TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3646Multimodal571Agents544Frontier LLMs466Inference & serving277Image segmentation186Graph learning175Learning verifiable rewards1703D scene164Evals108Voice AI104Classifier & causal discovery89Flow matching81Forecasting time81Training & fine-tuning64Teacher policy distillation53All 32 fields

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in embodied control loops1 paper raises it · 0 address it

    High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

    Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

    Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

    • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

Coming with more sources: more tagged papers
  • Federated learning51+37.8%
  • Agents544+4.8%
  • Quantum machine learning240.0%
  • Sensing communication150.0%
  • Frontier LLMs466−2.1%
  • Character recognition OCR17−5.6%
  • Voice AI104−10.3%
  • Inference & serving277−10.4%

Papers

  • arXiv cs.CVOct 19

    Toolkit for Facial Deidentification

    Esteban Leiva-Montenegro, Matthieu Pillot, Manfred Gonzalez-Hernandez, Vitomir Struc, Peter Peer +1

    This work presents a novel open-source toolkit designed for the evaluation of face deidentification techniques with available evaluation models. The framework provides a complete evaluation pipeline, including preprocessing, deidentification, and performance assessment, based on data utility, image quality, and identity protection metrics. It supports a variety of datasets, enabling researchers to easily benchmark new deidentification techniques. Results show the effectiveness of some techniques on maintaining privacy while preserving image utility. The toolkit is aimed at unifying future research by providing a standard evaluation framework for privacy-enhancing technologies in facial biometrics. Implementation is available at github.com/blazm/deid-toolkit.

    PDF
  • arXiv cs.CVOct 19

    DCR-TSF: Dual-Level Compositional Reasoning with Triadic Spherical Fusion for Training-Free Zero-Shot Composed Image Retrieval

    Gwang-Ho Na, Ho-Joong Kim, Seong-Whan Lee

    Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image that reflects an intended textual modification while maintaining semantic consistency with a reference image. Existing training-free ZS-CIR methods typically rely on fine-grained generated target descriptions, which often overemphasize reference-specific visual details and lead to appearance-biased retrieval. Moreover, since these descriptions are generated through multimodal large language models (MLLMs), the direct influence of the original image-text query can be weakened in the final retrieval representation. In this paper, we propose DCR-TSF, a training-free ZS-CIR framework that combines Dual-level Compositional Reasoning (DCR) and Triadic Spherical Fusion (TSF). DCR generates fine- and coarse-grained descriptions from the reference image and modification text, capturing complementary target-side semantics across different granularities. To preserve the original image-text query information, TSF constructs a composed-query anchor by spherically interpolating the reference image feature and modification text feature, and fuses it with the fine- and coarse-grained representations using a weighted…

    PDF
  • arXiv cs.CVOct 19

    Not All Similarity Is Leakage: Distribution-Aware Identity Leakage Assessment in Synthetic Face Datasets

    Paweł Borsukiewicz, Daniele Lunghi, Wendkûuni C. Ouédraogo, Fadi Boutros, Jacques Klein +1

    Synthetic data provides the means for more ethical and less biased facial recognition. Nonetheless, the limitations of generative models and the conditioning process they rely on pose a risk of identity leakage, resulting in synthetic samples that are overly similar to those seen in a generator's training set, mitigating privacy benefits. In this work, we show that previously proposed approaches are affected by two key limitations: high classifier dependence and a tendency to identify leakage with respect to real datasets that were not used in training. To address these shortcomings, we propose a novel metric called Scaled Overlap (SO), which adapts a non-parametric data-copying test for facial recognition and extends it to the identity level. By leveraging a multi-model setup that compensates for errors in individual classifiers, it provides insights into the true strength of identity leakage. Our analysis identifies leaking datasets (CemiFace, SFace2, IDNet) with the most acute leakage introduced by generative model conditioning in CemiFace, demonstrates that real datasets do not contribute equally to generator training, and shows that the majority of synthetic images are drawn…

    PDF
  • arXiv cs.AIOct 19

    CUA-Lite: An Open Platform for Computer Use Agents

    Zhanhui Zhou, Weichen Zhang, Haoran Liu, Lingjie Chen, Tianneng Shi +4

    Open resources for computer use agents (CUAs) -- environments, datasets, and models -- remain scattered: without a standard, these resources cannot be integrated and scaled; additionally, evaluation, RL, and SFT cannot share one infrastructure. We present CUA-Lite, an open platform for developing CUAs, built around three standardized abstractions: (1) Unified environment interface, under which we integrate 12 benchmarks across desktop, browser, and mobile, plus lightweight VM-free sandboxes that replicate OSWorld's desktop at much lower cost, providing over 30,000 verifiable tasks. (2) Unified supervised data format, into which we convert the major public CUA datasets, from GUI grounding and understanding to full rollouts, and record our fresh rollouts from frontier CUAs on these verifiable environments. (3) Model harnesses shared across evaluation, RL, and SFT, one per model and implemented for 14 model families. Each harness runs its model in these computer environments, producing the rollouts that evaluation and RL consume, or renders stored supervised data into the model's own training format for SFT. We release reference scores across the integrated benchmarks, and show that…

    PDF
  • arXiv cs.CVOct 19

    Risk Decomposition for Hallucination-Aware Video Sampling

    Chenyan Zheng, Fan Wu, Ruibo Li, Jiaxing Li, Minghao Yang +2

    Despite achieving high visual fidelity, video models still suffer from physical hallucinations, limiting their reliability as world simulators. Existing methods leverage model-internal or external signals to improve physical plausibility, but their roles and limitations require a unified explanation. We propose a two-dimensional physical-hallucination risk framework that defines low-density sampling risk and high-density drifting risk. The first risk captures generations assigned low likelihood by the video model, for example, a ball suddenly teleporting despite the model favoring continuous motion, while the second risk captures physical inconsistencies in high-likelihood generations, for example, a ball bouncing progressively higher without additional energy. Our analysis explains how model-internal signals steer sampling toward higher-density regions of the learned distribution to address low-density sampling risk. However, higher model likelihood does not guarantee physical plausibility, motivating external guidance to address high-density drifting risk. Based on this framework, we develop Hallucination-Aware Sampler (HA-Sampler), which applies external physical guidance…

    PDF
  • arXiv cs.CVOct 19▲ 16

    PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

    Yuanhang Lei, Baofei Liu, Xingxuan Li, Tao Cheng, Zixuan Wang +7

    Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed framework that learns continuous neural skinning fields from static geometries to construct compact deformation subspaces. Specifically, we propose a Neural Skinning Fields Autoencoder that predicts shape-dependent deformation subspaces without per-object network training. To learn these subspaces without simulation trajectories, we develop a Physics-Informed Self-Supervised Learning strategy that combines skinning-field normalization with conflict-aware gradient correction, stabilizing joint optimization under physical and orthogonality constraints. The learned representation supports efficient reduced dynamics with user control and contact interactions, together with direct animation binding to meshes, point clouds, and 3D Gaussians. For prescribed rig animation, we further introduce a self-supervised complementarity objective to learn complementary elastic responses without enforcing complementarity constraints at runtime. Experiments demonstrate cross-shape generalization of the learned skinning…

    Code
  • arXiv cs.AIOct 19

    FinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI Safety

    Joseph Thomas Thacil, Reetu Raj Harsh, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali

    Generating high-quality synthetic datasets at scale remains a fundamental challenge for training specialized AI systems in data-scarce domains. We present a comprehensive methodology that produces 14.3 million quality-filtered synthetic training examples from a structured taxonomy of 632,000 scenario specifications. Our four-stage pipeline ad- dresses critical challenges in synthetic data quality, diversity, and realism through: (1) systematic pre-generation research establishing optimal generation parameters via diminishing returns analysis, (2) conditional auto evolution mechanisms that remediate low-diversity batches during generation, (3) a two-layer semantic deduplication architecture combining lexical and embedding-based methods, and (4) LLM-as-Judge quality evaluation filtering samples based on behavioral correctness and tuple fidelity. Empirical analysis across three domains (Banking, Insurance, Financial Services) demonstrates domain-specific deduplication patterns ranging from 9.9% to 40.6%, with output generation modes exhibiting highest redundancy. Our batch size optimization reveals mode-specific diversity saturation thresholds, enabling principled allocation…

    PDF
  • arXiv cs.CVOct 19

    Learning the Dose Manifold: A Latent Diffusion Framework for Volumetric Dose Prediction in Automated Radiotherapy Treatment Planning

    J. Boyer-Chammard, R. Vauclin, M. C. Biston, P. Maury, M. Gau +5

    Automated treatment planning (ATP) aims to reduce the unwarranted inter-planner variability of manual planning, while improving treatment quality and efficiency. Most ATP pipelines rely on the prediction of the achievable three-dimensional dose distribution for a given anatomy and the subsequent optimization of machine parameters to reproduce it. Diffusion-based methods are largely slice-wise due to the high dimensionality of radiotherapy data, and assume a one-to-one mapping between anatomy and optimal dose despite the multi-objective nature of treatment planning. They are evaluated on their ability to match reference doses and rarely on their integration in ATP frameworks. We present LaDose, a latent diffusion framework for fully volumetric dose prediction. An autoencoder learned on dose distributions, trained so that perturbed latents decode to plausible doses, compresses dose maps 128-fold and enables 3D diffusion on a single GPU. Prescription values are represented as exact scalar vectors that bypass the image encoder, avoiding resampling and latent compression. Multiscale classifier-free guidance allows for the modulation of clinical trade-offs at inference, without…

    PDF
  • arXiv cs.CVOct 19

    Procedural Exposure Bias in Skill-Augmented Language Model Agents

    Qing Yang, Yuqi Xiong, Pengcheng Huang, Zhipeng Xu, Zhenghao Liu +3

    External skills provide language-model agents with reusable procedural knowledge, yet how models use such knowledge after it is supplied remains poorly understood. We identify Procedural Exposure Bias (PEB), the tendency of language models to increasingly favor an action as its associated procedural pattern is repeatedly exposed in a skill, even when the interaction state and action relevance remain unchanged. We find that PEB strongly depends on how procedural knowledge is represented: presenting the same content visually substantially attenuates exposure-induced shifts in action preference relative to textual presentation. Further analysis shows that this attenuation primarily arises from visual encoding rather than structured layout. Although repeated procedural signals remain recoverable from Visual representations, they exert a weaker influence on downstream action prediction, distinguishing signal accessibility from its use as action evidence. This effect also extends to executable action selection, where increasing exposure more strongly favors the corresponding action under Text than Visual. Layer-wise analyses show that exposure-dependent action evidence becomes more…

    PDF
  • arXiv cs.CLOct 19

    Honeyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock Politeness

    Caixin Kang, Sitong Gong, Tianyu Yan, Kaipeng Zhang, Yoichi Sato +1

    The Chinese idiom "kou mi fu jian" ("honeyed words, hidden daggers") names speech that is polite in form but hostile in function. We present ZhenhuanBench, a 1,592-item benchmark built from expert commentary on Empresses in the Palace, covering speaker intent, emotion-language mismatch, and per-listener uptake. Text-only evaluation covers 34 LLMs. GPT-6 Astra leads the leaderboard at 73.48% overall, while its listener-reaction score is 58.37%. The annotations also supply supervised traces and string-verifiable training rewards. With 338 gold traces, an 8B model outperforms teacher distillation on identical items. Subsequent RL saturates, and chance correction reduces the estimated recoverable performance gap by a factor of 7.5. Our CPR-GRPO loop (Compress-Probe-Replenish) uses this estimate to weight gold supervision, reaching 67.0 on public multiple-choice tasks and 74.5 under the training-matched hidden protocol. Without target-task training, CPR outperforms Base, SFT, and GRPO across six Chinese and English pragmatic and sarcasm evaluations. On three external datasets, training with CPR yields higher mean Macro-F1 than SFT and GRPO.

    PDF
  • arXiv cs.LGOct 19

    HierDTA: Hierarchical Structure-Aware Representation Learning for Drug--Target Affinity Prediction

    Huangchao Xu, Baohua Zhang, Qian Liu, Zhong Jin, Yi Du

    Drug--target affinity (DTA) prediction plays an important role in computer-aided drug discovery, where reliable computational models can help prioritize compound--protein pairs before experimental validation. A key challenge in DTA prediction is to effectively mine multi-level molecular information from drug structures while accurately modeling the binding-site environment of target proteins. To address these issues, we introduce HierDTA, a hierarchical structure-aware framework for DTA prediction. \textcolor{black}{HierDTA represents each drug as an atom--motif heterogeneous graph and introduces an augmentation module that propagates functional-motif semantics to the corresponding atoms. For proteins, kinase-domain structures are converted into residue interaction graphs. The resulting atom and residue representations are integrated using cross-attention to capture pair-specific relationships, while molecule fingerprints and pretrained ESM-2 embeddings provide complementary global information. Compared with state-of-the-art methods, HierDTA achieves superior performance on the Davis dataset across all metrics and attains the highest \(r_m^2\) of 0.791 on KIBA. It also exhibits…

    PDF
  • arXiv cs.PLOct 19

    Blame-aware Recomposition for Secure Compilation Proofs of Low-Level Compartment Isolation

    Basile Schlosser, Jérémy Thibault, Catalin Hritcu

    The security guarantees of existing formally verified compilers for compartmentalized programs in unsafe languages like C stop at a rather high level, assuming a built-in protection mechanism and a block-based memory model. Verifying a concrete, low-level enforcement mechanism for compartment isolation is still a major challenge for current proof techniques. In particular, Abate et al.'s proof technique fails because one of their proof steps, recomposition, essentially requires hiding all information about the code of each compartment, which is not practically achievable at a low level. We propose an extension of their proof technique to a low-level setting where compartments can fully observe each other's code. To do so, we introduce an overlay semantics that allows us to characterize these observations as a form of undefined behaviour, and we use a novel variant of recomposition that we call blame-aware recomposition, which essentially allows recomposing executions as needed in the original high-level proof technique, even if the low-level context observes the code, because this context is ultimately going to be discarded. We apply this new proof to a compartment isolation…

    PDF
  • arXiv cs.LGOct 19

    ORBIT: Autoregressive Time Series Generation via Next Frequency-Band Prediction

    Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Chenchen Sun, Yisheng An +3

    Deep generative models provide an effective modern solution to alleviating the problem of data scarcity by synthesizing realistic time series. However, despite the considerable progress achieved by existing deep time series generators, two key challenges remain: (1) learning hierarchical representations for heterogeneous temporal patterns; and (2) coordinating the generation process of heterogeneous temporal dynamics. To address these key bottlenecks, in this work, we propose ORBIT, a unified deep generative framework for time series. Specifically, we develop two key components: the Frequency-Hierarchical VQ-VAE (FH-VQ-VAE) and the Frequency-Band Autoregressive Transformer (FBAR). The former learns hierarchical representations by decomposing latent temporal representations into different frequency bands and applying residual quantization with increasing token budgets. The latter establishes a novel low-to-high frequency autoregressive direction, yielding a time series generation process that first constructs global temporal structures and then incrementally incorporates fine-grained temporal details. These compact designs not only disentangle heterogeneous temporal patterns for…

    PDF
  • arXiv cs.LGOct 19

    CorteXforge: Scenario-Based RF Dataset Generation on Real Testbeds

    Andréa Joly, Leonardo S Cardoso, Jean-Marie Gorce

    Deep learning for radio frequency (RF) signal analysis relies on large annotated datasets, yet synthetic datasets trade physical realism for controllability, while uncontrolled over-theair measurements offer realism but limited reproducibility. We present CorteXforge, a scenario-based framework for generating realistic and reproducible RF datasets on programmable software defined radio (SDR) testbeds. High-level RF scenarios are automatically translated into synchronized experiments executed on the SLICES-RI/CorteXlab platform, producing fully annotated Signal Metadata Format (SIGMF) datasets that capture hardware impairments and propagation effects. We validate CorteXforge through automatic modulation classification using ModForge, an over-the-air (OTA) dataset generated with the framework. Cross-domain experiments reveal a synthetic-to-real performance gap and show that synthetic pretraining remains beneficial for adaptation to OTA data. CorteXforge provides a practical foundation for reproducible RF dataset generation and future research on domain generalization.

    PDF
  • arXiv cs.CVOct 19

    AVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional Alignment

    Mingyang Wu, Kaituo Feng, Bohao Li, Kaixiong Gong, Zihao Yin +1

    Dense temporal audio-visual captioning is important for multimodal video understanding and generation. However, prior work is constrained by three main limitations: (1) the lack of a dataset combining high temporal resolution, longer videos, and bidirectional alignment between time and events; (2) the reliance of most existing RL methods on checklists; and (3) the lack of a benchmark that bidirectionally evaluates event semantic correctness and temporal accuracy. To address these challenges, we propose: (1) AVTime-50K, a high-quality 50K-scale dataset with temporally precise, semantically accurate captions and longer videos; (2) AVTime, a state-of-the-art model optimized with a novel Bidirectional Temporal-Semantic Alignment (BiTSA) reward that imposes explicit bidirectional constraints between time and events; and (3) AVTime-Bench, a specialized benchmark that introduces a novel bidirectional evaluation of temporal accuracy and semantic correctness. Our code, models, and datasets are available at https://huggingface.co/collections/Apryle/avtime.

    PDF
  • arXiv cs.CLOct 19

    Balance-Aware Pivot Selection for Parallel Diffusion LLM Decoding

    Yejin Lee, Hyundong Jin, Yo-Sub Han

    Diffusion language models enable parallel token generation, offering a promising alternative to sequential autoregressive decoding. Existing acceleration methods use predictive confidence to enable parallel token commitment while preserving generation quality. However, confidence-based selection prioritizes reliable token predictions without explicitly considering how token positions shape the remaining decoding schedule. Moreover, such ordering does not always reflect inter-token dependencies, suggesting that confidence need not be the sole criterion for token selection. Motivated by this limitation, we propose Balance-Aware Pivot Decoding (BPD), which favors central pivots within contiguous masked intervals and decodes the selected positions in parallel. Balanced pivots yield logarithmic decoding depth in the interval length. Our practical method accounts for model uncertainty by combining confidence-based prefilling with confidence-thresholded center selection. We evaluate the resulting quality-efficiency tradeoff on LLaDA and Dream across five mathematical reasoning, code generation, and instruction-following benchmarks. Our implementation is available at:…

    PDF
  • arXiv cs.LGOct 19

    FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation

    Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao +7

    Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer is an exact typed constraint, such as an entity, date, event, or numerical indicator, that determines the next query. This strict answer-conditioned dependency makes small intermediate errors cascade into plausible but wrong search trajectories. We introduce FinHopper, a benchmark for complex financial agents with controlled reasoning depth from 1 to 6 hops, covering stocks, funds, and macroeconomic facts, with gold intermediate answers for process-level evaluation. To construct FinHopper at scale, we design a state-transition-based synthesis framework that composes verified atomic financial QA patterns into dependency-preserving chains, followed by targeted in-synthesis verification, model-ensemble checking, and public-search validation by financial experts. Experiments with 20 LLM-agent configurations show that public search tools are necessary but insufficient: performance drops sharply as hop depth increases, the best model remains far below human experts, and process-aware…

    PDF
  • arXiv cs.AIOct 19

    Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems

    Marco Polignano, Het Darshan Mehta, Pasquale Lops, Ernesto William De Luca, Giovanni Semeraro

    Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision4Rec, an open and modular framework that makes decision models useful for recommendation. A knowledge graph writes the logs of each recommendation scenario as short statements on a defined scale, such as "sold: top 10%". A pool of agents, proposes candidates, and a residual ranker keeps the best 30. A decision model, trained once on real choices of three scenarios, reads them through one interface of typed questions, and a fusion step combines its answers with the score of the ranker. Any model with this interface can be used, and we run the commercial Jev, the released open Kev and Kev models trained by us on recommendation requests. The framework with a trained 4B decision model is 25 to 36% above the best trained baseline in NDCG@10 in three sparse Amazon catalogues, one of them never used to train the decision model, and almost tie with baselines on the dense Steam dataset. Most of the gain comes from the pool, and with a trained recommender it comes from what the agents know about its candidates rather than…

    PDF
  • arXiv cs.AIOct 19

    AuDQ: Auditable Data Quality through Agentic Rule Discovery

    Jacopo Biggiogera, Nicolas Colombo, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali

    High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable through immutable execution traces. As a first step toward validating this vision, we present a concrete implementation of its agentic rule-discovery core with two rule acquisition modes (Full-Agentic and Guided) and a human-in-the-loop (HITL) review interface. We define an evaluation framework and run experiments addressing whether our fully autonomous, divide-and-conquer agentic rule discovery produces rules of the same quality and diversity as those specified by a human expert, reporting preliminary results on two real world industry datasets in the finance and retail domains.

    PDF
  • arXiv cs.LGOct 19

    Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

    Xuyuan Xiong, Siyu Chen, Zihan Shao, Yue Su, Weiyang Jin +3

    Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters. They are trained with backpropagation through time (BPTT). To save training compute, BPTT is often truncated to the last few loops, but truncation yields biased gradients that may weaken the benefit of looping. In this work, we study the value of truncation in looped transformer training in a systematic way: we jointly vary model size, training tokens, and forward and backward loop counts across nearly 600 training runs and fit a unified scaling law that captures the effects of looping and truncation through effective parameters. Despite the training-compute savings of truncation, our fitted law favors full BPTT when forward and backward loop counts are jointly optimized. In matched-compute runs, full BPTT through fewer loops consistently outperforms truncated settings of the same compute. The law further shows that at fixed model size, the compute-optimal loop count and training-token budget both grow with compute. When model size is also free, the law identifies two fully trained loops as the best looped setting. Experimentally, this setting…

    PDF
Load more
PDF