arXiv subjects

Search papers

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

At least 1,495 records · Page 83Linked to original sources

arXiv2026

Building Presentation Intelligence for High-Quality Slide Generation

PowerPoint presentations (PPTs) are a dominant medium for communication across diverse domains, yet high-quality PPT generation still depends heavily on labor-intensive human effort. Recent advances in large language models (LLMs) for agentic tasks have created both new opportunities and challenges (Chen et al., 2026) for automatic PPT generation. In this work, we present a unified training framework for automatic PPT generation toward presentation intelligence, integrating cross-validated data synthesis, guided teacher enhancement, and verifiable reward optimization. We first construct a cross-validated pipeline for data synthesis, with explicit control over both difficulty and validity. We then develop a teacher-enhancement framework grounded in rules and prior knowledge to substantially strengthen the instructional capacity of teacher models. Building on this, we further improve supervised fine-tuning (SFT) through a mixed-teacher strategy and a lightweight outcome-driven trajectory filtering method. Finally, based on the resulting SFT models, we introduce a suite of verifiable aesthetic metrics together with a GRPO-based reinforcement learning framework to optimize slide-level visual attributes beyond text-only supervision. Experiments show that our enhanced SFT pipeline improves Qwen-3.6-27B and Qwen-3.6-35B-A3B by 7.45 and 9.35 points on PresentBench, respectively, surpassing GLM-5.2 while maintaining strong generalization. Reinforcement learning further improves performance across five aesthetic dimensions, compensating for the limitations of SFT in visual refinement. Overall, the results demonstrate the effectiveness of our framework for high-quality PPT generation.

cs.LG↗

arXiv2026

Strong uniqueness for fractional stochastic differential equations with sign drift

Establishing pathwise uniqueness for stochastic differential equations driven by fractional Brownian motion with Hurst parameter $H>1/2$ remains challenging, particularly for discontinuous drifts beyond the regularity regimes of existing theories. A canonical example is the sign drift, for which uniqueness fails in the corresponding deterministic equation. In this paper, we complement recent strong existence results by establishing pathwise uniqueness for the equation with sign drift perturbed by fractional Brownian motion for every $H\in(1/2,1)$, thus obtaining strong well-posedness. Our proof develops a new approach based on the infinite iteration of an inequality arising from a fixed-point relation, combined with tail probability estimates exploiting the Gaussian structure of the noise. The methods and results cover a broader class of Gaussian Volterra processes satisfying suitable local nondeterminism and positivity conditions.

math.PR↗

arXiv2026

Continuous-depth Deep Gaussian Processes

Deep Gaussian processes (DGPs) are appealing Bayesian regression models, but their standard discrete-depth parameterization often becomes harder to optimize as depth grows. We argue that depth is better treated as a latent continuous evolution than as a long discrete stack. We therefore propose a continuous-depth formulation in which the latent representation follows a stochastic differential equation with a depth-indexed drift family equipped with a GP-based prior. This reframes the core design choice as the prior placed on that family, rather than adopting a purely neural continuous-depth parameterization as in neural ODE or neural SDE models. We study two instantiations of this idea: CDGP, a direct GP prior over the state--depth drift, and FlowDGP, a flow-evolved prior that captures richer depth dependence at lower training cost. To motivate the redesign, we analyze how the single-sample DGP objective can become increasingly sensitive under repeated layer composition, while residual DGP is a useful first repair that still remains a finite discrete construction. We also give pathwise sensitivity analysis for the continuous-depth formulation. Experiments on synthetic, benchmark, and large-scale regression tasks show that residual DGP improves over plain DGP, while CDGP and FlowDGP provide a stronger overall story across the regimes we study.

stat.ML↗

arXiv2026

Equilibria and Learning in Competitive Market Making

We propose a market-making game played among $N \ge 2$ strategic market makers and a single non-strategic representative trader. In a continuous quote space, standard finite-game arguments do not apply, while non-convex and discontinuous payoffs rule out classical continuous existence results and complicate learning. Nonetheless, we characterize pure-strategy Nash equilibria (PSNEs) and show that at least one PSNE always exists under minimal assumptions on the underlying asset value distribution, and that the equilibrium bid-ask spread widens strictly with asset value volatility. To obtain a tractable learning framework, we discretize prices and, under an additional regularity condition, show that the time-averaged play of no-internal-regret learners approaches the continuous Nash price envelope as the tick size vanishes. Finally, we empirically validate our theoretical results through numerical simulations.

cs.GT↗

arXiv2026

On the generation of the symmetric group by index relations of three prefix reversals

The cubic pancake graphs are Cayley graphs over the symmetric group Sn generated by three prefix reversals. There is the folllowing open problem: characterize all the sets of three prefix reversals that generate Sn. Blanco and Golubyatnikov give a complete solution of the problem when any of the two smallest or the two largest lengths but n are included in a triple of prefix reversals. According to their conjectures, we give some conditions implying a triple of prefix reversals does not generate Sn. Moreover, Using the symmetric groups that can already be generated by three prefix reversals, we can derive some recurrence conditions.

math.GR↗

arXiv2026

Working Through Representation: Malleable Workspaces for Human-Agent Knowledge Work

Generative AI supports knowledge work, yet conversational histories may not capture the evolving organization that guides subsequent action. We introduce the Malleable Workspace, a conceptual model of how humans and agents form and revise a Work Representation and use its organization to advance work within a wider Work Environment. We developed it iteratively through conceptual analysis, comparison of 58 papers, and the construction and three-month longitudinal study of MalleableSpace with seven experienced agent users. Systems varied in what they represented as units and relations. System-assembled context was common; more systems supported local incorporation of agent outputs than reorganization, and fewer supported consequential agent-driven changes beyond the representation. The field study showed how representational roles and organization developed in use. These observations refined the model's account of how representation-grounded action depends on and can change the Work Environment. We contribute a conceptual and analytic foundation for representation-centered human--agent design.

cs.HC↗

arXiv2026

CURTAIN: Towards a Foundation Model for Neutrino Telescopes

Neutrino telescopes record more than a trillion photon detections per year, yet there does not exist a self-supervised learning (SSL) task which fully satisfies all three conditions: improving as the pretraining set grows, transferring to a different detector, and outperforming the best model trained without pretraining at all. We introduce CURTAIN, a temporal masking scheme and the first SSL task for neutrino telescopes that achieves all of these goals. Downstream performance monotonically improves with the number of pretraining events, as predicted by scaling laws. Our encoder builds on DeepIce, currently the leading model on the NuBench benchmarks direction reconstruction task. Pretraining it with CURTAIN reduces its median angular error by 45% and its median energy error by 31% compared to training from scratch. It also transfers to a detector geometry never seen in pretraining, reducing the median angular error by 36% compared to training from scratch. At matched capacity and pretraining data, CURTAIN-pretrained encoders beat those pretrained by existing SSL tasks on both tasks and at every pretraining set size.

hep-ex↗

arXiv2026

Your Home Remembers: A Voice-Enabled Household Memory Assistant for Conversational Retrieval

Everyday household information is often exchanged in conversations but never written down, making details easy to forget or misremember. We present a voice-enabled smart-home assistant that acts as a household memory by recording conversations and retrieving information from stored and newly captured speech. The assistant runs on an Android tablet with a modular architecture in which speech-recognition, diarisation, embedding and language models can be configured or replaced through an orchestration layer. On-device wake-word detection and VAD-based query capture support hands-free interaction. Recorded audio is processed in configurable chunks, transcribed and diarised, converted into turn-aware passages with conversation-level timestamps, and indexed in a vector store. For memory queries, a retrieval-augmented generation pipeline selects key passages and uses them to generate an answer. The interface supports recording, conversation management and inspection of timestamped sources.

cs.HC↗

arXiv2026

Can Reciprocal RIS Perform as Non-Reciprocal RIS?

Yes, if and only if some optimal non-reciprocal RIS (i.e., maximizing a given performance metric) makes the round-trip channel transmitter-RIS-transmitter symmetric, which holds if the channel transmitter-RIS has rank one or if single-stream transmission is optimal.

cs.IT↗

arXiv2026

Laser-design methodology for extending an available wavelength range of dual-wavelength injection-seeded laser

This paper describes a method for expanding the applicable wavelength range of dual-wavelength oscillation injection-locked lasers. Special focus is placed on the laser design that enables simultaneous oscillations at both the gain center and gain tail, requiring the most stringent requirements. We show that a sufficient performance can be achieved by introducing a wavelength-dependence property onto the output coupling mirror, without giving any losses in the laser resonator. We also show how we can determine such wavelength-dependent property on the basis of experimental measurements. Using the designed output-coupler, in practices, we demonstrate simultaneous oscillations with an equal output power, across a variety of wavelength combinations of near the gain center and around the gain tail in which the wavelength separation amounts 60 nm at the most.

physics.optics↗

arXiv2026

Intrinsic Angular Momentum Contribution to the Sagnac Response of a Rotating Helical Optical Fiber

We investigate rotation-induced phase accumulation of structured light in a mechanically rotating uniform helical optical fiber using a four-component optical Dirac-like equation. In the paraxial and weak-geometry regime, the intrinsic dynamics contain a torsion-induced geometric coupling and a mechanical rotation--angular-momentum coupling. We show that, in a common-path mirror-reflection geometry, both the torsion-induced geometric phase and the conventional area-dependent Sagnac contribution cancel over a complete round trip, whereas the intrinsic rotation--angular-momentum phase survives. The surviving phase depends on the intrinsic total angular momentum of the structured optical mode and provides a common-path interferometric route for probing intrinsic angular momentum effects in rotational sensing.

physics.optics↗

arXiv2026

Parameter Learning in Active Inference via Variational Message Passing

Active inference casts perception, learning and planning as variational inference, where the Expected Free Energy (EFE) defines the planning objective. Recent work showed that EFE minimization can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors, and that the resulting entropy-corrected objective is minimized by sum-product message passing (SP-MP) on modified factor functions. These formulations treat model uncertainty as inference over a finite set of known models. We extend them to planning during learning, where beliefs over the observation and transition parameters $θ_A$, $θ_B$ are Dirichlet priors. Closed-form Dirichlet updates are usually obtained by a structured mean-field factorization between parameters and states, but under exactly that factorization the information-gain corrections vanish. We resolve this by giving every factor its own parameter prior, frozen during a rollout. Conjugacy then makes each factor belief a product of a marginal over the categorical variables and a one-step Bayes posterior of the parameters. This reintroduces the datum-dependent parameter posteriors that mean-field factorization destroys. We show that evaluating the epistemic priors under the resulting Bethe joint recovers the information gains. Stationarity of this single closed-form objective yields SP-MP whose factor functions are augmented by the information-gain weight. Experiments on two grid POMDPs, in which only a planner that learns the model finds the safe route, show that the method plans to efficiently learn $θ_A$ and $θ_B$. It reaches the goal on every episode, whereas SP-MP planners with the same inference update plateau or take the risky route.

cs.AI↗

arXiv2026

Silicon Samples Match the Answers but Not the Respondents

Silicon sampling generates survey respondents by having a large language model (LLM) answer a survey as a person with given demographic attributes, and the resulting synthetic populations are increasingly used in place of human ones. Existing evaluations focus on individual-answer accuracy, per-question answer distributions, and correlations across questions. None of these compares the respondents themselves, so a generator whose respondents have combinations of answers found in no human respondent can still score well if it reproduces every answer distribution. We propose the respondent coverage gap (RCG), which represents each respondent as a point defined by their complete answer profile and measures how far each human respondent is from the nearest generated one, relative to the distance between human samples. On two US social surveys, all six LLMs we evaluate leave human respondents uncovered, and under our main settings, they fall behind a baseline that samples each answer independently from the human marginals. Across the prompting and inference settings we test, every LLM has a higher RCG than a Gaussian copula fitted to the human data.

cs.CL↗

arXiv2026

When Annotation Patterns Are Learned: Skin-Tone Dependence in Dermatology Concepts

Concept bottleneck models (CBMs) let clinicians inspect and correct skin disease diagnoses through clinical concepts, but only if the concept annotations are reliable. We therefore audit the reliability of SkinCon, a widely used dermatology concept dataset, across skin tones. Within the same disease and with near duplicates removed, erythema is annotated far less often on dark than on light skin, with an odds ratio of 0.17. In contrast, hyperpigmentation and hypopigmentation are annotated more often, with odds ratios of 6.2 and 4.5, respectively. We refer to this pattern as tone-dependent concept annotation. An evidential concept model trained on these annotations learns the same pattern and reproduces it on unseen images. Such a model may agree with potential erythema omissions rather than contradict them. Consistent with this, three label error detectors underperform a disease-only baseline at finding erythema that dermatologist captions mention but SkinCon labels as absent. The three detectors are based on confident learning, training dynamics, and the model's own evidential uncertainty. Concept annotations should thus be audited within each subgroup before explanations built on them can be trusted.

cs.CV↗

arXiv2026

Beyond Phenotypic Similarity: Relation Refinement and Selective Population Graph Learning for Multimodal Brain Disorder Diagnosis

Population graph learning supports brain disorder diagnosis by sharing information across subjects. Its effectiveness, however, depends on whether the relationships guiding this exchange are relevant to diagnosis. Similarity in demographic or acquisition attributes does not necessarily indicate diagnostic agreement, and heterogeneous subjects may require different representation updates within the same population graph. We propose PopDRP, a framework that combines diagnosis-guided relation refinement with hierarchical selective state-space learning. Using only training labels, Contrastive Affinity Refinement calibrates attribute-based affinities according to diagnostic agreement. Neural Graph Rectification then refines these relationships using fused functional-connectivity and non-imaging representations, guided by graph reconstruction and dual-view alignment objectives. On the resulting graph, a Selective Pyramid State-Space backbone integrates input-dependent state updates, graph diffusion, and hierarchical pooling and unpooling to learn population representations at multiple resolutions. Together, these components connect the refinement of inter-subject relationships with selective representation learning over the population graph. Experiments on ABIDE and ADHD-200 under stratified ten-fold cross-validation show improved accuracy and AUC over the compared baselines. Ablation studies further support the contributions of relation refinement and the selective hierarchical backbone to classification performance.

cs.AI↗

arXiv2026

Same molecule, Different Knowledge: Cross-Identifier Binding Failures in LLMs For chemistry

Chemical AI workflows routinely represent the same molecule through multiple co-referring identifiers, including trivial names, IUPAC names, and SMILES, implicitly assuming that these representations provide interchangeable access to an LLM's knowledge. To test this assumption, we first introduce a controlled benchmark and show that it does not hold. Across foundation models spanning 7B to 72B parameters, even chemistry-specialized models, co-referring molecular identifiers consistently expose different subsets of the model's knowledge. We then conduct a series of controlled behavioral, representational, and causal analyses to characterize this failure. We show that even when a model can identify a molecule from its SMILES and retrieve a fact through the corresponding name, the same fact can remain inaccessible directly from SMILES. We term this phenomenon \emph{cross-identifier binding failure}. Further analysis of internal representations, conflicting identifiers, and parameter editing shows that neither improved chemical representation competence nor modification of individual facts is sufficient to establish reliable access across identifiers. Together, these results indicate that the core failure lies in the binding between an identifier and knowledge already present in the model. Motivated by this diagnosis, we introduce Binding Self-Distillation, a simple mitigation that uses lexical identity during training to transfer the model's existing knowledge access to the structural route. This enables factual retrieval directly from SMILES at inference time, without requiring a name lookup or training the underlying model from scratch.

cs.LG↗

arXiv2026

Assortment optimization under the perception-adjusted Luce model

The Perception-Adjusted Luce Model (PALM) introduced by by Echenique et al. (2018) is a sequential choice model that can accommodate violations of regularity and choice overload, behaviors not captured by the utility-maximization framework. Flores et al. (2019) studied the assortment problem under the PALM and proved that, for the case of two levels, there is always an optimal solution that is revenue-ordered by level. They also conjectured that revenue-ordered by levels remain optimal for the general PALM with any number of levels. We resolve this question in the affirmative by showing that every PALM instance admits an optimal assortment that includes, within each level, all products at or above a level-specific revenue threshold. The proof involves first showing how the conjecture which deals with a discrete optimization problem, can be reduced to proving certain property of a related continuous optimization problem. Specifically, we study a continuous refinement of the assortment decision under the same PALM choice rule. Although the refinement permits partial utility selections, we prove it always has an optimum that selects complete revenue tiers. This allows us to show that the assortment problem is polynomial-time solvable when the number of levels is fixed.

math.OC↗

arXiv2026

Broadband emitter localization and prefabrication two-photon interference from InAs/InP quantum dots monolithically grown on an InGaAsP/InP distributed Bragg reflector

We demonstrate a monolithic telecom C-band single-photon platform based on low-density InAs/InP quantum dots grown on an InGaAsP/InP distributed Bragg reflector, with simulated upward light-extraction efficiency exceeding 10% within the 40 nm spectral band. Enhanced light extraction is crucial for wide-field photoluminescence imaging, enabling approximately 3 nm statistical centroid-localization precision of QD emitters due to improved signal-to-noise ratio. The identified charged exciton emitting at 1549.5 nm exhibits single-photon emission purity up to 94.7%, validated by a raw peak-area integration under pulsed quasi-resonant excitation. Under these conditions, photons emitted sequentially from the unprocessed planar structure reveal a raw two-photon interference visibility of 51% of the photon wave packet within the 2 ns time window and 41% over a 4 ns integration window, all without Purcell enhancement typical for cavity-embedded emitters. Combining broadband extraction, high photon coherence, and emitter preselection on a native III-V wafer, this architecture paves the way for marker-based deterministic fabrication of high-quality monolithic nanophotonic devices.

cond-mat.mes-hall↗