arXiv:2607.00806v1 Announce Type: new Abstract: Recent discoveries of electron-induced coherence in both resonant and non-resonant interactions have introduced new perspectives in the field. In non-resonant processes, coherence has been observed in dipolar dissociation, where electron-induced excitation forms a coherent superposition of states of opposite parities, resulting in asymmetry in the angle-differential cross-section of the process relative to the incident electron beam. Notably, an isotope effect has been observed in $D_2$ at 50 eV, where heavier isotopes exhibit diminished asymmetry due to their longer dissociation times. Here, we report the isotope effect on quantum coherence in $D_2$ across different electron energies. Additionally, we investigate the role of coherence in the isotopologue HD. Our findings reveal that the asymmetric masses in HD do not influence electron-impact excitation, leading to similar asymmetry in the angular distributions of $H^-$ and $D^-$ ions. This observation is explained by the homonuclear-like behavior of HD within the Franck-Condon region.
Science Journals
arXiv:2607.00821v1 Announce Type: new Abstract: Superfluid $^4$He subjected to steady rotation develops a regular lattice of quantum vortices aligned with the rotation axis. We prepare this lattice in a rotating cryostat, perturb it with a constant heat flux, and visualize vortex deformation waves that propagate in the lattice and grow in energy with the forcing. Below twice the rotation rate, we show that these waves feature a continuous frequency spectrum whose structure corresponds to inertial waves. At larger frequencies, we report evidences supporting the observation of a turbulent cascade of Kelvin waves. Our experiments hence provide a direct approach to deepen our understanding of collective dynamics in perturbed quantum vortex systems across all quantum fluids.
arXiv:2607.00562v1 Announce Type: new Abstract: Debugging the Linux kernel remains a formidable challenge due to its vast codebase, complex architecture, and low-level programming intricacies. Effective fault localization (FL) is thus essential for efficient kernel debugging and maintenance. While existing FL techniques (both traditional and LLM-based) have shown promise in general-purpose software, they are ill-suited for the kernel context. In particular, recent LLM-based techniques often treat bug reports and source code as plain text, lacking deep integration of kernel-specific knowledge, which limits their ability to identify root causes and achieve fine-grained localization. We present CoHiKer, a novel LLM-based FL technique tailored to the Linux kernel. CoHiKer introduces two key innovations: (1) contrastive reasoning, which identifies root causes by analyzing the behavioral divergence between carefully mutated passing and failing test cases, and (2) hierarchical context analysis, which systematically narrows the localization scope from files to methods by integrating crash reports, syscall semantics, inter-file dependencies, and kernel-specific features. Unlike prior techniques that rely on static understanding and full-code input, CoHiKer decomposes the localization task and enables structured LLM prompting to reason semantically over meaningful contexts. We evaluate CoHiKer on an extended Linux kernel bug dataset against five state-of-the-art baselines. CoHiKer consistently outperforms all competitors, improving Top-1 localization accuracy by up to 26.07% at the file level and 56.85% at the method level over state-of-the-art LLM-based baselines, while achieving up to 8.84% and 28.9% reductions in token consumption, respectively. Furthermore, CoHiKer demonstrates strong generalizability on the non-kernel dataset, with comparable gains (15.5% and 5.3% in Top-1 at file and method levels).
arXiv:2607.00585v1 Announce Type: new Abstract: Zero-emission mobility depots are becoming resilience assets because one site can host EV charging, hydrogen-bus operation, stationary conversion equipment, and nearby critical-building backup. The key question is not raw outage export capacity: hydrogen exported to buildings can strand buses, EV availability is stochastic, and building demand shifts seasonally. We introduce a mobility-safe reserve certification framework for a coupled EV, hydrogen-bus, and critical-building hub. It combines a physics-hybrid universal differential equation building-load twin, one-sided split conformal reserve calibration, adaptive conformal inference for seasonal drift, and a mobility-first scheduling rule that protects post-event bus service before assigning hydrogen to buildings. Evaluation uses 495,221 real EV charging sessions across eight regions, AC Transit GTFS-derived hydrogen-bus service days, and EnergyPlus 25.2 simulations under real TMY3 weather. Across 66,816 held-out outage scenarios, a mobility-blind hydrogen-export policy served 39.2\% of building demand but protected buses in 0\% of cases and caused a 426.7 kg mean bus-hydrogen shortfall. A nominal mean-resource promise delivered only 45.4\% of commitments. The certified mobility-first policy was the only tested policy to achieve 100\% commitment delivery, 100\% bus protection, and zero mean bus-hydrogen shortfall, while serving 20.5\% of critical-building demand. Under a summer-to-winter load shift, adaptive conformal inference raised late-period empirical coverage from 0.687 to 0.831 and reached 0.891 overall coverage against a 0.90 target with lower mean reserve than static split conformal. Across 12 building/seed drift runs, it kept low late-coverage variability and the lowest mean reserve. These results show that resilience value in shared zero-emission hubs depends on service-aware certification, not raw export capacity alone.
arXiv:2607.00361v1 Announce Type: new Abstract: Vision--Language Models (VLMs) are increasingly deployed in safety-critical applications, yet remain vulnerable to backdoor attacks. Existing methods primarily manipulate final outputs, often producing reasoning traces that are inconsistent or easily detectable. In this paper, we propose ReShift, the novel aha-moment-driven reasoning-level backdoor framework that explicitly redirects the internal chain-of-thought (CoT) trajectory while preserving surface-level coherence. ReShift introduces a Poisoned Reasoning-Aware Data Construction (PRDC) pipeline and a Supervised--Reinforcement Joint Optimization (SRJO) strategy to induce stable trigger-conditioned reasoning shifts. We further formalize Entropy Rebound as a principled signal for characterizing reasoning redirection and provide theoretical guaranties linking entropy gaps to trajectory-level divergence. Extensive experiments demonstrate that ReShift achieves high attack success rates while maintaining clean-task performance and realistic reasoning traces, substantially improving stealthiness against existing defenses.
arXiv:2607.00481v1 Announce Type: new Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and defenses at the prompt level, we show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments. In such applications, developer-defined schemas, structured arguments, and untrusted tool outputs are interleaved into a single shared model context. This architecture expands the attack surface by blurring the boundary between trusted control logic and untrusted data, allowing adversarial intent to be distributed across a multi-turn execution path. We exploit this architectural flaw through SMT, a black-box attack framework based on Simulated Moderation Traces. Departing from purely prompt-based interactions, SMT constructs a multi-turn trajectory that simulates a legitimate moderation-auditing workflow. Within this trajectory, a fabricated moderation frame leverages red-team testing as a pretext to elicit harmful generations. The subsequent validation feedback treats safety refusals as execution failures, prompting refinements that gradually weaken the model's safety constraints and ultimately trigger harmful outputs. Extensive empirical evaluations on prominent commercial LLMs from five different providers across two standardized safety benchmarks show that SMT consistently achieves the highest average attack success rate and HarmScore while requiring a near-minimal number of queries, substantially outperforming existing baselines. These findings demonstrate that prompt-level sanitization alone is fundamentally insufficient for defending tool-enabled LLM systems and highlight the urgent need for context-aware validation across schemas, arguments, tool outputs, and accumulated conversation state. The code is available at https://github.com/liujlong27/SMT.
arXiv:2607.00355v1 Announce Type: new Abstract: Phase-field models are typically derived from variational principles for a free-energy functional and are widely used to simulate complex multiphase phenomena in science and engineering. A central goal in designing numerical schemes for these models is to preserve the underlying energy-dissipation law. In this paper, we propose a class of relaxed Lagrange multiplier (RLM) schemes for phase field models. In contrast to popular scalar auxiliary variable (SAV) and invariant energy quadratization (IEQ) methods, which dissipate a modified energy involving auxiliary variables, the RLM schemes dissipate a relaxed version of the original energy and closely track the original energy dissipation rate. Compared with the classical Lagrange multiplier (LM) approach, the RLM schemes ensure that the resulting discrete system is uniquely solvable over a broad range of time steps. The key idea is to augment the LM formulation with a relaxation term, yielding a scalar quadratic equation for the multiplier with an explicit closed-form solution. The resulting schemes are linear and efficient because each time step requires solving only two linear systems with constant coefficients, at a cost comparable to that of SAV schemes. We construct both first-order and second-order variants and prove their energy stability. Numerical experiments verify the expected convergence rates and demonstrate that the RLM schemes accurately capture interface dynamics.
arXiv:2508.11664v2 Announce Type: replace-cross Abstract: Sleep stage classification is critical for diagnosing and managing disorders like sleep apnea and insomnia. However, conventional methods like polysomnography are costly and impractical for long-term, home-based monitoring. This study presents an energy-efficient approach for detecting four sleep stages (wake, rapid eye movement (REM), light sleep, deep sleep) using a single-lead electrocardiogram (ECG) signal. We evaluate various machine learning and deep learning models, introducing two windowing strategies: (1) a 5-minute window with 30-second steps for machine learning and (2) a 30-second window with 10-second steps for deep learning, enabling 10-second temporal resolution for real-time predictions. While deep learning models like MobileNet-v1 achieve high accuracy (92%) and F1-score (91%), their energy demands make them unsuitable for wearables. To address this, we design SleepLiteCNN, optimized for ECG-based sleep staging, achieving 89\% accuracy and 89% F1-score while minimizing energy use. Applying 8-bit quantization further reduces energy consumption to 5.48 microJ per inference, with 90% accuracy and F1-score. Additionally, field-programmable gate array (FPGA) deployment shows significant reductions in resource usage. This approach provides a practical, energy-efficient solution for continuous ECG-based sleep monitoring in resource-constrained wearable devices.
arXiv:2606.31087v2 Announce Type: replace Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose \emph{Training-Free Gated Reranking}, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU datasets and 9 MT domain-language combinations, demonstrate that our approach reduces computational costs by 15\%-80\% while improving average performance by up to 2\%. These findings indicate that higher computational cost does not guarantee better performance, and that reranking is most beneficial when targeted at high-uncertainty instances.
arXiv:2607.00886v1 Announce Type: new Abstract: Evaluation metrics are central to binary target segmentation because they determine how progress is measured, compared, and interpreted. In this paper, target denotes the task-defined positive region to be segmented rather than a generic foreground object. It may be salient, camouflaged, transparent, glass-like, mirror-like, shadow-like, lesion-like, or defined by other application-specific semantics. We treat existing metrics as compositions of modular design choices rather than isolated formulas. The proposed framework decomposes each metric into five stages covering prediction representation, target extraction, target matching, score computation, and metric reporting. We use this framework to analyze representative metrics and show how newer metrics address specific limits in earlier protocols. The stage choices keep each metric's assumptions visible. We then discuss the design space opened by the framework and its implications for task-aware evaluation protocols. Reference code is available at https://github.com/lartpang/PySODMetrics.
arXiv:2607.01201v1 Announce Type: new Abstract: The four-channel teleoperation architecture is a well-established framework for achieving transparency in bilateral systems. However, its performance in human-scale teleoperation is limited by high inertia, modeling challenges, and reliance on noisy and costly force/torque sensors. This paper introduces a sensorless four-channel architecture based on inverse dynamics modeling. The controller is implemented and validated on a customized WAM bilateral teleoperation setup. Experiments demonstrate that the proposed approach outperforms conventional two- and four-channel schemes as well as transparency-enhancement methods, improving position and force tracking, reducing operator effort, and increasing maximum transmittable impedance without external sensors. A door-opening case study involving sustained whole-body contact along the manipulator further demonstrates the effectiveness of the method in realistic human-scale manipulation tasks.
arXiv:2607.01216v1 Announce Type: new Abstract: We investigate the power of CUT queries to reveal the structure of unknown hypergraphs. While simple graphs allow for optimal $O(n)$-query connectivity algorithms, hypergraphs face a fundamental identifiability barrier in that distinct hypergraphs can share identical cut-profiles, making exact edge learning impossible in general, a primitive crucial in the graph connectivity algorithms. We first present a zero-error randomized algorithm that identifies the connected components of any weighted hypergraph using $O(n)$ expected queries, matching the $\Omega(n)$ lower bound. This approach bypasses the reconstruction barrier by introducing the notion of ``independent families'' -- vertex subpartitions that do not share hyperedges -- and iteratively coarsening them using auxiliary weighted graph connectivity techniques [Liao-Chakrabarty, 2024]. Second, we demonstrate that the impossibility of exact learning depends on hyperedge parity. For even-parity hypergraphs, we show that the structure is reconstructible using a M\"obius transform on the CUT function to implement binary-search-style vertex identification. This yields deterministic algorithms for obtaining $k$-connectivity certificates for $r$-bounded even hypergraphs in $\tilde{O}_r(kn)$ queries. Finally, we bypass parity and rank constraints for linear hypergraphs, achieving a subquadratic $\tilde{O}(kn^{1.5})$ query complexity for $k$-connectivity. This significantly improves upon the general $\tilde{O}(n^2)$ bound derived via symmetric submodular function minimization.
arXiv:2605.01896v2 Announce Type: replace Abstract: Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose $M^2$-REPA, the first representation alignment method tailored for multi-modal video generation. Our key insight is that foundation models trained on different modality spaces naturally capture distinct domain-specific priors, acting as complementary "experts." Specifically, we first decouple modality-specific features from the diffusion model's intermediate representations, then align each with its corresponding expert foundation model. To this end, we design two synergistic objectives: a multi-modal representation alignment loss that enforces feature-to-expert matching, and a modality-specific decoupling regularization that encourages complementarity across different modalities. This design enables joint optimization, fully exploiting priors from multiple foundation models. Extensive experiments demonstrate that our method significantly outperforms baselines in visual quality and long-term consistency.
arXiv:2605.02310v2 Announce Type: replace Abstract: Physics-informed neural networks provide a mesh-free framework for solving partial differential equation-governed problems in solid mechanics. However, most existing formulations in linear elasticity still learn the displacement field directly, which does not explicitly exploit the analytic structure of two-dimensional elasticity and becomes restrictive for fracture problems with crack face discontinuities and crack tip singularities. Moreover, existing Kolosov--Muskhelishvili informed neural network formulations still rely on residual-based loss functions with multiple boundary and interface terms, whereas a variational concept has not yet been established. To address these issues, a variational Kolosov--Muskhelishvili informed neural network framework for two-dimensional linear elastic problems with and without cracks is proposed in this work. The solution is represented by two holomorphic Kolosov--Muskhelishvili potentials and trained through an energy-based loss function derived from the principle of minimum total potential energy. For crack problems, a discontinuous stress potential representation is further introduced to embed the crack face condition and crack tip singularity directly into the solution ansatz. The proposed framework is validated on a series of benchmark problems with or without crack problems. The results show that variational Kolosov--Muskhelishvili informed neural network can accurately predict stress and displacement field as well as stress intensity factors. Compared with traditional neural network models, it achieves higher accuracy, simpler loss construction, and faster convergence in the considered cases. Overall, the proposed variational Kolosov--Muskhelishvili informed neural network provides an effective and physically consistent variational framework for two-dimensional linear elastic fracture analysis.
arXiv:2607.00008v1 Announce Type: new Abstract: Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples when available. We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.
arXiv:2605.03847v3 Announce Type: replace Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty. Existing approaches such as constrained optimization, safe reinforcement learning, and runtime assurance evaluate acceptability at the level of individual actions rather than across behavioral trajectories, and none addresses the multi-participant, uncertainty-laden nature of DCI deployments. This paper introduces mechanical conscience (MC), a novel concept and simplified mathematical framework that operationalizes trajectory-level normative regulation for both single-agent and distributed intelligent systems. Mechanical conscience is defined as a supervisory filter that minimally corrects a baseline policy's actions to reduce cumulative deviation from a normatively admissible region, while accounting for epistemic uncertainty. We introduce associated constructs, conscience score, mechanical guilt, and resonant dependability, that provide an interpretable vocabulary and computable governance signals for this emerging field. Core theoretical properties are established: admissibility equivalence, existence of optimal regulation, and monotonic deviation reduction. Illustrative results demonstrate that MC-regulated agents maintain trajectory-level normative acceptability where conventional controllers drift outside admissible bounds, and that the framework naturally extends to suppress interaction-induced emergent risk in multi-agent DCI settings.
arXiv:2511.22747v3 Announce Type: replace-cross Abstract: Let ${\mathcal C}(\Omega)$ be the linear code arising from a projective system $\Omega$ of $\mathrm{PG}(V).$ Consider the point-line geometry $\Gamma=({\mathcal P},{\mathcal L})$ and a projective embedding $\varepsilon\colon \Gamma\rightarrow \mathrm{PG}(V)$ of $\Gamma.$ We show that the projective code obtained by taking as projective system $\Omega:=\varepsilon(\mathcal{P})$ is minimal if the graph induced on the set $\Gamma\setminus\varepsilon^{-1}(H)$ by the collinearity graph of $\Gamma$ is connected for any hyperplane $H$ of $\mathrm{PG}(V)$. As an application, we prove that Grassmann codes, Segre codes, line polar Grassmann codes of orthogonal, symplectic, hermitian type, codes arising from dual polar spaces of orthogonal and symplectic type and codes arising from the point-hyperplane geometry of a projective space are minimal codes.
arXiv:2607.00141v1 Announce Type: new Abstract: This paper presents Adaptive Differentiable Model Predictive Contouring Control (AD-MPCC), a framework for autonomous racing that integrates differentiable MPCC with online parameter estimation to handle varying road-surface conditions. For online parameter estimation, we leverage a parameterized Pacejka Magic Formula together with a regularized moving-horizon estimation scheme with exponentially decaying weights to capture road interactions and update parameters in real time. Furthermore, we propose a differentiable MPCC (Diff-MPCC) framework that enables optimal adjustment of objective weights based on predefined long-horizon performance costs. To implement Diff-MPCC for online objective weight adaptation, we propose a Pacejka-informed machine learning model that is trained in a supervised manner using data generated by Diff-MPCC to tune the objective weights. Simulation results demonstrate that AD-MPCC reliably ensures safety and achieves faster lap times compared to baseline controllers in both single-surface and multiple-surface scenarios.
arXiv:2607.00102v1 Announce Type: new Abstract: The Obara-Saika (OS) method is one of the most widely used techniques in quantum chemistry for evaluating electron repulsion integrals (ERIs) via a set of recurrence relations that build higher angular momentum integrals from lower-order ones. The original derivation by Obara and Saika proceeded by directly relating integrals of differing angular momentum. In this work, we present a compact novel derivation of the OS vertical recurrence relation based solely on differential relations between Gaussian basis functions, expanding on a method suggested in earlier work. By explicitly deriving the required derivative expressions we identify all non-zero primitive terms contributing to the full ERI to develop a hierarchical formulation of the OS recursion relations. This approach has pedagogical value as a rigorous and self-contained derivation. Additionally, the resulting organization exposes independent primitive derivative quantities and may be useful for code generation and parallel implementations on modern GPU architectures.
arXiv:2607.00960v1 Announce Type: new Abstract: The flow and density field characteristics around a bubble curtain in a laboratory scale lock-exchange setup are investigated using two-phase large-eddy simulations. We study the detailed hydrodynamics and show that there are three qualitatively distinct (sub)regimes within the previously classified breakthrough regime. The occurrence of these regimes depends not only on air Froude number that characterises the relative strength of the bubble curtain and the gravity current, but also on an additional non-dimensional parameter: the density ratio between the salt and fresh water. The dependence on this additional parameter is also observed in how effective bubble curtains are in blocking the transport of salt to the fresh part of the lock. Hence, it has important implications for the optimisation of bubble curtains in ship locks.
arXiv:2607.00482v1 Announce Type: new Abstract: Reasoning language models frequently overthink: generating extended chains of behaviors such as hedging, approach abandonment, and self contradiction that consume tokens without improving answers. We show that these behaviors are not merely a consequence of length; even when controlling for response length, incorrect traces exhibit higher rates of unproductive self-reflection than correct ones. Addressing this requires identifying where self-reflection helps vs hurts, but obtaining these step-level annotations is costly. We observe that intermediate answer commitments within reasoning traces can provide a cheap proxy: by comparing each final answer candidate in the trace to the ground truth, we can determine whether subsequent reflection is productive without any additional supervision. Building on this insight, we propose DASH (Drift Aware advantage SHaping), which assigns segment-level credit based on whether each reasoning segment leads toward or away from correctness. On competition-level math benchmarks, DASH achieves the highest accuracy where overthinking is prevalent (AIME25: 50.8% vs. 45.4% GRPO) while reducing overthinking behaviors and achieving more productive self-correction than baselines.
arXiv:2506.12851v3 Announce Type: replace Abstract: Humanoid robots are promising to acquire various skills by imitating human behaviors. However, existing algorithms are only capable of tracking smooth, low-speed human motions, even with delicate reward and curriculum design. This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing through multi-steps motion processing and adaptive motion tracking. For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints to the maximum extent. For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance based on the current tracking error, creating an adaptive curriculum mechanism. We further construct an asymmetric actor-critic framework for policy training. In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions. Our method achieves significantly lower tracking errors than existing approaches and is successfully deployed on the Unitree G1 robot, demonstrating stable and expressive behaviors. The project page is https://kungfubot.github.io.
arXiv:2512.07784v2 Announce Type: replace Abstract: Optical thermalization has been recently studied in the 2D spatial evolution of (quasi-)monochromatic light waves propagating in multimode waveguides. Here, we investigate the spatio-temporal equilibrium properties of optical waves through the analysis of the (2+1)D Bose-Einstein thermal distribution and the corresponding classical Rayleigh-Jeans approximation. Numerical simulations of the nonlinear Schr\"odinger equation (NLSE) demonstrate relaxation toward the spatio-temporal Rayleigh-Jeans equilibrium state, as described by the corresponding wave turbulence kinetic equation. Remarkable adiabatic cooling phenomena stemming from the high-frequency tails of the Rayleigh-Jeans distribution are discussed and the consequent limitations of the classical approximation are highlighted. To overcome these issues, we make use of a quantum version of the NLSE whose associated kinetic equation describes relaxation toward the spatio-temporal Bose-Einstein equilibrium distribution. The analysis of thermodynamic properties reveals a strong dependence on the dispersion regime. In the anomalous dispersion regime, the system relaxes to positive-temperatures equilibrium states: as the number of modes of the waveguide increases, the fundamental spatial mode becomes macroscopically populated, while its temporal spectrum undergoes significant narrowing, ultimately leading to complete (2+1)D spatio-temporal condensation in the thermodynamic limit. In the normal dispersion regime, the system evolves toward negative-temperature equilibrium states characterized by an inverted spatial modal population. In this regime, we predict a phase transition to Bose-Einstein condensation at negative temperatures, which occurs by increasing the temperature above a negative critical value. Our work opens new avenues for future research and lay the groundwork for the development of spatiotemporal optical thermodynamics.
arXiv:2312.15427v3 Announce Type: replace Abstract: Stochastic optimization is a widely used approach for optimization under uncertainty, where uncertain input parameters are modeled by random variables. Exact or approximation algorithms have been obtained for several fundamental problems in this area. However, a significant limitation of this approach is that it requires full knowledge of the underlying probability distributions. Can we still get good (approximation) algorithms if these distributions are unknown, and the algorithm needs to learn them through repeated interactions? In this paper, we resolve this question for a large class of ''monotone'' stochastic problems, by providing a generic online learning algorithm with $\sqrt{T\log(T)}$ regret relative to the best approximation algorithm (under known distributions). Importantly, our online algorithm works in a semi-bandit setting, where in each period, the algorithm only observes samples from the random variables that were actually probed. Moreover, our result extends to settings with censored and binary feedback, where the policy only observes truncated or thresholded versions of the probed variables. Our framework applies to several fundamental problems such as prophet inequality, Pandora's box, stochastic knapsack, single-resource revenue management and sequential posted pricing.
arXiv:2405.03650v4 Announce Type: replace Abstract: We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicit scene representation and then rendered into semantically richer visual content. Conventional image-generation systems can produce visually realistic outputs from limited scene descriptions, but the added content is usually implicit in the generator rather than represented as an inspectable intermediate structure. In contrast, GCE seeks to make scene enrichment explicit at the scene-representation level while examining its visual consequences during generation, with the goal of encouraging generated content that is visually plausible, structurally coherent, and semantically richer than the sparse input. To instantiate GCE, we propose a jointly trained adversarial framework that enriches scene graphs by modeling object semantics and inter-object relations. Our approach first represents the input description as a scene graph, where nodes model objects and edges capture inter-object relations. The framework uses graph convolutional networks to predict additional objects and their relations to the existing scene. Finally, the enriched scene graph is passed through the downstream image-generation pipeline to generate the corresponding visual content. We evaluate the framework with proxy scene graph enrichment metrics, image-quality comparisons, qualitative examples, and user studies on the Visual Genome dataset.