SEARCH · Search arXiv

Results for “cs.AR”

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 2Linked to original sources

arXiv2026

Solaris: Towards Interfaces That Are Generated, Not Coded

Digital interfaces are traditionally implemented through intermediate representations such as code, requiring their appearance and behavior to be specified in advance. We introduce Solaris, an interface world model that instead generates an interactive UI directly, frame by frame, in response to user actions. Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds. To enable real-time generation while maintaining visual coherence over extended interactions, we combine autoregressive frame generation with few-step distillation and training on the model's own outputs. A language model complements the visual world model by interpreting user intent and specifying how interactions should affect the generated environment, separating high-level reasoning from visual rendering. By generating both the appearance and behavior of an interface dynamically, Solaris enables open-ended interactions that need not be explicitly programmed in advance. We view interface world models as a step toward a new paradigm for software, where interfaces are generated and adapted continuously around user intent rather than implemented as fixed collections of predefined states and

cs.CV↗

arXiv2026

Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance

The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication. Physician assistance instead requires coordinating these capabilities within the same interaction, where physicians issue underspecified requests, patients describe symptoms ambiguously, and EHR systems demand precise tool use. We introduce PhysAssistBench, a benchmark for interactive doctor-patient-EHR assistance. Built from real MIMIC-IV cases, PhysAssistBench uses a scalable pipeline to construct agentic patients: interactive, record-grounded agents that turn static EHR records into multi-turn clinical scenarios while preserving clinical factuality. PhysAssistBench provides a curated bilingual evaluation set of 1,296 manually reviewed and physician-validated turns. Experiments with leading LLMs show that current models remain unreliable in this setting, which exposes a key bottleneck for clinical LLMs: reliable assistance requires coordination across knowledge, communication, and systems, not isolated gains in any of them.

cs.CL↗

arXiv2026

Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?

Small leaderboard gaps are often interpreted as evidence that one language model is better than another, but their sign may depend on which benchmark items are included. We test this using item-level responses from five benchmarks and a family-label-free spectral approximation to multidimensional item-response theory (MIRT). In owner-disjoint folds, one owner half identifies items with low residual differential item functioning across model families (low-DIF); the resulting frozen, source- and easiness-balanced weights score models in the other half, while equally short matched-random subtests control for generic subtest variation. Full-benchmark and low-DIF rankings remain strongly correlated ($τ_b=.900$--$.948$). Yet in four of five benchmarks, 30.9--47.1\% of cross-family pairs initially within one percentage point reverse order, exceeding their matched-random medians by 16.9--28.6 percentage points (all $p=.001$). The fifth benchmark shows no reliable excess ($-0.9$ points, $p=.689$). The pattern survives all pre-specified population perturbations, and residual item--family signatures replicate across owner halves; however, no family shows a consistent advantage across benchmarks. Thus, globally stable rankings can still leave individual near-tie orderings sensitive to benchmark composition, and sub-one-point leaderboard gaps should be accompanied by evidence that the implied ordering is composition-robust.

cs.CL↗

arXiv2026

CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target

Generative Engine Optimization (GEO) is increasingly used to improve content visibility in LLM-based retrieval systems, yet its population-level effects under repeated optimization remain poorly understood. We introduce Content Homogenization under rAnking Signal Exploitation (CHASE), a controlled simulation framework for studying how content ecosystems are reshaped when creators repeatedly adapt documents to an LLM ranking signal. We use ranking as a proxy for source visibility and validate this abstraction against citations in grounded generated responses, obtaining a rank-citation AUC of 0.853 $\pm$ 0.093 across six domains. CHASE then iterates ranking, feature discrimination, rewriting, and evaluation over 20 rounds across different domains. Quality-ranking alignment decreases in all six domains: from R0 to R20, the change in Spearman's rho ranges from -0.107 to -0.018, with a mean change of -0.068, which means documents closer to the ranking feature profile become less aligned with independently judged document quality over the simulation horizon. A random-target control has shown that it is associated with adaptation toward ranking-derived incentives rather than iterative rewriting alone. The resulting ecosystem dynamics are strongly domain-dependent. Together, these findings show how repeated optimization against a fixed LLM ranking signal can reshape both content populations and the incentives faced by content creators.

cs.AI↗

arXiv2026

Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI

This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate whether to engage with explanations based on three types of expected utility: instrumental (will it help me act better?), hedonic (will it make me feel better?), and cognitive (will it improve my understanding?). Each utility is estimated through a lens shaped by well-documented cognitive biases, including illusion of control, automation bias, unrealistic optimism, impact bias, overconfidence, and confirmation bias. These biases can lead to two failure modes: excessive information-seeking that fragments attention without improving decisions, and insufficient information-seeking that leaves critical risks and misunderstandings unexamined. This challenge is particularly acute for agentic AI systems, where explanations must support not just understanding a single output but anticipating cascading actions, assessing risks, and deciding when to intervene. By integrating information-seeking psychology into HCXAI, we advocate for a shift from making explanations available to making them sought: designing systems that account for when and why users actually want to know.

cs.AI↗

arXiv2026

When are selector control strategies optimal for constrained monotone systems?

This paper considers optimal control problems defined by a monotone dynamical system, a monotone cost, and monotone constraints. We identify families of such problems for which the optimal solution is bang-ride, i.e., that it always operates on the constraint boundaries and switches between a finite number of state-feedback controllers. This motivates the use of simpler policies, such as selector control, that can be designed without perfect models and full state measurements. The approach is successfully applied to several variations of the health-aware fast charging problem for lithium-ion batteries.

math.OC↗

arXiv2026

PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action. We call this distribution-level requirement probabilistic alignment. However, existing evaluations largely assess individual-video plausibility and do not test whether repeated generations recover the correct distribution. This raises a central question: how far are current video generators from probabilistically aligned world modeling? To answer it, we formalize probabilistic alignment as a distributional criterion for world models and introduce PAWBench, a benchmark for evaluating video generators as stochastic samplers of world dynamics. We further introduce PAWEval, an outcome-level protocol that converts repeated video rollouts into empirical distributions over possible physical behaviors. Across 50 scenarios and eleven current systems, no model consistently matches the reference probabilities while recovering the range of valid behaviors. Having established this gap, we test whether language prompts, initial noise sampling, or model training can reshape the model's predictive distribution. We believe our work can serve as a foundation for future efforts to move towards probabilistically aligned world modeling.

cs.CV↗

arXiv2026

Quadratic Probing Insertions Are $ε^{-(1+o(1))}$

First proposed in 1968, quadratic probing has stood for more than half a century as one of the simplest and most widely used hash-table designs in computer science. It is conjectured that, at load factor $1 - ε$, the hash table achieves $O(ε^{-1})$ expected insertion time. But even proving a bound of the form $f(ε^{-1})$ for any function $f$ has remained open. In this paper, we prove that the expected insertion time is $ε^{-(1 + o(1))}$. This settles the complexity of the data structure up to sub-polynomial factors in $ε^{-1}$.

cs.DS↗

arXiv2025

Scalable FPGA Framework for Real-Time Denoising in High-Throughput Imaging: A DRAM-Optimized Pipeline using High-Level Synthesis

High-throughput imaging workflows, such as Parallel Rapid Imaging with Spectroscopic Mapping (PRISM), generate data at rates that exceed conventional real-time processing capabilities. We present a scalable FPGA-based preprocessing pipeline for real-time denoising, implemented via High-Level Synthesis (HLS) and optimized for DRAM-backed buffering. Our architecture performs frame subtraction and averaging directly on streamed image data, minimizing latency through burst-mode AXI4 interfaces. The resulting kernel operates below the inter-frame interval, enabling inline denoising and reducing dataset size for downstream CPU/GPU analysis. Validated under PRISM-scale acquisition, this modular FPGA framework offers a practical solution for latency-sensitive imaging workflows in spectroscopy and microscopy.

cs.AR↗

arXiv2026

Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL

Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions. Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search.

cs.CL↗

arXiv2026

On Good-for-MDPs Automata

Nondeterministic good-for-MDPs (GFM) automata are for MDP model checking and reinforcement learning what good-for-games (GFG) automata are for reactive synthesis: a more compact alternative to deterministic automata that displays nondeterminism, but only so much that it can be resolved locally, such that a syntactic product can be analysed. GFM has recently been introduced as a property for reinforcement learning, where the simpler Büchi acceptance conditions it allows to use is key. However, while there are classic and novel techniques to obtain automata that are GFM, there has not been a decision procedure for checking whether or not an automaton is GFM. We show that GFM-ness is decidable and provide an EXPTIME decision procedure as well as a PSPACE-hardness proof. We also compare the succinctness of GFM automata with other types of automata with restricted nondeterminism. The first natural comparison point are GFG automata. Deterministic automata are GFG, and GFG automata are GFM, but not vice versa. This raises the question of how these classes relate in terms of succinctness. GFG automata are known to be exponentially more succinct than deterministic automata, but the gap between GFM and GFG automata as well as the gap between ordinary nondeterministic automata and those that are GFM have been open. We establish that these gaps are exponential, and sharpen this result by showing that the latter gap remains exponential when restricting the nondeterministic automata to separating safety or unambiguous reachability automata.

cs.FL↗

arXiv2026

Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings

Frontier large language models (LLMs) have become attractive priors for optimization due to their large-scale pretraining that enables them to navigate a variety of optimization settings. However, the effectiveness of modern reasoning LLMs in batch optimization settings remains underexplored. Here we investigate the performance of the current generation of frontier LLMs as batch optimizers in both continuous and discrete settings. We find that while LLMs are competitive zero-shot batch optimizers for numerical test functions, their performance is brittle compared to classical non-LLM optimization approaches. However, LLM priors are significantly better in semantically rich settings, indicating that their batch optimization behavior is highly effective when navigating and reasoning over the discrete spaces most similar in structure to their pretraining data.

cs.LG↗

arXiv2026

Confidence-Gated Admission for Hardware Prefetching: When the Gate Matters More Than the Predictor

Learned cache prefetchers are typically evaluated against classical predictors that always issue requests, confounding the prediction model with the admission policy. We disentangle these variables with matched controls: the same admission gate is applied to both a 257-parameter online MLP and a classical stride predictor. The neural advantage vanishes; the MLP is indistinguishable from gated stride on random traffic and slower on most regular streams. The gate itself is architecturally useful independent of the predictor: on twenty SPEC CPU2017 programs in native ChampSim, it removes 35% of prefetches and improves accuracy from 11% to 15%, but DRAM reads change by only 0.07% demonstrating that proxy metrics do not predict endpoint behavior. We prove gate-closed execution reproduces the no-prefetch baseline exactly. The gate matters more than the predictor, and better proxies do not imply better endpoints.

cs.AR↗

arXiv2026

Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool

Machine-learning performance modeling is a uniquely hostile terrain for long-lived software: the assumptions baked into today's abstractions are invalidated by tomorrow's models and systems, forcing perpetual refactoring of performance-modeling frameworks. Meanwhile, AI coding agents have become fast and capable enough that regenerating an entire library is cheaper than paying down the tech debt of incrementally patching it. We describe SMART, a rigorous symbolic performance-modeling library for ML systems whose main branch contains almost no code: the repository is a DAG of self-contained natural-language design docs, coding sub-agents regenerate the implementation from only the docs on new version updates, and every human change is a natural-language edit to a doc--self-documenting by construction. Two ingredients make regeneration reliable: (i) a design-doc style built around step-by-step worked examples that act as in-context demonstrations for the generating agents, and (ii) a minimal, recursively defined operator IR with symbolic (SymPy) cost expressions, a fast analytical roll-up mode for large sweeps, and a slow modulo-scheduling mode for fine-grained schedule studies. Regenerated implementations reproduce hand-audited reference models--including DeepSeek-V3 serving on a TPU pod slice--to round-off precision, suggesting that design docs--not code--can be the durable artifact for ML-systems co-design tools.

cs.PL↗

arXiv2026

Great Expectations: Benchmarking the Real-World Performance of RVV 1.0 in HPC

Following the ratification of the RISC-V Vector Extension (RVV 1.0), new commercially available silicon has been adopting the extension. This paper revisits the question of RISC-V viability for High-Performance-Computing (HPC) by benchmarking the latest RVV 1.0-capable hardware (SiFive X280 (Tenstorrent Blackhole), SpacemiT X60 (K1) and X100/A100 (K3), and T-Head C920v2 (Sophon SG2044)). We assess these platforms using standard HPC benchmarks (BLAS, FFTW, HPL, HPCG) and synthetic workloads (STREAM, FMA throughput) and compare them to a state-of-the-art HPC ARM64 chip (NVIDIA Grace). Our findings show that while RVV 1.0 delivers significant performance improvements over scalar execution, hardware-specific implementation challenges remain. We detail these performance characteristics and discuss the remaining hurdles for RISC-V, including RVV, to become a mainstay in the HPC landscape.

cs.DC↗

arXiv2026

Huawei's $τ$ Chip Was Supposed to Melt?

Heat is the sharpest concern on $τ$ scaling law --- the time-scaling principle behind Huawei's folded silicon, named for the delay $τ$ (``Tao'') it sets out to shrink. Our Kirin measurements turned that objection upside down. The reason is one every commuter already knows: on a chip, as in a workday, it is the travel that burns the majority of the energy, not the work at the desk.

cs.AR↗

arXiv2026

Transversality Conditions for Boundary Constraints Defined by Differential Equations

What are the transversality conditions for an optimal control problem when the boundary conditions are defined by differential equations? This seemingly bizarre question is motivated by trajectory optimization problems in the $N$-body system. The question, however, is more fundamental and goes beyond problems in astrodynamics to nonintegrable dynamical systems in general. The main contribution of this paper is the development of generic initial- and final-time transversality conditions for optimal control problems whose boundary conditions are defined in terms of differential equations with side conditions. The mathematical definition of differential boundary conditions are part of the foundations developed in this paper. To support the new fundamentals, the concept of coordinated/uncoordinated clock times and weak adjoint covectors are introduced. In the case of uncoordinated clock times, the new transversality conditions reveal that there exists a special situation where a weak adjoint covector is orthogonal to the vector field of the boundary differential equation. This condition is sharply different from the classical statement of orthogonality with respect to the endpoint manifold. The theorems developed in this paper are generic. An application of the theorems to several cases in the three-body problem are described in separate papers.

math.OC↗

arXiv2026

Four-Entropic Matroids Are Quaternary

For an integer $q\ge2$, a matroid is $q$-entropic if its rank function, multiplied by $\log q$, is the joint-entropy function of random variables on a $q$-element alphabet. We prove that a matroid is $4$-entropic if and only if it is representable over $\F_4$. The corresponding statements for alphabet sizes two and three were known. The proof combines minor closure and the excluded-minor characterization of quaternary matroids with structural properties of quasigroups of order four. Thus arbitrary four-symbol partition representations yield no matroids beyond the quaternary ones. As an application, every access structure admitting an ideal perfect scheme with a uniform four-symbol secret and four-symbol active shares also admits an ideal $\F_4$-linear scheme.

math.CO↗