中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.CL) 2026-06-12

Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures

Authors:
Ishani Mondal↗Javad Baghirov↗Jordan Boyd-Graber↗

Scientific figures compress complex pipelines into a single canvas, yet understanding them requires paper-grounded, step-by-step narration aligned with visual highlights a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. We propose MINARD (Multimodal Interpretation of Narrated Architecture via Region Decomposition), a pipeline that generates paper-grounded narrations and sequentially grounds them to figure regions. We also release FigTalk, a benchmark with new sequential and component-level grounding metrics derived. On FigTalk, MINARD generates humanlike, paper-faithful narrations and outperforms narration-conditioned figure spatial grounding compared to existing approaches in both automatic and human evaluation

Read & Discuss → View Source →
02.
arXiv (CS.AI) 2026-06-25

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

Authors:
Ke Zhao↗Zixiang Di↗Hong Qian↗Xiang Shu↗Yaolin Wen↗Qitao Shi↗Bingdong Li↗Xingyu Lu↗Xiangfeng Wang↗Jun Zhou↗Ke Tang↗Yang Yu↗…

arXiv:2606.25832v1 Announce Type: cross Abstract: Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized language models with strong optimization generalization capabilities. The code is available at https://github.com/Hsiang-1/MiniOpt.

Read & Discuss → View Source →
03.
arXiv (CS.AI) 2026-06-25

Omni-Perception Policy Optimization for Multimodal Emotion Reasoning

Authors:
Zhiyuan Han↗Beier Zhu↗Wenwen Tong↗Pengyang Shao↗Peipei Song↗Xinyi Wang↗Jiangnan Chen↗Lewei Lu↗Xun Yang↗

arXiv:2606.25325v1 Announce Type: new Abstract: We find that current emotion-oriented Omni-MLLMs still lack reliable omni-modal perception: they (i) underutilize multimodal cues in their reasoning trajectories and (ii) exhibit unfaithful behavior, often hallucinating modality-specific statements from other modalities. Building on these insights, we propose OPPO (Omni-Perception Policy Optimization), a reinforcement learning framework that explicitly optimizes multimodal perception. First, an Omni-Perception Reward decomposes ground-truth reasoning into fine-grained visual, acoustic, and emotion cues and rewards trajectories that semantically recover these cues. Second, an Omni-Perception Loss compares the policy under full and unimodally masked inputs, applying a KL penalty only to modality-specific evidence tokens to suppress cross-modal hallucination. We further introduce MEP-Bench, a diagnostic benchmark that quantifies utilization and faithfulness. Experiments show that OPPO achieves state-of-the-art performance on MER-UniBench and MME-Emotion, while substantially improving utilization and faithfulness scores on MEP-Bench, highlighting the importance of sufficient and faithful omni perception for multimodal emotion reasoning.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-16

The limits of interpretability in multiple linear regression

Authors:
Anand Sharma↗Chen Liu↗Daniele Coslovich↗Misaki Ozawa↗

arXiv:2606.16013v1 Announce Type: cross Abstract: Interpreting machine-learning models has attracted increasing attention, particularly in the physical sciences, where one often seeks to understand the underlying mechanisms rather than merely make predictions. Multiple linear regression is often regarded as an interpretable alternative to more complex models, such as deep neural networks, because its predictions are expressed as explicit weighted sums of input features. However, when input features are strongly correlated, namely in the presence of multicollinearity, the learned weights can exhibit large dataset-to-dataset fluctuations and oscillatory behavior across physically similar features, making their interpretation difficult or even impossible. Although the instability of the weights under multicollinearity is well known in statistics, its consequences for physical interpretation, in particular its connection to oscillatory weights across physically similar features, have not been systematically clarified. Here, we theoretically discuss the mechanism behind this loss of interpretability by analyzing the eigenmodes of the feature correlation matrix. We show that small-eigenvalue modes associated with multicollinearity amplify fluctuations in the weights and generate oscillatory patterns that do not necessarily reflect meaningful contributions. We test this theoretical picture numerically on physics datasets and show that Ridge regularization suppresses these unstable modes, although the resulting weights must still be interpreted with caution. We further confirm the generality of our findings beyond physics by analyzing a diverse collection of publicly available datasets. Our results clarify why, in the presence of multicollinearity, physical interpretation can remain difficult even for linear regression models.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-16

CmdNeedle: Measuring the Incompleteness of Command Denylists for AI Agents

Authors:
Chuyang Chen↗Zhiqiang Lin↗

arXiv:2606.15549v1 Announce Type: cross Abstract: The adoption of AI agents is increasing rapidly. Terminal AI agents, i.e., AI agents that run in terminal environments, are a widely used type of AI agents. Terminal AI agents rely heavily on shell command execution to interact with the host systems. They adopt a three-list command-gating mechanism to mitigate security risks introduced by command execution, with denylists serving as the load-bearing component. However, modern operating systems often ship a large, ever-expanding set of shell commands with complex functionalities. Our observation is that even a built-in denylist of Claude Code, well-maintained by its developers, can overlook bypass commands that invalidate its effectiveness. Such negligence leads to fragile command denylists that cannot even block operations that practitioners expect them to block. This paper presents the first systematic characterization of command denylist fragility in terminal AI agents. The paper formalizes the command denylist fragility problem and proposes an LLM-driven pipeline, CmdNeedle, to detect such fragility. It prompts the LLM to propose possible bypasses and iteratively repairs them using feedback from a validator that executes them in a sandbox. In the evaluation, we applied CmdNeedle to 1,709 real-world command denylists (containing 13,332 denylist rules) collected from GitHub. The evaluation shows several key findings, including that 69.0–98.6% of the denylists are fragile, that this fragility occurs consistently across projects and agents, and the validity of several possible root causes for this fragility. Our pipeline and findings will hopefully facilitate future research and practice regarding the command denylists used by AI agents.

Read & Discuss → View Source →
06.
arXiv (CS.AI) 2026-06-11

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

Authors:
Guilin Zhang↗Chuanyi Sun↗Shahryar Sarkani↗John M. Fossaceca↗

arXiv:2606.04145v2 Announce Type: replace-cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality. As Gao et al. (2023) showed, this proxy diverges from world feedback (downstream eval metrics) under sustained optimization pressure, a phenomenon known as reward overoptimization. Existing platform schedulers ignore this divergence: non-clairvoyant schedulers optimize JCT without any quality signal, SLAQ-style quality-aware schedulers use training loss (a weaker proxy that drops monotonically through hacking), and classical per-job early stopping requires human monitoring and does not free shared GPUs. We propose EvalStop, a composable scheduling primitive that terminates jobs on k consecutive eval-score declines, releases GPUs, preserves the best checkpoint, and delegates to any base scheduler. We frame scheduler-level early stopping as a detection problem and evaluate it in a discrete-event simulator whose RLHF workload mixes reward-hacking and structurally healthy runs, with ground-truth labels hidden from schedulers. On RLHF-heavy workloads (80% RLHF, 64 GPUs), EvalStop achieves precision 98% / recall 99% / FPR 1.5% while improving JCT by 9% and cutting wasted compute by 22% over SRTF-Est (p

Read & Discuss → View Source →
07.
arXiv (quant-ph) 2026-06-25

Expanding the Neutral Atom Gate Set: Native iSWAP and Exchange Gates from Dipolar Rydberg Interactions

Authors:
Pedro Ildefonso↗Andrew Byun↗Aleksei Konovalov↗Javad Kazemi↗Michael Schuler↗Wolfgang Lechner↗

arXiv:2512.05037v2 Announce Type: replace Abstract: We present a native realization of iSWAP and parameterized exchange gates for neutral-atom quantum processing units. Our approach leverages strong dipole-dipole interactions between two different dipole-coupled Rydberg states, employing optimal control techniques to design high-fidelity, time-efficient gate pulses. To minimize experimental complexity, we utilize global driving fields acting identically on all atoms and apply pulse smoothing techniques. While detrimental van-der-Waals interactions pose a significant challenge, we demonstrate that for both $^{133}$Cs, as a representative alkali atom, and $^{88}$Sr, an alkaline-earth species, high-fidelity pulses can nevertheless be obtained over a broad range of parameters. We identify candidate protocols with reduced susceptibility to noise and analyze their performance under realistic conditions, accounting for atomic motion, Rydberg decay, and experimentally motivated laser frequency and intensity noise. Crucially, we demonstrate that in both Alkali and alkaline-earth-based systems, we can obtain fast iSWAP gates with fidelities of $99.9\%$ under realistic experimental conditions. These results pave the way for expanding the neutral-atom gate set beyond conventional Rydberg-blockade-based entangling gates.

Read & Discuss → View Source →
08.
arXiv (CS.LG) 2026-06-17

Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation

Authors:
Chanuka A. S. Hewa Kaluannakkage↗Rajkumar Buyya↗

arXiv:2606.10774v2 Announce Type: replace Abstract: Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations. Operating over lossy wireless links under constraints, these systems cannot rely on retransmissions, so model parameters must be accepted as partial chunks, leading to two key failure modes, which are selection bias, where poor-quality links are systematically under-represented in gossip aggregation, and update staleness, where asynchronous nodes contribute outdated models. We prove that classical gossip aggregation introduces irreducible selection bias proportional to the link-loss rate. We propose DFL-AA (Decentralized Federated Learning with Adaptive AoI-weighted Aggregation), which corrects selection bias using Inverse Probability Weighting (IPW) with online channel estimation and mitigates staleness via Age-of-Information (AoI) decay without requiring a global clock. We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines across varying loss rates and heterogeneous channel conditions on fixed directed topologies.

Read & Discuss → View Source →
09.
arXiv (CS.CL) 2026-06-16

CoBit: Language Modeling with Bitstream Diffusion

Authors:
Georgios Batzolis↗Mark Girolami↗Luca Ambrogioni↗

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion approaches have narrowed this gap. In this work, we further close the autoregressive gap by modeling text as a continuous diffusion process over fixed-width binary bitstreams. We refer to the resulting model as CoBit (Continuous Bitstream Diffusion). Our approach represents semantic tokens as analog bit sequences and uses a matched-filter residual parameterization to isolate contextual learning from analytic independent-bit posteriors. Crucially, we adopt a stochastic sampler that applies Langevin-type corrections gated by the entropy-rate profile, concentrating stochasticity in high-information regions while remaining nearly deterministic elsewhere. On LM1B, our 130M-parameter model reaches a generative perplexity (GenPPL) of 59.76 at matched real-data entropy (4.31) using 256 neural function evaluations (NFEs), outperforming prior DLM baselines and reaching the autoregressive reference. On OpenWebText (OWT), our sampler establishes a new continuous-DLM Pareto frontier, achieving GenPPL 27.06 at entropy 5.26 using 4x fewer steps than previous 1024-NFE baselines. Scaling the same recipe to a 462M-parameter model (CoBit-M) further improves the OWT GenPPL-entropy frontier over the 130M model (CoBit-S) and over medium-scale continuous and discrete DLM baselines, reaching GenPPL 19.5 at entropy 5.40, near real-data entropy (5.44), and approaching pretrained GPT-2 Medium over the high-quality region. As an additional benefit, bitstream diffusion removes the O(V) vocabulary scaling bottleneck of standard DLMs: by predicting O(log V) bitwise logits via semantic bit-patching, it lowers memory and raises throughput, a scalable paradigm as vocabulary sizes grow.

Read & Discuss → View Source →
10.
arXiv (CS.CL) 2026-06-24

AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach

Authors:
Murilo Gazzola↗Hugo Gobato Souto↗Samuel Silva↗J\'ulia Schubert Peixoto↗Felipe Siqueira↗Andr\'e Luis Pedroso de Morais↗Caio Gomes↗

The explosive growth and complexity of product data within the dynamic Brazilian e-commerce landscape demand robust and specialized methods for structured information extraction. Traditional approaches to Product Attribute Value Extraction (PAVE) often struggle with the linguistic nuances and sheer diversity of product descriptions in Portuguese. To address this critical gap, this paper introduces two major contributions. First, we present AI-PAVEBr, a specialized system engineered with Large Language Models (LLMs) to perform high-accuracy PAVE specifically for Brazilian e-commerce catalogs. Second, to facilitate reproducible research and provide a definitive benchmark, we introduce and share the Golden Set, a new, meticulously curated, and manually annotated dataset for PAVE in Portuguese. We detail the creation process and structure (Entity, Category, Subcategories) of this high-quality reference set. Our experiments conclusively show that AI-PAVE-Br, leveraging targeted prompt engineering, dramatically outperforms conventional Named Entity Recognition (NER) baselines. This work not only delivers a superior, scalable solution for a major non-English market but also enriches the NLP community with a valuable, publicly available resource for future PAVE research.

Read & Discuss → View Source →
11.
arXiv (CS.AI) 2026-06-17

From Noise to Order: Learning to Rank via Denoising Diffusion

Authors:
Sajad Ebrahimi↗Bhaskar Mitra↗Negar Arabzadeh↗Ye Yuan↗Haolun Wu↗Fattane Zarrinkalam↗Ebrahim Bagheri↗

arXiv:2602.11453v3 Announce Type: replace-cross Abstract: Learning-to-rank (LTR) methods have traditionally been limited to discriminative machine learning approaches that model the probability of the document being relevant to the query given some feature representation of the query-document pair. We propose an alternative denoising diffusion-based generative approach to LTR that instead models the full joint distribution over features and relevance labels. While in discriminative LTR, an over-parameterized ranking model may find different ways to fit the training data, we posit that candidate solutions that can explain the full data distribution under the generative setting maybe better at estimating relevance. Thus, we propose DiffusionRank that extends TabDiff, an existing diffusion model for tabular datasets, to create generative alternatives to classical discriminative pointwise and pairwise LTR objectives. Our work demonstrates improvements from DiffusionRank over discriminative counterparts on four standard LTR datasets and points to a rich space for future exploration to leverage ongoing advancements in deep generative models for LTR. Our code is publicly available at https://github.com/sadjadeb/DiffusionRank.

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-15

Incentives Of EdTech: A Systematic Review Of EduNLP Research

Authors:
Gabrielle Gaudeau↗Aoife O'Driscoll↗Jasper Degraeuwe↗Andrew Caines↗Donya Rooein↗Zeerak Talat↗

While the Natural Language Processing community has dedicated significant resources in developing educational technologies (EdTech) that support this shift, it remains unclear whose interests are being best served among the stakeholders of education. In this paper, we present a systematic literature review of 204 papers published in venues of the Association for Computational Linguistics' Special Interest Group on Building Educational Applications in 2024 and 2025, and validate these against EdTech papers from the wider ACL Anthology. By examining stakeholder inclusion and the prioritisation of research tasks, our findings reveal a critical tension: a push and pull between private-sector incentives and the foundational needs of educational infrastructure. Our analysis reveals that teachers are systematically under-represented as beneficiaries of research (33.3%) despite being the most affected, that real-world deployment remains rare (9.8%), and that ethical engagement tends toward acknowledgement rather than action. Drawing on exemplary papers in our corpus, we offer concrete recommendations for more responsible EduNLP research practices.

Read & Discuss → View Source →
13.
arXiv (CS.CL) 2026-06-15

Rethinking the Trust Region in LLM Reinforcement Learning

Authors:
Penghui Qi↗Xiangxin Zhou↗Zichen Liu↗Tianyu Pang↗Chao Du↗Min Lin↗Wee Sun Lee↗

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal learning dynamic: updates to low-probability tokens are aggressively over-penalized, while potentially catastrophic shifts in high-probability tokens are under-constrained, leading to training inefficiency and instability. To address this, we propose Divergence Proximal Policy Optimization (DPPO), which substitutes heuristic clipping with a more principled constraint based on a direct estimate of policy divergence (e.g., Total Variation or KL). To avoid huge memory footprint, we introduce the efficient Binary and Top-K approximations to capture the essential divergence with negligible overhead. Extensive empirical evaluations demonstrate that DPPO achieves superior training stability and efficiency compared to existing methods, offering a more robust foundation for RL-based LLM fine-tuning. Our code is available at https://github.com/sail-sg/Stable-RL.

Read & Discuss → View Source →
14.
arXiv (CS.CL) 2026-06-15

ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

Authors:
Karamvir Singh↗Arvind Jain↗

Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch – a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.

Read & Discuss → View Source →
15.
arXiv (CS.LG) 2026-06-11

Efficient Multinomial Logistic Bandit via Frequent Directions

Authors:
Linzhe He↗Yu-Jie Zhang↗Sifan Yang↗Lijun Zhang↗

arXiv:2606.11968v1 Announce Type: new Abstract: This paper studies efficient online algorithms for multinomial logistic bandits (MLogB), where the feedback distribution over $K+1$ outcomes follows a multinomial logistic model of $d$-dimensional action vectors. A representative UCB-type algorithm, OFUL-MLogB, achieves a regret bound of $\tilde{\mathcal{O}}(Kd\sqrt{T})$, but still requires $\mathcal{O}(K^3d^3)$ time and $\mathcal{O}(K^2d^2)$ space per round due to parameter estimation and optimistic reward construction, which is prohibitive in high-dimensional settings. To address this limitation, we propose EOFD-MLogB, which integrates frequent directions matrix sketching into OFUL-MLogB. By maintaining a low-rank SVD sketch of the accumulated Hessian, constrained online Newton updates in parameter estimation and $Kd \times K$ spectral-norm computations in the reward bonus are reduced to one-dimensional root-finding tasks and $K \times K$ eigenvalue computations, respectively. This yields dominant per-round time complexity $\mathcal{O}(Kd(m+K)^2)$ and space complexity $\mathcal{O}(Kd(m+K))$, where $m \ll d$ is the sketch size. We further prove a regret bound of $\tilde{\mathcal{O}}(\Delta_T(Kd\ln\Delta_T+m)\sqrt{T})$, where the sketching error factor $\Delta_T$ is controlled by the $m$-truncated spectral tail of the Hessian. Thus, when the Hessian is approximately low-rank, the regret is close to that of OFUL-MLogB. Experiments validate the computational efficiency and competitive performance.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-12

It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO

Authors:
Naihao Deng↗Yilun Zhu↗Naichen Shi↗Clayton Scott↗Rada Mihalcea↗

Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and reliable behavior. In this work, we investigate how easily such guardrails can be broken by Group Relative Policy Optimization (GRPO). We show that one-shot GRPO training on a single biased example is sufficient to induce systematic bias, with stereotype-driven reasoning generalizing across attributes, categories, and benchmarks. We further find that models differ in their susceptibility based on the initial likelihood of producing biased outputs. Our results reveal a critical vulnerability in post-training: alignment can be overridden by a single example.

Read & Discuss → View Source →
17.
arXiv (CS.LG) 2026-06-17

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

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

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

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-25

PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

Authors:
Xianghui Wang↗Feng Chen↗Wenbo Zhang↗Hua Yan↗Zixuan Wang↗Changsheng Li↗Yinjie Lei↗

Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existing efforts predominantly focus on compute-centric efficiency to reduce per-step inference latency, the intrinsic policy efficiency of these models remains largely unexplored. Policy efficiency is fundamentally affected by two factors, namely the effective executable length of predicted action chunks and the total physical steps required to complete a task. These two factors jointly determine the total number of forward inference calls during execution. We observe that current VLA policies struggle with planning unreliability and action redundancy, suffering from severe prediction degradation at the tail of action chunks and tending to generate unnecessarily redundant physical steps. To address this, we propose PolicyTrim, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps. For reliable chunk extension, we employ a dynamic exploration strategy that explicitly rewards the successful completion of longer executable lengths, progressively pushing the trustworthy prediction horizon to its empirical limit. For step efficiency, we design a redundancy-aware reward that directly favors successful task completions with fewer steps while penalizing unreproducible shortcuts, effectively eliminating redundant physical actions. Extensive experiments across three benchmarks and three VLA models demonstrate that PolicyTrim improves action chunk utilization by 3$\times$ and reduces physical execution steps by 51.4\%. Ultimately, our framework delivers up to a 5.83$\times$ end-to-end deployment speedup without compromising task success rates.

Read & Discuss → View Source →
20.
arXiv (quant-ph) 2026-06-24

Spectrally engineered collinear type-0 SPDC source with enhanced spectral brightness for entanglement distribution

Authors:
Dong-Gil Im↗Jungmo Lee↗Kyungdeuk Park↗Dongkyu Kim↗Yonggi Jo↗Yong Sup Ihn↗

arXiv:2606.24036v1 Announce Type: new Abstract: Entangled photon sources with high spectral brightness are important resources for photonic quantum information processing, particularly in quantum communication and quantum networking where usable photon flux of entangled photons is often constrained by channel loss and source inefficiency. Here, we demonstrate a spectrally engineered type-0 spontaneous parametric down-conversion (SPDC) source with enhanced spectral brightness for entanglement distribution. By pumping a 30-mm ppKTP crystal with an ultra-narrowband laser slightly detuned from degeneracy, photon-pair generation is concentrated into a narrow spectral bandwidth while retaining the strong nonlinear interaction of type-0 phase matching. The source produces a coincidence rate of 44.6 kHz corresponding to a detected spectral brightness of 0.507 MHz/mW/nm. We further integrate the source into a Sagnac interferometer to generate polarization-entangled photon pairs and demonstrate entanglement distribution through a 2.56 km free-space round-trip channel. Our results show that spectral engineering provides a practical route to compact, spectrally bright entangled-photon sources for quantum communication applications.

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-25

Speech Codec Probing from Semantic and Phonetic Perspectives

Authors:
Xuan Shi↗Chang Zeng↗Tiantian Feng↗Shih-Heng Wang↗Jianbo Ma↗Shrikanth Narayanan↗

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.

Read & Discuss → View Source →
22.
arXiv (CS.CL) 2026-06-25

SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment

Authors:
Tianyu Dong↗Yangyang Liu↗Jiang Zhou↗Xinwei Wu↗Xiaohu Zhao↗Hao Wang↗Heng Liu↗Linlong Xu↗Longyue Wang↗Weihua Luo↗Shaolin Zhu↗Deyi Xiong↗…

Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational efficiency. However, low-resource languages, which suffer from a scarcity of high-quality training data, often have their tokens routed to different experts than those predominantly activated by high-resource inputs, which limits cross-lingual expert sharing. This cross-lingual routing divergence consequently hinders their efficacy in multilingual contexts. To address this issue, we propose SARA (Semantically Anchored Routing Alignment), a framework designed to transfer specialized capabilities from high-resource languages as anchors to low-resource languages. SARA explicitly aligns the routing distribution of multilingual inputs with high-resource semantic anchors using a symmetric Jensen-Shannon (JS) divergence constraint. Unlike traditional distillation methods that operate on output logits, SARA directly aligns the internal routing distributions of MoE layers, encouraging mechanistic consistency in expert selection across languages. We conduct experiments on 2 LLMs across 5 low-resource languages and 3 benchmarks. Experiment results demonstrate that SARA outperforms standard instruction tuning, e.g., +0.8% on Qwen3-30B-A3B and +1.2% on Phi-3.5-MoE-instruct on Global-MMLU. Further analyses show that SARA effectively addresses performance bottlenecks in low-resource languages, providing a scalable pathway to enhance multilingual capabilities in sparse architectures.

Read & Discuss → View Source →
23.
arXiv (CS.CV) 2026-06-17

Beyond Benchmarks: Continuous Edge Inference for Fine-Grained Roadside Perception

Authors:
Aditya Mishra↗Haroon Lone↗

Continuous AI inference on resource-constrained edge hardware introduces deployment effects that are largely invisible to conventional benchmark evaluation, including temporal instability in streaming video, thermal throttling under sustained load, and workload-dependent performance variability. We present Edge-TSR, a deployment-oriented continuous edge inference system for sustained roadside perception on the NVIDIA Jetson Orin Nano. Edge-TSR integrates detection, tracking, fine-grained classification, and a lightweight track-aware temporal stabilization mechanism that improves streaming inference consistency with negligible computational overhead. Our central finding is that benchmark-centric evaluation systematically overstates deployed edge inference performance. Across three state-of-the-art baselines, we observe consistent 20-30% relative degradation when transitioning from static-image evaluation to real-world streaming deployment. Edge-TSR addresses this gap through temporal inference stabilization, recovering up to 10.16% classification accuracy over per-frame inference baselines while maintaining sustained real-time performance under continuous operation. We evaluate the complete system under diverse real-world deployment conditions, jointly characterizing inference quality, latency, throughput, and thermal behavior during long-duration operation. A 55-minute vehicular deployment over a 26 km route demonstrates sustained operation at 16.18 FPS within safe thermal limits on a single embedded device without cloud offload. Our findings show that deployment-aware evaluation and temporal inference stabilization are necessary components of continuously operating edge AI systems intended for real-world sensing deployments. We release a sample annotated streaming video evaluation dataset and full system implementation to support reproducible deployment-centric evaluation.

Read & Discuss → View Source →
24.
arXiv (CS.AI) 2026-06-12

Valid Inference with Synthetic Data via Task Exchangeability

Authors:
Lezhi Tan↗Tijana Zrnic↗

arXiv:2606.13629v1 Announce Type: cross Abstract: There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social scientists are arguing for the use of LLM-generated "silicon samples" in pilot studies; AI evaluations increasingly rely on "LLM-as-a-judge" outputs; and proteomics research is accelerated by generative models that produce synthetic protein structures. These developments raise an intriguing possibility: synthetic data may help researchers ask more questions, run more studies, and accelerate discovery. But they also raise a fundamental concern: synthetic data can be biased, noisy, and misspecified. In this work, we propose statistical principles for using synthetic data in scientific research with provable validity guarantees. The key insight is a new technical condition that we call task exchangeability. Informally, this is a requirement that the researcher can identify historical tasks, for which real data is available, such that their current task of interest is exchangeable with the historical tasks in an appropriate mathematical sense. We develop methods for valid inference under task exchangeability, together with extensions that provide guarantees even beyond exchangeability. We demonstrate the framework on public opinion surveys with silicon samples and AI evaluation with autoraters.

Read & Discuss → View Source →
25.
arXiv (CS.CL) 2026-06-11

AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable

Authors:
Meysam Alizadeh↗Fabrizio Gilardi↗Mohsen Mosleh↗Enkelejda Kasneci↗

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

Read & Discuss → View Source →