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.CV) 2026-06-11

Findings of the MAGMaR 2026 Shared Task

作者:
Alexander Martin↗Dengjia Zhang↗Joel Brogan↗Francis Ferraro↗Jeremy Gwinnup↗Reno Kriz↗Teng Long↗Kenton Murray↗Andrew Yates↗Xiang Xiang↗

This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR). In this shared task participants submitted systems focused on either (i) video retrieval or (ii) grounded generation of articles given retrieved videos. Teams could submit to either task. For the retrieval task, we had 2 participating teams that submitted a total of 17 systems – all of which beat a baseline derived from the winner of last year's shared task. On the generation side, we had 4 teams submit 16 systems. All teams had at least one generated report that was labeled the best by a human annotator.

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

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

作者:
Yucheng Li↗Huiqiang Jiang↗Yang Xu↗Jianxin Yang↗Yi Zhang↗Yizhong Cao↗Yuhao Shen↗Fan Zhou↗Rui Men↗Jianwei Zhang↗An Yang↗Bowen Yu↗…

Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model entropy, which demonstrates a clear negative linear relationship with the rise of entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.

阅读与讨论 → 访问原文 →
03.
medRxiv (Medicine) 2026-06-16

High-Risk Anti-Seizure Medication Use in Childbearing-Age People with Epilepsy in a Taenia solium Endemic Region

作者:
Allen↗S. E↗Wardle↗M. T↗Moyano↗L. M↗Vilchez↗Bustos↗J. A↗Garcia↗H. H↗O'Neal↗…

Background: People of childbearing potential with epilepsy in regions endemic for Taenia solium, where neurocysticercosis (NCC) is highly prevalent, represent a vulnerable population due to the elevated burden of epilepsy and resource limitations. Clinical practice in these settings remains poorly characterized. This study characterized anti-seizure medication (ASM) prescribing patterns by medication risk profiles among people of childbearing potential with epilepsy in Northern Peru, a region highly endemic for T. solium. Methods: Participants were drawn from a prospective, population-based epilepsy cohort in Tumbes, Peru (2006 to 2020). The analytic population included females with epilepsy aged 15 to 49 years. The primary outcome was pregnancy-associated ASM risk of congenital malformations and adverse neurodevelopmental outcomes. ASMs were classified as ''Established Low Risk'' (lamotrigine, levetiracetam), ''Possible Risk/Inadequate Data'' (carbamazepine, phenobarbital, phenytoin), and ''Established High Risk'' (valproic acid). Prescription patterns were examined in relation to demographic and clinical characteristics. Results: Among 1,975 individuals with epilepsy, 685 were people of childbearing potential. Approximately 34.9% met criteria for probable or definite NCC. Most ASM prescriptions were in the ''Possible Risk/Inadequate Data'' category (87.0%), and 12.8% received ''Established High Risk'' medications. In multivariable analysis, high-risk prescribing was associated with prior ASM use and polytherapy. Discussion: People of childbearing potential with epilepsy were predominantly treated with carbamazepine, phenytoin, phenobarbital, and valproate, reflecting local ASM availability. Despite evidence supporting lamotrigine and levetiracetam in pregnancy, prescribing patterns reflect local formulary constraints. These findings highlight a gap between guideline recommendations and real-world prescribing in resource-limited settings, underscoring the need for context-specific treatment strategies.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-12

Iterating Toward Better Search: A Two-Agent Simulation Framework for Evaluating Agentic Search Architectures in E-Commerce

作者:
Jetlir Duraj↗Jayanth Yetukuri↗Shuang Zhou↗Dhruv Varma↗Rui Kong↗Ishita Khan↗Qunzhi Zhou↗

arXiv:2606.12924v1 Announce Type: new Abstract: We present a modular two-agent simulation framework for evaluating conversational shopping assistant architectures. An independent buyer agent, configured with personas, missions, and patience levels, is paired with an interchangeable responder that integrates with a real e-commerce search API. Holding the buyer constant across experiments enables controlled comparison of responder designs on identical scenarios. Using 2011 conversations across 14 persona buckets, we establish four empirical findings. First, rolling-window memory outperforms intent-extraction memory on all quality metrics while being 35% faster per query. Second, illustrating rapid evidence-driven iteration, a systematic failure analysis of a responder version enables targeted fixes that reduce failure and near-failure rates by 62% across the full dataset. Third, swapping the responder LLM backbone from Gemini~2.5 to Llama~3.3~70B costs 0.16–0.45 points despite identical architecture. Finally, we document systematic philosophical disagreement between frontier LLM judges: Gemini rewards process correctness while Claude demands concrete outcomes, despite using the same evaluation prompt.

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

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 →
06.
arXiv (CS.CV) 2026-06-19

Rethinking Robust Adversarial Concept Erasure in Diffusion Models

作者:
Qinghong Yin↗Yu Tian↗Heming Yang↗Xiang Chen↗Xianlin Zhang↗Yue Ming↗Xueming Li↗Yue Zhang↗

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to identify and suppress target concepts, thus reducing the likelihood of sensitive outputs. However, these methods often neglect the specificity of adversarial training in DMs, resulting in only partial mitigation. In this work, we investigate and quantify this specificity from the perspective of concept space, i.e., can adversarial samples truly fit the target concept space? We observe that existing methods neglect the role of conceptual semantics when generating adversarial samples, resulting in ineffective fitting of concept spaces. This oversight leads to the following issues: 1) when there are few adversarial samples, they fail to comprehensively cover the object concept; 2) conversely, they will disrupt other target concept spaces. Motivated by the analysis of these findings, we introduce S-GRACE (Semantics-Guided Robust Adversarial Concept Erasure), which grace leveraging semantic guidance within the concept space to generate adversarial samples and perform erasure training. Experiments conducted with seven state-of-the-art methods and three adversarial prompt generation strategies across various DM unlearning scenarios demonstrate that S-GRACE significantly improves erasure performance 26%, better preserves non-target concepts, and reduces training time by 90%. Our code is available at https://github.com/Qhong-522/S-GRACE.

阅读与讨论 → 访问原文 →
07.
arXiv (math.PR) 2026-06-24

Sim-to-Real Betting on the E-Process: Bringing "simulators" to anytime-valid confidence sequences

作者:
Yujia Chen↗Bowen Weng↗

arXiv:2606.24038v1 Announce Type: cross Abstract: This note describes an integration of the sim-to-real performance estimate with betting (from Chen et al.) and the safe anytime-valid inference (from Ramdas et al.). Using the scaled simulators. The method produces efficient, reliable certificates for the mean estimate, an approach that is especially valuable in robot performance testing. This note gives a primary, self-contained account of the construction; preliminaries of the respective methods are kept at a minimum, and one shall refer to the original works for full detail. Some synthetic examples demonstrating the proposed algorithm can be found at https://github.com/ISUSAIL/Bet4Sim2Real-EProcess.

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

Effective Geometry and Position-Dependent Mass in Dual-$q$ Quantum Mechanics

作者:
A. Boumali↗A. Makhlouf↗

arXiv:2606.12444v1 Announce Type: new Abstract: This work investigates the deformed-derivative formalism introduced by Borges, with emphasis on the relation between the linear operator $D_{(q)}$ and its nonlinear dual counterpart $D^{(q)}$. Directly inserting the dual derivative into the kinetic term leads to a nonlinear Schrödinger equation and obscures the usual interpretation of superposition and probability. We show that this nonlinearity can be removed by a simultaneous transformation of the coordinate and of the wave function. The transformed problem is an ordinary linear Schrödinger equation in a deformed coordinate, and its representation in the physical coordinate is equivalent to a Hermitian position-dependent-mass (PDM) Hamiltonian. In this formulation, the deformation parameter $q$ determines both the effective mass profile and the associated metric. The formalism is applied to the free particle, the infinite square well, the rectangular barrier, and the harmonic oscillator in the weak-deformation regime. Comparison with the nonadditive-translation approach of Costa Filho et al. shows that the Borges dual-$q$ framework provides an alternative route to the same effective geometric structure. For $q1$, the effective length is increased, which lowers the spectrum and suppresses tunneling relative to the undeformed limit $q=1$.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.LG) 2026-06-11

PianoKontext: Expressive Performance Rendering from Deadpan Context

作者:
Dmitrii Gavrilev↗

arXiv:2606.12282v1 Announce Type: cross Abstract: Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes. However, flow matching audio editing models manipulate only synchronized music samples of the same duration, limiting their understanding of expressive timing. We introduce PianoKontext, a flow matching rendering model for classical piano music that generates variable-length performances in the latent space of a pretrained Music2Latent model. We synthesize MIDI scores into deadpan audio and employ Dynamic Time Warping (DTW) in the latent space to construct paired data for training. The aligned embeddings are concatenated in DiT blocks, allowing for a simple and effective learning of the dependencies between the score and performances. Audio samples are available at our demo page: https://realfolkcode.github.io/pianokontext_demo/.

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

A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions

作者:
Jianghan Shen↗Siqi Luo↗Yue Li↗Jiyao Liu↗Wanying Qu↗Yi Zhang↗Ziyan Huang↗Tianbin Li↗Ming Hu↗Xiaohong Liu↗Yirong Chen↗Junjun He↗…

arXiv:2606.16733v1 Announce Type: new Abstract: Policy gradient algorithms for language models optimize the same objective $J(\theta) = \mathbb{E}*{\tau \sim p*\theta(\tau)}[R(\tau)]$, which has exactly two factors: the trajectory probability $p_\theta(\tau)$ and the reward $R(\tau)$. Every method from REINFORCE to PPO to GRPO and their descendants modifies one or both factors to address a specific failure in the preceding formulation. Existing surveys organize these methods by domain or chronology, which obscures the rationale behind each design choice and the precise location of its intervention within the gradient estimator. This survey revisits the landscape of LLM policy optimization from $J(\theta)$ on first principles and uses the trajectory side, induced by $p_\theta(\tau)$, and the reward side, induced by $R(\tau)$, as the two axes along which methods are located. It covers the path from REINFORCE and PPO to GRPO, as well as post-GRPO variants, Agentic RL, and GRPO-OPD. The resulting framework is unified, diagnostic, and extensible: it analyzes methods from a shared objective, identifies which side each method modifies and why, and applies the same trajectory and reward axes across these settings. Across these settings, the framework also exposes compound failures that no single-side fix resolves and that therefore require joint design of the trajectory side and the reward side. The boundary cases and coupled failures identified by this map mark where existing solutions run out and provide a principled starting point for designing the next generation of LLM policy optimization algorithms.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CL) 2026-06-18

Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation

作者:
Fan Xu↗Yangjie Dan↗Keyu Yan↗Yong Ma↗Mingwen Wang↗

Chinese dialects discrimination is a challenging natural language processing task due to scarce annotation resource. In this article, we develop a novel Chinese dialects discrimination framework with transfer learning and data augmentation (CDDTLDA) in order to overcome the shortage of resources. To be more specific, we first use a relatively larger Chinese dialects corpus to train a source-side automatic speech recognition (ASR) model. Then, we adopt a simple but effective data augmentation method (i.e., speed, pitch, and noise disturbance) to augment the target-side low-resource Chinese dialects, and fine-tune another target ASR model based on the previous source-side ASR model. Meanwhile, the potential common semantic features between source-side and target-side ASR models can be captured by using self-attention mechanism. Finally, we extract the hidden semantic representation in the target ASR model to conduct Chinese dialects discrimination. Our extensive experimental results demonstrate that our model significantly outperforms state-of-the-art methods on two benchmark Chinese dialects corpora.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-17

LLM-Aided Joint Secrecy Precoding and Trajectory for RSMA-Based Heterogeneous UAV Networks

作者:
Lijie Zheng↗Ji He↗Shih Yu Chang↗Yulong Shen↗

arXiv:2507.17188v3 Announce Type: replace-cross Abstract: This paper investigates secure communications in rate-splitting multiple access (RSMA) enabled heterogeneous UAV networks, where multiple UAVs collaboratively serve ground terminals in the presence of eavesdroppers. By jointly considering secrecy rate maximization and propulsion energy consumption minimization, we formulate a multi-objective optimization problem involving UAV trajectory design, service association, power allocation, and secrecy precoding under mobility, collision-avoidance, service-capacity, and communication constraints. The formulated problem is highly non-convex due to the coupling among UAV trajectories, RSMA transmission variables, and secrecy constraints.To address the resulting non-convex and highly coupled optimization problem, we propose a hierarchical optimization framework. The inner layer uses a semidefinite relaxation (SDR)-based S2DC algorithm combining penalty functions and difference-of-convex (D.C.) programming to solve the secrecy precoding problem with fixed UAV positions. The outer layer introduces a Large Language Model (LLM)-guided heuristic multi-agent reinforcement learning approach (LLM-HeMARL) for trajectory optimization. LLM-HeMARL efficiently incorporates LLM-generated expert heuristic policy, enabling UAVs to learn energy-aware, security-driven trajectories without the inference overhead of real-time LLM calls. The simulation results show that our method outperforms existing baselines in secrecy rate and energy efficiency, with consistent robustness across varying UAV swarm sizes and random seeds.

阅读与讨论 → 访问原文 →
13.
arXiv (quant-ph) 2026-06-16

Spectrally Corrected Polynomial Approximation for Quantum Singular Value Transformation

作者:
Krishnan Suresh↗

arXiv:2603.03998v2 Announce Type: replace Abstract: Quantum Singular Value Transformation (QSVT) provides a unified framework for applying polynomial functions to the singular values of a block-encoded matrix. QSVT prepares a state proportional to $\bA^{-1}\bb$ with circuit depth $O(d\cdot\mathrm{polylog}(N))$, where $d$ is the polynomial degree of the $1/x$ approximation and $N$ is the size of $\bA$. Current polynomial approximation methods are over the continuous interval $[a,1]$, giving $d = O(\sqrt{\kap}\log(1/\varepsilon))$, and make no use of any properties of $\bA$. We observe here that QSVT solution accuracy depends only on the polynomial accuracy at the eigenvalues of $\bA$. When all $N$ eigenvalues are known exactly, a pure spectral polynomial $p_{S}$ can interpolate $1/x$ at these eigenvalues and achieve unit fidelity at reduced degree. But its practical applicability is limited. To address this, we propose a spectral correction that exploits prior knowledge of $K$ eigenvalues of $\bA$. Given any base polynomial $p_0$, such as Remez, of degree $d_0$, a $K\times K$ linear system enforces exact interpolation of $1/x$ only at these $K$ eigenvalues without increasing $d_0$. The spectrally corrected polynomial $p_{SC}$ preserves the continuous error profile between eigenvalues and inherits the parity of $p_0$. QSVT experiments on the 1D Poisson equation demonstrate up to a $5\times$ reduction in circuit depth relative to the base polynomial, at unit fidelity and improved compliance error. The correction is agnostic to the choice of base polynomial and robust to eigenvalue perturbations up to $10\%$ relative error. Extension to the 2D Poisson equation suggests that correcting a small fraction of the spectrum may suffice to achieve fidelity above $0.999$.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-12

A Theory of Training Profit-Optimal LLMs

作者:
Sophie Hao↗William Merrill↗

arXiv:2605.16430v3 Announce Type: replace-cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure. While it is established that scaling up LLMs reliably increases model quality (quantified in terms of loss or downstream evaluations), it is unclear how these quality improvements translate to potential revenue, and whether revenue increases would offset costs of larger-scale training and inference. In this work, we develop an economic model for characterizing the rational behavior of an LLM training firm by combining scaling laws with microeconomic theory. Under our model of firm behavior, LLM quality can be increased with more parameters and training tokens, leading to more potential adoption by consumers, who each have a quality threshold for using the LLM. On the other hand, additional parameters and training tokens both incur additional costs. We analyze the profit maximization problem for this model under compute-bound and data-bound regimes. In the compute-bound regime, optimal model size and token budget track hardware efficiency $E$ (FLOPs/\$) at a near-linear rate; total training cost then scales sub-quadratically in $E$. Data efficiency improvements incentivize larger models and training expenditure. When we are limited to $D$ data, profit-optimal training expenditure scales as $D^2/E$, i.e, increase with data and decreases with hardware efficiency (as well as data efficiency). Finally, we analyze practical trends in training expenditure: current trends are consistent with our most permissive model variants in the compute-bound regime, but are not profit-optimal in the data-bound regime or assuming hardware advances will stall. Overall, our results provide a theory of profit-optimal LLM training, providing a foundation for engaging critically with industry statements and supporting long-term economic decision making.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.LG) 2026-06-25

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs

作者:
Mingyi Li↗Taira Tsuchiya↗Kenji Yamanishi↗

arXiv:2602.01903v3 Announce Type: replace Abstract: This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimization and policy optimization, both built on optimistic follow-the-regularized-leader with log-barrier regularization. For global optimization, our algorithms achieve first-order, second-order, and path-length regret bounds in the adversarial regime, and in the stochastic regime, they achieve a variance-aware gap-independent bound and a variance-aware gap-dependent bound that is polylogarithmic in the number of episodes. For policy optimization, our algorithms achieve the same data- and variance-dependent adaptivity, up to a factor of the episode horizon, by exploiting a new optimistic $Q$-function estimator. Finally, we establish regret lower bounds in terms of data-dependent complexity measures for the adversarial regime and a variance measure for the stochastic regime, implying that the regret upper bounds achieved by the global-optimization approach are nearly optimal.

阅读与讨论 → 访问原文 →
16.
bioRxiv (Bioinfo) 2026-06-20

Evaluation of Trypanosoma brucei Phosphofructokinase Allosteric Inhibition: An In-Silico Study

作者:
Gumbis↗Houston↗D. R↗

Human African trypanosomiasis, caused by a protozoan parasite Trypanosoma brucei, is a neglected tropical disease for which well-tolerated, conveniently administered, and highly efficacious medicines are still missing. Previously, T. brucei Phosphofructokinase was targeted by small-molecule inhibitor development efforts. This approach has shown promise both in vitro and in vivo. In this study, we have used these wet-lab results, evaluated the compounds already characterised by Molecular Dynamics simulations, found relationships between in silico and wet-lab data and used these observations to evaluate compounds that we selected through several different approaches of virtual screens. We observed that inhibitor-ATP interactions are highly predictive of the inhibitory activity. Several compounds selected through virtual screens have outperformed previously characterised compounds.

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

LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

作者:
Anastasiia Kucherenko↗Fran\c{c}ois Brouchoud↗Dimitri Percia David↗Andrei Kucharavy↗

arXiv:2606.24585v1 Announce Type: new Abstract: While the validity of LLMs' use in the legal context remains subject to ethical and legal debate, legal professionals are already experimenting with personal LLMs, if only for translation and reformulation. However, even such a seemingly innocuous use can introduce biases through case processing speed if LLM assistants selectively refuse assistance on certain topics. To better anticipate such biases, we investigate several modern small LLMs that are most likely to be used as on-device assistants, to assess the impact of overrefusal on legal prompts. Surprisingly, we find that authority-style prefixes (``you are acting as an assistant of the national supreme court'', ``[...] defense lawyer'') systematically increase refusal rates by 2–20x over the no-prefix baseline, while a known role-play jailbreak prefix shows mixed effects, sharply increasing refusals in some models and barely shifting them in others. The finding suggests that small on-prem deployable LLMs are unstable under contextual framings that a real institutional user might naturally introduce, and further investigation is essential to minimize opportunities for bias.

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

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

作者:
Roie Kazoom↗Yotam Gigi↗George Leifman↗Tomer Shekel↗Genady Beryozkin↗

Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change captioning datasets typically describe overall image-level differences, leaving fine-grained localized semantic reasoning largely unexplored. To close this gap, we present RSRCC, a new benchmark for remote sensing change question-answering containing 126k questions, split into 87k training, 17.1k validation, and 22k test instances. Unlike prior datasets, RSRCC is built around localized, change-specific questions that require reasoning about a particular semantic change. To the best of our knowledge, this is the first remote sensing change question-answering benchmark designed explicitly for such fine-grained reasoning-based supervision. To construct RSRCC, we introduce a hierarchical semi-supervised curation pipeline that uses Best-of-N ranking as a critical final ambiguity-resolution stage. First, candidate change regions are extracted from semantic segmentation masks, then initially screened using an image-text embedding model, and finally validated through retrieval-augmented vision-language curation with Best-of-N ranking. This process enables scalable filtering of noisy and ambiguous candidates while preserving semantically meaningful changes. The dataset is available at https://huggingface.co/datasets/google/RSRCC.

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

Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation

作者:
Seungjin Choi↗

arXiv:2606.11865v1 Announce Type: cross Abstract: Conformal Bayes combines Bayesian posterior predictives with conformal calibration to produce prediction sets that are both statistically valid and geometrically efficient. We study conformal Bayes under label shift from a unified perspective, identifying two complementary approaches that restore nominal target-domain coverage through importance-weighted conformal calibration but operate through independent mechanisms. Post-hoc calibration tilts the posterior predictive toward the target domain and corrects the conformal threshold via an importance-weighted quantile, leaving the parameter posterior unchanged. In-training adaptation tilts the parameter posterior itself to the target domain, producing a corrected predictive whose highest predictive density region serves as the highest predictive density (HPD) based prediction set under the fitted target predictive; efficiency is model-dependent and does not imply finite-sample conditional optimality. Two controlled experiments show that in an unbiased training regime both strategies achieve valid coverage equally, while in a lead-optimization regime in-training adaptation acts as a debiasing operator, reducing interval width at unchanged coverage.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-19

AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

作者:
Faqiang Qian↗Kang An↗Weikun Zhang↗Ziliang Wang↗Xuhui Zheng↗Liangjian Wen↗Yong Dai↗Mengya Gao↗Yichao Wu↗

arXiv:2509.25148v2 Announce Type: replace Abstract: Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose AAPA (Adversarially Anchored Preference Alignment), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-11

An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination

作者:
Xu Li↗Shuqi Tian↗Xun Han↗Kuncheng Zhao↗Xinyi Li↗

Traffic law liability determination is critical for assigning legal penalties, requiring the simultaneous identification of interdependent statutory provisions across multiple legal dimensions. However, existing retrieval-augmented generation methods suffer from a multi-dimensional retrieval bottleneck: single axis architectures compress complex legal queries into a single pathway, causing interdependent statutory dimensions to be overlooked. To address this, we propose OMAGR, an ontology-guided framework that decomposes queries into ontology-aligned anchors and executes parallel graph retrieval across each dimension, ensuring independent retrieval across dimensions before fusion. To evaluate the proposed method, we created the TrafficLaw-QA dataset, an expert-validated benchmark dataset containing 200 questions and 527 legal provisions. Results show that TrafficOmni-RAG outperforms baselines on Context Precision and Faithfulness metrics. The findings demonstrate that parallel multi-anchor retrieval effectively resolves the multi-dimensional retrieval bottleneck, offering a promising direction for traffic law liability determination research.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.AI) 2026-06-15

PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-Space Continuum

作者:
Milos Gravara↗Cynthia Marcelino↗Andrija Stanisic↗Stefan Nastic↗

arXiv:2606.14356v1 Announce Type: cross Abstract: Applications in the 3D Computing Continuum, which unifies edge, cloud, and space, require combining multiple AI tasks such as object detection, time-series analytics, and natural language processing into Compound AI systems. These systems must satisfy stringent Service Level Objectives (SLOs) on accuracy, latency, and cost. A key mechanism for maintaining SLO compliance of Compound AI systems is runtime model selection, where AI models are dynamically switched for each workflow task. However, existing distributed and compound AI frameworks do not natively support runtime model selection. We present PLAIground, a framework that enables runtime model selection for Compound AI systems. PLAIground introduces Compoundable AI Model (CAIM) abstraction, which decouples task semantics from AI model implementations via Task and Data Contracts, enabling model switching without workflow changes. Additionally, PLAIground introduces Pixie, an SLO-driven runtime model selection algorithm, which dynamically selects the most suitable model for each task during execution. Our evaluation on two realistic Compound AI workflows demonstrates that Pixie achieves up to 91.3% accuracy while maintaining SLO compliance where fixed-model strategies either violate cost and latency budgets up to 21x or miss accuracy targets by 4%.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CV) 2026-06-16

Text region detection in historical astronomical diagrams

作者:
Zeynep Sonat Baltac{\i}↗Rapha\"el Baena↗Fei Meng↗Somk\'eo Norindr↗Florence Somer↗Matthieu Husson↗Mathieu Aubry↗

Text detection is a crucial task in the analysis of historical documents. While datasets and benchmarks exist for text detection in manuscripts and maps, the study of text in mathematical diagrams has received little attention. To address this, we introduce a large-scale, diverse, open-access dataset of 948 historical astronomical diagrams containing 10,940 oriented polygonal text regions. Our dataset spans ten centuries (8th to 18th) and seven main linguistic traditions: Arabic and Persian (115), Chinese (332), Byzantine (233), Latin (185), Hebrew (48), and Sanskrit (35). It captures a wide range of diagram styles and textual content, from symbols to multi-line paragraphs. Each text instance is annotated with ordered polygons that precisely delineate text regions and encode the reading direction. In addition, we annotated the 2,293 regions in Latin diagrams with 20 class labels. We evaluated several strong baselines on our dataset, including TESTR, DeepSolo++, and Poly-DETR, a simple extension of DINO-DETR that we design to predict ordered polygon vertices. Poly-DETR achieves state-of-the-art performance on the MTHv2 and cBAD2019 benchmarks and provides a solid, simple baseline on our dataset. Code and dataset available online.

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

GradPower: Powering Gradients for Faster Language Model Pre-Training

作者:
Jinbo Wang↗Mingze Wang↗Jiaqi Zhang↗Wei Wang↗Peng Pei↗Xunliang Cai↗Weinan E↗Lei Wu↗

arXiv:2505.24275v4 Announce Type: replace Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $g=(g_i)_i$, GradPower first applies the elementwise sign-power transformation: $\varphi_p(g)=(sign(g_i)|g_i|^p)_{i}$ for a fixed $p>0$, and then feeds the transformed gradient into a base optimizer. Notably, GradPower requires only a single-line code change and no modifications to the base optimizer's internal logic, including the hyperparameters. When applied to Adam (termed AdamPower), GradPower consistently achieves lower terminal loss across diverse architectures (LLaMA, Qwen2MoE), parameter scales (66M to 2B), datasets (C4, OpenWebText), and learning-rate schedules (cosine, warmup-stable-decay). The most pronounced gains are observed when training modern mixture-of-experts models with warmup-stable-decay schedules. GradPower also integrates seamlessly with other state-of-the-art optimizers, such as Muon, yielding further improvements. Finally, we provide theoretical analyses that reveal the underlying mechanism of GradPower and highlight the influence of gradient noise.

阅读与讨论 → 访问原文 →