Francesco Mantegna, Dulhan Jayalath, Gereon Elvers, Tasha Kim, Benjamin Ballyk, Alex Fung, Sungjun Cho, Teyun Kwon, Luisa Kurth, Miran Özdogan, Gilad Landau, Pratik Somaiya, Natalie Voets, Mark Woolrich, Oiwi Parker Jones

We introduce LibriBrain100, a large-scale MEG dataset for speech decoding designed from the ground up for reproducible, standardised evaluation. LibriBrain100 more than doubles the size of the original LibriBrain release, resulting in over 100 hours of high-quality MEG acquired while subjects listened to naturalistic continuous speech. With $\sim$80 hours from a single subject, LibriBrain100 sets a new record for deep, within-subject neural data (8$\times$ more than the next comparable dataset and roughly 80$\times$ more than other datasets). To demonstrate the payoff of this depth-first design, we evaluate on a word-classification benchmark---an increasingly well-established stepping stone towards the open challenge of noninvasive brain-to-text decoding. Using an existing decoding model, we achieve state-of-the-art performance---validating both the quality of the recordings and the value of within-subject data at scale. Because collecting 80 hours of data per user is impractical for real-world applications, we also collected $\sim$40 minutes of additional data from each of 32 subjects. Using the same word-classification benchmark, we demonstrate the value of broad multi-subject data: supervised finetuning of a pre-trained model can substantially compensate for limited per-subject data. We provide standard train, validation, and test splits, all reproducible through an open-sourced Python library that supports easy downloading, optional preprocessing, and data loading for common deep learning frameworks. In addition, the dataset and evaluation infrastructure are being released alongside an open machine-learning competition with a public leaderboard for standardised benchmarking. Ultimately, our hope is that LibriBrain100 will accelerate progress towards practical non-invasive brain-computer interfaces, capable of restoring communication to people living with severe paralysis.

arXiv

MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment

Dongyue Li, Ziniu Zhang, Lu Wang, Hongyang R Zhang

We study learning a mixture of $k$ Plackett-Luce models from multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has many applications in AI alignment and preference optimization. Prior work has studied mixtures of Bradley-Terry models from pairwise comparisons. However, estimating a mixture of multi-way ranking models can become theoretically unidentifiable when $k$ exceeds $m/2$, where $m$ is the ranking length. We design an efficient algorithm to address this issue by first augmenting the rankings to a larger size (e.g., generating comparisons from a base model), followed by a gradient-based estimation to reduce inference cost (in the input embedding space). With this procedure in mind, we then fit a mixture of Plackett-Luce (PL) models via an expectation-maximization-style iteration, or MoPLEx in short. We conduct extensive experiments to verify this algorithm. First, we find that the gradient-based approximation estimates true probabilities with less than 5% error on models with up to 34 billion parameters. Second, MoPLEx improves clustering and ranking accuracy by an average of 43.7% and 15.2% over baselines using a single PL model or a mixture of Bradley-Terry models, on UltraFeedback and PERSONA datasets. These results demonstrate the effectiveness of MoPLEx for tackling multi-way rankings following heterogeneous preferences through measuring alignment via gradients.

arXiv

BanglaMamba: Exploring State Space Models for Bangla Fake News Detection

M. K. Khalidi Siam

Fake news detection has become an important Natural Language Processing (NLP) task due to the rapid spread of misinformation through online news platforms and social media. While transformer-based models such as BanglaBERT achieve strong performance for Bangla text classification, their quadratic computational complexity makes them less suitable for long-document processing in resource-constrained environments. This paper investigates Mamba-based State Space Models (SSMs) as an efficient alternative for Bangla fake news detection. We propose BanglaMamba and compare it with pre-trained BanglaBERT and a similarly configured BERT model trained from scratch. Experimental results show that BanglaBERT achieves the highest Macro-F1 score (0.9260), while BanglaMamba (0.9029) achieves performance comparable to the from-scratch CustomBERT (0.9057) despite using a different architecture. Meanwhile, BanglaMamba achieves approximately $2.2\times$ higher inference throughput and 49% lower inference peak GPU memory usage than the BERT-based models. Cross-dataset evaluation shows that BanglaBERT generalizes better to an external dataset, highlighting the importance of large-scale pretraining. These findings demonstrate that Mamba-based SSMs can provide a competitive and computationally efficient alternative to Transformer-based architectures for Bangla fake news detection, particularly in resource-constrained settings.

arXiv

The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers

Samuele Vallisa, Federico Ravenda, Claudio Palominos, Rui He, Andrea Raballo, Antonietta Mira, Philipp Homan, Wolfram Hinzen

Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such data tend to concentrate on lower-dimensional sub-manifolds, a form of compression quantified by the Intrinsic Dimensionality (ID), the minimum number of independent variables needed to represent them without significant information loss. In this work, we ask whether the grammatical role of tokens, as marked by their part-of-speech (PoS) tag, shapes the local geometry of this manifold. To this end: (1) We investigate the layer-wise evolution of ID, finding that closed-class items expand earlier and collapse sooner than open-class ones; (2) We show its expansion and contraction to be explained by changes in the neighborhood structure, and hence in the relations between words within a sentence; (3) We compare encoders (ModernBERT, bigbird-roberta-large) and decoders (gemma-2-2B, Llama-3.2-3B), finding that the two families evolve differently across layers, consistently with how each integrates context;(4) We show that geometric features alone recover a token's grammatical role, and use them to interpret how the semantic content of each PoS evolves across layers in a downstream classification task.

arXiv

Belief Cascades Drive Persuasion in LLM Agent Networks

Haoyi Qiu, Genglin Liu, Pranav Narayanan Venkit, Kung-Hsiang Huang, Saadia Gabriel, Chien-Sheng Wu, Nanyun Peng

Multi-agent LLM systems increasingly debate answers, coordinate research, simulate users, and mediate information flows, making agent-to-agent persuasion a basic but undermeasured capability. We introduce a controlled testbed for studying how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies. Across four LLM backbones, five graphs, and 55 policy statements, we find that persuasion dynamics depend on the interaction between topology, competition, topic, and model prior. Additionally, we show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence, showing that agents not assigned to persuade can still transmit persuasive force. Finally, analyzing post text alone misses important movement: planned strategies are only partly realized in executed messages, action choices can diverge from message content, and persuadees rarely state the stance shifts detected by probes. These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process, using belief probes, exposure provenance, and action logs to identify who influenced whom and whether visible language reflects underlying stance movement.

arXiv

RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts

Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib, Sahraoui Dhelim

Existing approaches to building line-level Arabic handwritten-text-recognition (HTR) training data either rely on fully manual annotation, which does not scale, or on automatic OCR-to-reference alignment methods not yet extended to multi-script, two-zone (main-plus-margin) manuscript layouts with a provable correctness guarantee. We present RefLAM (Reference-grounded Line Annotation for Manuscripts), a pipeline converting manuscript page images and clean transcriptions into validated, line-level ground truth without sacrificing human oversight. RefLAM couples a deep-learning page-segmentation model with a multimodal large language model (MLLM) for structured OCR and a diacritic-agnostic fuzzy alignment engine that grounds each OCR line in a contiguous span of the reference text, with a character-level confidence score in $[0,100]$. A perfect score is provably equivalent to character-for-character identity of the normalised strings (the Confidence-100 rule), verified with no counterexample across the released corpus. A reviewer can thus trust a perfect score, confirming most lines at a glance rather than retyping them, so annotation becomes triaged, with attention concentrated on uncertain alignments. Across 7 fully page-validated books we measured a 75$\times$ throughput gain over manual annotation (3,000 vs. 40 lines/hr); applying the same guarantee to 7 further books, we retained 16,533 confidence-100 main-text lines within one week, excluding sub-100 lines rather than manually correcting them. Using RefLAM, we release AraMS-28k: 14 historical Arabic manuscript books, 3,043 pages, and 27,971 main-text and 629 margin-line annotations with bounding boxes, layout labels, and insertion anchors for 191 margin entries (30.4%). We also finetune Muharaf-pretrained baselines (including HATFormer) on AraMS-28k and report CER results confirming its practical utility for downstream HTR training.

arXiv

SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation

Ben Lagnese, Manas Gaur

Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in knowledge graphs. Graph-based RAG can capture entity relationships, yet supervised graph retrieval typically requires labeled question-answer data that may not be available for newly constructed graphs. We address this limitation with SelfGraphRAG, a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever. The generated questions capture multi-hop paths and local neighborhoods, providing relational supervision without manual annotation. Experiments on multi-hop question answering and classification benchmarks show that SelfGraphRAG improves retrieval precision and downstream reasoning performance over embedding-based baselines. These results suggest that knowledge graph structure can provide useful supervision for training graph retrievers when labeled data are unavailable.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.