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 fields3113Multimodal502Agents484Frontier LLMs419Inference & serving252Image segmentation1693D scene150Learning verifiable rewards145Graph learning142Voice AI93Classifier & causal discovery83Forecasting time74Flow matching66Evals62Federated learning48Teacher policy distillation46All 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

  • Training & fine-tuning42+90.9%
  • AI safety29+61.1%
  • Computer vision31+55.0%
  • Evals62+34.8%
  • Federated learning48+29.7%
  • Code models13+18.2%
  • Quantum machine learning24+14.3%
  • Image & video generation20+5.3%

Papers

  • arXiv cs.ROOct 16

    AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation

    Jiawei Geng, Zhenyang Liu, Yuzheng Wu, Yanwei Fu

    Rapid progress in embodied intelligence has enabled increasingly capable robots to follow language instructions and manipulate diverse objects. However, strong results in structured environments do not automatically transfer to open-world conditions, where clutter, occlusion, and changing viewpoints can obscure the spatial relationships required for action. To address this perceptual gap, a virtual active-perception paradigm is introduced. AWAM, an Active World-Action Model actively plans where to observe and imagines what will be seen along the planned trajectory before acting. Task-related virtual camera motion is predicted and used as a structured query into a geometry-conditioned world model, producing a reusable spatial prior for manipulation, which is later compressed into a fixed memory and fused with live observations through cross-attention for diffusion-based action prediction. AWAM achieves competitive success rates with 75.9% on LIBERO-Occ, 62.4% on LIBERO-Plus, 76.5% on RLBench-OG Occlusion1, and 94.4% in real-robot trials. These results support improved robustness to the evaluated occlusions and distribution shifts, addressing part of the gap between structured…

    PDF
  • arXiv cs.LGOct 16

    Forecasting Voltage Time Series under Anomalies Using a WGAN Model With Lipschitz Control and Progressive Kernel Critic Strategy

    Najmieh Sadat Safarabadi

    In time-series forecasting tasks, the use of recursive forecasting on high-dimensional data substantially increases the complexity of the prediction process. The main challenge is that long-term dynamics becomes harder to model, since the sequences show greater temporal variability. To counteract this limitation and improve the modeling of long-term dynamics, and more importantly, address high-dimensional recursive forecasting, this paper uses a Wasserstein GAN equipped with a progressive Lipschitz penalty and an adaptive kernel. This model is capable of taking a window of the data stream and forecasting the next values, subsequently reconstructing the time-series stream and dynamically adapting its kernel to each new window. The proposed model is a deep learning framework based on a Wasserstein GAN (WGAN-CLP) with an adaptive kernel to model alterations in streaming voltage time series. To establish the methodological foundation, we review the WGAN-LP formulation another variant model in this class and extend its framework through an adaptive kernel critic model. We then evaluate this extended model using power ratios, correlation coefficient (CC), and relative root mean squared…

    PDF
  • arXiv cs.CLOct 16

    Sentence-Level Topic Modeling with Lexical and Contextual Evidence

    Federica Granese, Serena Villata, Charles Bouveyron

    Topic modeling faces a fundamental granularity dilemma: probabilistic topic models assign topics at the word level, whereas transformer-based methods operate at the document level. The latter overlooks that real-world documents typically cover multiple topics, whereas the former relies on individual words, which rarely provide sufficient context to identify them. We introduce SentenceETM, a neural topic model that assigns a topic to each sentence by jointly using lexical and contextual evidence. Each topic is described both by a distribution over the vocabulary, defined through word embeddings, and by a Gaussian over sentence embeddings concentrated on a topic-specific low-dimensional subspace. The topic of a sentence generates both its words and its embedding and is marginalized exactly, so that its posterior combines the two sources of evidence. Document proportions are inferred with amortized variational inference, while the Gaussian parameters are re-estimated in closed form. Experiments show that SentenceETM consistently improves sentence-level topic assignment over state-of-the-art approaches, and a case study of a presidential debate shows how sentence-level topics reveal…

    PDF
  • arXiv cs.PFOct 16

    Data-Driven Prediction of Optimal MPI Rank Placement and Node Count for Memory-Bound CFD on AMD EPYC Clusters

    Marcin Lawenda, Łukasz Szustak, Aleksandra Krasicka

    Users who run a memory-bound OpenFOAM case on an AMD EPYC cluster must decide how many nodes to use and how many MPI ranks to place on each core complex. The fastest choice is often not the cheapest one. This paper revisits our earlier analytical model of this performance and energy trade-off with 560 measured configurations of the motorBike case on five Zen 4 and Zen 5 EPYC processors, including socket power from processor telemetry. On up to four nodes, small meshes are both fastest and cheapest on a single node on most processors. For the largest mesh the largest node count is both the fastest and the cheapest option, because its speedup is superlinear. A genuine trade-off arises only for medium meshes, where full speed costs a median of 20 to 97% more node hours than the cheapest option. The L3 miss rate and the halo traffic per cell are consistent with this pattern. For a new mesh of the same case, the configuration that was optimal on the nearest measured mesh is near optimal in 75 to 85% of the decisions. Running the two configurations it recommends for speed and for cost raises this share to 85 to 90% for runtime and node hours and determines the trade-off with median…

    PDF
  • arXiv cs.CVOct 16

    FloodVLM-Pix: Language-Guided Pixel-Level Flood Understanding

    Chengyang Zhang, Zhihao Wang, Zhiyu Long, Xueqian Wang, Quanming Yao +2

    As climate change intensifies, floods are becoming more frequent and destructive, making accurate flood understanding an urgent priority. However, existing vision-language models perform poorly on flood-related tasks, suffering from attentional bias and inaccurate descriptions of flood magnitude. To bridge this gap, we construct the first large-scale remote sensing flood multi-modal benchmark that supports language-level flood understanding and pixel-level flood segmentation. The benchmark contains 131,200 flood image patches and corresponding 443,100 textual descriptions for flood severity and evolution. Based on this benchmark, we propose FloodVLM-Pix, a language-guided pixel-level flood understanding model that includes a flood prior module and a multi-temporal flood pixel decoder to achieve accurate flood understanding. The flood prior module automatically distills sub-region flood spatial priors and inputs priors into FloodVLM-Pix, solving the attentional bias problem in flood language understanding. The flood pixel decoder introduces a novel general-specific feature fusion mechanism to address performance degradation caused by interference (e.g., clouds or mountain shadows)…

    PDF
  • arXiv cs.CVOct 16▲ 88

    MOSS-Image Technical Report

    MOSI. AI

    Recent closed-source image generation systems can produce diverse visual content from simple compositions to information-dense graphics, yet open-weight text-to-image models still struggle with dense text and intricate layouts. To narrow this gap, we introduce MOSS-Image, an open generation system that combines high-fidelity visual synthesis with intent-aware composition. First, we pretrain a 5B single-stream diffusion transformer (DiT) from scratch with a carefully designed recipe, enabling bilingual long-form text rendering and precise layout control. Second, we develop an intention-aware agentic prompt enhancement (PE) module that translates diverse user requests into detailed content and layout specifications. Together, they enable MOSS-Image to generate text-rich and layout-coherent images. We further introduce LongLongTextBench (LLTB) for evaluating long-form English and Chinese text rendering, and RealLayoutArena (RLA) for end-to-end layout-rich generation. MOSS-Image achieves state-of-the-art performance among open-weight models on LLTB, with an average text coverage of 96.3%. On RLA, MOSS-Image ranks second in the end-to-end system comparison, while its backbone ranks…

    Code
  • arXiv cs.ROOct 16

    Beyond Success Rate: Interventional Evaluation of Memory in Vision-Language-Action Systems

    Keyuan Luo, Yi Xie, Wanyun Ling, Yuanzhe Li, Ziyue Li +1

    When we say that a robot uses memory, does that memory actually play a role? Success-rate ablations alone cannot establish the use of task-relevant facts: they change information and computation together, while aggregate rates can hide offsetting gains and losses. We propose an Interventional Memory Evaluation Protocol (IMEP) for vision-language-action (VLA) systems to address four questions: (1) Does memory provide a net benefit? (2) Under what conditions does memory help? (3) Do changes to memory alter task outcomes? (4) Are these effects specific to task-relevant facts? At the retrieval interface, we compare target-fact substitutions with fact-preserving replacements, minimal numerical perturbations, and exact replicas, while assessing decision correctness separately from motor execution success. We evaluate within-episode, cross-episode, and agentic memory. In cross-episode learned-bank experiments, a one-unit-in-the-last-place (ULP) intervention, including its installation procedure, changes 11.9% of seed-paired outcomes, while changing key facts produces no clear additional effect over fact-preserving replacements. To examine when memory helps, we introduce ChainBench,…

    PDF
  • arXiv cs.AIOct 16

    Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries

    Junchi Liao

    Modern LLM applications rely on runtime monitors that inspect tool calls, traces, streams, detector outputs, and verifier inputs. This creates an interface-reliability problem: a framework path may remain operational while policy-relevant evidence never reaches its decision point. In one representative case, a regex detector returned a positive match, but the framework stranded the result before the block decision. This differs from jailbreaks and detector errors because the evidence is already recognized yet disconnected from enforcement. We study this repair-boundary signature with canary contracts: parent/fixed confirmation units that place a known payload only on the changed evidence surface and record monitor visibility together with the downstream decision for action-boundary cases. Applying the protocol to public framework repairs, we confirm 18 evidence-path failures across 11 LLM or agent safety project groups and four implementation ecosystems. Nine are established-boundary repairs, eight are new-surface policy-coverage gaps, and one is a boundary-only evidence case. Fourteen reach E1 enforcement boundaries: seven native action outcomes, six configured enforcement…

    PDF
  • arXiv cs.CVOct 16

    UniPolar: Joint Image and Polarimetric Restoration under Compound Degradations via Physical Consistency Learning

    Yang Jin, Guangyu Guo, Linghao Shen, Binglu Wang

    Polarimetric image restoration aims to recover polarization angle images and reliable polarimetric quantities from degraded observations. Beyond visual fidelity, it also requires preserving the physical relationships underlying reliable polarimetric estimation. However, existing methods typically address either device- or environment-induced degradations in isolation, limiting their applicability to color polarization filter array (CPFA) imaging, where both often coexist. Such compound degradations jointly perturb image intensities and cross angle polarization differences. Consequently, improved image fidelity alone does not necessarily ensure accurate Stokes, DoLP, and AoLP recovery. To address this challenge, we propose UniPolar, a coupled Image Stokes framework for joint image polarimetric restoration from compound-degraded CPFA observations. Specifically, UniPolar employs two complementary streams to reconstruct four polarization-angle images and directly predict Stokes difference components. To coordinate these streams, Degradation Conditioned Cross Domain Interaction combines Dual Domain Frequency Interaction for frequency selective evidence exchange with Degradation…

    PDF
  • arXiv eess.IVOct 16

    Benchmarking and Improvement of Artifact Segmentation Methods in H&E-Stained Whole Slide Imaging

    Julia Merta, Daniel Mendelsohn, Benedikt Schoser, Joanna Polanska, Michal Marczyk

    Technical artifacts introduced during tissue preparation or slide scanning remain a major obstacle to developing robust computational pathology algorithms for hematoxylin and eosin (HE)-stained whole-slide images (WSIs). Despite the growing number of quality-control tools, their real-world utility remains hard to assess because of the limited number of publicly available implementations and the lack of systematic, multi-dataset comparisons. This paper presents a benchmark of artifact segmentation methods for HE-stained WSIs. After a literature review, six publicly available algorithms were selected and compared in terms of their ability to segment artifact-free tissue and selected artifact classes. Two publicly available datasets and a newly introduced dataset released to support further research were used for evaluation. Tissue samples from multiple medical centers and different organs are included, enabling evaluation across heterogeneous data sources. Segmentation performance was assessed using Dice Index, pixel-level recall, and false discovery rate for artifact-free tissue segmentation. For algorithms supporting multiclass artifact segmentation, class-wise Dice Index and…

    PDF
  • arXiv cs.CVOct 16

    STC-MGNet: Spatial-Temporal-Channel Attention-Enhanced Multimodal Graph Network for Pedestrian Intention Prediction

    Yuanzhe Li, Meng Wang

    Accurate prediction of pedestrian crossing intentions plays a critical role in enhancing the safety of pedestrian-vehicle interactions in autonomous driving. However, effectively capturing subtle spatiotemporal patterns in pedestrian pose sequences and integrating complementary visual and ego-vehicle motion information remain challenging. This paper proposes a spatial-temporal-channel attention-enhanced multimodal graph network (STC-MGNet) for pedestrian crossing intention prediction. STC-MGNet introduces a spatial-temporal-channel (STC) attention-enhanced pose graph encoder to learn discriminative representations from pedestrian pose sequences. Three parallel attention branches selectively emphasize informative skeletal joints, observation frames, and feature channels, with their outputs integrated through learnable fusion weights. To leverage complementary visual and ego-vehicle motion information, a multi-stage cross-modal channel modulation mechanism is introduced to adaptively refine pose representations through modality-specific channel gating at successive graph encoding stages. Experimental results demonstrate that STC-MGNet achieves accuracy rates of 70%, 87%, and 88% on…

    PDF
  • arXiv cs.LGOct 16

    RTSM: Adapting Recursive Models to Multivariate Time-Series Classification

    Georg Tenzing, Anna Tegon, Luca Benini, Thorir Mar Ingolfsson

    Accurate multivariate time-series classification requires extracting temporal features and integrating information across a sequence. Weight-tied refinement offers a way to repeatedly process these features without allocating new parameters at each stage. Applying this principle to time series requires choosing both a temporal representation and a latent-state organization suited to classification. We introduce the Recursive Time-Series Model (RTSM), which combines a learned convolutional temporal tokenizer, single-state weight-tied refinement, and a pooled classification readout. Across all 30 UEA datasets, RTSM achieves 72.81% mean accuracy under validation-based configuration and checkpoint selection, the highest observed mean among the 17 evaluated deep-learning models and 1.60 percentage points above MambaSL. Ablations on eight datasets favor the proposed tokenizer over a simple convolutional embedding and the single-state model over the tested two-state variants. The complete classifier reaches 86.10% mean accuracy versus 84.79% for a separately trained tokenizer-only classifier. These findings identify temporal encoding and state organization as key design choices for…

    PDF
  • arXiv cs.LGOct 16

    Client-Aware Security Adaptive Early Exit Vision Transformers for Heterogeneous Federated Learning

    Sahar Refaei Ghalibafan, Samira Nazari, Christian Herglotz, Maksim Jenihhin, Mahdi Taheri

    Federated learning (FL) trains a shared model across data-owning clients without centralizing raw data, but client data difficulty and compute budgets can differ. We study local early-exit Vision Transformer (ViT) inference, where an intermediate classifier may return a prediction before the final Transformer stage. The proposed method replaces one global acceptance threshold with a client-specific base threshold from label entropy and shallow-exit confidence, then adjusts each input using predictive entropy, confidence, top-two class margin, and exit depth. Aggregation uses only clients that updated a parameter. Security-aware routing reaches 88.70% CIFAR-10 accuracy with 32.0% depth saving and 73.7% ImageNet-1K top-1 accuracy with 30\% saving. On matched six-client non-IID CIFAR-100, full-depth accuracy is 72.28% versus 68.20--71.80% for four heterogeneous-FL baselines; robustness-aware routing reaches 70.01% with 32.55% saving.

    PDF
  • arXiv cs.AIOct 16

    OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting

    Kwangryeol Park, Seulki Lee

    Self-supervised representation learning has advanced time series forecasting by capturing robust features from unlabeled data. However, existing contrastive and masking-based methods often struggle to explicitly model the underlying temporal flow, either by treating time lag as noise or by disrupting the inherent temporal dynamics essential for forecasting. To address these limitations, we propose OliO (**O**DE-based **Li**near Transition **O**perator), a plug-and-play self-supervised learning method that learns bidirectional temporal flows as a continuous and structurally consistent dynamical system. OliO introduces a transition operator derived from linear Ordinary Differential Equations (ODEs) to align latent representations across arbitrary time shifts. By imposing a strictly upper triangular constraint on the transition matrix, we mathematically ensure numerical stability and enforce a robust polynomial boundary that effectively captures long-term dependencies while preventing the exponential divergence typically found in unconstrained ODE-based models. This structural constraint induces a temporally coherent representation space that preserves the underlying flow essential…

    PDF
  • arXiv cs.CLOct 16

    Language Models Learn to Improve Language Models

    Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He +5

    Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning experimental feedback into a learned ability to propose effective improvements across models faces two challenges. First, training such an ability with real feedback is expensive: reinforcement learning (RL) requires evaluating tens of thousands of proposals, each potentially requiring a full model-training run. Even at ten GPU-hours per run, reward collection alone would consume hundreds of thousands of GPU-hours, motivating a cheaper surrogate. Second, surrogate feedback can become unreliable as policy optimization favors overestimated proposals when the proposal distribution shifts. To address these challenges, we propose LM2LM, which trains LLMs with RL to generate effective LM improvement proposals. To provide scalable feedback, we use a research world model (RWM), a frozen LLM that predicts proposal gains from real experimental records provided in context, as the reward model for RL. To maintain feedback reliability, we periodically execute current-policy proposals ranked highly…

    PDF
  • arXiv cs.LGOct 16

    How Finite-Rank Bottlenecks Shape the Low-Rank Adaptation Landscape

    Long Nguyen-Chi, Quynh Nguyen, Thanh Nguyen-Cung, Binh T. Nguyen

    Low-rank adaptation (LoRA) has become the standard method for parameter-efficient fine-tuning of large pretrained models, yet theoretical explanations for why low-rank updates suffice remain incomplete. Most existing analyses rely on the Neural Tangent Kernel (NTK) regime, which linearizes the network around the pretrained weights. In this work, we take a different approach that requires no linearization: our key observation is that, once the backbone is frozen, the loss sees each adapted weight matrix only through a finite-rank linear map induced by the frozen activations. Trace-norm regularization then forces the optimizer to pick a low-rank matrix among all matrices that produce the same observed output. This yields global minimizers whose ranks are controlled by the rank of this map, which we call the \emph{bottleneck rank}, rather than the sample size. For multi-head attention, we obtain tighter rank upper bounds by exploiting two additional invariances: row-wise softmax is insensitive to additive row constants in the score matrix, and value updates are observable only after attention weighting and frozen output projection. For the factorized LoRA objective with weight…

    PDF
  • arXiv cs.AIOct 16

    Robust Function Calling for LLM Agents Under Interface Drift

    Aniruddha Chattopadhyay, Kanishka Halder, Partha Sarathi Roy

    Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics remain fixed, creating a practical reliability problem for function-calling systems. We study this failure mode as interface drift and evaluate whether a lightweight, training-free repair layer can recover robustness without retraining the base model. Our method, SchemaShield-Lite, combines schema validation, candidate-set retry for missing tool names, and one-shot constrained repair. On Qwen3.5-9B, it raises DICE-300 accuracy from 0.717 to 0.813 and BFCL-200 accuracy from 0.580 to 0.805, recovering 19/22 and 33/45 drift-induced failures with no observed repair harms. Naive retry does not explain the gains. Ablations show that candidate-set drift, especially distractor tools, accounts for most observed damage, while description and schema edits alone are less harmful. The results position validation-and-repair as a practical robustness layer for deployed LLM-agent tool use.

    PDF
  • arXiv cs.LGOct 16

    SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product Computation

    Seyed Kamaledin Setarehdan

    Modern deep learning systems increasingly rely on high-dimensional vector operations, in which large input and parameter vectors are repeatedly stored, transferred, and processed. Although substantial research has focused on reducing neural-network model size through pruning, quantization, knowledge distillation, and efficient architectures, the storage, memory-traffic, and communication costs associated with repeatedly presented high-dimensional input vectors remain important practical considerations, particularly in distributed and edge-computing environments. This paper proposes the SETAREH (Sorting-assisted Energy-concentrating Transform for Approximate Representation using Haar wavelets) transform, a Haar-wavelet-based sparsification approach for approximating the inner product between a fixed high-dimensional coefficient vector and successive input vectors. By applying the same sequence of permutations and Haar transforms to both vectors, SETAREH preserves the exact inner product before truncation. It then retains only a subset of the transformed coefficient-input pairs, reducing their representation cost while introducing a controllable approximation error. To evaluate…

    PDF
  • arXiv cs.LGOct 16

    Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning

    Yalda Shabanzadeh, Diyuan Wu, Marco Mondelli

    Pretrained models are often reused across downstream tasks, motivating the question of whether this transfer learning procedure can provide a substantial performance improvement, namely, in terms of the scaling law. We address this question in the prototypical setting of high-dimensional regression, where (i) a pretrained \emph{source} model is trained via ridge regression, and (ii) a fine-tuned \emph{target} model is regularized via the $L_2$ distance from the source estimator. First, we establish a deterministic equivalent for the risk of this two-step procedure under both model and covariance shift. Next, by specializing the deterministic equivalent to a shared regression function and commuting power-law covariance spectra, we identify a regime where the resulting scaling law achieves the minimax-optimal exponent. Notably, in this regime, the optimal source regularization depends on source data only, indicating its universality across all targets. Furthermore, we show that the same optimal rate is achieved by performing the fine-tuning step via one-pass stochastic gradient descent. We support our theoretical analysis via experiments on both synthetic settings and language…

    PDF
  • arXiv cs.LGOct 16

    HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning

    Ardan Suphi, Ben Moseley, Gareth S Collins, Valentin T Bickel, Vidhya G Rangarajan

    The High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter (MRO) acquires imagery of Mars at 25--30 cm/pixel, supporting studies of martian geology, climate history, and landing-site characterization. Its 14-detector focal plane assembly includes several overlapping detectors that enable the acquisition of three-channel colour-infrared images, which are important for identifying compositional variations and studying active surface processes. In 2023, a detector in the center of the focal plane assembly (RED4) began failing intermittently, creating a gap in acquired imagery and reducing the instrument's colour-imaging capability by half. The HiRISE processing pipeline provides a synthetic red (SYN4) channel obtained by linearly scaling the co-located infrared (IR10) channel. However, this approach cannot capture observed non-linear relationships between the colour channels, limiting its accuracy and applicability. Here, we present HiPredict, a machine-learning framework that reconstructs RED4 from co-located IR10 and blue-green (BG12) imagery, neighbouring red-channel observations, and acquisition metadata. The model employs a U-Net…

    PDF
Load more
Model
PDF