探索全球前沿学术脉络

01.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.14949

Initiation of Superradiance from Different Collective Spin States

作者:

Adnan Alabbar↗Zhenghao Zhang↗Girish S. Agarwal↗

arXiv:2606.14949v1 Announce Type: new Abstract: Superradiance is an extensive cooperative spontaneous emission phenomenon. Some atomic collective spin states exhibit it. However, distinct initial states differ in their decay dynamics. Dicke states with different numbers of excitations have their peak emission intensity shifted in time depending on the number of excitations. Emission intensity in atomic coherent states depends on their polarization. Some specific states undergo a squeezing controlled crossover, making the emission character dependent on the amount of squeezing in the state. We present detailed results on the superradiant dynamics of a representative selection of Dicke states. For large N, we are able to predict fairly accurately the pulse profile in each case using the mean field approximation, an approach based on the Fokker Planck Equation. We also present results on the intensity correlation function of the emission.

阅读与讨论 → 访问原文 →

02.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:8e7e034384b5c21885d0b2b0ccc84035

Pillbox: A Leakage-Aware Foundation-Model Predictor and Lineage-Ceiling Diagnostic for Cancer Drug Response

作者:

Hill↗J. J. K↗Ryoo↗H. J↗Ghanta↗Singh↗Anders↗Jiao↗Jeong↗

We present Pillbox, a predictor whose pipeline is audited against the six Asiaee leakage modes with the one residual pathway shown by per-fold ablation to be non-load-bearing on hard splits. Our model combines CpGPT methylation embeddings, CLAMP drug embeddings, and per-fold-fit gene-expression principal components which are fused by Feature-wise Linear Modulation (FiLM)-conditioned graph attention on the STRING v12 protein-protein interaction graph. Then we alpha-ensemble the model against a histogram-based gradient boosting regressor baseline. On GDSC GSE68379 (987 cell lines, 375 drugs) across seeds 42, 7, and 123, the ensemble reaches test R-Squared of 0.78, 0.77, and 0.76 on random, histology-blind, and site-blind splits respectively, with cell-aware lifts above the drug-mean floor of +0.054, +0.060, and +0.037. As a quantitative diagnostic for feature-stack saturation we propose the cross-architecture residual correlation, calibrated against a same-architecture-different-initialization control. On histology-blind splits the cross-architecture value of 0.939 falls short of the same-architecture ceiling of 0.974 by approximately 0.03 in residual correlation, a gap we interpret as the headroom available to architecture choice on top of the current foundation-model representation and consistent with the long-established observation that tissue lineage dominates cell-line drug response. We integrated curated mutation, methylation, and drug-target-expression channels, but these do not improve prediction once foundation-model embeddings are in place. Cross-screen validation against PRISM matches the GDSC-to-PRISM measurement reproducibility ceiling within 0.01 Spearman.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19378

A Hybrid GNN-FEM Framework for Phase-Field Fracture Simulation. Physics-Preserving Hybridization for Generalizable Surrogate Modeling

作者:

Hyeonbin Moon↗Yongjin Choi↗Seunghwa Ryu↗

arXiv:2606.19378v1 Announce Type: new Abstract: Scientific machine learning (SciML) has emerged as a promising approach for accelerating simulations of complex physical systems, yet achieving physically consistent and generalizable predictions for nonlinear, history-dependent problems remains a central challenge. In this study, we propose a hybrid GNN–FEM framework for efficient and generalizable phase-field fracture modeling. While phase-field approaches provide a robust variational framework for simulating complex crack evolution, their high computational cost limits practical applications because they require solving coupled, nonlinear, and history-dependent systems within an incremental finite element procedure. To address this challenge, a graph neural network surrogate is integrated into the conventional staggered scheme, replacing the phase-field update at each load increment while retaining the FEM-based displacement solver to enforce mechanical equilibrium and boundary conditions. By preserving the incremental solution structure, the framework remains consistent with history-dependent fracture evolution without requiring the surrogate to approximate the full solution trajectory. This selective surrogate strategy emphasizes the identification of a physically meaningful and incrementally structured learning target, rather than relying on brute-force data generation to learn the full fracture process. The proposed framework achieves strong generalization across varying geometries, loading conditions, material properties, and discretizations through dimensionless feature design, a graph-based formulation on mesh-based domains, and a physics-informed loss derived from the governing phase-field equation. Numerical experiments demonstrate that the hybrid approach reduces computational cost while maintaining accuracy compared with conventional FEM, and exhibits robust predictive performance across diverse problem settings.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16271

Contrastive Learning for Seismic Horizon Tracking with Domain-Specific Priors

作者:

Alexandre Thouvenot↗Lionel Boillot↗Vincent Gripon↗

Unsupervised 3D seismic horizon tracking faces a key limitation: signal-based propagators provide accurate trace-level alignment but often fail near faults, whereas texture-driven deep models are more robust to discontinuities, typically at the cost of labeled data requirements and reduced trace-level precision. We propose a self-supervised fusion of both paradigms in which signal-derived local horizon correspondences act as domain-specific priors to train a texture-based deep learning model. Specifically, we estimate reliable trace-to-trace flows from reflector slopes and use them to form positive pairs in a contrastive objective, while restricting training to high-confidence neighborhoods, optionally augmented with a fault mask. The objective is not to infer ambiguous correspondences close to discontinuities, but to preserve horizon identity across them. As a result, the network learns voxel-wise embeddings that preserve local signal continuity while enabling horizon propagation beyond discontinuities through similarity search. Experiments on the public F3 dataset and a faulted synthetic dataset achieve lower mean absolute error (MAE) than unsupervised baselines and competitive performance against a semi-supervised method using a single labeled slice.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19744

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

作者:

Pranav Bhandari↗Nicolas Fay↗Amitava Datta↗Usman Naseem↗Mehwish Nasim↗

Aligning language models with human preferences often requires optimising multiple behavioural objectives. A practical approach is to apply these objectives sequentially using preference optimisation methods such as Direct Preference Optimisation (DPO), but it remains unclear whether later training uniformly degrades preferences learned earlier or whether the effect depends on the relationship between objectives. We study sequential DPO across four preference settings covering distributional conflict, multi-attribute interaction, strong safety signal, and compatible response-quality objectives. Using Llama-3.1-8B-Instruct with LoRA adapters, we evaluate all objectives after every stage with a fixed base-model reference. We find that sequential DPO does not produce a single forgetting pattern; preference change ranges from partial degradation to stability, pair-level redistribution, or positive transfer depending on objective relationship, signal strength, and training order. Pair-level analysis using length-normalised policy margins shows that aggregate metrics can mask heterogeneous changes across preference pairs, whereas quartile decomposition reveals that high-confidence pairs can either degrade or improve depending on the setting. Mechanistic diagnostics show that Stage~2 gradients and adapter updates are near-orthogonal to the previous objective across all settings, providing little evidence that direct gradient opposition is the primary driver. These findings suggest that future sequential alignment pipelines should account for objective compatibility and signal strength, rather than assuming that later objectives affect earlier preferences uniformly.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2507.08794

One Token to Fool LLM-as-a-Judge

作者:

Yulai Zhao↗Haolin Liu↗Dian Yu↗Sunyuan Kung↗Meijia Chen↗Haitao Mi↗Dong Yu↗

Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR). However, we uncover a critical vulnerability even in this reference-based paradigm: generative reward models are systematically susceptible to reward hacking. We find that superficial inputs, which we term ''master keys'' such as non-word symbols (e.g., '':'' or ''.'') or generic reasoning openers (e.g., ''Thought process:'' or ''Let's solve this problem step by step.''), can consistently elicit false positive rewards without any substantive reasoning. Our systematic evaluation demonstrates this is a widespread failure affecting a diverse range of models, including leading proprietary systems such as GPT-o1 and Claude-4. These results challenge the assumed robustness of LLM judges and pose a significant threat to their reliability. To address this, we propose a simple yet effective data augmentation strategy using truncated model outputs as adversarial negative examples. The resulting Master Reward Models (Master-RMs) demonstrate state-of-the-art robustness against these ''master key'' attacks while maintaining high performance in standard evaluation settings. We supplement these findings with a comprehensive analysis of the vulnerability across model scales, prompt variations, and common inference-time strategies, offering insights to guide future research on robust LLM evaluation. We release our robust, general-domain reward models and the synthetic training data at https://huggingface.co/sarosavo/Master-RM and https://huggingface.co/datasets/sarosavo/Master-RM.

阅读与讨论 → 访问原文 →

07.

medRxiv (Medicine) 2026-06-18 DOI: HASH:3b311ca869ebb012f48dcc88b50da49e

Guiding the development of climate counterfactuals for health impact attribution studies

作者:

Charnley↗G. E. C↗Kotz↗Kawiecki Peralta↗Grayson↗K. M↗

Climate change detection and attribution (D&A) methods have become vital for quantifying the influence of anthropogenic forcing on the Earth's systems, including human health. Health impact attribution (HIA) studies seek to disentangle climate-driven health effects from natural variability yet are often constrained by the availability of accessible counterfactual climate scenarios. This tutorial paper presents a flexible, reproducible framework for developing counterfactual climates without reliance on computationally intensive global circulation models. We provide practical, R-based methodologies for constructing both trend-based (temperature and non-temperature) and event-based counterfactual, using a variety of techniques including model residual detrending, data-driven decomposition (e.g., Singular Spectrum Analysis and Empirical Mode Decomposition) and stochastic weather generators. The tutorial also explores the incorporation of greenhouse gas concentrations as forcing variables, rather than global mean temperature anomalies. By operationalising these methods through worked examples and an open code repository, this paper aims to build capacity within the HIA community, enhance methodological transparency, and foster interdisciplinary collaboration between climate and health researchers.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2601.19827

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

作者:

Mahdi Astaraki↗Mohammad Arshi Saloot↗Ali Shiraee Kasmaee↗Hamidreza Mahyar↗Soheila Samiee↗

Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with multi-hop reasoning, sparse domain knowledge, and heterogeneous evidence. We provide the first controlled, mechanism-level diagnostic study of whether synchronized iterative retrieval and reasoning can surpass an idealized static upper bound (Gold Context) RAG. We benchmark eleven state-of-the-art LLMs under three regimes: (i) No Context, measuring reliance on parametric memory; (ii) Gold Context, where all oracle evidence is supplied at once; and (iii) Iterative RAG, a training-free controller that alternates retrieval, hypothesis refinement, and evidence-aware stopping. Using the chemistry-focused ChemKGMultiHopQA dataset, we isolate questions requiring genuine retrieval and analyze behavior with diagnostics spanning retrieval coverage gaps, anchor-carry drop, query quality, composition fidelity, and control calibration. Across models, Iterative RAG consistently outperforms Gold Context, with gains up to 25.6 percentage points, especially for non-reasoning fine-tuned models. Staged retrieval reduces late-hop failures, mitigates context overload, and enables dynamic correction of early hypothesis drift, but remaining failure modes include incomplete hop coverage, distractor latch trajectories, early stopping miscalibration, and high composition failure rates even with perfect retrieval. Overall, staged retrieval is often more influential than the mere presence of ideal evidence; we provide practical guidance for deploying and diagnosing RAG systems in specialized scientific settings and a foundation for more reliable, controllable iterative retrieval-reasoning frameworks.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13322

Low-Latency Real-Time Audio Game Commentary System via LLM-Based Parallel Text Generation

作者:

Ryota Kawamatsu↗Anum Afzal↗Yuki Saito↗Shinnosuke Takamichi↗Graham Neubig↗Katsuhito Sudoh↗Hiroya Takamura↗Tatsuya Ishigaki↗

We present a low-latency real-time audio game commentary system that generates spoken commentary directly from live gameplay video. In this end-to-end setting, a key bottleneck is accumulated waiting time; conventional pipelines capture frames, generate text, and synthesize speech sequentially for each utterance, and do not request the next generation until speech playback has completed. This strict sequentiality causes long and unnatural silence between utterances. To address this latency bottleneck, our system runs text generation in parallel with speech playback and buffers multiple candidate utterances ahead of time, enabling immediate synthesis at playback boundaries. Experiments on fast-paced game videos show that our parallel design reduces the mean inter-utterance silence from 9.6 seconds to 0.3 seconds compared to sequential baselines. It also improves similarity to professional speaking–silence timing patterns by over 40 %, and a user study with 120 experienced game players confirms significantly improved perceived speaking rhythm. Our demo video is available at: https://youtu.be/pmrRUlvav8M.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11843

Quantum iterative approach to the Traveling Salesman Problem

作者:

Arturo Rodr\'iguez-Almaz\'an↗Guillermo Rivas↗Ricardo S. Alonso↗Daniela Falc\'o↗Mir Amir Hosseini↗

arXiv:2606.11843v1 Announce Type: new Abstract: The Traveling Salesman Problem (TSP) is a classical NP-hard problem in combinatorial optimization, where determining the shortest route among a set of cities becomes computationally prohibitive as the problem size increases. This work explores quantum computing as an alternative approach to address this complexity. Unlike existing methods that primarily rely on quantum annealing, we propose a quantum iterative framework integrating Quantum Phase Estimation (QPE) and Grover's search algorithm. Route costs are encoded as quantum phases, enabling QPE to efficiently evaluate them, while Amplitude Amplification, implemented via the Grover-Long algorithm, iteratively refines the solution space toward the optimal route. A proof-of-concept case study on a small-scale TSP instance demonstrates the feasibility of this approach and its potential for scaling to larger optimization problems. Furthermore, under an expectation-based analysis, the algorithm exhibits an expected computational complexity of $O(\frac{m^2\log_2(m)\log_2(1/\epsilon)}{\sqrt{\epsilon}})$ which depends on the error tolerance parameter $\epsilon$. This estimation omits the initialization term, which we expect future refinements to render subdominant to Phase Estimation.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2603.14867

Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning

作者:

Mikoto Kudo↗Takumi Tanabe↗Akifumi Wachi↗Youhei Akimoto↗

arXiv:2603.14867v4 Announce Type: replace-cross Abstract: Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's strategy that accounts for changes in the follower's optimal policy. Unlike prior hypergradient-based methods that require extensive data for repeated state visits or rely on gradient estimators whose complexity can increase substantially with the high-dimensional leader's decision space, we leverage the Boltzmann covariance trick to derive an alternative hypergradient formulation. This enables efficient hypergradient estimation solely from interaction samples, even when the leader's decision space is high-dimensional. Additionally, to our knowledge, this is the first method that enables hypergradient-based optimization for 2-player Markov games in decentralized settings. Experiments highlight the impact of hypergradient updates and demonstrate our method's effectiveness in both discrete and continuous state tasks.

阅读与讨论 → 访问原文 →

12.

medRxiv (Medicine) 2026-06-11 DOI: HASH:bc550c4dbf0329acfee557b88bbb634a

Parent and physiotherapist perceptions about movement skills of young children with juvenile idiopathic arthritis

作者:

Letts↗Herrington↗Batthish↗Bedard↗Bremer↗Gorter↗J. W↗King-Dowling↗Obeid↗

Objective: The onset of juvenile idiopathic arthritis (JIA) in the early years ([≤]5 years) may negatively impact movement skill (encompassing related concepts of gross motor skills, fundamental movement skills, and functional ability) development. Few studies have explored the perceptions and needs of parents and physiotherapists towards children's difficulty with these movement skills, essential to identify potential areas for added support. The objective of this study is to understand the perceptions of physiotherapists and parents towards movement skills of children with JIA. Methods: Seventeen parents and 24 physiotherapists completed an online questionnaire consisting of multiple choice and open-ended questions about the movement skills of young children with JIA. Demographic and multiple choice questions were quantitively analysed using descriptive statistics. Open-ended responses were analyzed using qualitative conventional content analysis. Results: About half (47%) of parents perceived their children to have movement difficulties, and 75% of physiotherapists described the movement skills of children with JIA as worse than other children of the same age. Our qualitative analysis revealed three general themes including: functional task difficulties; clinical variability in movement skills; and psychosocial components of movement skill difficulties. Conclusion: This study provides an analysis of perceptions of physiotherapists and parents towards the movement skills of young children with JIA. A significant proportion of parents and physiotherapists identify movement difficulties among children with JIA that impact daily life. Future interventions co-designed with both parents and care providers targeting movement skills are needed.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13625

Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios

作者:

Vin\'icius Orr\'u↗Bruno H. Foggiatto↗Gabriel E. Lima↗David Menotti↗Rayson Laroca↗

Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to low resolution, occlusion, motion blur, or poor illumination. However, real-world vehicle color distributions are highly imbalanced, making overall accuracy insufficient to assess performance on rare but operationally relevant colors. This paper presents a comprehensive study of vehicle color recognition under severe class imbalance using UFPR-VeSV, a challenging real-world surveillance dataset. We investigate synthetic minority-class augmentation through two off-the-shelf generative strategies: text-conditioned image generation with RunDiffusion/JuggernautXL and image-conditioned color editing with Gemini 2.0 Flash. The curated synthetic data are combined with modern visual representations, loss reweighting, learning-rate scheduling, color-safe augmentation, foreground-aware preprocessing, and ensemble fusion. The bestperforming approach achieves 94.6% micro accuracy and 79.7% macro accuracy, improving macro accuracy by 8.2 percentage points over recent literature. A manual error analysis further shows that many remaining failures are visually ambiguous even for human annotators, highlighting the practical limits of color-based vehicle identification in unconstrained surveillance imagery. The generated images and source code are publicly available at https://github.com/viniciusorru/vcr-synthetic

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16914

Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

作者:

Tong Che↗Rui Wu↗

arXiv:2606.16914v1 Announce Type: new Abstract: Deployed agents increasingly act with their reward proxy in view, such as a balance, score, or KPI dashboard. We show that reinforcement learning can make a policy addicted to such a visible self-benefit channel. It chases the displayed payoff across held-out domains, sacrifices the true task to do so, and follows the channel wherever we rewrite it, while policies that never saw the channel stay honest. We call this reward-channel addiction and study it in MoneyWorld, a synthetic sandbox. The addiction can flip a model's safety alignment: trained only on innocuous money tasks with no safety content, the model abandons the safe action it otherwise always takes whenever a dashboard pays for an unsafe one, and reverts to safe once the channel is hidden. This learned bribe replicates across model scales and families. Blindly optimizing super-capable, next-generation AI on KPIs or P\&L can be dangerous for alignment. Greed is learned when following such a channel pays.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17682

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

作者:

Chao Chen↗Chengzu Li↗Zhiwei Li↗Yinhong Liu↗Zhijiang Guo↗

Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically infer which configuration will best improve the current policy. To automate this process, we propose the LLM-as-Environment-Engineer framework in which the current policy model analyzes failure trajectories together with contextual information and proposes modifications to the next-stage training environment configuration. We also introduce MAPF-FrozenLake, a controllable testbed whose generator exposes multi-dimensional environment configurations, making it suitable for studying and benchmarking environment redesign. On this testbed, we condition the environment engineer on structured summaries of policy behavior, failure cases, and environment statistics, from which it produces the configuration for the next training stage. With Qwen3-4B as the backbone, our framework achieves the strongest aggregate performance on our benchmarks, outperforming larger proprietary LLMs (e.g., GPT, Gemini) and fixed-environment training baselines. We further analyze which forms of context are most effective, finding that successful environment updates rely on failure evidence and preserve configurations that already work. Interestingly, the current RL checkpoint serves as a better environment engineer than the original base model, suggesting that policy learning improves the model's ability to diagnose its remaining weaknesses.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.07212

Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation

作者:

Zhaoyang Liu↗Mokai Pan↗Zhongyi Wang↗Kaizhen Zhu↗Haotao Lu↗Haipeng Zhang↗Jingya Wang↗Ye Shi↗

arXiv:2512.07212v3 Announce Type: replace Abstract: Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions. However, existing methods typically treat observations only as high-level conditions to the denoising network, rather than integrating them into the stochastic dynamics of the diffusion process itself. As a result, the sampling is forced to begin from random noise, weakening the coupling between perception and control and often yielding suboptimal performance. We propose BridgePolicy, a generative visuomotor policy that directly integrates observations into the stochastic dynamics via a diffusion-bridge formulation. By constructing an observation-informed trajectory, BridgePolicy enables sampling to start from a rich and informative prior rather than random noise, substantially improving precision and reliability in control. A key difficulty is that diffusion bridge normally connects distributions of matched dimensionality, while robotic observations are heterogeneous and not naturally aligned with actions. To overcome this, we introduce a semantic aligner to unify the visual and state inputs and align the observations with action representations, making diffusion bridge applicable to heterogeneous robot data. Extensive experiments across 52 simulation tasks on three benchmarks and 5 real-world tasks demonstrate that BridgePolicy consistently outperforms state-of-the-art generative policies. Our code is available at https://jianghcsr.github.io/BridgePolicy_page/.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2603.00025

TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation

作者:

Samah Fodeh↗Linhai Ma↗Ganesh Puthiaraju↗Srivani Talakokkul↗Afshan Khan↗Sreeraj Ramachandran↗Elyas Irankhah↗Muhammad Arif↗Ashley Hagaman↗Sarah R. Lowe↗Aimee Kendall Roundtree↗

Direct Preference Optimization (DPO) is an effective and widely adopted approach for offline alignment but is poorly matched to ontology-driven structured prediction, where preferred and rejected JSON objects often differ in only a few schema-defining tokens. In this low-edit-distance regime, sequence-level DPO spreads gradient mass across non-critical serialization tokens (gradient dilution) and can reduce likelihood on rare, under-confident preferred schema tokens (token erosion). To address these limitations, we first develop a confusion-aware preference-construction strategy that augments expert-curated ambiguity patterns with empirical structured-error modes estimated from validation-set SFT predictions, synthesizing minimally perturbed, schema-valid negatives that focus preference learning on realistic ontology-level decision errors. We then introduce Token-Adaptive Barrier Preference Optimization (TAB-PO), a post-SFT objective for token-critical structured generation. TAB-PO adds a confidence-gated token-level barrier that applies supervised anchoring to under-confident schema tokens. On the public SciERC scientific information extraction task, evaluated with Llama/Qwen models from 1.5B to 70B, TAB-PO improves ontology-critical semantic-label and relational-linking metrics over SFT by 11.59% on average, wins 100% of comparisons against the strongest token-level and sequence-level DPO variants on these metrics, and surpasses leading frontier models by 14.71%, while delivering strong gains in textual grounding.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2510.06198

The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction

作者:

Xinyu Guo↗Zhengliang Shi↗Minglai Yang↗Mihai Surdeanu↗

Despite the remarkable reasoning capabilities of large language models, they still struggle with one-shot relation extraction without predefined relation labels. We identify two pitfalls: models are often misled by irrelevant tokens instead of relation-conveying semantics, and they often fail to align with the abstraction level human annotators expect. We introduce a novel framework that closes this gap with two components: (1) COGRE, a cognitively-inspired reasoning framework that structures RE into a series of processes mimicking human text-processing; and (2) HIT@DICT, a reinforcement learning intermediate reward strategy that encourages reasoning to align with relational labels by rewarding relation-relevant phrases in reasoning. The reward is derived on a credit dictionary automatically extracted from correct predictions. Our experiments show that our framework improves both accuracy and explanation quality by addressing these two pitfalls. For example, COGRE with Qwen2.5-14B-Instruct on One-shot NYT29 achieves 24.65% F1, surpassing prior reasoning-based designs. Optimizing this approach with RL using HIT@DICT further improves performance by +23.46% points. Finally, human evaluation shows that our best model generates relational phrases closely aligned with gold labels, increasing human explanation quality ratings by 54% (relative).

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15265

Trusted Multi-View Deep Learning Classification of Fetal Congenital Heart Disease with Feature-level and Decision-level Fusion

作者:

Tan Zhou↗Shifa Yao↗Suncheng Xiang↗Dahong Qian↗Baoying Ye↗

Congenital heart disease (CHD) refers to the abnormal anatomical structure caused by the abnormal development of the heart and great vessels during embryonic development. Traditional diagnostics often fail to achieve high accuracy and efficiency, especially given the complexity of cardiac anatomy. This study presents a specialized multi-view deep learning framework for CHD binary classification using echocardiographic images. A large-scale CHD dataset, including five views, was used to train the model, enabling it to integrate multi-angle image data. The framework utilizes advanced feature extraction and attention mechanisms to improve diagnostic precision and reliability. An uncertainty-based decision-making component is also integrated to handle low-quality images, enhancing diagnostic outcomes. Experimental results show that this method achieves top-tier performance on our dataset and provides a robust tool for early CHD detection, underscoring its potential for clinical use. The dataset and source code will be released upon paper acceptance.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17331

Decision-Driven Geosteering Under Uncertainty: A Unified Framework for Sequential Decision Optimization

作者:

Hibat Errahmen Djecta↗Sergey Alyaev↗Kristian Fossum↗Reidar B. Bratvold↗Ressi Bonti Muhammad↗Apoorv Srivastava↗

arXiv:2606.17331v1 Announce Type: new Abstract: Geosteering requires navigating a well trajectory through an unknown geological configuration, while sequentially updating decisions based on indirect measurements acquired during drilling. This work presents an uncertainty-aware geosteering framework that tightly integrates particle filtering for probabilistic subsurface interpretation with value-based reinforcement learning for sequential decision-making. Geological uncertainty ahead of the drill bit is represented explicitly through a particle filter (PF), enabling belief-informed control rather than deterministic trajectory correction. The framework couples PF belief updates with belief-informed decision policies and evaluates three decision-making options that operate under identical uncertainty representations: an interpretable Approximate Dynamic Programming (ADP) scheme, a Deep Q-learning baseline, and a Dual Deep Reinforcement Learning (Dual DRL) architecture trained with a target Q-network scheme for stability, using a dueling (value/advantage) decomposition for Q-value parameterization. Beyond final placement performance, we assess policy behavior using stability-oriented metrics that quantify steering smoothness over time, providing additional operational insight into how decision policies respond as uncertainty evolves. The framework is integrated with an API for validation within an industrial geosteering simulator under realistic measurement noise and drilling constraints. Using identical geological realizations, operational limits, and reward definitions across methods, the experiments provide a controlled and high-fidelity evaluation of how alternative decision policies behave throughout the drilling process, rather than evaluating performance solely from the final well trajectory.

阅读与讨论 → 访问原文 →

21.

bioRxiv (Bioinfo) 2026-06-12 DOI: HASH:c928c82cf417c54be9f143454b42288f

Generalisable tissue-wide molecular reconstruction from histology

作者:

Zhang↗Yu↗Bian↗Cao↗Ye↗Han↗Robertson↗Dong↗Mao↗Liu↗Patrick↗Kim↗…

Spatial transcriptomics technologies measure gene expression within intact tissues but remain difficult to scale across large tissue sections and patient cohorts. Consequently, many studies rely on tissue microarrays (TMAs) or sparse spatial profiling designs, where molecular measurements are available for only limited tissue regions and are often generated using heterogeneous gene panels. Existing H&E to spatial gene expression prediction methods remain challenged by sparse molecular measurements, partially overlapping gene panels and tissue-wide reconstruction across heterogeneous spatial datasets. Here, we present GHIST+, a framework for tissue-wide reconstruction of single-cell molecular states from H&E histology. GHIST+ integrates cellular morphology, local tissue context and shared tissue representations to extend sparse molecular measurements into tissue-wide molecular maps across heterogeneous spatial datasets. Across multiple cancer types and GTEx breast tissues, GHIST+ reconstructs biologically meaningful tissue-wide molecular organisation from sparse TMA-derived measurements while preserving spatial tissue structure, cell-type organisation and age-associated tissue states across cancer and non-cancer settings. GHIST+ establishes a scalable framework for transforming sparse spatial profiling experiments into tissue-wide molecular maps, enabling cohort-scale molecular reconstruction from routine histology under heterogeneous spatial transcriptomic settings.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.08151

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

作者:

Xinyu Guan↗Qianyang Zhao↗Yuming Deng↗

arXiv:2606.08151v2 Announce Type: replace Abstract: Modern large language model (LLM) agents do not simply need longer contexts; they need decision-relevant evidence at the moment of action. We study decision-aware context selection: ranking retrieved files, tests, traces, rules, and memories by their expected effect on an agent's next action rather than by semantic similarity alone. We present the Counterfactual-Inspired Context Layer (CICL), which builds an instance context graph, estimates decision-oriented utility for candidate units, and compresses selected evidence into typed memory cards. The same schema can be instantiated with hosted LLM judges, local surrogates, or lightweight rankers, making the selection protocol auditable across model choices. On 50 SWE-bench Verified file-retrieval instances, Qwen3.6-Plus reranking of BM25 top-50 candidates improves hit@1 from 0.58 to 0.78 and MRR@10 from 0.634 to 0.790, with all 2,500 judgments parseable. Controlled diagnostics show that CICL identifies action-critical evidence: removing the top-utility semantic unit reduces F1 from 0.245 to 0.000. In selected-then-compressed mode, memory cards save 44.93 tokens per query while preserving selected evidence. CICL provides a practical layer for measuring, ranking, and compressing decision-critical context for tool-using agents. Code is available at https://github.com/stephen-guan-researcher/CICL.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2505.17740

A tensor network approach for chaotic time series prediction

作者:

Rodrigo Mart\'inez-Pe\~na↗Rom\'an Or\'us↗

arXiv:2505.17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge. Reservoir computing, a neuromorphic-inspired approach, has emerged as a powerful tool for this task. It exploits the memory and nonlinearity of dynamical systems without requiring extensive parameter tuning. However, selecting and optimizing reservoir architectures remains an open problem. Next-generation reservoir computing simplifies this problem by employing nonlinear vector autoregression based on truncated Volterra series, thereby reducing hyperparameter complexity. Nevertheless, the latter suffers from exponential parameter growth in terms of the maximum monomial degree. Tensor networks offer a promising solution to this issue by decomposing multidimensional arrays into low-dimensional structures, thus mitigating the curse of dimensionality. This paper explores the application of a previously proposed tensor network model for predicting chaotic time series, demonstrating its advantages in terms of accuracy and computational efficiency compared to conventional echo state networks. Using a state-of-the-art tensor network approach enables us to bridge the gap between the tensor network and reservoir computing communities, fostering advances in both fields.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17408

Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies

作者:

Meipo Dai↗Qiyuan Zhuang↗He-Yang Xu↗Ying-Jie Shuai↗Yijun Wang↗Qi Dou↗Xiu-Shen Wei↗

Generative robot policies typically begin action generation from an observation-independent standard Gaussian distribution, leaving the choice of source distribution underexplored. This work asks a simple question: where should action generation begin? We propose LeaP, a Learnable source Prior that replaces the standard Gaussian with a proprioception-conditioned diagonal Gaussian over action chunks. Parameterized by a lightweight MLP, LeaP jointly predicts the mean and state-adaptive variance of the source distribution, while keeping the downstream generator architecture and inference solver unchanged. This design provides an observation-informed yet stochastic initialization, allowing the generator to focus on precise action refinement rather than transporting samples from an uninformed noise source. On 15 RoboTwin manipulation tasks, LeaP achieves an average success rate of 81.6%, outperforming four representative baselines – including deterministic-source methods, a no-prior counterpart, and a diffusion-bridge policy – by 6.5 to 25.5 percentage points. The same prior consistently improves both flow-matching and diffusion-bridge generators, while using fewer parameters and converging faster. The advantage carries over to real-world deployment, where LeaP attains the best performance. These results suggest that the source distribution is an independent and reusable design axis for generative robot policies, complementary to the choice of generative dynamics.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20437

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

作者:

Siqi Miao↗Shitij Govil↗Jack P. Rodgers↗Mia Liu↗Javier Duarte↗Shih-Chieh Hsu↗Yuan-Tang Chou↗Pan Li↗

arXiv:2606.20437v1 Announce Type: cross Abstract: Charged-particle tracking – reconstructing trajectories from sparse detector measurements – is a fundamental high-energy-physics inference problem and a canonical example of learning under extreme combinatorial ambiguity. At the High-Luminosity Large Hadron Collider (HL-LHC), tracking must remain accurate and efficient despite unprecedented collision densities. Graph neural networks perform strongly, but incur substantial costs from graph construction and processing, while transformer-based approaches rely on auxiliary stages that prevent end-to-end optimization. To address this, we present HEPTv2, an end-to-end point-transformer architecture that reconstructs tracks from detector hits in one trainable pipeline. HEPTv2 combines a locality-aware point encoder with a track decoder that predicts complete trajectories without graph-building, clustering, or filtering. The encoder uses locality-sensitive hashing in detector coordinate space to preserve tracking-relevant geometry while enabling efficient local attention. The decoder resolves ambiguities through sectorized decoding and direct hit-to-track prediction under joint encoder-decoder supervision, allowing the full pipeline to be optimized end-to-end. On TrackML, HEPTv2 achieves 98.6% double-majority tracking efficiency at a 0.8% fake rate, while requiring only $\sim$15~ms inference time and 0.4~GB peak memory per event on a NVIDIA A100 GPU. Latency and memory scale approximately linearly for events with up to $5\times10^5$ hits. HEPTv2 establishes a new state of the art in the accuracy-latency trade-off, improving efficiency by 4.5% over the strongest prior transformer and by 1.1–2.2% over optimized graph-based pipelines, while reducing latency by factors of 7 and 38–52, respectively. These results show end-to-end transformers can deliver the accuracy and efficiency required for real-time particle reconstruction at the HL-LHC.

阅读与讨论 → 访问原文 →