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 fields3443Multimodal542Agents516Frontier LLMs439Inference & serving268Image segmentation179Learning verifiable rewards1613D scene159Graph learning156Voice AI99Evals97Classifier & causal discovery86Forecasting time78Flow matching72Training & fine-tuning63Teacher policy distillation51All 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
  • Training & fine-tuning63+6200.0%
  • Code models23+2200.0%
  • AI safety45+2150.0%
  • Small LLMs11+1000.0%
  • Robotics29+866.7%
  • Computer vision46+820.0%
  • Evals97+781.8%
  • Image & video generation34+580.0%

Papers

  • arXiv cs.CVOct 18

    HullProbe: Measuring Interventional Part Reliance in Maritime Vessel Classifiers

    Faisal Mohammad, Mohamed Younis

    Recognizing a vessel's type from an image supports maritime surveillance and sanctions monitoring, but a classifier can reach high accuracy by leaning on the generic hull instead of the more distinctive superstructure, and is then fooled when a vessel is re-hulled or occluded. De-biasing methods claim to remove such reliance, yet the field certifies them with worst-group accuracy, a proxy that needs group labels and only infers reliance from accuracy. We measure the reliance directly. HullProbe swaps a registered anatomical part of a vessel for another instance's and reads how much that part drives the decision, using a same-class swap to control for compositing artifacts. Because a surface vessel is a hull and a superstructure arranged along one axis, its parts form a 2x3 grid whose 2^6 = 64 swaps we evaluate exhaustively, and a single Walsh transform returns each part's interventional influence and its interaction spectrum. On planted shortcuts, where the true reliance is known, the measure tracks worst-group accuracy (r = -0.94 over 45 configurations), and replacing its learned segmenter with human annotations changes the hull-share by less than the audit's resolution. On the…

    PDF
  • arXiv cs.CLOct 18

    TIRE: Top-Down Formula Instantiation with Reliable Execution for Physics Problem Synthesis

    Xiaoyu Wu, Zhaoxin Yu, Xinglin Xiao, Nan Xu

    Advancing physics reasoning in large language models requires scalable training data that connect physical laws, concrete problem scenarios, and verifiable numerical answers. Expert-designed problems offer top-down control over physical laws, conditions, and scenarios, but require costly human effort. LLM-based synthesis from texts scales efficiently, but model-generated answers and assessments leave supervision vulnerable to hallucinations. We introduce TIRE, a framework for Top-Down Formula Instantiation with Reliable Execution that brings knowledge-driven problem construction to large-scale data generation. Top-down instantiation uses reusable physical formulas and their applicability conditions to control the physical relations and numerical configurations of generated problems. Reliable execution establishes reference answers before problem generation, providing a common numerical foundation for problem construction and teacher distillation. Together, these mechanisms combine control over problem content with execution-grounded supervision for both supervised fine-tuning and reinforcement learning. Using TIRE, we construct TIRE-19k, spanning nine subfields of physics. Across…

    PDF
  • arXiv cs.CROct 18

    Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use

    Tianhe Lu, Sakuna Harinda Jayasundara, Eric Spero, Ewan Tempero, Robert Biddle +1

    Cryptographic API misuse in large language model-generated code can compromise software security. While many existing approaches improve code security by modifying model parameters or inputs, how representation changes associated with different cryptographic API repairs can support a shared intervention for safer code generation remains underexplored. To investigate this, we construct 48,000 matched program pairs across four programming languages and ten cryptographic API misuse categories. Each pair changes a specified API decision while preserving the programming task. Subtracting the misuse program's internal representation from its secure counterpart's gives a repair vector. Across five models, comparisons of mean repair vectors reveal stronger organization by misuse category than by language. These category-specific patterns also support a shared intervention. We introduce CrypSteer, which extracts a shared direction by normalizing repair differences and selecting a principal component aligned with repairs across misuse categories. With model weights fixed, adding one shared direction per model to its internal activations during generation improves aggregate target security…

    PDF
  • arXiv stat.MLOct 18

    Decision-Target Reversal under Informative Label Missingness

    Farinborz Setoudehtazangi, Geoffrey J. McLachlan

    Informative label missingness can improve classification efficiency because the pattern of label availability may itself contain information about the discriminant structure. We show that this advantage need not persist across deployment objectives: with the data-generating model and statistical experiments held fixed, informative partial classification can be favourable under one loss and unfavourable under another. We call this phenomenon decision-target reversal. For binary Gaussian discrimination, we derive a local cost-sensitive excess-risk expansion and, in one dimension, obtain explicit critical cost ratios at which the first-order risk ordering reverses. We show that the required covariance geometry arises under finite uncertainty-dependent missingness mechanisms with a fixed marginal missing-label proportion. We then extend the analysis to multiclass finite-action problems through loss-specific active-boundary curvature, yielding a general decision-target frontier. Monte Carlo experiments illustrate the predicted reversals, and a descriptive gastrointestinal-lesion application with agreement-defined label availability illustrates sensitivity to deployment costs. The…

    PDF
  • arXiv cs.CLOct 18

    MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity

    Jiajun Tan, Fei Sun, Xinyu Ma, Shixuan Zhang, Du Su +4

    Memory serves as the core component of LLM-based agents, enabling personalized responses via extracting and using user preferences from past interactions. However, its use may reduce response diversity, thereby narrowing the range of information available to users. Existing evaluations rely largely on synthetic interactions and cover few memory systems, leaving the effects of memory on response diversity insufficiently evaluated in real-world scenarios. We introduce MemBubble, a benchmark of 1000 instances built on preferences extracted from real user-assistant conversations. To measure the extent to which memory concentrates response distributions, we construct test queries in scenarios distinct from user preferences while preserving topical relevance through shared preference categories. Across multiple LLMs and memory mechanisms, entropy decreases by 34.7% on average compared with directly providing the full interaction history, highlighting the important role of memory processing in diversity loss. We also explore simple user-side interventions and changes in information availability but find that these do not effectively close the diversity gap. Our findings highlight the…

    PDF
  • arXiv cs.LGOct 18

    Trackable Skill Library Lifecycle Management for Agentic Reinforcement Learning

    Xi Zhu, Yuanlin Duan, Changyi Yang, Kai Mei, Riyang Bao +2

    Skill-augmented agentic RL has emerged as an effective approach to improving LLM agents on long-horizon tasks. Despite this progress, individual skills may follow distinct trajectories as the policy evolves, with some becoming redundant after the model internalizes their capabilities, others remaining valuable as external scaffolding, and still others turning harmful. However, existing skill library systems fail to identify each skill's true contribution due to free-riding among co-retrieved skills, difficulty confounding across tasks, and the absence of skill-specific counterfactual evidence, which prevents reliable skill lifecycle management. We propose TrackRL, an agentic RL framework where skill tracking drives skill library full lifecycle management. Specifically, within each GRPO group, we turn grouped sampling into online randomized controlled experiments. Independent random injection and within-group contrasts on the same task isolate each skill's true contribution, and reliability-weighted aggregation accumulates evidence across groups. As evidence accumulates, we continuously track skill utility, which measures the skill's causal contribution as external scaffolding,…

    PDF
  • arXiv cs.CLOct 18

    The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering

    Debopriyo Banerjee, Owais Aijaz, Ahmer Tabassum, Zhuohan Xie, Preslav Nakov +1

    Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it cannot anticipate which passages a question requires and discards document-level context that resolves cross-passage references. We introduce evidence-based generation (EBG), requiring models to return an answer with line-level citations, and a joint Ans+Evid metric that scores correctness and grounding simultaneously. We reformulate two corpora into evidence-grounded multi-document QA benchmarks- MultiHop-RAG and QASPER-MP, a multi-paper adaptation of QASPER with realistic short paper cues, and pair them with a controlled synthetic two-hop haystack and an evidence-augmented NoLiMa spanning 10K-1M characters. Across ten proprietary frontier and three open-weight LLMs, EBG isolates two RAG limitations that long-context models avoid: similarity retrieval surfaces any relevant chunk far more reliably than all required chunks for multi-fact queries, and chunking destroys document meta-information needed to resolve identity-bearing queries. EBG also exposes grounding failures invisible to…

    PDF
  • arXiv cs.LGOct 18

    Beyond Policy Discrepancy: Capability-Aware Multi-Teacher On-Policy Distillation

    Xuanfeng Yang, Le Gui, Jiaming Wang, Xuan Zhang

    Multi-teacher on-policy distillation (MOPD) integrates domain specialists into a shared student, but determining how strongly each teacher should supervise remains challenging. Existing discrepancy-based allocation can assign strong supervision even when the student already matches or exceeds the teacher's task performance, since behavioral mismatch does not necessarily imply a remaining capability deficit. We propose Capability-Aware Multi-Teacher On-Policy Distillation (CA-MOPD), which combines specialist merging with capability-guided allocation to account for what the student has already learned. CA-MOPD first merges reinforcement-learning specialists into a strong student initialization, then uses verifier-estimated teacher--student capability gaps to adjust domain-level distillation strength. Supervision decreases as capability gaps close and increases when estimated student capability regresses, while dense token-level guidance remains provided by the teachers. Across six benchmarks spanning mathematics, code generation, and instruction following, CA-MOPD achieves an average score of 32.22, outperforming naive MOPD, Open-MOPD, and the merged initialization by 0.86, 0.83,…

    PDF
  • arXiv cs.CLOct 18

    Memories That Outlive Their Reasons: Dependency-Tethered Memory for Tool-Using LLM Agents

    Yiqi Wang, Jinqian Ju, Jiaqi Zhang, Zhangkai Wu, Yiqun Duan +3

    Agents now act on the Web, publishing packages, models and datasets through registry APIs, and remembering past verifications spares them the work. But a verdict rests on premises. When a signing key is revoked, everything built on it stops passing, yet the advisory names only the key, and the old verdicts of its dependents may never share a retrieval window with it. This non-locality of invalidation turns memory into a liability: in long simulated chats, an agent reading a memory of atomic facts publishes 62% of the objects whose failure lies upstream, each backed by a record that was true when written. Yet derivation is local even when invalidation is not. Tether records, at write time, the exact versions each verdict derives from, and at read time withdraws any verdict whose support has failed anywhere in the store; the agent reads the same fields as before. On Fallout, a generator of versioned worlds with hypothesis-blind simulated histories shared by every memory, Tether publishes 0.3% of upstream-failing objects across three domains when relations are stated with their verdicts, with 37% fewer verification calls than checking everything. A-Mem and Graphiti re-verify most…

    PDF
  • arXiv cs.CLOct 18

    Behave Like Experts: Fusing Data with Semantic Knowledge for Effective and Efficient Semantic Map Construction

    Zhu Liu, Zhen Hu, Yuxuan Liu, Ying Liu

    Semantic map models (SMMs) construct a graph that reflects conceptual similarity by comparing cross-lingual form-meaning mappings. Experts build such models not only by obeying the data constraint, i.e., the connectivity hypothesis, which states that conceptual nodes belonging to the same form must be connected, but also by incorporating their prior semantic knowledge. Current automatic methods ignore this knowledge, which harms both accuracy and efficiency by enlarging the search space of candidate graphs. In this paper, we fuse the distributional semantic knowledge hidden in the internal representations of language models into a top-down, data-driven algorithm. This expert-like behavior re-sorts the candidates in a huge search space, guided by conceptual semantics similarity. Experiments on a self-collected benchmark of 10 datasets and comprehensive metrics show that our method builds SMMs both effectively and efficiently.

    PDF
  • arXiv cs.LGOct 18

    ClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer

    Yanyan Wu, Guanyu Zhu, Changbin Zhao, Jin Zhang, Dexu Yu +5

    Offline sepsis treatment aims to learn treatment policies from retrospective ICU trajectories. Decision Transformer-based methods provide a natural sequence modeling framework for this task, but they mainly rely on raw physiological states and historical clinician actions. Such raw trajectory tokens may not explicitly capture clinical semantics that clinicians use in practice, such as patient severity, recent treatment response, and current risk priorities. To address this limitation, we propose ClinSDT, an LLM-assisted Decision Transformer framework for offline sepsis treatment. ClinSDT uses a frozen LLM as a semantic bridge rather than a treatment decision maker. It constructs three clinical semantic views from ICU trajectories, namely Profile, Context, and Advisory, and inserts their encoded representations as independent tokens into a Decision Transformer policy. To support policy refinement and rollout, ClinSDT further trains a Treatment-Response Forecaster to estimate the next physiological state, SAPS-II change, and predictive uncertainty from state-action inputs. In the second training stage, the forecaster screens local counterfactual treatment candidates, and only…

    PDF
  • arXiv cs.CVOct 18

    LC-TSRNet: A Land-Cover-Guided Two-Stage Network for Annual MODIS Surface Reflectance Time Series Reconstruction

    Wenjuan Zhang, Xuesong Ma, Zhen Li, Meixiang Wang, Caimeng Yi +3

    MODIS surface reflectance (SR) products often suffer from data gaps due to cloud contamination and sensor malfunctions, limiting their applications in long-term and large-scale studies. Most existing methods rely on cloud-free observations from optical time series or introduce SAR time series as auxiliary information. However, due to the coarse spatial resolution of MODIS, cloud-free reference images are difficult to obtain, and SAR imagery is not well matched to the spatial resolution of MODIS, making it difficult to provide effective prior constraints. To address these issues, this study proposes LC-TSRNet for seamless reconstruction of annual MODIS SR products. In the first stage, an annual land cover map is introduced as prior knowledge, and CSPM is designed by leveraging the spectral similarity within identical land cover types, thereby providing prior spectral constraints for missing regions. In the second stage, to address large-area, persistent, and overlapping gaps in MODIS imagery, SMRM is designed to adaptively exploit and integrate multi-scale spatiotemporal contextual information. Meanwhile, to address the limited collaborative utilization of spatio-temporal-spectral…

    PDF
  • arXiv cs.LGOct 18

    Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents

    Yiming Xu, Qian Yang, Zihan Chen, Yuefei Wu, Wenhan Zeng +2

    Large language model (LLM) agents increasingly rely on external memory to accumulate past experiences for continual adaptation. However, effectively reusing memory requires accurately assessing its value, as retrieved experiences may become unreliable when transferred across task contexts. Despite its importance, memory valuation remains largely underexplored, with existing methods relying on historical retrieval success rates that overlook the context dependency of memory usefulness and the varying reliability of estimates under different amounts of evidence. Inspired by the Bayesian brain hypothesis, we propose BEAM (Bayesian-style Evolutionary Agentic Memory), a framework that reformulates memory value evaluation as a parameterized cognitive inference process, where memory value is represented as a context-conditioned dynamic belief rather than a passive historical statistic. Specifically, BEAM infers memory value beliefs from current task contexts and continuously calibrates them using execution feedback as empirical evidence, transforming memory from passive storage into an adaptive cognitive mechanism for continual self-evolution. Extensive experiments across reasoning and…

    PDF
  • arXiv cs.LGOct 18

    Polynomial Learning of Positive ReLU Networks under Gaussian Inputs

    Zhijie Zheng

    We study positive, bias-free, one-hidden-layer ReLU networks under standard Gaussian inputs. We obtain algorithms with polynomial sample and real-arithmetic complexity, without separation or conditioning assumptions on the hidden directions. When the conditional label mean is a width-$k$ network with total output weight at most one, the learner achieves squared prediction error $\varepsilon$ with output width at most $k+\min\{k,d\}$ and complexity linear in one plus the residual second moment. For arbitrary labels with bounded second moment, we obtain a positive ReLU network of width $O(k\log(2/\varepsilon))$. Its risk is bounded by the irreducible noise variance plus $Ck^3\log^{9/2}(2k/\varepsilon)$ times the squared distance of the conditional mean to the target class, plus $\varepsilon$. The proofs combine implicit Hermite moments, orthogonal tensor-train compression, and a direction decoder whose probability of returning a direction far from every atom is bounded linearly in the compression and estimation errors. Exact Gaussian localization refines the resulting direction covers. In the agnostic setting, a cone-constrained convex program with a scale-dependent penalty…

    PDF
  • arXiv cs.ROOct 18

    Compile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds

    Jingwen Bai, Guochao Bai, Canbo Zhang, Shuangqi Li, Minchao Hu +2

    Embodied AI lacks the data-rich pretraining that gave language models their agents and skills, so new manipulation capability costs demonstrations per task or a frontier model in every episode. We study a third route: a strong general model acts only as an offline author that writes, runs, diagnoses and repairs a manipulation skill in simulation until it passes an exam on layouts drawn after freezing; the frozen skill then runs as code alone or under a cheap caller that reads only its description. We call this skill-level recursive self-improvement Skill-RSI and specify a compile protocol (isolated, audited author; hidden validation layouts; no-feedback and inherit-only controls; tamper-evident ledger) and a reuse protocol that runs the identical files with executors from another model family. On 7 RoboTwin 2.0 tasks with cluttered tables, Claude Code compiled 4 tasks into 7 frozen skills, 5 from a first draft needing only qualification, at USD 4.29-8.22 of author cost each (USD 55 per skill counting the 13 failed campaigns). The other three tasks did not compile in 18 campaigns, including five with GPT-6 and a pre-registered 150-layout run: on the hardest task every campaign…

    PDF
  • arXiv cs.LGOct 18

    Self-organizing reinforcement learning: a swarm approaches the explore-exploit optimum

    Galen J. Wilkerson

    The explore/exploit trade-off is the core problem of reinforcement learning (RL). We show that a minimal foraging swarm approaches its optimum - the ideal-free / Nash allocation of a multi-agent resource-sharing game (an equilibrium, not a return maximum) - with no learner and no reward signal. Agents explore by heavy-tailed (Levy) flights, recruit neighbours to a discovery through a threshold cascade on their proximity network, and disperse as a patch crowds; this cascade cycle balances exploration and exploitation and drives foragers toward the ideal free distribution. The swarm attains the shape of this optimum (committed foragers track richness with slope 0.94) but not its exact equilibrium - it stays measurably exploitable - reaching it dynamically (~150 steps) through the coupling of recruitment to movement: remove the coupling and matching collapses (0.94 -> 0.08). The RL sits at the level of the problem and the allocation reached, not the micro-rule: no step evaluates payoff (reward-free by construction, though the crowd signal is informationally tied to payoff), and the swarm reaches the allocation without learning it (quality plateaus and re-settles after resources…

    PDF
  • arXiv cs.AIOct 18

    Explore or Confirm? LLM Agents Misallocate Measurements Under Noise

    Abdul Karim, Matt Keon

    As model reasoning gets cheaper, the physical experiment becomes the slow and costly step in discovery. Each experiment returns a noisy reading: a high value can mean a good candidate or a lucky draw. With a fixed budget, an AI agent must keep choosing between exploring a new candidate and confirming a promising one by re-testing it. We measure that choice in Wellocate, a simulated assay campaign with known true values. It is built on a generated landscape and on two real protein datasets, GB1 and PhoQ, scrambled so no model can answer from memory. We test five language models as minimal agents, with no tools and no memory beyond the history in each prompt. They misallocate in both directions. Three over-confirm, spending most of the budget re-testing. On the generated landscape one under-confirms, trusting single readings, and there every model ends with a worse final pick than a basic scripted strategy. Each failure has its own cause. The over-confirmers run short of new candidates worth trying: a list of untried candidates cuts their re-testing and, on real protein data, makes two of them pick much better. A running summary of their readings or a description of the landscape…

    PDF
  • arXiv cs.DBOct 18

    Which Code Changes Need Re-embedding? CIPBench and the Limits of Multi-Signal Index Maintenance

    Nannan Zhao, Jiameng Zhang, Taoyu Zhong, Hao Wang, Bo Wang

    Repository-level retrieval-augmented generation systems must keep vector indexes synchronized with continuously evolving code, yet there is no principled basis for deciding which changed code units actually need new embeddings. We ask whether the retrieval impact of a code change can be anticipated before that embedding is computed. Across 10 open-source repositories in Python, Go, and JavaScript, we characterize how a change propagates from syntactic substantiality through embedding displacement to retrieval impact. The links are informative but not deterministic: syntactic class separates displacement sharply, yet impact depends on a unit's retrieval exposure as much as on how far its representation moves, and recurring counterexamples bound what any single signal can decide. We formalize the decision as CIPBench, a benchmark that scores maintenance policies under a strict pre-embedding information boundary. Prediction works, and one signal exhausts it. A ranker using only a unit's change history substantially reduces retrieval harm relative to random and recency-based scheduling. Combining it with three further signals--individually discriminative and largely unassociated with…

    PDF
  • arXiv cs.CLOct 18

    Generation-Heavy Hybrid Machine Translation

    Nizar Yahya Habash

    The state of the art techniques in Machine Translation (MT) require large amounts of symmetric resources from source and target languages. This is true regardless of whether the approach is Transfer or Interlingua, Symbolic or Statistical. Symmetry within these approaches is necessary to ensure quality, robustness and retargetability. In reality, such symmetry, whether it is in terms of structural transfer lexicons, interlingual dictionaries or parallel corpora, is a major bottleneck in developing any MT system. This dissertation presents an approach to MT that addresses the lack of symmetry by exploiting symbolic and statistical target language resources in source-poor/target-rich language pairs. This approach is called Generation-Heavy Hybrid Machine Translation (GHMT). Expected source language resources include a syntactic parser and a simple one-to-many translation dictionary. No transfer rules or complex interlingual representations are used. Rich target language symbolic resources are used to overgenerate multiple structural variations from a target-glossed syntactic dependency representation of source language sentences. Statistical target-language resource are then used…

    PDF
  • arXiv math.OCOct 18

    Non-Acceleration of the Heavy-Ball Method in 1D

    Konstantinos Fotopoulos, Michael Helcig, Karl Deck, Jannis Alsbach

    Despite having an asymptotically optimal rate of convergence on convex quadratics, the acceleration of Polyak's heavy-ball method and a characterization of its dynamics within more general settings have remained long standing open problems. Recently, the work of Goujaud et al. [Math. Program. (2025)] made progress regarding acceleration in the context of smooth, strongly convex minimization: for a small enough inverse condition number, either the method does not accelerate on quadratics, or there exists a smooth strongly convex function such that heavy-ball cycles over the roots of unity. The constructed functions have two variables, thus leaving the question of acceleration over univariate functions open. In this work, we use a Fourier-based analysis to i) provide a proof for the non-acceleration of the heavy-ball method over the class of univariate smooth strongly convex functions. We also ii) provide a strict enlargement of the previous root-of-unity cycling region, with insights regarding the "fractional" sets of Goujaud et al. [arXiv:2502.19916], and iii) give a higher dimensional cycling instance which is not covered by root-of-unity cycling.

    PDF
Load more