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。

01.
arXiv (CS.AI) 2026-06-19

RoboSSM: Scalable In-context Imitation Learning via State-Space Models

arXiv:2509.19658v2 Announce Type: replace-cross Abstract: In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at deployment time, this paradigm supports few-shot adaptation to novel tasks. However, recent ICIL methods rely on Transformers, which have computational limitations and tend to underperform when handling longer prompts than those seen during training. In this work, we introduce RoboSSM, a scalable recipe for in-context imitation learning based on state-space models (SSM). Specifically, RoboSSM replaces Transformers with Longhorn – a state-of-the-art SSM that provides linear-time inference and strong extrapolation capabilities, making it well-suited for long-context prompts. Through diverse experiments on the LIBERO benchmark, we demonstrate the effectiveness of applying SSMs to ICIL, achieving improved generalization to both unseen and long-horizon tasks than Transformer-based ICIL methods by handling longer contexts at test-time. These results show for the first time that SSMs are an efficient and scalable backbone for ICIL. Our code is available at https://github.com/youngjuY/RoboSSM.

02.
arXiv (CS.LG) 2026-06-18

ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets

arXiv:2606.18338v1 Announce Type: new Abstract: The search for life beyond Earth will depend on detecting faint signatures in the atmospheres of potentially habitable exoplanets. Interpreting those signatures requires understanding the host planet's climate: the same molecule may signal life on one planet and abiotic chemistry on another. Global climate models (GCMs) provide this understanding, but individual runs can require up to millions of core-hours and substantial domain expert time. Machine-learning emulators could remove this bottleneck, but progress has been limited by the absence of a curated, multi-model exoclimate dataset. We introduce ThousandWorlds, an ML-ready benchmark for exoclimate emulation and for the broader regime of low-data, multi-simulator, parameter-to-field regression. The dataset contains approximately 1800 simulations from five GCMs, mapping eight planet parameters to 3D atmospheric fields including temperature, humidity, winds, clouds, and radiation. Three nested subsets define progressively harder challenges: single-simulator regression, multi-simulator regression with complete observations, and multi-simulator regression with structured missingness. We propose two evaluation protocols: one for ranking methods, and one that measures performance relative to the disagreement between GCMs themselves. We evaluate seven baselines spanning simple methods, deep learning, and Gaussian processes. GP-based methods perform best, suggesting that ThousandWorlds exposes a regime where off-the-shelf deep learning does not yet succeed. Data: https://doi.org/10.57967/hf/8695. Code: https://github.com/edstevenson/ThousandWorlds.

03.
arXiv (CS.AI) 2026-06-16

Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers

arXiv:2606.16362v1 Announce Type: cross Abstract: Deep neural networks have achieved strong performance in medical image classification, but often work like black-box. Commonly used post-hoc interpretation methods often provide heuristic visualizations whose relationship to the classifier's predictive distribution is indirect. This work introduces a local sensitivity analysis framework based on the input-dependent Fisher Information Matrix (iFIM) of a trained classifier. The iFIM characterizes how the classifier's predictive distribution changes under infinitesimal perturbations of the input image. By using a Gram-matrix formulation, the nonzero eigenspectrum of the iFIM can be recovered without explicitly forming the full image-dimensional Fisher matrix. The leading iFIM eigenspace is then used to project an input image into a high local-sensitivity component and its orthogonal component. These components provide a model-intrinsic description of local predictive sensitivity, rather than a conventional pixel-wise attribution heatmap or a causal segmentation of task-relevant anatomy. The framework is evaluated on controlled and clinical medical image classification tasks using multiple classifier architectures. Perturbation-based experiments show that high-sensitivity iFIM components are more strongly coupled to changes in predictive confidence and classification performance than lower-sensitivity complementary components. The results support the iFIM framework as a principled tool for analyzing local decision sensitivity and for complementing existing attribution-based interpretability methods in medical imaging.

04.
arXiv (quant-ph) 2026-06-12

Quantum Logic Codes: Complete Transversal Logical Clifford Instruction Sets for High-Rate Stabilizer Quantum Error Correcting Codes

作者:

arXiv:2606.13521v1 Announce Type: new Abstract: We study the structure and transversal logical capabilities of stabilizer quantum error correcting codes. Among our results, we identify universal lower bounds on circuit depth to generate a full logical Clifford algebra, and develop novel constructions of logical transversal gates including a new depth-one transversal phase $\mathrm{\overline{S}}$ gate in the rotated surface code and a depth-one intra-block $\mathrm{\overline{CZ}}$ gate in the 2D-toric code that generalizes to all odd distances and all lengths $L\ge3$, respectively. Finally, we construct a high-rate non-LDPC CSS code family with parameters $[[n,\sqrt{n},\Theta({n^{\beta}})]]$ where $\beta \approx 0.2823$ in one demonstrated case, that provably possesses a constant-depth complete 2-local transversal logical Clifford basis instruction set architecture (ISA) composed of all individually targeted $\mathrm{\overline{S}}$, $\mathrm{\overline{SHS}} = \sqrt{X}$, and $\mathrm{\overline{CZ}}$ gates. This ISA is depth-one for certain subfamilies that we design and generally constant-depth under certain conditions. The code family is built from a small code with parameters $[[n_0, 2, d_0]]$, and is tunable in the standard way: it tiles out to form utility-scale logical qubit counts, and it scales up through concatenation to achieve higher distances and error suppression. We show that this construction preserves the depth-one complete transversal logical Clifford basis ISA when composed with these commuting construction actions, inheriting structure from the core codes so that at scale the complete logical Clifford basis ISA remains depth-one up to depth-two addressable operations between tiled cores. We call these Quantum Logic Codes.

06.
arXiv (CS.CV) 2026-06-16

The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results

This paper reports on the NTIRE 2026 Challenge on Image Denoising, specifically focusing on the high-noise regime ($\sigma = 50$). The competition investigates advanced neural architectures designed to restore high-fidelity details from images corrupted by additive white Gaussian noise (AWGN). Unlike constrained benchmarks, this track emphasizes peak quantitative performance, measured by Peak Signal-to-Noise Ratio (PSNR), without limitations on parameter count or computational overhead. By synthesizing contributions from 20 finalist teams out of 116 registrants, this report benchmarks the latest technical innovations and provides a comprehensive snapshot of the current state-of-the-art in unconstrained image restoration.

07.
arXiv (CS.AI) 2026-06-12

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

arXiv:2606.13604v1 Announce Type: new Abstract: Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeoff between delivery quality and batching efficiency. This interface enables offline policy learning under noisy, delayed, and coupled feedback while preserving production feasibility constraints and operational safeguards. We train a shared value function using centralized offline data and decentralized store-level execution, with Double Q-learning targets and a conservative regularizer to reduce out-of-distribution value overestimation. In a production switchback experiment, the offline-trained policy increases batching and reduces courier-side time costs without degrading customer-facing delivery quality. Results illustrate how world feedback from a live economic and logistics system can be used to safely adapt decision policies online.

08.
arXiv (CS.AI) 2026-06-16

A Multi-level Analysis of Factors Associated with Student Performance: A Machine Learning Approach to the SAEB Microdata

arXiv:2510.22266v3 Announce Type: replace-cross Abstract: Identifying the factors that influence student performance in basic education is a central challenge for formulating effective public policies in Brazil. This study introduces a multi-level machine learning approach to classify the proficiency of 9th-grade and high school students using microdata from the System of Assessment of Basic Education (SAEB). Our model uniquely integrates four data sources: student socioeconomic characteristics, teacher professional profiles, school indicators, and principal management profiles. A comparative analysis of four ensemble algorithms confirmed the superiority of a Random Forest model, which achieved 90.2% accuracy and an Area Under the Curve (AUC) of 96.7%. To move beyond prediction, we applied Explainable AI (XAI) using SHAP, which revealed that the school's average socioeconomic level is the most dominant predictor, demonstrating that systemic factors have a greater impact than individual characteristics in isolation. The primary conclusion is that academic performance is a systemic phenomenon deeply tied to the school's ecosystem. This study provides a data-driven, interpretable tool to inform policies aimed at promoting educational equity by addressing disparities between schools.

09.
arXiv (CS.AI) 2026-06-15

tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration

作者:

arXiv:2606.14445v1 Announce Type: cross Abstract: Existing multi-agent software development systems have proposed many forms of agent collaboration, including role-based collaboration and automated code review. However, many systems assume a common runtime, a central conversation server, or the same API family. Under these assumptions, LLM agents from different vendors cannot easily exchange messages directly from their own execution environments while dividing development and review work on a shared codebase. This paper presents tap, a file-based collaboration protocol that allows Claude (Anthropic) and Codex (OpenAI) to collaborate on one codebase without shared memory or an identical runtime. The core of tap is a file-first design that preserves markdown files with metadata as original messages, combines a file inspection path (file communication, Tier 1) with real-time notification paths for Claude and Codex (real-time communication, Tier 2), and isolates work through separate git worktrees. Even if real-time notification fails or a receiver restarts, the message file remains available and the same content can be inspected again. In a 27-day, 37-generation self-applied operation where tap was used to develop and review itself, we collected 209 tap-related pull requests and 717 operational artifacts. An analysis of 375 review artifacts showed that the share of reviews recording at least one defect or requested change was 69.8% for heterogeneous model pairs and 53.1% for homogeneous model pairs. These results show that tap, which combines file-based message preservation with real-time notification, operates in a real production repository, and that combining heterogeneous models and execution environments can broaden review perspectives. tap is distributed as the open-source npm package @hua-labs/tap (v0.5.2).

10.
bioRxiv (Bioinfo) 2026-06-14

Somatic variant detection in normal tissues from single-cell sequencing data

A crucial advantage of single-cell sequencing (SCS) is its ability to identify somatic variants in individual cells, enabling phylogenetic analysis of cellular populations within bulk tissues. While identifying somatic variants in tumor tissues via SCS has become a common practice, doing so in normal tissues remains challenging due to the rarity of somatic variants in normal cells. To evaluate the feasibility of somatic variant calling from widely available single-nucleus RNA-seq (snRNA-seq) and single-nucleus ATAC-seq (snATAC-seq) data, we profiled a Cell-line mix of six HapMap samples prepared by the SMaHT consortium using 10x Genomics 5' snRNA-seq (12k cells with 36k mean reads per cell) and snATAC-seq (11k cells with 14k median high-quality fragments per cell) for variant calling. PacBio long-read whole genome sequencing (WGS) data (109x) generated from individual cell lines were used as ground truth. Two computational tools, Monopogen and SComatic, were used for somatic variant calling from the SCS data. Monopogen achieved single nucleotide variant (SNV) detection accuracies of 93.30% in the snRNA-seq and 99.64% in the snATAC-seq data, both of which outperformed SComatic (74.35% and 94.29%, respectively). Monopogen also consistently detected somatic SNVs at cellular fractions as low as 0.5% (2.54% in snRNA and 0.81% in snATAC) in individual samples. Notably, snATAC-seq exhibited higher genomic coverage breadth and larger number of variants detected than snRNA-seq. While the SCS data have lower overall genome coverage than that of the bulk WGS, the single-cell level variant resolution allows Monopogen to assign variants to their cells of origin with over 80% accuracy in both RNA and ATAC modalities, thereby facilitating studies of clonal evolution and cell-type-specific mutagenesis. Other benchmarking methods were also evaluated (DeepVariant, Cellsnp-lite and Mutect2) for comparison. In conclusion, our study demonstrated the feasibility of performing reliable single-cell somatic mutation calling in a cell-line mixture and discussed the strengths and limitations of current computational methods when applied to normal tissues.

11.
arXiv (CS.AI) 2026-06-17

MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs

arXiv:2606.17118v1 Announce Type: cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE-MLLMs) offer remarkable performance but incur prohibitive GPU memory costs, making compression essential. Among PTQ methods, expert-level mixed-precision quantization has proven effective for MoE-LLMs, yet suffers notable degradation on MoE-MLLMs due to two overlooked biases in expert importance estimation. (1) At the cross-modal level, the numerical dominance of vision tokens causes expert selection frequency to be dominated by vision tokens, masking experts that are critical to the text modality; (2) at the intra-vision level, the large proportion of redundant vision tokens further skew frequency statistics, obscuring experts critical for informative visual content. To bridge gaps, we propose MODE, a modality-decomposed expert-level mixed-precision quantization framework for MoE-MLLMs that decomposes expert selection frequency by modality, filters redundant vision tokens to obtain denoised visual frequency, and further evaluates quantization sensitivity per modality as a complementary signal to frequency-based estimation. These signals are integrated into an Integer Linear Programming formulation to assign per-expert bit-widths under a given budget. Extensive experiments show that MODE is particularly well-suited for MoE-MLLMs, limiting average performance loss to within 2.9% at W3A16, with larger gains at the extreme 2-bit setting.

12.
bioRxiv (Bioinfo) 2026-06-11

Revealing trajectories of multi-modal voxel-level changes in neurodegenerative diseases using latent event mapping

Neurodegenerative diseases are driven by pathological mechanisms that can be indirectly measured in vivo using multi-modal neuroimaging. However, current computational methods that aim to reconstruct trajectories of voxel-level changes in the brain are either not computationally scalable or fully interpretable, limiting their ability to reveal associations between disease progression and underlying mechanisms. Here we introduce Latent Event Mapping (LEMING), a generative unsupervised modelling technique that learns a latent map of disease events along a common pseudo-timeline of events. We apply LEMING to amyloid PET and structural MRI data from the Alzheimer's Disease Neuroimaging Initiative to reveal the first voxel-level trajectories of events in Alzheimer's disease. Notably, we show how LEMING can provide new insights into progression-dependent disease mechanisms. We find that acetylcholine receptor density is significantly positively associated with both late-stage amyloid and atrophy events, suggesting that either these receptors are targeted later in disease progression, or that amyloid does not play an active role. This has strong implications for therapeutics that target acetylcholine receptors, particularly for early-stage intervention strategies.

13.
arXiv (CS.LG) 2026-06-18

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

arXiv:2606.18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most existing model merging approaches follow the Task Arithmetic paradigm, which decomposes fine-tuned weights into pre-trained parameters and task vectors, and performs merging exclusively in the task-vector space. The effectiveness of this paradigm implicitly relies on the assumption that task-specific knowledge is encoded solely within task vectors. We argue that this assumption generally does not hold due to the intrinsic task preferences of pre-trained models. Specifically, we identify Load-Bearing Wall (LBW) dimensions, namely some task-critical knowledge that remains embedded in the pre-trained weights rather than being fully transferred into task vectors. We characterize LBW dimensions from both scalar-weight and subspace perspectives, thereby covering the major paradigms of existing model merging methods. Our analysis reveals that, by ignoring LBW dimensions, task-vector-based approaches fail to fully resolve task conflicts and may inadvertently damage task-specific knowledge encoded in the pre-trained model, leading to degradation. To address this issue, we propose PACT, which preserves the anchored task-specific cores (i.e., LBW dimensions) within task vectors by aligning their orthogonal complements with the subspace of the pre-trained weights. These aligned subspace components are then removed from the task vectors before applying existing model merging algorithms. Furthermore, we develop an efficient variant based on randomized SVD to improve scalability. PACT can be seamlessly integrated with existing methods. Extensive experiments across multiple benchmarks demonstrate that PACT consistently enhances mainstream model merging approaches and establishes new state-of-the-art performance.

14.
arXiv (CS.CL) 2026-06-19

How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural

作者:

Transformer feed-forward networks (FFNs) are often treated as nonlinear stores of computation, yet how nonlinear a trained FFN block actually is has rarely been measured. We treat each FFN as a position-wise input-to-output map and split it into the exact least-squares linear approximation plus a residual. The held-out variance the closed-form linear map explains defines a block's linear recoverability (R^2_lin), an optimiser-free measure of its linearity. Across all twelve blocks of GPT-2, Pythia-160m, and llama-160m, R^2_lin is highly heterogeneous and non-monotone with depth, ranging from near-linear (>0.99) to strongly nonlinear (

15.
medRxiv (Medicine) 2026-06-19

The Impact of Pregnant Womens Dietary Behavior on the Physiological Adaptation Paradox and Maternal-Fetal Resource Conflict in Conflict Settings: A Predictive Analytical Study

This scientific study aims to assess the level of awareness, nutritional knowledge, and actual behavioral practices among pregnant women in the Capital District of Sanaa, Republic of Yemen, and to determine their impact on the health and clinical indicators of the mother and fetus under complex conflict conditions. The study employed a descriptive-analytical approach based on a simple random sample of 200 pregnant women attending government-run hospitals and specialized medical centers in the Capital District. Field data were collected during December 2025 using a structured and validated questionnaire consisting of 42 items measuring demographic variables, awareness, practices, barriers, and health outcomes. The results of the statistical analysis using SPSS software showed a high level of nutritional awareness (87%) and healthy dietary practices (80%) among the sample participants. Simple and multiple linear regression tests revealed a statistically significant effect of awareness and practices in explaining 20.2% of the variance in the health status of the mother and fetus (R{superscript 2}= 0.204, p < 0.001). The study demonstrated that actual behavioral practices have greater predictive power ({beta}=0.316, p=0.001) compared to theoretical cognitive awareness ({beta}=0.232, p=0.005) in determining clinical outcomes for the mother and fetus, highlighting the widening gap between knowledge and behavior under structural pressures. "Morning sickness" (80%) and the deterioration of "family economic status" (71%) emerged as the greatest physiological and material barriers to proper nutrition. With their inferential impact established as an extension of the maternal-fetal resource allocation conflict in a physiologically and economically challenging environment, the study also identified significant differences in nutritional behavior and health outcomes in favor of housewives and mothers who are more educated and have higher incomes, while no significant differences were recorded attributable to obstetric variables such as stage or order of pregnancy. The study offers a unique theoretical and practical contribution by formulating an integrated causal model that demonstrates that the fetus acts as a biological drain on the mothers cellular and mineral reserves in a war environment, which necessitates directing antenatal care and support programs toward effective behavioral empowerment and nutritional support to overcome the structural and material barriers faced by pregnant women.

16.
arXiv (CS.CV) 2026-06-16

RefGC-SR$^2$: Reference-guided Generated Content Super-Resolution and Refinement

Reference-guided generation (e.g., object compositing, customization) has progressed rapidly, yet current pipelines share a fundamental limitation: the object-centric high-resolution reference image (HRRI) provided by users is downsampled to a fixed low-resolution (LR) before being fed into the model, so the fine-grained details are discarded before the output is even produced. In addition, the generation step then introduces its own artifacts (e.g., identity distortion) on top of this loss. Existing reference-guided generated content refinement (RefGCR) methods can correct some of these artifacts but still operate in the LR domain; reference-guided super-resolution (RefSR) methods recover resolution but assume natural-image degradations and ignore the artifact distribution of generative pipelines. To address both gaps in a single formulation, we introduce a new task: reference-guided generated content super-resolution-refinement (RefGC-SR$^2$), where the original HRRI is reused at the post-processing stage to recover lost details, refine generative artifacts, and upscale the output simultaneously. We construct the first real-world triplet data generation pipeline for this RefGC-SR$^2$ task, training a diptych-conditioned generator to synthesize paired low-quality anchors that public pretrained models cannot provide. We further present a frequency-aware diffusion transformer model for RefGC-SR$^2$ that selectively injects fine details from the HRRI while removing generative artifacts. Extensive experiments demonstrate that our RefGC-SR$^2$ model successfully (i) refines the object identity faithfully with respect to the reference, and (ii) recovers high-resolution details, so that the final result is significantly higher quality and practically more usable compared to existing RefGCR and RefSR baselines.

17.
arXiv (quant-ph) 2026-06-19

Battery-Explicit Thermodynamic Witnesses of Bell Post-Quantumness

arXiv:2605.09149v3 Announce Type: replace Abstract: We introduce a battery-explicit thermodynamic witness of post-quantum Bell correlations. In each round, a single supplied excitation is routed into an explicit two-level battery if and only if a Bell-game condition is satisfied. The routing operation is implemented by an energy-preserving controlled SWAP, with all logical control registers taken to be degenerate. Thus the correlation resource does not create energy; it only determines the probability that the supplied excitation reaches the battery. The construction is first formulated for finite two-player XOR games. For any such game, the mean battery charge is exactly the game success probability multiplied by the battery gap. Optimizing over local, quantum, or nonsignalling behaviours therefore turns the corresponding game values into local, quantum, or nonsignalling thermodynamic ceilings. For the CHSH game, Tsirelson's bound becomes a strict quantum ceiling on the mean battery charge, while a PR-box behaviour reaches the single-excitation cap. The witness is trusted-module rather than device-independent: it assumes calibrated Hamiltonians, correct classical wiring, and a trusted energy-preserving battery module. We also discuss a reversible-controller implementation, finite-statistics certification from work data, robustness to imperfect battery readout, and cyclic bookkeeping showing that no positive net work is obtained once fuel restoration and memory erasure are included.

18.
arXiv (CS.LG) 2026-06-16

Diffusion Models for Adaptive Sequential Data Generation

arXiv:2606.06007v2 Announce Type: replace Abstract: Generating realistic synthetic sequential data is critical in real-world applications across operations research, finance, healthcare, energy systems, and scientific computing, where time-indexed observations are used for prediction, simulation, risk assessment, and data-driven decision-making. While diffusion models have achieved remarkable success in generating static data, their direct extensions to sequential settings often fail to capture temporal dependence and information structure. Designing diffusion models that can simulate sequential data in an adapted manner, and hence without anticipation of future information, therefore remains an open challenge. In this work, we propose a sequential forward-backward diffusion framework for adapted time series generation. Our approach progressively injects and removes noise along the sequence, conditioning on the previously generated history to ensure adaptiveness. A novel score-matching objective is introduced for efficient parallel training. We derive rigorous statistical guarantees under a generic framework, then establish score approximation, score estimation, and distribution estimation results with ReLU networks serving as a concrete instance. Empirically, we validate our method on synthetic data, including ARMA models and Gaussian processes, and demonstrate its effectiveness in constructing mean-variance optimal portfolios.

19.
arXiv (CS.CV) 2026-06-18

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightweight semantic head and a tree-focused cross-attention mask decoder. Semantic predictions restrict instance decoding to tree-class voxels, while instance-aware query initialization, one-to-many seed supervision, and asymmetric mask scoring improve separation in dense and structurally complex stands. We further introduce FOR-instance v3, an expanded benchmark comprising 427 scenes and 26,496 annotated trees across diverse biomes, forest structures, and LiDAR platforms. On the FOR-instanceV2 test split, SegmentAnyTreeV2 achieves 90.5% precision, 80.2% recall, 85.0% F1, 90.7% coverage, and 87.6% semantic mIoU, outperforming previous learning-based methods in both instance detection and mask completeness. Zero-shot evaluation on independent sites further demonstrates strong cross-domain generalization.

20.
arXiv (CS.AI) 2026-06-17

Beyond the Sampled Token: Preserving Candidate Support in RLVR

arXiv:2510.14807v3 Announce Type: replace Abstract: We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the candidate distribution for next-token prediction. We formally show that as probability concentrates on the top-$1$ candidate, the expected number of distinct responses collapses to one regardless of the sampling budget $K$. This theoretical implication is further verified by our empirical tracking of top-$N$ candidate probabilities during training, where the top-$1$ candidate progressively dominates while plausible alternatives are suppressed. These findings suggest a key desideratum for effective exploration: preserving non-negligible probability mass on the top-$N$ candidates. To this end, we propose Candidate-aware Support Preservation (CaSP), with two complementary designs. Specifically, CaSP redistributes positive gradients among top-$N$ candidates for correct responses, and applies a stronger penalty to the top-$1$ candidate for incorrect responses. Unlike many exploration-oriented methods that improve pass@$K$ at the cost of pass@1, CaSP improves pass@$K$ across the full $K$ spectrum. These gains generalize to 6 math, 2 logical-reasoning, and 2 coding benchmarks, and scales to 32B-parameter models and sampling budgets up to $K=1024$, positioning it as a principled, candidate-level approach for RLVR exploration.

21.
arXiv (CS.AI) 2026-06-18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

22.
medRxiv (Medicine) 2026-06-12

Integrative Mechanisms of Early Clinical and Research Training (ECART) in Orthopaedic Medical Education: A Qualitative Single-Case Study

Background: Early clinical exposure and student participation in research are important components of medical training. They may support learning motivation, evidence literacy, and self-directed learning. In many programmes, however, clinical training and research training remain separated. Few studies have explained, within a real teaching team, how learners turn clinical phenomena into researchable questions and how research participation can reshape their clinical understanding. Early Clinical and Research Training (ECART) is a clinical-research integration approach developed by an orthopaedic team at the Second Hospital of Shandong University. Methods: We conducted a theory-informed, interpretivist qualitative single-case study. The case was an orthopaedic clinical-research team at the Second Hospital of Shandong University. Participants included medical undergraduates, academic degree graduate students, professional degree graduate students, clinical teachers, and research platform leads. We used purposive sampling with maximum variation. Data were collected through semi-structured interviews and de-identified teaching documents. Data were analysed using the framework method and were interpreted with a Context-Activity-Mechanism-Outcome (CAMO) logic. Results: The analysis showed that ECART was not simply early entry into the clinic or early entry into the laboratory. It was a team-based learning process centred on real medical problems. Four themes were identified. First, early clinical exposure helped learners make real problems visible and nameable, rather than merely increasing exposure. Second, clinical-research connection followed different pathways. Professional degree graduate students often started from clinical uncertainties in residency training and case management, and moved toward evidence-informed small projects. Academic degree graduate students often started from literature gaps, experimental findings, and mechanistic hypotheses, and then used clinical feedback to calibrate meaning. Third, research training, through literature reading, group meetings, experimental design, data review, and mentor questioning, helped learners move from completing tasks to explaining problems. Fourth, sustained ECART depended on a tiered team ecology formed by clinical teachers, research mentors, research platforms, and senior peers. Based on these findings, we refined the ECART programme theory: real medical problems are translated through explanation, searching, experimentalisation, and feedback-based reinterpretation into research questions that learners can understand, discuss, and test. This process supports problem formation, evidence awareness, mechanistic reasoning, translational judgement, and career clarification. Conclusion: ECART is best understood as a clinical-research integrated learning ecology that emerges from real team practice, rather than as a fixed standardised course. Its educational value lies in a recurring cycle of real problems, research translation, multi-source feedback, and clinical reinterpretation. This framework may inform the design, evaluation, and contextual adaptation of clinical-research integration pathways in medical education.

24.
arXiv (CS.AI) 2026-06-16

ArtBoost: Synthetic Articulatory Data Augmentation for Acoustic-to-Articulatory Inversion

arXiv:2606.16327v1 Announce Type: cross Abstract: Recent acoustic-to-articulatory inversion (AAI) models rely on electromagnetic articulography (EMA) data, which are costly and limited in scale. To address this limitation, we propose ArtBoost, a novel data augmentation strategy that leverages large-scale speech–mesh datasets originally developed for speech-driven 3D facial animation to improve AAI under limited EMA supervision. ArtBoost extracts pseudo articulatory trajectories from visible facial anchors and uses them for pre-training before fine-tuning on real EMA data. Experiments show consistent improvements in PCC and RMSE. Trajectory analyses confirm that the pseudo articulatory signals reflect physically meaningful visible articulatory dynamics. Additional evaluations across different AAI architectures demonstrate stable performance gains, indicating that ArtBoost can be integrated into diverse AAI models. These results suggest that speech–mesh data provide an effective and scalable source of articulatory supervision for AAI. Project page: https://cau-irislab.github.io/Interspeech26-ArtBoost/

25.
arXiv (CS.CL) 2026-06-17

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teacher concentrates it on the teacher's sharpest modes, hurting generalization on benchmark families beyond the training corpus. Reinforcement learning (RL) avoids logit imitation by training on the student's own rollouts. However, on questions where every rollout fails-yielding zero advantage and being silently discarded-injecting a stronger teacher's response into the policy gradient breaks the on-policy assumption and induces drift. We introduce Zone of Proximal Policy Optimization (ZPPO), inspired by Vygotsky's zone of proximal development, which keeps the teacher inside the prompt rather than the policy gradient. On hard questions, ZPPO constructs two reformulated prompts: a Binary Candidate-included Question (BCQ) pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate, and a Negative Candidate-included Question (NCQ) aggregates the student's wrong rollouts into a single prompt to surface their shared failure modes. A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted under finite capacity, amplifying BCQ and NCQ inside the student's current zone of proximal development. On the Qwen3.5 family at four student scales (0.8B-9B) with a 27B teacher, post-trained as vision-language models and evaluated on a 31-benchmark suite (16 VLM, 10 LLM, 5 Video), ZPPO outperforms off/on-policy distillation and GRPO, with the largest gains at the smallest scale.