Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.AI) 2026-06-16

Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft

arXiv:2606.15684v1 Announce Type: new Abstract: We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks. Our benchmark reflects four core characteristics of real-world collaboration: agent heterogeneity, mandatory collaboration, dynamic environments, and strict real-time constraints with failure risks. To enable this, we develop the TickingCollab framework, which supports the generation of diverse dynamic environments and abstracts Minecraft's primitive APIs to enable declarative YAML task specifications for composing these events. Building on this, we design a feasibility-aware automated benchmark generation pipeline, where an LLM drafts structurally diverse task configurations and feasibility verifier filters out invalid ones using approximate constraints. Evaluations demonstrate that lang latency and inherent difficulty of coordinating under partial observability and agent heterogeneity cause LLMs to frequently fail under dynamic environments and fall significantly short of a global-knowledge oracle.

02.
arXiv (quant-ph) 2026-06-17

Quantum Resources and Wigner Symmetry in Nucleon-Nucleon Scattering from Effective Field Theory

arXiv:2606.17148v1 Announce Type: cross Abstract: We study quantum resources in the spin degrees of freedom, such as entanglement, stabilizer magic, and non-local magic, in low-energy nucleon-nucleon scattering through next-to-leading order in pionless effective field theory. Treating each nucleon spin as a qubit, we calculate the corresponding resource-generating powers of the scattering operator at generic center-of-mass momentum and scattering angle $\Theta$. The analysis retains $S$- and $P$-wave channels generated by two-derivative contact interactions. When the microscopic physics exhibits Wigner's $SU(4)$ spin-flavor symmetry, the neutron-proton amplitude becomes proportional to the spin-space identity operator and therefore generates no new resources after scattering, extending an observation previously made for leading-order $S$-wave scattering. The same-nucleon channel remains resource-generating because constraints from identical particles project out part of the Hilbert space. These results show how enhanced symmetries, partial-wave structure, and resource generation are intertwined in low-energy two-body scattering.

03.
arXiv (CS.AI) 2026-06-11

HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation

arXiv:2606.11559v1 Announce Type: new Abstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful trajectories or terminal outcomes, and the student's current decision context. We introduce HERO, a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback. After each rollout, HERO reflects on the completed interaction to convert each observation into a compact turn-level diagnosis, that captures actionable feedback about the original action such as its necessity, validity or failure cause. On TauBench and WebShop, HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO. It is especially effective under limited training turn budgets, where successful rollouts are rare and GRPO provides weak reward-contrast signals.

04.
arXiv (quant-ph) 2026-06-17

Stochastic signal sensing with finite energy and dead time at the fundamental quantum limit

arXiv:2606.18133v1 Announce Type: new Abstract: State preparation, measurement, and reset operations take finite time and use finite energy in realistic experiments, yet the impact of this on optimal quantum metrological protocols is not properly understood. We study the effect on sensing a stochastic signal, relevant for the detection of ultralight dark matter and other searches for fundamental physics. We prove that two-mode squeezed vacuum is the optimal probe state given a finite mean-energy constraint for a family of incoherent sensing problems, including noise sensing and quantum illumination. For estimating a gain independent of a loss, we show that entanglement is a required resource to achieve the fundamental quantum limit and observe a non-Gaussian to Gaussian transition in the optimal unentangled state as the dead time increases. We apply our results to bulk acoustic wave resonators.

05.
arXiv (CS.CL) 2026-06-11

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a sequence-level Bradley-Terry objective across timesteps, leaving per-prefix (state-wise) optimality implicit. We study how to recover token-level preference optimality using only standard sequence-level pairwise comparisons. We introduce Token-level Bregman Preference Optimization (TBPO), which posits a token-level Bradley-Terry preference model over next-token actions conditioned on the prefix, and derive a Bregman-divergence density-ratio matching objective that generalizes the logistic/DPO loss while preserving the optimal policy induced by the token-level model and maintaining DPO-like simplicity. We introduce two instantiations: TBPO-Q, which explicitly learns a lightweight state baseline, and TBPO-A, which removes the baseline through advantage normalization. Across instruction following, helpfulness/harmlessness, and summarization benchmarks, TBPO improves alignment quality and training stability and increases output diversity relative to strong sequence-level and token-level baselines.

06.
arXiv (CS.CV) 2026-06-16

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions and parent-to-child semantic hierarchies. To overcome these limitations, we introduce a text-driven fusion framework empowered by hyperbolic manifold learning. During training, BLIP-extracted text prompts serve as topological anchors within the hyperbolic space, guiding vision-attribute alignment through hyperbolic embeddings that naturally accommodate varying semantic granularities. By exploiting the exponential volume growth dictated by the Poincaré ball's negative curvature, this approach seamlessly embeds hierarchical trees to encode coarse-to-fine semantics without metric saturation, while the vast peripheral space prevents texture distortion during cross-modal fusion. At inference, the fusion process autonomously adapts to input content using the learned text-attribute priors, completely eliminating the need for textual input. Experimental results show our method outperforms state-of-the-art approaches on benchmark datasets, with code available at https://github.com/Shaoyun2023/TEDFusion.

07.
arXiv (CS.AI) 2026-06-17

Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)

arXiv:2606.18135v1 Announce Type: cross Abstract: In this work, we introduce the Certus Caliber Classification Gunshot Dataset (C3GD), a publicly accessible data set developed for the analysis of firearm muzzle blast sounds. The dataset aims to provide a wide variety of firearms, calibers, cartridges, microphones, and microphone locations with metadata detailed beyond what is currently otherwise available. It comprises more than 8000 field-collected data points from 28 firearms across 16 calibers. Because data collection in the field is costly, much of the existing research has been done using gunshot audio collected from the internet, which increases the risk of low-quality data and label noise. This dataset is primarily focused on caliber classification, but can also be used for gunshot detection, audio separation, and audio signal processing, providing a diversified and real-world reference. The dataset aims to provide enough diversity to be able to generalize to more real-world applications while also providing enough metadata for detailed academic analysis.

08.
bioRxiv (Bioinfo) 2026-06-16

Orion: Towards Lab Automation with Computer-Using Agents

Laboratory discovery increasingly depends on computational workflows that connect experimental data to analysis, interpretation and follow-up hypotheses. Yet these workflows remain constrained by labor-intensive use of specialized software, visual inspection through graphical user interfaces, and integration of knowledge across multiple sources. Here, we present Orion, a computer-using AI agent for biomedical image analysis and interpretation that moves towards lab automation by automating this computational layer of laboratory work. Orion combines large language models with terminal execution, GUI control and adaptive multi-step reasoning in a shared computing environment. It can inspect visual data, operate standard scientific software, mine web resources and conduct end-to-end analysis and interpretation workflows without requiring bespoke software integrations. Across benchmarks, Orion achieved over 90% accuracy on biomedical database and literature retrieval tasks, learned to use the popular tools CellProfiler and QuPath for quantitative analysis of cellular and tissue images, respectively, and facilitated autonomous discovery in experimental imaging data. In 100 hours of autonomous exploration of a large-scale perturbation imaging dataset, Orion generated 52 research reports, of which human scientist review prioritized 22 plausible mechanistic hypotheses. These results show that computer-using AI agents can substantially expand the reach of laboratory automation, providing a scalable and auditable route from experimental imaging data to quantitative analysis, reports and biologically grounded hypotheses.

09.
arXiv (CS.AI) 2026-06-17

Sustainable Metal-Organic Framework Water Harvesters in the Artificial Intelligence Era

arXiv:2605.29179v2 Announce Type: replace-cross Abstract: Metal-organic frameworks (MOFs) are excellent candidates for water harvesting due to their tunable pore environments, which can be precisely engineered to capture and release water in arid conditions. Integrating artificial intelligence (AI) into MOF discovery can further accelerate the design of high-performance sorbents by identifying structural features that enhance atmospheric water harvesting (AWH), stability, and cycling efficiency. In this Perspective, we examine key MOF design principles, including cooperative adsorption, operational relative humidity (RH), uptake capacity, hysteresis, and scalability. We highlight recent design advancements such as multivariate strategies and long-arm linker extension, and examine how these principles tune pore capacity and hydrophilicity, while preserving stability and crystallinity. Furthermore, we discuss how AI, large language models (LLMs), and data mining can accelerate the discovery process through predictive synthesis, inverse design, and elucidating synthesis-structure-property relationships for the next generation of MOF water harvesters.

10.
arXiv (CS.LG) 2026-06-15

MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning

arXiv:2606.14354v1 Announce Type: new Abstract: Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates. This Work-in-Progress paper presents MUFFLe, a communication-efficient update compression scheme that integrates generalized deduplication (GD) into the FedAvg pipeline. MUFFLe deduplicates repeated patterns across the update vector, yielding a fixed-rate, variable-count compression scheme. Preliminary experiments on IID MNIST with 20 clients show that MUFFLe reaches the target accuracy of $92.93\%$ with 38~MB cumulative uplink communication, compared with 75~MB for 8-bit quantization, 86~MB for Top-$k$ sparsification, and 310~MB for uncompressed FedAvg. These results demonstrate the feasibility of applying GD to communication-efficient federated learning.

11.
arXiv (CS.AI) 2026-06-17

AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting

arXiv:2606.17461v1 Announce Type: cross Abstract: Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, yet current FGCG optimization flows remain largely manual. Recent LLM-based RTL optimization approaches remain limited by two key drawbacks: (1) the inability to process long waveform traces spanning millions of cycles, and (2) the difficulty of scaling optimization to large hierarchical codebases while preserving correctness. In this work, we present AUTOGATE, the first agentic framework for industry-grade RTL power optimization, enabling workload-aware clock-gating optimization across large hierarchical codebases. AUTOGATE introduces a Machine Learning (ML)-LLM co-design that bridges waveform-level analysis and RTL rewriting. Specifically, we design an ML-based clustering algorithm that distills raw toggling traces into compact, structured representations that guide LLM-based RTL rewriting. This enables accurate identification and application of clock-gating opportunities without requiring LLMs to directly process raw waveform data. To enhance scalability, AUTOGATE employs a hierarchical multi-agent architecture that decomposes large designs into independently optimizable modules, enabling coordinated optimization across deep design hierarchies. We evaluate AUTOGATE on a diverse set of designs ranging from small RTL designs to large industrial-grade codebases. Experimental results show that AUTOGATE consistently reduces dynamic power relative to baselines. Across the small-design suite, AUTOGATE reduces dynamic power by 49.31% on average. On industry-scale designs, it achieves 19.34% and 7.96% dynamic power reductions on NVDLA and BlackParrot, respectively, and up to 6.86% on highly optimized proprietary production designs.

12.
arXiv (CS.AI) 2026-06-15

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents

arXiv:2606.07027v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce the subjectivity of global partitioning, we introduce the Global Entity Stain Tracking module, which extracts visually verifiable task entities and tracks how their stain concentrations and states evolve along the trajectory, allowing task phases to be objectively separated by changes in the entity evidence flow. To improve the accuracy of local verification, we introduce the Local Stain Evidence Linking module. Centered on the triggering entities of each candidate key node, it retrieves relevant steps based on their stain concentrations and state changes, and dynamically constructs high-density evidence windows for verifying true key nodes. Extensive experiments on AndroidWorld and OGRBench show that StainFlow relatively improves online RL success by 3.2% and trajectory completion judgment accuracy by 1.8%.

14.
arXiv (CS.CV) 2026-06-17

StereoFactory: A Unified Merging Framework for Robust Stereo Matching

Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck: incorporating new data requires costly joint retraining. Model merging offers a scalable post-hoc alternative by integrating knowledge from specialized models after source checkpoints are available. However, existing merging methods typically retain all available models or rely on greedy inclusion, which can preserve harmful task-vector interference. We propose StereoFactory, a coarse-to-fine evolutionary framework for adaptive model merging. Stage~1 employs a genetic algorithm to search the combinatorial space of model subsets, determining which models should participate. Stage~2 addresses module-level knowledge specialization (different functional modules exhibit distinct preferences for knowledge sources) through CMA-ES optimization of architecture-adaptive routing over the selected task vectors, with optional module-level scaling. Experiments across two architectures and four benchmarks demonstrate that StereoFactory consistently achieves the best four-benchmark average under the same checkpoint pool, reducing the average error from 3.80 to 3.30 on NMRF and from 2.88 to 2.19 on FoundationStereo relative to the strongest controlled baseline. The post-hoc search requires only 2.7–3.7\% of the corresponding joint-retraining wall-clock time. Analysis reveals that knowledge contributions are inherently module-specific, and selected subsets can transfer across architectures with minimal degradation. Code will be publicly released upon acceptance at: https://github.com/XiandaGuo/StereoFactory.

15.
PLOS Computational Biology 2026-06-10

A mean-field model of neural networks with PV and SOM interneurons reveals connectivity-based mechanisms of gamma oscillations

by Farzin Tahvili, Martin Vinck, Matteo Di Volo Classic theoretical models of cortical oscillations are based on the interactions between two populations of excitatory and inhibitory neurons. Nevertheless, experimental studies and network simulations suggest that interneuron subclasses such as parvalbumin (PV) and somatostatin (SOM) exert distinct control over oscillatory dynamics. Yet, we lack a theoretical understanding of the mechanisms underlying oscillations in E-PV-SOM circuits and of the differences with respect to the classical mechanisms for oscillations in simpler E–I networks. Here, we derive a biologically realistic mean-field model of a canonical three-population E-PV-SOM circuit. This model robustly generates oscillations whose features are consistent with experimental observations, including the relative timing of PV and SOM activity and the effects of optogenetic perturbations. By reducing the model to a linear analytical form, we demonstrate that gamma oscillations emerge directly from the cell-specific connectivity of the three-population circuit. This connectivity motif alone accounts for experimentally observed phase relationships, with PV activity consistently leading that of SOM neurons. Together, this mean field model identifies a distinct structural mechanism giving rise to oscillations in canonical E–PV–SOM circuits and provides theoretical primitives for constructing large-scale, cell-type-specific models of cortical dynamics.

16.
arXiv (quant-ph) 2026-06-19

Strain- and Electric-Field-Tunable Valley Polarization in Mo0.75V0.25Te2(Mo3VTe8) for Valleytronic Application

arXiv:2606.19954v1 Announce Type: cross Abstract: Valley polarization in 2D TMDs is promising for low-power valleytronic and spin-valley information processing, but time-reversal symmetry in pristine nonmagnetic TMDs keeps the K+ and K- valleys degenerate, limiting device applications. In this work, we investigated the structural stability, electronic properties, and tunable valley polarization of V-alloyed MoTe2 monolayer, Mo0.75V0.25Te2, using first-principles density functional theory (DFT) calculations. Substitutional alloying of MoTe2 with V introduced magnetic exchange interaction, which, together with spin-orbit coupling (SOC), lifted the valley degeneracy at the unequal valleys. The alloyed structure was found to be energetically and dynamically stable due to the absence of imaginary phonon modes. In pristine MoTe2, SOC produced spin splittings of 34.0 meV and 218.9 meV in the conduction bands and valence bands, respectively, but no valley polarization was observed. In contrast, Mo0.75V0.25Te2 exhibited spontaneous valley polarization of 37.3 meV in the conduction band and 78.2 meV in the valence band. The valley polarization was further enhanced by external electric fields and biaxial strain. A transverse electric field along the crystal c axis produced the maximum valley splitting of 132.8 meV in the valence band, whereas biaxial tensile strain increased the valence band valley splitting up to 160.8 meV. The maximum conduction band valley splitting reached 54.4 meV under 2% biaxial compressive strain. These results demonstrated that V alloying, combined with electric-field and strain engineering, provides an effective strategy for achieving large and tunable valley polarization in MoTe2. Thus, Mo0.75V0.25Te2 can be considered a promising 2D platform for tunable valleytronic device applications, such as transistors and sensors.

17.
arXiv (CS.LG) 2026-06-19

Optimal Ansatz-free Hamiltonian Learning In Situ

arXiv:2606.19486v1 Announce Type: cross Abstract: Characterizing the features of a Hamiltonian that governs a quantum system serves as a fundamental subroutine of quantum device calibration, signal sensing, and error correction. Recent works proposed protocols have achieved the optimal Heisenberg-limited scaling learning ansatz-free Hamiltonians from their real-time evolutions without fully specifying interaction structures. However, these protocols rely on both deep circuits with interleaving probes and control, and extremely short time resolution, making them difficult to implement on near- and intermediate-term in situ quantum experiments. In this work, we propose a computationally efficient, control-free, and ancilla-free algorithm that uses only Pauli product state preparation and measurement, and learns an ansatz-free Hamiltonian $H$ with $||H||\leq\Lambda$ in total evolution time of $\Theta(\frac{\Lambda}{\epsilon^2}\log(\frac{\Lambda}{\epsilon}))$. The evolution time cost of our algorithm is optimal for any control-free protocols as we further prove a lower bound of $\Omega(\frac{\Lambda}{\epsilon^2}\log(\frac{\Lambda}{\epsilon}))$. Technically, our method introduces a randomized-sampling framework that combines band-limited kernel-based time sampling with a displacement sieve for Hamiltonian structure learning. The characteristic probe time resolution depends only on $\Lambda$ instead of $\varepsilon$, which makes our protocol especially appealing in the high-precision regime for sensing and calibration applications. We also show that the algorithm maintains the same asymptotic total evolution time in the presence of state-preparation-and-measurement (SPAM) noise when the Hamiltonian is local after calibration. Our results demonstrate the fundamental cost of experimentally friendly Hamiltonian learning and provide a practical route to rigorous in situ characterization of near-term quantum platforms.

18.
arXiv (CS.CL) 2026-06-16

Understanding the Behaviors of Environment-aware Information Retrieval

Recent retrieval-augmented generation (RAG) approaches have demonstrated strong capability in handling complex queries, yet current research overlooks a critical challenge: different retrievers require fundamentally different query formulation strategies for optimal performance. In this work, we present the first systematic analysis of how LLMs can learn to adapt their query formulation strategies for different retrievers via reinforcement learning (RL). Our empirical study reveals that RL effectively teaches an LLM to tailor its queries to specific retriever characteristics. We discover that different retrievers exhibit surprisingly distinct optimal query styles (e.g., descriptive vs. question-like), suggesting strategies learned for one retriever ineffective for another. We further show that performance can be enhanced by incorporating retriever-specific human guidance and by scaling model size. To facilitate learning over multi-retrieval-step trajectories, we introduce a branching-based rollout technique that improves training stability. Our work provides the first empirical evidence and actionable insights for building truly retriever-aware RAG systems. Code and resources are available at https://github.com/LCO-Embedding/Envs-aware-Information-Retrieval.

19.
arXiv (CS.CL) 2026-06-11

Neuron-based Personality Trait Induction in Large Language Models

Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and is designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PersonalityBench, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI.

20.
arXiv (CS.AI) 2026-06-17

Structural Preservation and the Logical Expressiveness of Graph Neural Networks

arXiv:2606.17882v1 Announce Type: new Abstract: Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggregation, combination, and activation functions. These choices define restricted classes of GNNs for which tight correspondences with logical formalisms can be obtained, by showing that logical formulae can be translated into equivalent GNNs and, conversely, that GNNs can be translated into equivalent formulae. In this paper we take a semantic perspective by establishing the logical expressiveness of classes of GNN classifiers that are preserved under structural properties: embeddings (extensions), injective homomorphisms, and homomorphisms. We show that, for each such property, there exists a fragment of graded modal logic characterising the class of GNNs. In particular, preservation under embeddings, injective homomorphisms, and homomorphisms corresponds to existential graded modal logic, its existential-positive fragment, and existential-positive modal logic, respectively. These results characterise the expressiveness of broad classes of GNNs independently of specific architectural choices, but we also show that each of these classes admits a GNN architecture of the same expressiveness. Technically, our approach uses a new well-quasi-order result for trees of bounded height, yielding finite representations of unravelling-invariant classes.

21.
arXiv (CS.LG) 2026-06-15

Diffusion Policy Optimization without Drifting Apart

arXiv:2606.13795v1 Announce Type: new Abstract: RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement. We identify the cause as the double-drift phenomenon: optimizing a variational surrogate can let the ELBO separate from the true log-likelihood, which then makes the resulting proxy policy gradient misaligned with the true policy gradient of expected return. We propose DiPOD, a diffusion policy optimization framework that maintains tight-bound behavior throughout training by interleaving self-distillation with policy-improving gradient updates. This leads to a simple and practical algorithm: augmenting each diffusion policy-gradient update with an on-policy ELBO regularizer. Across diffusion language model post-training and continuous-control diffusion policies, DiPOD substantially stabilizes training and reaches higher rewards than previous methods.

22.
arXiv (CS.CV) 2026-06-12

PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations–cases where models reach the right answer while misperceiving visual evidence. We address this process-level misalignment with PaLMR, a framework that aligns not only outcomes but also the reasoning process itself. PaLMR comprises two complementary components: a perception-aligned data layer that constructs process-aware reasoning data with structured pseudo-ground-truths and verifiable visual facts, and a process-aligned optimisation layer that constructs a hierarchical reward fusion scheme with a process-aware scoring function to encourage visually faithful chains-of-thought and improve training stability. Experiments on Qwen2.5-VL-7B show that our approach substantially reduces reasoning hallucinations and improves visual reasoning fidelity, achieving state-of-the-art results on HallusionBench while maintaining strong performance on MMMU, MathVista, and MathVerse. These findings indicate that PaLMR offers a principled and practical route to process-aligned multimodal reasoning, advancing the reliability and interpretability of MLLMs.

23.
arXiv (CS.LG) 2026-06-11

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

arXiv:2601.08136v2 Announce Type: replace Abstract: Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge. A fundamental difficulty that distinguishes online RL from standard generative modeling is the lack of direct samples from the target Boltzmann distribution defined by the Q-function. To address this, two seemingly distinct families of methods have been proposed for diffusion policies: a noise-expectation family, which uses a weighted average of noise as the training target, and a gradient-expectation family, which employs a weighted average of Q-function gradients. However, it remains unclear how these objectives are formally related, or whether they can be synthesized into a more general formulation. In this paper, we propose a unified framework, reverse flow matching (RFM), which rigorously addresses the problem of training diffusion and flow models without direct target samples. By adopting a reverse inferential perspective, we formulate the training target as a posterior mean estimation problem given an intermediate noisy sample. Crucially, we introduce Langevin Stein operators to construct zero-mean control variates, deriving a general class of estimators that share the same expectation. We show that existing noise-expectation and gradient-expectation methods are simply two specific instances within this broader class. This unified view yields two key advancements: it extends the capability of targeting Boltzmann distributions from diffusion to flow policies, and it enables the principled combination of Q-value and Q-gradient information to form an effective estimator, thereby improving training efficiency and stability. We instantiate RFM to train a flow policy in online RL and demonstrate improved performance on continuous-control benchmarks compared to diffusion policy baselines.

24.
arXiv (quant-ph) 2026-06-17

Singular Vector Finite Element Basis Functions for Tetrahedra in Complex Electromagnetic Geometries

arXiv:2606.18140v1 Announce Type: cross Abstract: Electromagnetic finite element method (FEM) implementations using traditional basis functions struggle to accurately represent field behavior near singular features such as conducting wedges. To combat this, specialized singular basis functions have been introduced to directly model the singular fields in these regions, leading to substantially improved performance. While these efforts have been pursued extensively in 2D, few functions have been developed for 3D elements. In this work, we develop basis functions for this in tetrahedra. Unlike prior functions, these basis functions are additive, meaning they are included alongside the standard vector basis functions to achieve more robust performance. Further, these functions are designed to be adaptable to tetrahedra touching several unique singular features by using combinations of basis functions singular with respect to each node and edge in the element, making them applicable to highly complex geometries. Higher-order interpolatory versions of the basis functions for modeling singular behavior with greater accuracy are also provided. These basis functions lead to substantial improvements in accuracy relative to the standard basis functions, and allow otherwise expensive simulations to be performed at far lower costs. As an application example, we perform simulations to extract critical quantities for designing superconducting qubits that significantly depend on the behavior of singular fields. In Ansys HFSS, this took 21.27 hours and a peak memory usage of 6.23 TB with 800 processors available, while using our singular basis functions achieved comparable results in 196 seconds while using 27.24 GB of memory and only 16 processors. Due to these benefits, our singular basis functions could be applied to enable design optimization of electromagnetic geometries with dominantly singular behavior, such as superconducting qubits.

25.
arXiv (CS.LG) 2026-06-16

Localized Kernel Projection Outlyingness: A Two-Stage Approach for Multi-Modal Outlier Detection

arXiv:2510.24043v4 Announce Type: replace Abstract: This paper presents Two-Stage LKPLO, a novel multi-stage outlier detection framework that overcomes the coexisting limitations of conventional projection-based methods: their reliance on a fixed statistical metric and their assumption of a single data structure. Our framework uniquely synthesizes three key concepts: (1) a generalized loss-based outlyingness measure (PLO) that replaces the fixed metric with flexible, adaptive loss functions like our proposed SVM-like loss; (2) a global kernel PCA stage to linearize non-linear data structures; and (3) a subsequent local clustering stage to handle multi-modal distributions. Comprehensive 5-fold cross-validation experiments on 10 benchmark datasets, with automated hyperparameter optimization, demonstrate that Two-Stage LKPLO achieves state-of-the-art performance. It significantly outperforms strong baselines on datasets with challenging structures where existing methods fail, most notably on multi-cluster data (Optdigits) and complex, high-dimensional data (Arrhythmia). Furthermore, an ablation study empirically confirms that the synergistic combination of both the kernelization and localization stages is indispensable for its superior performance. This work contributes a powerful new tool for a significant class of outlier detection problems and underscores the importance of hybrid, multi-stage architectures.