SEARCH · Search arXiv

Results for “cs.PF”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

7,800 records · Page 3Linked to original sources

arXiv2026

End-to-End Data Movement: Paradigm Reexamination and Principles for Efficiency

High-performance data transfer is often viewed through raw bandwidth, with 100+ Gbps international links seen as the primary enabler. Yet this network-centric view confuses provisioned speed with sustainable throughput. Suboptimal rates occur even on 10 Gbps links, and faster networks only magnify the issue. We examine six paradigms - network latency, TCP congestion control, CPU performance, virtualization, and others - that critically impact data movement workflows. These reflect common engineering assumptions shaping system design, procurement, and operations. To bridge the gap between raw bandwidth and application-level throughput, we introduce the "Drainage Basin Pattern" - a conceptual model for reasoning about end-to-end constraints across heterogeneous hardware and software at varying target rates. Our findings are validated via production-scale deployments, from 10 Gbps links to U.S. DOE ESnet technical evaluations and transcontinental trials over 100 Gbps operational links. Results show that bottlenecks typically lie outside the network core, and that holistic hardware-software co-design delivers consistent, predictable performance for demanding bulk and streaming transfers. A burst buffer subsystem, together with data staging, is introduced at every tier to decouple data movement from erratic production storage and sustain wide-area transfer, with a quantitative bound for sizing the buffer capacity it requires. The primary goal is to transform such transfers from unpredictable struggles into routine, line-rate operations accessible to any regular user. Finally, we correct two industry misconceptions: using aggregated traffic rate as a measure of application efficiency, and conflating operational complexity with technical expertise.

cs.DC↗

arXiv2026

Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms

Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes token-normalized metrics incomplete, since average output-token energy can decrease even when total request energy increases. We characterize this behavior with a decomposed energy model: a fixed one-time prefill with a fixed generation setup cost, while each output-token generation step adds marginal step energy. We evaluate this LLM inference energy model on NVIDIA H100 and H200 GPUs across dense and mixture-of-experts (MoE) models, reporting both request energy and token energy as functions of model type (M), phase (P), batch size (B), context length (C), and output length (N). For Llama-3.2-1B on H200 at batch-16 and context-4K, increasing output length from 10 to 512 tokens reduces token energy from 7.46 to 0.72 J/token while total batched inference-window energy increases from 1.19 to 5.93 kJ. Batching also reduces token energy, but the gain is context-bounded: at 10 output tokens, the batch-16 to batch-1 gain falls from 6.31x at context-512 to 1.17x at context-4K. MoE models amplify this effect: sparse routing and fragmented expert execution increase fixed energy at low concurrency, while batching spreads that energy across more generated tokens and substantially narrows the dense-vs.-MoE token-energy gap. These results show that energy-aware serving should jointly optimize both request energy and token energy, rather than only reducing per-token energy cost.

cs.PF↗

arXiv2026

The Price of Remembering: A Calibrated Energy Law for Computation

Where does a computer's energy go? Mostly into keeping, not into computing. A bit held in fast storage draws power for every second it stays there, and it costs energy again each time it moves between storage levels. We call the first cost \emph{rent} and the second \emph{fare}, and we state one law: the energy of a computation is at least its operations, plus rent on every live bit for as long as it lives, plus fare on every bit moved. The model under the law prices control as well as data. There is no free clock, and any unpriced register would make the theorems false. One lemma does most of the work: every use of a value is paid for by rent, by fare, or by computing the value again. Three things follow. Exact attention brings every past token back for every new one, so its energy grows with the square of the context length, while a recurrent model with a fixed state grows linearly. The square is a theorem for machines that never re-read past tokens. Under a stated serving hypothesis it is the fare on every past token, which passes the model's own arithmetic near ten thousand tokens, the point where long-context serving becomes bandwidth-bound today. Known bounds on memory over time become joule floors: on any sequential machine with volatile working storage, sorting $n$ items pays rent proportional to $n^2/\log n$ bit-steps on most inputs, and the bound for scrypt makes every password guess cost joules that no amount of parallel hardware reduces.

cs.PF↗

arXiv2026

Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning

Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token beyond a single forward pass. However, we identify a latent overthinking phenomenon: most token predictions are already correct after the first pass, but are sometimes revised into errors in later iterations. We ask whether selectively skipping latent iterations can improve accuracy, and reveal significant potential with an oracle iteration policy that boosts performance by up to 7.3%. Motivated by this, we propose Think-at-Hard (TaH), a looped transformer optimized for selective iteration. TaH employs a lightweight neural decider to trigger latent iteration, only at tokens likely to be incorrect after the standard forward pass. During latent iterations, depth-aware Low-Rank Adaptation (LoRA) modules shift the objective from general next-token prediction to focused hard-token refinement. A duo-causal attention mechanism extends attention from the token sequence dimension to an additional iteration depth dimension, enabling cross-iteration information flow with full sequential parallelism. Experiments on nine benchmarks show consistent gains across math, QA, and coding tasks. With identical parameter counts, TaH outperforms always-iterate baselines by 3.8-4.4% while skipping iterations on 93% of tokens, and exceeds single-iteration Qwen3 baselines by 3.0-3.8%. When allowing <3% more parameters from LoRA and decider, the gains further increase to 5.3-6.2% and 6.1-6.8%, respectively. Our code is available at https://github.com/thu-nics/TaH.

cs.CL↗

arXiv2026

Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection

Camera-LiDAR fusion is widely used in autonomous driving to enable accurate 3D object detection. However, bird's-eye view (BEV) fusion detectors can degrade significantly under domain shift and sensor failures, limiting reliability in real-world deployment. Existing robustness approaches often require modifying the fusion architecture or retraining specialized models, making them difficult to integrate into already deployed systems. We propose a Post Fusion Stabilizer (PFS), a lightweight module that operates on intermediate BEV representations of existing detectors and produces a refined feature map for the original detection head. The design stabilizes feature statistics under domain shift, suppresses spatial regions affected by sensor degradation, and adaptively restores weakened cues through residual correction. Designed as a near-identity transformation, PFS preserves performance while improving robustness under diverse camera and LiDAR corruptions. Evaluations on the nuScenes benchmark demonstrate that PFS achieves state-of-the-art results in several failure modes, notably improving camera dropout robustness by +1.2% and low-light performance by +4.4% mAP while maintaining a lightweight footprint of only 3.3 M parameters.

cs.CV↗

arXiv2026

Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods

Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner also requires predictable and bounded resource usage even on long streams. This requirement becomes even more critical when learning moves from servers to near-sensor embedded systems where memory and processing are scarce resources. In state-of-the-art stream learning, however, we perceive a strong focus on concept drift adaptation, whereas resource usage is often an evaluation byproduct. To close this gap, we benchmark seven representative stream classifiers on 13 real and synthetic streams under model-size budgets from 128\,KiB to approximately 8\,MiB. Our benchmark comprises a total of 6,463 experiments. We measure failure-aware accuracy, peak model size, time to budget exhaustion, and prediction-plus-update latency. The results reveal two distinct resource failure modes. Adaptive ensembles can exceed small budgets almost immediately because of their initial footprint, even when their size remains stable thereafter. Incremental trees can fit initially but grow throughout a long stream, with HoeffdingTrees (HT) and Extremely Fast Decision Trees (EFDT) increasing by median factors of 7.37 and 5.87. Explicitly compact methods remain the only viable option under the smallest budgets, but are usually overtaken as larger budgets make adaptive ensembles competitive. Hence, many state-of-the-art methods are only partially applicable in embedded systems or for long-running systems. We therefore call on the stream-learning community to make bounded resource usage a first-class design objective alongside drift adaptation, and propose concrete steps toward this goal, including an API through which stream learners can explicitly expose and respect resource budgets.

cs.LG↗

arXiv2026

Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading

Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is very expensive and often hits a ``memory wall'', i.e., even when using 3D parallelism (pipeline, tensor, data) and aggregating the memory of many GPUs, it is still not enough to hold the necessary data structures (model parameters, optimizer state, gradients, activations) in GPU memory. To compensate, state-of-the-art approaches offload the optimizer state, at least partially, to the host memory and perform hybrid CPU-GPU computations. However, the management of the combined host-GPU memory is often suboptimal and results in poor overlapping between data movements and computations. This leads to missed opportunities to simultaneously leverage the interconnect bandwidth and computational capabilities of CPUs and GPUs. In this paper, we leverage a key observation that the interleaving of the forward, backward, and update phases generates fluctuations in the GPU memory utilization, which can be exploited to dynamically move a part of the optimizer state between the host and the GPU memory at each iteration. To this end, we design and implement Deep Optimizer States, a novel technique to split the LLM into subgroups, whose update phase is scheduled on either the CPU or the GPU based on our proposed performance model that addresses the trade-off between data movement cost, acceleration on the GPUs vs the CPUs, and competition for shared resources. We integrate our approach with DeepSpeed and demonstrate 2.5$\times$ faster iterations over state-of-the-art approaches using extensive experiments.

cs.LG↗

arXiv2026

The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem

Large language model providers are compute constrained, and their universal response to congestion is to degrade service: route queries to smaller models, cut reasoning effort, truncate context. The industry's accounting says this saves money. We show the accounting is wrong, because it prices a query when the customer buys an answer. A degraded answer fails with some probability, and a failed answer either returns as a retry, inflating arrivals when the system is most loaded, or departs as churn, destroying lifetime value on a ledger no cost dashboard displays. We model inference allocation with three classical primitives: a newsvendor whose stockout cost is churned lifetime value, a geometric retry multiplier in which the recycled product is dissatisfaction, and a two-regime transient queue whose arrival rate is made endogenous by retries. Statically, there is a nonempty, measurable regime in which a cheaper model saves energy per satisfied answer while consuming strictly more capacity per satisfied answer, so the discount inverts exactly when capacity binds. Dynamically, a reactive throttle fired during a surge can cross an ignition threshold beyond which it manufactures more traffic than it sheds, and a release rule set below the degraded equilibrium converts a transient surge into a permanent degraded regime. With heterogeneous customers, throttling is a transportation problem in retry-inflated load whose optimal policy rations intelligence by critical ratio, class by class, and whose dual, the shadow price of intelligence, prices a marginal query by class and by hour; closed-form trajectories make it computable in milliseconds. Stochastic analysis sharpens rather than erodes the thesis: the ignition boundary acquires a predicted width, and noise punishes the reactive policy that parks the system against it. Under congestion, throttling is not a cost lever but a demand lever.

math.OC↗

arXiv2026

DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures

High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores. However, Host processor needs consecutive elements distributed across DRAM banks, while PIM cores need consecutive elements within their local banks. This necessitates data rearrangements in ML kernel execution that pose significant performance and programmability challenges, further exacerbated by the need to support diverse PIM devices. Current compilation approaches lack systematic optimization for diverse ML kernels and multiple PIM devices, and may largely ignore data rearrangement costs during the compute code optimization step. We show that data rearrangements and compute code optimization are interdependent, and need to be jointly optimized during the tuning process. Therefore, we design DCC, the first data-centric ML compiler for PIM systems that jointly co-optimizes data rearrangements and compute code in a unified tuning process. DCC integrates a multi-layer PIM abstraction to support multiple PIM backends. DCC enables effective co-optimization of data partitioning strategies with compute loop partitioning schemes. DCC applies PIM-specific code optimizations, and leverages a fast and accurate performance prediction model to select the bestperforming code schedule for a given kernel on a target PIM architecture. Our evaluations in various individual ML kernels show that DCC achieves up to 7.68x speedup (2.21x average) on HBM-PIM, and up to 13.17x speedup (3.92x average) on AttAcc PIM, over GPU-only execution. In end-to-end LLM inference, DCC on AttAcc accelerates GPT-3 and LLaMA-2 by 4.52x average (up to 7.71x in LLaMA-2) over GPU. DCC is open-sourced at https://github.com/SPIN-Research-Group/DCC.

cs.AR↗

arXiv2026

SchedBlame: Who Ran While You Waited? Culprit-Attributed CPU Contention for Containers on Stock Kernels

Containers that share a machine compete for CPU. When one slows down, the operator needs to know which co-tenant is responsible, and no deployed signal can say. Pressure stall information, per-cgroup wait counters, and run-queue latency histograms are all victim-side: they report that a container waited, never who it waited for. Recovering the culprit means a kernel patch, full scheduler tracing, or statistical inference: unportable, too costly to leave on, or unreliable when victims coexist. SchedBlame is an eBPF tracer that attributes CPU contention to the cgroups that caused it, on stock kernels, continuously. It inverts the accounting: instead of measuring how long a victim waited, it measures the CPU time every other cgroup consumed while that victim was runnable but not running on the same CPU. The mechanism is a per-CPU bitmap of which measured cgroups are waiting, maintained from the kernel's own runnable counts at four scheduler hooks. Every run slice carries that bitmap, so one 16-byte record charges CPU time to a full row of a competitor x victim blame matrix; the kernel stores no per-pair state. Three properties follow. Slices are self-describing, so userspace holds no waiting state and a lost record costs measurements, not correctness. The measured set is reconfigured by publishing an epoch, invalidating every cache and per-CPU bitmap in constant time while the hooks keep running. Sampling never touches waiting state, so rescaling by the inverse keep probability keeps the estimator unbiased. SchedBlame splits each container's per-second CPU demand into runtime, internal contention, external contention, and throttling, flags anomalies against a rolling 99th-percentile baseline, and names the competitors responsible. In production on unmodified 4.18 and 5.10 kernels, tracking 84 containers on a 96-core host, it costs about 1% of Redis throughput and 6% of one core.

cs.OS↗

arXiv2026

Reparameterization through Coverings and Topological Weight Priors

We generalise the reparameterization trick (RT) applied in variational autoencoders (VAEs) letting these have latent spaces of non-trivial topology - i.e. that of base manifolds covered with other ones, on which some technique for RT is available. That is possible since covering maps are measurable - moreover, this allows to establish an inequality on KL-divergence between pushforward (PF) densities on the base latent manifold, bounding it with KL-divergence between pullbacks on the cover, in some cases making the KL-term of VAE's ELBO analytically tractable, despite the topological non-triviality of the supporting latent manifold. Our development follows a route close but somewhat alternative to reparameterization on Lie groups, the latest proposal for which is to reparameterize PFs of normal densities from the Lie algebra - "through" the exponential map, seen by us as a particular case of what we propose to call reparameterization via covering (RVC). We demonstrate the working of our approach by constructing a VAE with the latent space of Klein bottle (not a Lie group) topology, which we call KleinVAE, successfully learning an appropriate artificial dataset. We discuss potential applicability of such topology-informed generative models as weight priors in Bayesian learning, particularly for convolutional vision models, where said manifold was peculiarly shown to have some relevance.

cs.LG↗

arXiv2026

A Unified Particle Filter LSTM for Data-Driven Process Simulation

Data-driven process simulation aims to generate realistic case trajectories from historical event logs without requiring an explicitly specified model of the underlying dynamics. Deep sequence models can capture complex temporal dependencies through next-activity probabilities and conditional time distributions. However, event logs provide only a partial view of the underlying process state, often recording activity completions without the corresponding service-start times. Consequently, the same observed process history may be consistent with multiple plausible latent process conditions, whereas standard recurrent models compress each process prefix into a single deterministic recurrent state. We propose a Unified Particle Filter LSTM (Unified PF-LSTM) that maintains and sequentially updates a weighted set of recurrent-state hypotheses. We summarize this particle belief using its weighted mean and learned features based on the moment-generating function. The resulting representation is used to predict a categorical distribution over the next activity and conditional quantiles of the current activity's sojourn time. The framework is trained end-to-end from event-log data and evaluated on three real-world emergency department datasets. The results show that the proposed framework consistently outperforms the considered data-driven baselines in reproducing routing, duration, and system-level behavior across all datasets, with particularly strong gains in settings where complex process dynamics are only partially reflected in the available event logs.

cs.LG↗

arXiv2025

Security Science (SecSci), Basic Concepts and Mathematical Foundations

This textbook compiles the lecture notes from security courses taught at Oxford in the 2000s, at Royal Holloway in the 2010s, and currently in Hawaii. The early chapters are suitable for a first course in security. The middle chapters have been used in advanced courses. Towards the end there are also some research problems.

cs.CR↗

arXiv2026

Fully Distributed GNE Algorithms for Multi-Robot Placement without Consensus on Multipliers

Recent machine learning research has increasingly focused on equilibrium analysis in non-cooperative games rather than solely on optimal solutions. Many such problems involve shared constraints and can be formulated as Generalized Nash Equilibrium Problems (GNEPs). For strongly monotone games, existing methods compute consensus-based variational GNEs (v-GNEs) by exchanging Lagrange multipliers. We propose a fully distributed continuous-time algorithm for shared linear equality constraints that converges without multiplier exchange and reaches any GNE, reducing communication overhead and improving privacy. Discrete-time schemes are also provided, and the method is validated on a multi-robot placement task.

cs.LG↗

arXiv2026

TSExplorer: An interactive data annotation and exploration tool for time-series data

We present TSExplorer, a cross-platform tool for interactive annotation and exploration of time-series data. The tool enables users to inspect high-dimensional datasets through multiple complementary 2D visualizations derived from high-dimensional feature representations. TSExplorer is designed as a general-purpose research tool supporting a wide range of workflows, including exploratory data analysis, annotation of unlabeled or partially-labeled datasets, comparison of feature representations, and post-hoc inspection and refinement of existing labels with interactive visual feedback.

cs.HC↗

arXiv2026

Towards a universal language of concepts: A survey

Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose that programs are a strong candidate for universal representation of concepts. We review computational models of concept learning that use programs as their concept representation and evaluate their contribution toward a universal representational language.

cs.AI↗

arXiv2026

VIBE: Video Instruction-aligned Background music gEneration

Current video-to-music (V2M) models lack semantic control and fail to penalize instruction violations, largely due to their reliance on reconstruction objectives and the representational bottleneck of static cross-modal conditioning in Diffusion Autoregressive (DAR) architectures. To resolve this, we introduce VIBE, a novel text-and-video-to-music (T+V2M) generation model that leverages: (1) Conditioning Connection, a depth-wise cross-layer conditioning mechanism that dynamically bridges the planning and diffusion refinement heads and (2) a comprehensive reward modeling taxonomy, optimizing for both hard, verifiable constraints (e.g., tempo, key) and soft, subjective qualities (e.g., musicality, multimodal alignment) with a structured 5-stage training curriculum. Upon evaluation using audio-visual alignment, instruction following, and audio quality metrics, along with a subjective human evaluation study, we observe that VIBE demonstrates enhanced controllability and instruction adherence while performing comparably to most evaluated baselines on generation fidelity and multimodal alignment.

cs.SD↗

arXiv2026

MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts

While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of approximately 59K words per book. The benchmark supports evaluation under domain, author, and language shifts. Evaluation of representative AA methods shows that no single method consistently performs best across settings, and performance generally degrades under distribution shifts. Transformer-based detectors can retain generator-related information across languages, although transfer effectiveness varies by language pair, whereas statistical and fingerprint-based detectors are more language-dependent. We envision MultiGhostBench as a valuable resource for the development and evaluation of robust AA methods. The dataset and code can be found at https://github.com/GrecoMT/MultiGhostBench.

cs.CL↗