中 EN
登录 注册账户

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。

登录 注册账户
01.
arXiv (quant-ph) 2026-06-15

Extending Covariant Fluctuation Theorems into Quantum Regime through Quasiprobability Approach

作者:
Ji-Hui Pei↗Tingzhang Shi↗Jin-Fu Chen↗H. T. Quan↗

arXiv:2606.14519v1 Announce Type: cross Abstract: The covariant formulation of stochastic thermodynamics requires treating the stochastic work as a 4-vector, posing significant challenges for quantum systems due to the non-commutativity. We introduce a new quasiprobability distribution for the work 4-vector, which combines the Wigner and Margenau-Hill quasiprobabilities. This extends the covariant fluctuation theorems from classical to quantum regime. We illustrate our findings with a scalar field driven by classical particles with a generalized version of trace formula. Our work establishes a quasiprobability approach to studying relativistic quantum thermodynamics in a covariant way.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-19

FundaPod: A Multi-Persona Agent Pod Platform with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research

作者:
Di Zhu↗Lei Nico Zheng↗Zihan Chen↗

arXiv:2605.27864v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction. Institutional fundamental research, by contrast, requires human analysts or AI agents to gather evidence, identify business drivers, compare competing viewpoints, and generate investment memos. Its broader goal is not merely to predict outcomes, but to produce investment plans that are transparent, reusable, and verifiable, while contributing to the cumulative development of investment knowledge. We present FundaPod, a multi-persona agent platform for AI-assisted fundamental investment research. We argue that fundamental research is a human-centric decision-support task that is qualitatively distinct from trading-signal generation, and is therefore better served by an independence-preserving architecture. In FundaPod, AI agents with different personas, such as value investors or macro strategists, conduct research independently under a shared provenance contract. Their disagreements are then surfaced post hoc for adjudication by the human portfolio manager (PM) through a knowledge-graph memory system. This paper contributes five design principles for human-AI hybrid systems supporting fundamental research, grounded in design-science practice and theories of cognitive isolation and human-machine coordination. It also describes four architectural mechanisms: a persona distillation pipeline that turns public investor materials into deployable agents; a declarative skill registry that lets the planner derive typed task graphs; a grounded evidence model that links memo claims to verifiable sources; and a knowledge-graph "second brain" that connects tickers, memos, analysts, and themes. We demonstrate the architecture through a complete case study and a persona-based memo comparison.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-19

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots

作者:
Gulshan Saleem↗Nisar Ahmed↗Muhammad Imran Zaman↗Ali Hassan↗

Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input filters cannot inspect retrieved documents, while output monitors cannot prevent malicious payloads from reaching the model. Consequently, retrieval-augmented generation (RAG) chatbots remain vulnerable to indirect injection, where a poisoned knowledge-base document compromises every user whose query retrieves it. We present a three-layer framework that intercepts both direct and indirect prompt injection throughout the inference pipeline. Layer 1 screens user input using a rule-based pattern library and a fine-tuned semantic anomaly classifier. Layer 2 enforces a provenance-based instruction hierarchy during context assembly, preventing retrieved content from overriding operator policy. Layer 3 audits model output using a policy rule engine and semantic drift detector before delivery. A continuous audit loop aggregates structured logs and supports retraining to adapt the classifier to emerging attack patterns. The framework is model-agnostic and deploys as middleware without modifying the underlying LLM. Evaluation on 5,080 samples across GPT-4o, Llama 3, and Mistral 7B shows that the framework reduces Attack Success Rate (ASR) from 71.4\% to 11.3\%, outperforming the best single-layer baseline by 27.3 percentage points and a published guardrail system by 23.8 percentage points, while maintaining a 4.8\% false positive rate and a median latency overhead of 61.2 ms. Ablation studies confirm that all three layers provide complementary protection and that their combined effect exceeds the sum of individual contributions.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-18

DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs

作者:
Lizhuo Luo↗Shenggui Li↗Yonggang Wen↗Tianwei Zhang↗

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, we propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-17

Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

作者:
Ankita Samaddar↗Sandeep Neema↗Daniel Balasubramanian↗Xenofon Koutsoukos↗

arXiv:2606.18223v1 Announce Type: cross Abstract: With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL). These agents employ neurosymbolic approaches such as behavior trees with learning-enabled components (LECs) to learn, reason, adapt, and implement security rules while maintaining critical operations. However, these autonomous networks are partially observable systems, i.e., the cyber-attacker's (red agent's) actions are not observable, making it difficult for the defender to predict red actions, learn red policies, or assess the attacker's intrusion levels. To address this, we propose a Policy Learning Technique using imitation learning to learn policies for partially observable RL agents with discrete states and discrete actions. We apply this technique in an autonomous cyber environment to predict red agent's actions from network observations and defender actions. Integrated with a neurosymbolic cyber-defense agent, our method effectively handles different red policies and achieves high prediction accuracy across diverse simulated scenarios.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.LG) 2026-06-25

Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach

作者:
Cristian Brugnara↗Lea Multerer↗Marco Forgione↗Laura Azzimonti↗

arXiv:2606.24966v1 Announce Type: new Abstract: Estimating parameters of dynamical systems from sparse, noisy, and irregularly sampled data is often severely ill-conditioned. When multiple related datasets are available, they provide additional information if the shared structure and variability are properly modeled. We propose a hierarchical Bayesian framework for probabilistic meta-learning in dynamical systems, modeling dataset-specific parameters as draws from a shared population distribution. A numerical ODE solver is embedded within gradient-based MCMC to enable efficient posterior inference of the shared population and dataset-specific parameter distribution. Experiments show improved predictive performance over unpooled methods, highlighting the potential for data-efficient system identification in settings with sparse data.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-16

Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms

作者:
Hiroyuki Kokubu↗

arXiv:2606.13693v1 Announce Type: cross Abstract: Automated scoring of ESG narrative disclosures with large language models (LLMs) is gaining traction, yet whether reasoning-heavy frontier models add value commensurate with their cost remains empirically unsettled. We evaluate this question on a corpus of ten Japanese listed firms across three rubric axes – quantitative targets, progress-tracking infrastructure, and external-standard alignment – using a four-model consensus design that combines a reasoning-on frontier model with three reasoning-off contemporaries. Across 120 firm x axis x model scores, the pooled mean absolute deviation between the reasoning-on model and each reasoning-off counterpart is 0.38 on a 5-point scale; only 2% of pairwise comparisons reach a two-point deviation, and none exceeds two points. Per-firm cost accounting shows the reasoning-on arm alone costs roughly 5.6x as much as the three-provider reasoning-off ensemble, for outcomes that differ only within small margins. We conclude that in span-based ESG narrative scoring, reasoning-heavy deployment does not materially improve outcomes relative to reasoning-off consensus, while substantially increasing operational cost. We discuss implications for cost-effective ESG auto-scoring pipelines and LLM deployment governance in applied accountability settings. An earlier version of this work is available on SSRN (Abstract ID 6683303).

阅读与讨论 → 访问原文 →
08.
arXiv (quant-ph) 2026-06-12

Beyond the Unruh vacuum: multi-time correlations in black hole collapse and evaporation

作者:
Konstantinos Xenos↗Charis Anastopoulos↗Andreas F. Terzis↗

arXiv:2606.13383v1 Announce Type: new Abstract: The black hole information paradox originates from the thermal character of Hawking radiation, which appears to erase information about the collapsing matter. However, thermality constrains only observables defined at a single time and leaves the structure of temporal quantum correlations largely unexplored. Here we show that multi-time quantum-field correlations provide a concrete mechanism for the survival of pre-collapse information in black hole evaporation. Using a two-dimensional model of gravitational collapse and evaporation, we demonstrate that late-time multi-time correlations are not fully reproduced by the Unruh vacuum. In particular, they contain a contribution that depends explicitly on parameters characterizing the pre-collapse state, despite the thermal character of the asymptotic radiation. Our results identify measurable multi-time correlations as carriers of information in Hawking radiation and suggest that formulations of the black hole information paradox based solely on single-time observables are incomplete.

阅读与讨论 → 访问原文 →
09.
medRxiv (Medicine) 2026-06-17

Characterisation of disease progression in hantavirus haemorrhagic fever with renal syndrome

作者:
Armstrong↗Rus↗Knap↗Drousiotis↗Eyers↗Buchan↗I. E↗Avsic-Zupanc↗Hiscox↗J. A↗Korva↗

Hantaviruses can cause haemorrhagic fever with renal syndrome (HFRS). This is a clinically variable disease in which severe outcomes are hypothesized to arise from dysregulated host responses. To characterise this, longitudinal, label-free plasma proteomics was used to compare disease progression in a unique well-defined cohort of patients infected with either Dobrava virus (DOBV) or Puumala virus (PUUV) hantaviruses. Patients were stratified by clinical severity. The average viral load in the first available sample from hospitalized patients was higher in those who went on to have severe infection, and higher in patients infected with DOBV. There was marked separation of infected patients from controls across early, mid and late disease, including after viral RNA clearance, suggesting a sustained systemic host-response signature. Proteomic signatures were consistent with a strong acute-phase response in both mild and severe disease. There was evidence of activation of the adaptive humoral response at later stages. Hierarchical clustering identified severity-associated pathways linked to endothelial dysfunction, thrombocytopenia, vascular leakage and renal injury. These findings define a durable plasma proteomic signature of hantavirus disease and support a model in which severe HFRS is driven by persistent inflammatory, complement and platelet/coagulation pathway activation rather than viral burden alone.

阅读与讨论 → 访问原文 →
10.
bioRxiv (Bioinfo) 2026-06-21

SPA-C: an hybrid tool to accurately scaffold genomes using Hi-C and Deep-Learning

作者:
Mergez↗Mourad↗Hernandez-Raquet↗Zytnicki↗

Genome assembly is a computational pipeline designed to reconstruct chromosomes from small sequencing reads. Following their assembly, contiguous sequences (contigs) are arranged into chromosome-long sequences during scaffolding. Hi-C, a long-range linkage information between regions of the genome widely used in recent large sequencing projects, is often required to correctly order contigs. Several tools have been developed to automate this task following either statistical or deep-learning approaches. Statistical approaches summarise 2D Hi-C matrices into contact densities across sequences, thus ignoring informative visual patterns. The sole existing deep-learning tool uses a transformer-based computer vision model to correct the assembly. It has been trained on several species and uses Hi-C matrices directly. Yet it comes as a supplementary step in the scaffolding process, introducing extra computation time, and has been trained on a dataset that might contain labelling errors, which could provide sub-optimal results. We propose SPA-C, an hybrid pipeline combining the strengths of both approaches. Linkage prediction is handled with a frugal CNN-based model and a graph-solving algorithm is used to generate the scaffolds. Through our input's design, the model is able to both correct errors within assemblies and link contigs, leveraging small, local Hi-C contact matrices. We handled low-complexity regions that might induce erroneous predictions using an external tool, improving the overall accuracy of generated assemblies. On a benchmark of six various genomes and four standard metrics, SPA-C outperformed four out of four state-of-the-art methods while achieving comparable start-to-end computation time.Python and Bash scripts are available on GitHub (https://github.com/SPA-C/SPA-C.git) and Zenodo (https://doi.org/10.5281/zenodo.19000361).

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CL) 2026-06-15

Abstracting Cross-Domain Action Sequences into Interpretable Workflows

作者:
Gaurav Verma↗Scott Counts↗

Sequential or time-stamped interaction logs provide objective records of digital application usage, yet their granularity and noise often obscure meaningful insights into people's work. Such insights are essential for improving digital products in ways grounded in real-world user interactions. Prior research has applied deep learning models to cluster user actions into high-level activities, but these approaches are highly sensitive to noise and struggle to generalize across applications. To address this limitation, we introduce WorkflowView, a framework that uses large language models (LLMs) to abstract low-level action sequences into high-level activities. We establish the effectiveness and generality of our approach across three distinct, challenging sequential tasks and diverse domains: (a) zero-shot task description reconstruction from browser logs (achieving high semantic similarity, $\mu_{sim} = 0.91$), (b) few-shot student dropout prediction using MOOC interaction logs (reaching weighted $F_1 = 0.90$ with only five few-shot examples), and (c) anonymized, privacy-preserving analysis of AI tool integration within document workflows in Microsoft Word. Our work demonstrates that LLM-based abstraction is a robust and efficient path forward for transforming low-level behavioral data into high-level, interpretable, and actionable insights. We also discuss practical considerations for deploying LLM-based inferences within logging infrastructures, including computational efficiency and user privacy.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CV) 2026-06-16

On the Adversarial Robustness of Multimodal LLM Judges

作者:
Zihan Wang↗Guansong Pang↗Zelin Liu↗Wenjun Miao↗Jin Zheng↗Xiao Bai↗

Multimodal Large Language Models (MLLMs) are increasingly used as automated judges, e.g., for image quality and safety assessment. However, their adversarial robustness remains largely unexplored, threatening the fairness and reliability of automated judging. To bridge this gap, we introduce RobustMLLMJudge, the first general framework for evaluating the adversarial robustness of general-purpose MLLMs when functioning as judges. It covers diverse attacks against popular judge approaches across quality and safety evaluation scenarios. Using RobustMLLMJudge, we reveal that i) different MLLM judges are highly vulnerable to score-inflating adversarial attacks; and ii) although effective, these attack methods face a critical challenge due to unique constraints in the evaluation protocols of MLLM judges. We further propose MGSIA, namely Manifold-Guided Semantic Induction Attack, a novel method that bypasses these constraints to enable more effective and transferable attacks on MLLM judges. The core idea of MGSIA is to combine affirmative semantic induction with high-score manifold alignment: it maximizes the probability that judges yield affirmative responses (e.g., "Yes") to binary semantic queries, while regularizing adversarial representations toward high-score centers estimated from proxy protocols. Together, these objectives yield transferable score-inflating perturbations. Extensive experiments demonstrate the superiority and generalizability of MGSIA in deceiving advanced MLLM judges under different evaluation scenarios, highlighting the need for robust MLLM judges. Code and data will be made available at https://github.com/mala-lab/RobustMLLMJudge.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.AI) 2026-06-15

AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

作者:
Seunghan Lee↗Jun Seo↗Jaehoon Lee↗Sungdong Yoo↗Minjae Kim↗Tae Yoon Lim↗Dongwan Kang↗Hwanil Choi↗SoonYoung Lee↗Wonbin Ahn↗

arXiv:2605.07121v2 Announce Type: replace Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters only and retains no trace of the interactions in which the entity has participated. In this paper, we depart from this static view and propose that each entity be modeled as an adaptive process whose representation is refined every time the entity participates in a fact. To this end, we propose AdaTKG, which maintains a per-entity memory that is updated with every observed interaction, with the memory accumulating online and predictions improving as more interactions arrive. Specifically, we instantiate the memory update as a learnable exponential moving average governed by a single shared scalar instead of using learnable parameters for each entity, enabling AdaTKG to handle entities unseen during training. Extensive experiments confirm consistent gains over TKG baselines, demonstrating the effectiveness of adaptive memory. Code is available at: https://github.com/seunghan96/AdaTKG

阅读与讨论 → 访问原文 →
14.
arXiv (CS.CV) 2026-06-16

Seeing Roads Through Words: A Language-Guided Framework for RGB-T Driving Scene Segmentation

作者:
Ruturaj Reddy↗Hrishav Bakul Barua↗Junn Yong Loo↗Thanh Thi Nguyen↗Ganesh Krishnasamy↗

Robust semantic segmentation of road scenes under adverse illumination, lighting, and shadow conditions remain a core challenge for autonomous driving applications. RGB-Thermal fusion is a standard approach, yet existing methods apply static fusion strategies uniformly across all conditions, allowing modality-specific noise to propagate throughout the network. Hence, we propose CLARITY that dynamically adapts its fusion strategy to the detected scene condition. Guided by vision-language model (VLM) priors, the network learns to modulate each modality's contribution based on the illumination state while leveraging object embeddings for segmentation, rather than applying a fixed fusion policy. We further introduce two mechanisms - one which preserves valid dark-object semantics that prior noise-suppression methods incorrectly discard, and a hierarchical decoder that enforces structural consistency across scales to sharpen boundaries on thin objects. Experiments on the MFNet dataset demonstrate that CLARITY establishes a new state-of-the-art (SOTA), achieving 62.3% mIoU and 77.5% mAcc.

阅读与讨论 → 访问原文 →
15.
bioRxiv (Bioinfo) 2026-06-22

PanRes: A database of latent and acquired antimicrobial resistance allowing 3D-based protein homology search

作者:
Vojtkova↗Baltusis↗Martiny↗H.-M↗Baral↗Pyrounakis↗Beleon↗Freitag↗Pico-Tomas↗Kaas↗R. S↗Petersen↗…

Antimicrobial resistance databases are central to genomic surveillance, but resistance determinants remain distributed across resources with different scopes, structures, and annotations. We developed PanRes, a curated resistance database of 11,717 genes integrating acquired and latent determinants of antibiotic, biocide, and metal resistance within a unified ontology. We predicted representative protein structures and clustered them by structural similarity, grouping proteins into 598 structurally conserved clusters coherent despite sequence divergence. Their structure-guided alignments were used to build Hidden Markov Models (HMMs) for remote homology search. In wastewater metagenomes from seven European cities, PanRes 3D-based HMMs expanded detection beyond high-confidence BLAST, with 35.2% of retained hits identified only by the HMMs and generally showing greater divergence from known proteins. For beta-lactamases, several proteins retained beta-lactamase-like folds and catalytic geometry despite weak sequence similarity. PanRes is available through an interactive web platform (https://panres.rambio.dk/), a structure-informed resource for exploring the whole resistome.

阅读与讨论 → 访问原文 →
16.
arXiv (quant-ph) 2026-06-19

Complexity of detecting large coefficients in the Pauli basis

作者:
Santiago Cifuentes↗

arXiv:2606.19545v1 Announce Type: new Abstract: We study the problem of deciding, given a mechanism to prepare a quantum state $\rho$ and a value $\varepsilon > 0$, whether there is some non-identity Pauli matrix $P$ such that $|Tr(P \rho)| \geq \varepsilon$. We consider that the state $\rho$ is described as the result of tracing out some of the qubits of a pure state prepared by a circuit $C$, and we assume the promise that either there is a Pauli matrix satisfying the stated condition or, instead, that for all non-identity Pauli matrices $P$ it is the case that $|Tr(P\rho)|\leq \varepsilon/2$. The problem is in $QCMA$, and we prove that if it belongs to $BQP$ then $NP \subseteq BQP$. The result is obtained through a reduction from the minimum-weight code problem, and it holds even when $\rho$ is assumed to be a pure state (i.e. when no qubits are discarded) and $\varepsilon$ is constant. This resolves an open question regarding the existence of efficient tomographic procedures to find the largest coefficients of a quantum state in the Pauli basis: namely, they do not exist under the standard hypothesis $NP \nsubseteq BQP$.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.AI) 2026-06-17

Knowledge Reutilization in Meta-Reinforcement Learning

作者:
Yuan Meng↗Bo Wang↗Juan de los Rios Ruiz↗Xiangtong Yao↗Zhenshan Bing↗Fuchun Sun↗Alois Knoll↗

arXiv:2606.18132v1 Announce Type: new Abstract: Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magnitude guidance. To bridge reusable task knowledge with different embodiments, we introduce a semantic-magnitude interface and a lightweight temporal adaptor, which convert frozen meta-knowledge into temporally aligned subgoals for embodiment-specific low-level controllers. Experiments on multiple locomotion agents show that our framework reduces final-step tracking error by 94.75% – 99.79% compared with recent state-of-the-art baselines and achieves comparable deployment performance with about 23.8% of their interaction data.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.LG) 2026-06-12

Masked Neural Detection for Constrained Channel Coding in Molecular Communication

作者:
Melih \c{S}ahin↗Ozgur B. Akan↗

arXiv:2606.12489v1 Announce Type: cross Abstract: Molecular communication (MC) suffers from severe diffusion memory because molecules released for one symbol may arrive during later symbols. Neural sequence detectors, especially sliding bidirectional recurrent neural networks (SBRNNs), can substantially outperform threshold detectors in such channels. This raises a central question for MC channel coding: does a code whose advantage was established under threshold detection retain it when both coded and uncoded transmission are evaluated with neural detection? This letter answers this question for run-length-limited ISI-mitigation (RLIM) codes, a class of constrained codes previously shown to provide large BER gains in MC. Across the tested operating points, the best RLIM-SBRNN receiver beats the best uncoded receiver, chosen between threshold and SBRNN detection, in $46$ of $59$ cases, with a mean gain of $10.36\times$ over those wins. We also propose an RLIM-tailored training mask for compact SBRNN detectors, improving the unmasked RLIM-SBRNN in $227$ of $236$ comparisons with $3.267\times$ mean gain when masking is beneficial. Finally, the compact masked RLIM-SBRNN is competitive with channel-state-aware MLSE despite using no channel knowledge.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.AI) 2026-06-11

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning

作者:
Yichao Zhong↗Yidan Lu↗Yuhang Lu↗Tianyang Tang↗Haoguang Mai↗Yixuan Pan↗Tianyu Li↗Li Chen↗Jingbo Wang↗Zhongyu Li↗Peng Lu↗Hongyang Li↗…

arXiv:2606.11092v2 Announce Type: replace-cross Abstract: Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball positions and strike timings; in contrast, task reward-driven RL struggles to explore and discover valid kicks from scratch. We therefore introduce RoboNaldo, a three-stage motion-guided curriculum RL framework for high-impulse humanoid interaction. A single human-kick reference is used as a scaffold and progressively shifts optimization towards shooting performance. The curriculum first learns a stable whole-body kicking prior, then adapts the kick to free-kick settings where the ball is stationary at random positions, and finally extends it to moving-ball shooting through a locomotion-command and kick-trigger interface. A high-level heuristic planner controls this interface during training, while alternative high-level controllers can drive the same low-level policy at inference. In simulation, RoboNaldo demonstrates free-kick shot error 48.6% lower and shoot velocity 2.96x than prior work baselines. In real world on a Unitree G1 with onboard perception, RoboNaldo attains 0.73 m and 0.86 m average target shooting error from 3 m away in free-kick and moving-ball cases, accordingly. And the post-contact ball velocity reaches 13.10 m/s, which is 59-71% of reported professional open-play shot speed. Project page: https://opendrivelab.com/RoboNaldo.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CL) 2026-06-16

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

作者:
Xiwen Chen↗Wenhui Zhu↗Peijie Qiu↗Xuanzhao Dong↗Hao Wang↗Haiyu Wu↗Huayu Li↗Aristeidis Sotiras↗Yalin Wang↗Abolfazl Razi↗

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are often non-injective with respect to semantic content: distinct reasoning paths receive identical rewards. This leads to a Diversity-Quality Inconsistency, where the policy collapses into a narrow set of dominant modes while ignoring equally valid but structurally novel strategies. To bridge this gap, we propose Diversity-aware Reward Adjustment (DRA), a theoretically grounded framework that calibrates the reward signal using the semantic density of sampled groups. By leveraging Submodular Mutual Information (SMI), DRA implements an Inverse Propensity Scoring (IPS) mechanism that effectively de-biases the gradient estimation. This creates a repulsive force against redundancy, driving the policy to achieve better coverage of the high-reward landscape. Our method is plug-and-play and integrates seamlessly with GRPO variants. Empirical evaluations on five math benchmarks demonstrate that DRA-GRPO consistently outperforms strong baselines, achieving an average accuracy of 58.2% on DeepSeek-R1-Distill-Qwen-1.5B with only 7,000 training samples and $55 cost, highlighting the critical role of diversity calibration in data-efficient alignment. The code is available at https://github.com/xiwenc1/DRA-GRPO.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning

作者:
Haolong Qian↗Xianliang Yang↗Yinuo ma↗Lirong Che↗Feng Lu↗Ye Guo↗Lei Song↗Jiang Bian↗Chun Yuan↗

arXiv:2606.16152v1 Announce Type: new Abstract: Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher reward model scores provide more useful supervision. We identify a counterintuitive Quality-Utility Paradox in mathematical reasoning distillation. Data refined or synthesized by a stronger Oracle obtains higher perceived quality according to reward models, yet consistently underperforms traces generated by the SLM itself and selected through rejection sampling across Qwen2.5, LLaMA-3, and DeepSeek families. Our analysis shows that Oracle refinement couples logical repair with distributional drift away from the SLM's native reasoning distribution. This drift increases the learner's adaptation cost and can outweigh the benefit of improved reasoning logic. To test this mechanism, we introduce Style-Aligned Refinement, which preserves the native trajectory of the SLM while retaining logical repair from the Oracle. This intervention lowers adaptation cost and restores downstream utility. These findings suggest that effective mathematical reasoning distillation should jointly optimize perceived solution quality and learner-data compatibility, rather than relying solely on reward-model scores. The datasets and code are available at https://github.com/Dracoqhl/Quality-Utility-Paradox.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-16

Tying the Loop – Tied Expert Layers in Mixture-of-Experts Language Models

作者:
Martin Jaggi↗

Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory. To address this, we introduce Expert Tying, an architectural modification that shares expert parameters across consecutive transformer layers while preserving independent, layer-wise routing and attention. We evaluate this approach across common, state-of-the-art architectures, including OLMoE, Qwen3, and DeepSeek-style MoEs. Our pretraining experiments demonstrate that tying experts can reduce memory footprint by almost 2x at virtually no degradation in perplexity or downstream quality. By exploiting the parameter redundancy inherent in MoE pathways, our method provides a highly favorable compute-to-memory trade-off, advancing efficient training and scaling of next-generation LLMs.

阅读与讨论 → 访问原文 →
23.
medRxiv (Medicine) 2026-06-25

Dissecting the genetic architecture of knee alignment reveals its contribution to osteoarthritis risk

作者:
Faber↗B. G↗Alomar↗Coveney↗C. R↗Chen↗Orr↗S. E↗Mimpen↗J. Y↗Nikolic↗Flynn↗…

Objectives: To investigate the biological and clinical relevance of knee alignment in osteoarthritis by integrating population-scale imaging, genome-wide association, and functional genetic analyses. Methods: Femorotibial angle was derived from dual-energy X-ray absorptiometry scans in UK Biobank using machine-learning methods. Associations with knee and hip osteoarthritis outcomes were assessed. A genome-wide association study of mean femorotibial angle was performed, followed by fine-mapping and pathway enrichment analyses. Mendelian randomization was used to explore potential causal relationships. Results: Varus alignment was strongly and progressively associated with knee pain, knee osteoarthritis, and total knee replacement (HR 3.42 [95% CI 2.92, 4.02]), with no association observed for hip osteoarthritis. GWAS identified 20 independent loci associated with femorotibial angle, enriched for pathways related to skeletal development, cartilage biology, and endochondral ossification. Post-GWAS analyses demonstrated regulatory effects across fetal and adult joint tissues, supporting life course influences on alignment. Genetic correlation analyses showed shared architecture between femorotibial angle and knee osteoarthritis. Causal analyses suggested that genetic liability to osteoarthritis reduces femorotibial angle ({beta} -0.11 [-0.16, -0.06]), while evidence for an overall causal effect of femorotibial angle on osteoarthritis risk was limited (OR 0.93 [0.79, 1.10]). Conclusions: Knee alignment and susceptibility to knee osteoarthritis are partially genetically determined. At the population level, these genetic determinants support a causal effect of osteoarthritis on knee alignment, whereas evidence for a causal effect of alignment on knee osteoarthritis was limited. Furthermore, this study identifies novel genetic loci linking knee alignment with pathways involved in skeletal development and cartilage biology relevant to osteoarthritis.

阅读与讨论 → 访问原文 →
24.
arXiv (quant-ph) 2026-06-24

Chemical tuning of magnetic ordering and cryogenic magnetocaloric response in zircon-type Gd1-xErxVO4

作者:
Ming Zeng↗Muqing Su↗Liang Ming↗Xiaolong Yang↗Wang Chen↗Lingwei Li↗Hai-Feng Li↗

arXiv:2606.08916v2 Announce Type: replace-cross Abstract: Chemical substitution offers an effective route to tune magnetic ordering and magnetocaloric performance in rare-earth oxides for cryogenic refrigeration. Here we investigate the structural evo lution, magnetic properties, and magnetocaloric effect of polycrystalline zircon-type Gd1-xErxVO4 (x=0, 0.1, 0.25, 0.5, and 0.75). Powder X-ray diffraction confirms that all samples crystallize in the tetragonal zircon structure without detectable impurity phases. Substitution of Gd3+ by the smaller Er3+ ion produces a systematic lattice contraction and modifies the magnetic behavior of the rare-earth sublattice. In particular, the magnetic ordering temperature is suppressed from 3.65(2) K in GdVO4 to 2.76(2) K in Gd0.9Er0.1VO4 , accompanied by a weakening of the spin-flop-like field-induced anomaly observed in the parent compound. A low Er concentration correspondingly improves the low-temperature magnetocaloric performance, with Gd0.9Er0.1VO4 exhibiting a max imum magnetic entropy change of 45.1 J kg-1 K-1 for mu_0 Delta H=7T. These results demonstrate that weak Er substitution effectively tunes the competition among exchange interactions, dipolar coupling, and magnetic anisotropy, optimizing the balance between magnetic ordering and available spin entropy in zircon-type rare-earth vanadates, which is crucial for developing efficient cryogenic refrigeration materials.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CL) 2026-06-19

Uncertainty Decomposition for Clarification Seeking in LLM Agents

作者:
Gregory Matsnev↗

Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insufficient for interactive large language model (LLM) agents and call for underspecification-aware, decomposed, and communicable uncertainty representations that can unlock new agent capabilities such as proactive clarification seeking and shared mental-model building. Practical deployment constraints – black-box APIs, interactive latency budgets, and the absence of labeled trajectories – rule out logprob-based, multi-sampling, and training-based methods, leaving prompt-based estimation as the most viable family for surfacing such signals at deployment time. We answer this call with a simple prompt-based decomposition that separates action confidence from request uncertainty (u), enabling the agent to ask for clarification when the task specification is ambiguous. To evaluate it, we introduce two clarification-augmented benchmarks (WebShop-Clarification and ALFWorld-Clarification) in which 50% of tasks are deliberately underspecified, and systematically compare the proposed decomposition against ReAct+UE and Uncertainty-Aware Memory (UAM) across five LLM backbones (GPT-5.1, DeepSeek-v3.2-exp, GLM-4.7, Qwen3.5-35B, GPT-OSS-120B) on these variants together with the standard WebShop, ALFWorld, and REAL benchmarks for fault detection. Averaged across the five backbones, the proposed decomposition improves clarification F1 on ALFWorld-Clarification by 73% over ReAct+UE and by 36% over UAM, and leads clarification F1 on every backbone on WebShop-Clarification and on four of five backbones on ALFWorld-Clarification, indicating that the gains generalize beyond a single LLM.

阅读与讨论 → 访问原文 →