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 (CS.AI) 2026-06-16

On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents

作者:
Gengsheng Li↗Mao Zheng↗Mingyang Song↗Ruiqi Liu↗Tianyu Yang↗Jie Sun↗Qiyong Zhong↗Haiyun Guo↗Junfeng Fang↗Dan Zhang↗Jinqiao Wang↗

arXiv:2606.15912v1 Announce Type: cross Abstract: Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students, but we find that it suffers a characteristic failure mode in this setting: small student errors compound across turns and push the trajectory out of the teacher's familiar state distribution, so the teacher's supervision becomes least reliable precisely where the student needs it most.We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero.Strong guidance keeps early trajectories close to the teacher distribution and is then gradually withdrawn to recover the purely on-policy regime used at inference.On ALFWorld, ScienceWorld, and WebShop, distilling Qwen3 students from a Qwen3-30B-A3B teacher, Guided-OPD improves Score by 21.1\% and Success Rate by 25.5\% over vanilla OPD on average, with larger gains on smaller students.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.LG) 2026-06-11

Attention by Synchronization in Coupled Oscillator Networks

作者:
Fabio Pasqualetti↗Taosha Guo↗

arXiv:2606.12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates. Softmax attention requires exponentiation and global reduction, operations with high energy cost on von Neumann hardware and no natural physical analog. We show that Kuramoto synchronization dynamics (which arise in electrical, mechanical, superconducting, and charge-density-wave oscillator arrays, among other physical systems) implement a well-defined attention operation without either. The resulting mechanism, fixed-query oscillator attention, replaces softmax's arithmetic with the equilibration of a gradient flow on the sphere: queries are learned anchors fixed on the sphere, and free oscillators evolve under Kuramoto-Lohe dynamics until they settle at positions encoding attention weights via cosine similarity. Because the computation is equilibration, it requires no exponentiation; the only global operation is an affine normalization at readout. The fixed point is provably unique and globally attractive from almost every initial condition, a guarantee that holds across every physical realization. Empirically, at the minimal hardware configuration (oscillator dimension $d_{\mathrm{osc}}$ = 2), oscillator attention outperforms softmax on keyword spotting (+1.00 pp) and on subject-verb agreement (+5.27 pp on hard sentences, with zero training failures versus one in five for softmax). On causal language modeling, where softmax retains an advantage, oscillator attention closes the gap as $d_{\mathrm{osc}}$ grows: from +11.09 PPL at $d_{\mathrm{osc}}$ = 2 to +2.98 PPL at $d_{\mathrm{osc}}$ = 32 on WikiText-2, and from +2.39 PPL at $d_{\mathrm{osc}}$ = 2 to +0.57 PPL at $d_{\mathrm{osc}}$ = 32 on TinyStories. The main objective of this work is not to replace softmax in software but to provide a mathematically grounded blueprint for accurate attention on physical substrates.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-24

Pigeonholing: Bad prompts hurt models to collapse and make mistakes

作者:
Hyunji Nam↗Keertana Chidambaram↗Dorottya Demszky↗Natasha Jaques↗

While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing." **Unintentionally bad** contexts can happen without malicious jailbreaking intents: For example, a user asks the model to justify an incorrect math theorem or fails to correct the model's buggy code. Specifically, we investigate ``pigeonholing" in two scenarios: (1) when the user suggests a solution, and (2) when the conversation context includes the assistant's previous (incorrect) responses. Our experiments across 10 verifiable and open-ended tasks with 10 different models show that pigeonholing manifests in several ways: (1) repeating the incorrect answers from context (leading to 38-40% performance drop), (2) converging on a narrow set of answers in coding and text generation without exploring alternatives, and (3) flipping stance on controversial topics to align with the user or the assistant's previous claims. We find that pigeonholing worsens almost monotonically with the number of conversation turns (performance drops by additional 14+% as repeated mistakes increase from 1 to 5), and pigeonholing-induced mode collapse can happen even when the provided example is correct. As a step toward mitigation, we propose RLVR with synthetic errors which improves models by 43-60% under bad contexts compared to vanilla RLVR baselines.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-24

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

作者:
Yunhan Bu↗Quan Zhang↗Huaping Zhang↗Guotong Geng↗Chunxiao Gao↗Askar Hamdulla↗Juan Wang↗Qiuchi Li↗Baohua Zhang↗Shuai Lei↗Yunbo Cao↗Zhunchen Luo↗…

arXiv:2605.01482v3 Announce Type: replace Abstract: Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventions or counterfactual semantics. We empirically identify an "inverted U-shaped" correlation between reasoning-chain length and accuracy, revealing that excessive structural complexity can degrade performance. To address this, we propose a rule-based reinforcement learning strategy using Group Relative Policy Optimization. This approach dynamically optimizes the trade-off between structural depth and conciseness. Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework outperforms strong baselines while producing more traceable reasoning structures for complex fact verification.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-12

Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media

作者:
Chuang Li↗Lixuan Wang↗Yuqi Chen↗Ze Hong↗

arXiv:2606.12418v1 Announce Type: cross Abstract: The rapid proliferation of large language models (LLMs) has produced a striking cultural practice: using conversational AI for divination. This paper offers one of the first systematic studies of LLM-mediated divination in the context of Xuanxue, an internet-native umbrella term for mystical and spiritual practices on Chinese social media. Using a mixed-methods design, we analyze 23000+ posts and comments from Xiaohongshu and conduct 32 semi-structured interviews with users and professional diviners. Users primarily consult LLMs about pragmatic concerns - romantic relationships, careers, exams, and in-game gacha draws - via two intersecting pathways: trend-driven curiosity enabled by viral visibility and zero-cost access, and event-driven anxiety under conditions of uncertainty. A defining feature is collaborative prompt refinement, which turns users into active prompt engineers. Among commenters expressing a clear stance, perceived efficacy skews positive, with "accuracy" often justified through biographical fit and retrospective confirmation, consistent with Barnum and confirmation bias. Users also develop verification practices such as repeated trials and cross-model comparison. Professional diviners, by contrast, portray LLMs as lacking the "spiritual power" required for genuine divination, reflecting both ontological commitments and economic boundary-work. We also show how participants navigate tensions between scientific and metaphysical frames when interpreting AI-generated readings. Situating these findings in anthropological and cognitive-evolutionary theories of divination, we argue that LLM divination preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape how divinatory authority is constructed and evaluated.

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

Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

作者:
Xin Jin↗Huanqia Cai↗Zhen Li↗Zechao Zhan↗Dengyang Jiang↗Aiming Hao↗Yuming Jiang↗Chunle Guo↗Peng Gao↗Ming-Ming Cheng↗Steven C. H. Hoi↗

Reward models are central to text-to-image post-training, but visual preference is subjective and better represented as a distribution over rubric scores than as a deterministic scalar. Existing scalar, score-token, and pairwise reward models over-compress uncertainty and fine-grained score differences, while reasoning-based generative rewards provide stronger judgments but are costly to deploy and difficult to use as direct optimization signals. We propose Z-Reward, a teacher-student reward modeling framework that decouples reasoning-heavy judgment from efficient reward deployment. The teacher is a large VLM that uses reasoning to infer rubric-aligned score distributions, and is trained with Group-wise Direct Score Optimization (GDSO), which combines policy-gradient rewards from distribution expectations with direct pointwise and pairwise supervision on score distributions and score gaps. The student is trained with Reasoning-Internalized Score Distillation (RISD), which transfers the teacher's reasoning-conditioned score distribution into a compact VLM without requiring explicit reasoning chains at inference time. On our internally annotated evaluation set, the 27B GDSO teacher reaches 89.6% human preference accuracy, outperforming SFT, RewardDance, and GRPO, while the 9B RISD student reaches 88.6%, outperforming the OPD baseline and closely matching the larger teacher. We further show that Z-Reward can serve as a differentiable reward signal for text-to-image optimization, yielding a 41.3% net human-preference improvement over the SFT baseline.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-11

Making Models Unmergeable via Scaling-Sensitive Loss Landscape

作者:
Minwoo Jang↗Hoyoung Kim↗Jabin Koo↗Jungseul Ok↗

arXiv:2601.21898v2 Announce Type: replace Abstract: The rise of model hubs has made it easier to access reusable model components, making model merging a practical tool for combining capabilities. Yet, this modularity also creates a governance gap: downstream users can recompose released weights into unauthorized mixtures that bypass safety alignment or licensing terms. Because existing defenses are largely post-hoc and architecture-specific, they provide inconsistent protection across diverse architectures and release formats in practice. To close this gap, we propose Trap$^2$, an architecture-agnostic protection framework that encodes protection into updates during fine-tuning, regardless of whether they are released as adapters or full models. Instead of relying on architecture-dependent approaches, Trap$^2$ uses weight re-scaling as a simple proxy for the merging process. It keeps released weights effective in standalone use, but degrades them under re-scaling that often arises in merging, undermining unauthorized recomposition.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-16

Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs

作者:
Antonis Vasileiou↗Juan Cervino↗Pascal Frossard↗Charilaos I. Kanatsoulis↗Christopher Morris↗Michael T. Schaub↗Pierre Vandergheynst↗Zhiyang Wang↗Guy Wolf↗Ron Levie↗

arXiv:2602.10031v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine learning and signal processing. While MPNNs have a precise definition, there is no widely accepted criterion for what makes a mapping a spectral GNN. Most existing work restricts spectral GNNs to layered architectures based on linear spectral filters. Under this restriction, we show that spectral and spatial GNNs have largely equivalent expressive power. To promote progress in the field, we propose a precise definition of spectral GNNs based on eigenbasis symmetries, in contrast to the definition of MPNNs via neighborhood permutation symmetries. We further argue that the two perspectives offer complementary strengths. MPNNs provide a natural language for discrete structure and expressivity analysis through tools from logic and graph isomorphism, while the spectral perspective offers principled tools for understanding smoothing, bottlenecks, stability, and community structure. Overall, we argue that progress in graph learning will be accelerated by clarifying the similarities and differences between these perspectives and by moving toward a unified theoretical framework.

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

AMaNITA: an end-to-end workflow for native tRNA nanopore sequencing data analysis

作者:
Katopodi↗X.-L↗Pryszcz↗L. P↗Llovera↗Ollivier↗Cozzuto↗Ponomarenko↗Novoa↗E. M↗

Transfer RNA (tRNA) molecules serve as essential adapters during protein translation. While direct RNA sequencing (DRS) via Oxford Nanopore Technologies has emerged as a powerful platform for systematic tRNAome profiling, we currently lack a simple and robust statistical framework for nanopore tRNA data analyses. Here, we address this gap by developing AMaNITA (Abundance, Modifications, and Nanopore Intensity Toolbox Application), an end-to-end bioinformatic workflow that enables simplified, robust, and scalable analyses of nanopore native tRNA sequencing datasets. AMaNITA streamlines the entire analytical trajectory: from upstream processing (basecalling, mapping, filtering, batch effect correction) to downstream assessment of differential tRNA abundance and modification stoichiometry. The workflow generates an interactive HTML report for data exploration and analysis, allowing the user to download the source data files and resulting plots. AMaNITA can be executed using Singularity from the command line, without requiring installation of dependencies.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CL) 2026-06-16

Depth-Attention: Cross-Layer Value Mixing for Language Models

作者:
Boyi Zeng↗Yiqin Hao↗Zitong Wang↗Shixiang Song↗He Li↗Feichen Song↗Yifan Liu↗Ziwei He↗Xinbing Wang↗Zhouhan Lin↗

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-16

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

作者:
Jianqi Chen↗Biao Zhang↗Xiangjun Tang↗Peter Wonka↗

6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects. Project page: https://windvchen.github.io/PoseGAM/ .

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-11

Irresponsible AI: big tech's influence on AI research and associated impacts

作者:
Alex Hernandez-Garcia↗Alexandra Volokhova↗Ezekiel Williams↗Dounia Shaaban Kabakibo↗M\'elisande Teng↗

arXiv:2512.03077v2 Announce Type: replace-cross Abstract: The accelerated development, deployment and adoption of artificial intelligence systems has been fuelled by the increasing presence of big tech in the AI field. This trend has been accompanied by growing ethical concerns and intensified societal and environmental impacts. This position paper argues that irresponsible AI development is strongly driven by big tech's influence and involvement in the field. First, we examine the growing and disproportionate influence of big tech in AI research and argue that its drive for scaling and general-purpose systems is fundamentally at odds with the responsible, ethical, and sustainable development of AI. Second, we review key current environmental and societal negative impacts of AI and trace their connections to big tech's influence. Third, we discuss the underlying economic forces driving big tech's actions. Finally, as a call to action, we invite AI researchers to counter big tech's influence in irresponsible AI development through strategies that build on the responsibility of implicated actors and collective action.

阅读与讨论 → 访问原文 →
13.
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 →
14.
arXiv (CS.LG) 2026-06-19

Alternating Direction Method of Multipliers for Nonlinear Matrix Decompositions

作者:
Atharva Awari↗Nicolas Gillis↗Arnaud Vandaele↗

arXiv:2512.17473v3 Announce Type: replace-cross Abstract: We present an algorithm based on the alternating direction method of multipliers (ADMM) for solving nonlinear matrix decompositions (NMD). Given an input matrix $X \in \mathbb{R}^{m \times n}$ and a factorization rank $r \ll \min(m, n)$, NMD seeks matrices $W \in \mathbb{R}^{m \times r}$ and $H \in \mathbb{R}^{r \times n}$ such that $X \approx f(WH)$, where $f$ is an element-wise nonlinear function. We evaluate our method on several representative nonlinear models: the rectified linear unit activation $f(x) = \max(0, x)$, suitable for nonnegative sparse data approximation, the component-wise square $f(x) = x^2$, applicable to probabilistic circuit representation, and the MinMax transform $f(x) = \min(b, \max(a, x))$, relevant for recommender systems. The proposed framework flexibly supports diverse loss functions, including least squares, $\ell_1$ norm, and the Kullback-Leibler divergence, and can be readily extended to other nonlinearities and metrics. We illustrate the applicability, efficiency, and adaptability of the approach on real-world datasets, highlighting its potential for a broad range of applications.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.AI) 2026-06-12

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

作者:
Omar Alshahrani↗Muzammil Behzad↗

arXiv:2606.13211v1 Announce Type: new Abstract: AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucination: clinically plausible but factually incorrect outputs, including fabricated anatomical structures, missed findings, incorrect laterality, and invented measurements in generated reports, with direct consequences, for example, for biopsy decisions, staging, and treatment planning. This structured narrative synthesizes peer-reviewed studies, benchmark datasets, and FDA regulatory guidance across five imaging modalities to produce a cross-modality analysis of hallucination taxonomy, etiology, detection, and mitigation. Specifically, we address three questions in this study: (1) how can existing taxonomies be unified across modalities?, (2) how do medical-specialized foundation models hallucinate less than general-purpose ones?, and (3) which mitigation strategies are effective and compatible with FDA lifecycle oversight? We note that three taxonomic frameworks together cover the imaging pipeline in a way no single framework does alone. We also highlight that general-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks, indicating that narrow domain fine-tuning can introduce overfitting-induced confabulation. At the same time, the oversight of radiologists remains essential; for instance, a very high percentage of of AI-generated flags required expert correction before clinical use. Physics-informed architectural constraints, Chain-of-Thought prompting, and human-in-the-loop safeguards each address different failure modes and is effective when combined. All findings are mapped to the FDA's Total Product Lifecycle and Predetermined Change Control Plan frameworks, which treat hallucination management as a lifecycle obligation rather than a pre-deployment checklist.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.LG) 2026-06-15

Diffusion Policy Optimization without Drifting Apart

作者:
Haozhe Jiang↗Haiwen Feng↗Pieter Abbeel↗Jiantao Jiao↗Angjoo Kanazawa↗Nika Haghtalab↗

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.

阅读与讨论 → 访问原文 →
17.
arXiv (quant-ph) 2026-06-24

Offline Channel-Independent QAOA Angles for RIS Power Aggregation: Unit-Circle Phase Dictionaries and Infinite-Size Spin-Glass Limits

作者:
Burhan Gulbahar↗

arXiv:2606.24540v1 Announce Type: new Abstract: Reconfigurable intelligent surfaces (RIS) maximize received power by setting per-element phases. Discrete-phase optimization is NP-hard in the worst case, while the quantum approximate optimization algorithm (QAOA) applied to RIS faces limited phase alphabets, either per-problem angle optimization or uncharacterized training cost exposed to barren plateaus, and no scalable performance benchmark. We introduce a $2^{M}$-phase $\theta$ dictionary for optimizing power $\|\mathbf{A} \, e^{j\theta}\|^{2}$ having $K \times N$ channel matrix $\mathbf{A}$ and QAOA angle offline optimization with instance and size-independent infinite-size limit of the mixed-$q$ Gaussian ensemble of Basso et al. Our design bounds the spin-Hamiltonian interaction order to at most quartic for any $M$, and the deployed order-2 reduction lies below the even-$q\!\ge\!4$ regime in which constant-level QAOA limitations are proved. We perform analytical, state-vector, matrix-product-state and Pauli-path-simulation numerical studies for $N=K \leq 100$ and QAOA depth $p=9$, verifying offline angle transfer to Rayleigh, Rician/line-of-sight, cascaded double-fading and spatially-correlated RIS channels at $N\!\in\!\{5,12\}$. We observe performance reaching a near-optimal multi-start single-flip local-search reference for $N\!\le\!16$ under order-2 modeling with $2^{5}{=}32$-phase dictionary while the order-4 model shows a performance ceiling below the classical reference. The approach suggests a route to near-optimal large-$N$ performance on future fault-tolerant (FTQ) quantum computers, which enable the higher-depth QAOA circuits.

阅读与讨论 → 访问原文 →
18.
arXiv (math.PR) 2026-06-16

Mean-field BSDEs with non-Lipschitz coefficients and double mean reflections

作者:
Hanwu Li↗Jin Shi↗

arXiv:2510.11228v2 Announce Type: replace Abstract: The present paper is devoted to the study of mean-field backward stochastic differential equations (MFBSDEs) with double mean reflections whose generators are not Lipschitz continuous. With the help of the Skorokhod problem and some a priori estimates for MFBSDEs, we establish the existence and uniqueness results for doubly mean reflected MFBSDEs.

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

Context-Aware RL for Agentic and Multimodal LLMs

作者:
Peiyang Xu↗Bangzheng Li↗Sijia Liu↗Karthik R. Narasimhan↗Pramod Viswanath↗Prateek Mittal↗Xingyu Fu↗

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that improves long-horizon reasoning and multimodal performance through an indirect auxiliary objective. Instead of supervising only the final answer, ContextRL presents the model with a query, an answer, and two highly similar contexts, and rewards it for selecting the context that supports the query–answer pair, thereby encouraging fine-grained grounding. We construct contrastive context data in two domains: for coding agents, trajectories serve as contexts, yielding 1k pairs built via condition filtering; for multimodal reasoning, images serve as contexts, yielding 7K pairs built via generative editing and similarity search. ContextRL achieves average gains of +2.2% over standard GRPO on 5 long-horizon benchmarks, and +1.8% across 12 diverse visual question answering benchmarks. To disentangle the effect of the proposed objective from that of additional data, we compare against data-augmentation baselines that repurpose the same contrastive contexts as standard query–context–answer examples. These baselines provide little to no improvement, showing that the gains arise from the proposed context-selection objective rather than from the contrastive data alone.

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

Rational Sparse Autoencoder

作者:
Naiyu Yin↗Yue Yu↗

arXiv:2606.14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK. This hard-codes a particular sparsity mechanism into the model and can distort the reconstruction-versus-sparsity trade-off. We introduce the Rational Sparse Autoencoder (RSAE), which replaces the fixed encoder activation with a trainable rational function. Rational activations are flexible enough to uniformly approximate the activation primitives used by existing SAE families on compact domains (for TopK, the thresholded gate obtained after a separating top-k threshold is supplied), while also providing a richer function class for adapting to the observed pre-activation geometry. We realise this idea through a two-stage pipeline: an initialisation procedure that copies the pre-trained baseline SAE weights, plugs in rational coefficients obtained by the relaxed Remez exchange on synthetic data, and calibrates the scale parameters along with the rational coefficients; followed by a fine-tuning step under the standard sparsity-regularised reconstruction objective. Empirically, on residual-stream activations of three open-weight language models and across all three baseline activation families, the RSAE strictly improves on it after the fine-tuning step, both on reconstruction-side metrics and on downstream-behaviour metrics, without sacrificing feature-level interpretability under sparse probing. These gains are consistent across host language models, across baseline activation families, and across the full range of baseline sparsity we tested, while the upgrade itself adds only a handful of scalar parameters per autoencoder and runs in minutes on a single consumer GPU.

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

Z-Plane Neural Networks: Bounded Geometric Activation Replaces ReLU and LayerNorm

作者:
Sungwoo Goo↗Hwi-yeol Yun↗Sangkeun Jung↗

arXiv:2606.15669v1 Announce Type: cross Abstract: Modern deep neural networks rely on Euclidean scalar activations (e.g., ReLU) and global normalization techniques (e.g., LayerNorm) to prevent gradient instability in deep architectures. However, these mechanisms inherently cause dead neurons, discard critical directional information, and destroy the orthogonality of feature representations. Inspired by the frequency-modulation transmission of biological axons, we propose the Z-Plane Neural Network, which maps hidden states into 2D phasor bundles on a hypersphere. We introduce a novel geometric activation function, Radial Bounding($\mathbf{x} / \max(1, \|\mathbf{x}\|_2)$), which limits the energy magnitude while preserving the phase (direction). We demonstrate mathematically that this isotropic activation maintains 1-Lipschitz continuity and prevents gradient vanishing by preserving tangential gradients. Empirically, a 100-layer Z-Plane Multi-Layer Perceptron (MLP)-entirely devoid of ReLU and LayerNorm-successfully converges on the MNIST dataset with 98.34% accuracy and absolute numerical stability, proving that bounded geometric activation alone is sufficient for stable deep learning.

阅读与讨论 → 访问原文 →
23.
medRxiv (Medicine) 2026-06-11

Two modes of aversive control in suicidality: joint computational modelling exposes regime-specific clinical signatures invisible to symptom-based stratification

作者:
Laessing↗Karvelis↗Rashid-Cocker↗A. S↗Ruocco↗A. C↗Koudys↗J. W↗Kennedy↗J. L↗Zai↗C. C↗…

Suicidal thoughts and behaviours (STBs) are heterogeneous in their proximal dynamics, planning, and stress-sensitivity, yet most subtyping efforts remain symptom-driven and rarely validated across independent datasets. Computational mixture modelling offers a principled alternative: by fitting explicit models of learning and action selection and partitioning individuals by their latent parameter profiles, it can identify mechanistically distinct control strategies invisible to cross-sectional symptom measurement. We applied this approach to aversive Go/NoGo performance, jointly clustering two independently collected STB-enriched samples (N = 50 and N = 184) using tasks with the same structure but different duration, reversal timing, and clinical instrumentation. Two recurrent behavioural regimes emerged: a fast/adaptive regime characterised by rapid policy updating and elevated feedback reactivity, and a slow/perseverative regime characterised by slow updating, high choice determinism, and a pronounced cost following contingency reversal. These regimes were stable across initialisations, recovered more parsimoniously in joint than independent solutions, and were largely orthogonal to symptom-based stratification. Critically, stratification by regime exposed clinical-computational coupling structures substantially attenuated in pooled analyses. Pooled, population-level associations were modest and anchored by a broad affective burden axis. Within the slow/perseverative regime, coupling reorganised around learning dynamics and internalizing burden (depression, hopelessness, and active suicidal ideation) with markedly larger effect sizes. Within the fast/adaptive regime, a dissociation between anxious-compulsive and antisocial-disinhibitory profiles emerged along the same computational axis, invisible at the population level. These findings support a view of suicidality heterogeneity in which clinically similar individuals differ in the control strategies they recruit under aversive uncertainty - variation that symptom measurement alone cannot capture.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-17

EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent

作者:
Zeyao Du↗Tong Li↗Haibo Zhang↗

As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the query, recorded in a profile, or revealed only when the right question is asked. Benchmarks that expose full intent upfront and grade only the final choice can neither pose this long-horizon challenge nor explain which requirement an agent missed. To address this gap, we introduce EComAgentBench, a benchmark of 662 tasks grounded in real Amazon products and reviews. Each task scatters these requirements across a visible query, a tool-gated profile, and scripted clarification; an agent must uncover hidden intent, verify candidates against attributes and review evidence, and commit to a single product within 100 tool calls. Moreover, typed, source-tagged rubrics grade every task, attributing each failure to a requirement and its source. Construction is automated yet reliable, with every answer fixed in code before any text is generated and every sample validated. Our evaluation of seven models reveals that even the strongest attains only 57.1% overall accuracy, and rubric satisfaction degrades from visible to hidden sources. Overall, we believe EComAgentBench will serve as a reproducible foundation for moving shopping agents from single-query search toward dependable assistance over long horizons.

阅读与讨论 → 访问原文 →
25.
arXiv (quant-ph) 2026-06-16

Quantum Illumination with Symmetry-Constrained Random Unitaries

作者:
Sooryansh Asthana↗Sai Vinjanampathy↗

arXiv:2606.15586v1 Announce Type: new Abstract: Quantum illumination provides a quantum advantage in detecting weakly reflecting objects embedded in a noisy environment, even when environmental noise destroys most of the initial entanglement. We investigate this advantage using Haar-random probe states constrained to symmetry-resolved subspaces. Employing tools from quantum channel discrimination and asymptotic hypothesis testing, we derive the discrimination exponents associated with Haar-random probe ensembles and identify the role of symmetry in determining their performance. We show that typical states drawn from fixed-charge sectors achieve the same asymptotic quantum-illumination advantage as maximally entangled probes. In particular, we show that the effective thermal-noise suppression and the corresponding Chernoff exponent are governed by the dimension of the accessible symmetry sector. Our results reveal that the operational resource underlying quantum illumination can be generalized from fine-tuned structure of a specific probe state to the existence of a large symmetry-protected correlation subspace. These findings establish a direct connection between quantum illumination, symmetry-resolved typicality, and quantum channel discrimination, and demonstrate that near-optimal quantum hypothesis testing resources can emerge naturally from generic many-body quantum states constrained by conservation laws.

阅读与讨论 → 访问原文 →