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.

01.
arXiv (CS.CV) 2026-06-11

DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model

Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate. This is misaligned with physical interaction, where a high-frequency modality changes at hundreds of hertz, vision evolves more slowly, and language stays constant across an episode. A synchronous VLA oversamples slow modalities, undersamples fast ones, and caps action generation at the lowest effective frequency. We hypothesize that decoupling temporal processing per modality, letting each update and retain information at its own sensor rate, yields stronger representations and more robust control. We present DAM-VLA, which maintains per-modality latent buffers refreshed at sensor rates and read continuously by the action head, integrating new high-frequency modalities through gated cross-attention that leaves the pretrained backbone intact. Across seven contact-rich real-world manipulation tasks, DAM-VLA more than doubles the average success rate of the strongest synchronous baseline (95.2\% vs.\ 40.95\%) while sustaining smooth, reactive 100\,Hz control. Project website: \href{https://intuitive-robots.github.io/DAM-VLA/}{intuitive-robots.github.io/DAM-VLA/}

02.
arXiv (quant-ph) 2026-06-15

Quantum Entanglement of Bethe States

arXiv:2606.14140v1 Announce Type: cross Abstract: We investigate the quantum entanglement of Bethe states across a family of integrable spin chains, including the XXX$_{\frac{1}{2}}$ model, its higher-spin generalizations (XXX$_s$), and the non-compact $SL(2,\mathbb{R})$ chain. For on-shell eigenstates, we perform a comprehensive scan of the bipartite entanglement entropy across the entire spectrum of finite chains with periodic boundary conditions, and identify the Bethe solutions that minimize and maximize the entanglement. These extremal solutions follow systematic, spin-dependent patterns in the Bethe quantum numbers. In the XXX$_{\frac{1}{2}}$ spin chain, for the antiferromagnetic chain, the state with minimal entropy always coincides with the lowest-energy state (the ground state) within a given fixed-magnon sector. For the higher-spin XXX$_s$ model, however, the lowest-entropy state is not always identical to the ground state, and can even be the state of highest energy. By contrast, the Bethe roots that maximize entropy exhibit considerably more intricate structure. Our analysis further reveals how special Bethe root configurations, such as singular and strange solutions, affect entanglement, and it uncovers characteristic entanglement features in the non-compact $SL(2,\mathbb{R})$ chain that are absent from compact spin chains. For off-shell Bethe states, we develop an optimization algorithm that extremizes the entanglement entropy over rapidity distributions, enabling us to explore the maximum entanglement achievable by a Bethe state without imposing the Bethe ansatz equations.

03.
medRxiv (Medicine) 2026-06-22

The circulating blood proteome of childhood acute leukemia

The circulating blood proteome provides a systemic readout of disease biology and holds promise for advancing diagnostics and disease monitoring in pediatric leukemia. Here, we profiled 3072 proteins in diagnostic serum from 54 children with acute lymphoblastic leukemia (ALL), 21 with acute myeloid leukemia (AML), and 12 healthy controls using the Olink Proximity Extension Assay. We observed profound alterations in circulating protein levels in leukemia patients compared with controls and identified immunophenotype-specific proteins, including SIGLEC15 in B-cell precursor ALL (BCP-ALL), NOTCH1 in T-ALL, and CEBPA in AML, all which remained high even in patients with low (

04.
arXiv (CS.CV) 2026-06-15

Point Cloud Upsampling through Patch-based Frequency Superposition

In recent years, neural networks have become the dominant models in most point cloud upsampling methods. Although these approaches are achieving good results, they do have drawbacks, such as a lack of interpretability and data dependency. Moreover, they have to be trained on a dataset that is similar to the test data in order to perform well. To avoid these disadvantages, we propose Point Cloud Upsampling through Patch-based Frequency Superposition (PUtPFS), an optimization-based approach that selects subsets of points and estimates the surface of this set through superpositioning spatial frequencies. Then, new points are placed on this surface. By successively selecting points in the least dense regions of the point cloud, a uniform upsampling can be reached. With this method, we surpass the current best upsampling results in the commonly considered point-to-surface distance. Furthermore, we achieve the best Chamfer and Hausdorff distance among the optimization-based approaches. As an additional advantage, our method does not need any training data and is mathematically interpretable.

05.
arXiv (CS.LG) 2026-06-16

A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning

arXiv:2606.08583v2 Announce Type: replace Abstract: Deep learning on physiological time series is interpreted through domain-specific features – oscillatory rhythms in EEG, morphological complexes in ECG – yet these signals sit atop a broadband aperiodic 1/f-like envelope that covaries with arousal, age, and pathology. We introduce a spectral audit framework combining aperiodic/periodic decomposition, phase-preserving Fourier interventions, sham controls, and simulation validation. Aperiodic reliance was task-dependent and architecture-general: across six neural architectures, flattening drops exceeded 0.42 balanced-accuracy points for sleep-wake classification, reached 0.07-0.13 for clinical abnormality detection, and remained minimal for motor imagery. Six of seven EEG foundation models showed FDR-significant aperiodic reliance on clinical EEG; age/sex and recording-era controls reduced but did not eliminate the effect. Applying the audit to PTB-XL ECG revealed neural drops of 0.32–0.36 persisting after demographic matching, confirming this confound class extends beyond EEG. Aperiodic controls should become standard for interpretable physiological time-series deep learning.

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

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis

arXiv:2606.13220v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The approach is implemented through a Solution Investigator Agent, which estimates the ambiguity of an initial problem description, generates candidate hypotheses, asks targeted clarification questions, and updates hypothesis probabilities after each answer. Rather than producing an immediate response, the agent continues the investigation until the evidence makes one candidate explanation stronger than the alternatives. To evaluate the approach, we build a benchmark from solved technical forum threads in mechanical, electrical, and hydraulic domains. We use a three-agent evaluation pipeline in which a Problem-Solution Extractor Agent converts solved threads into structured cases, a Ground-Truth Evaluator Agent simulates the user while hiding the known solution, and the tested assistant attempts to recover the solution through dialogue. The experiments compare standard assistants, reasoning-oriented LLMs, and the proposed investigator-based model across LLM backbones. In addition to diagnostic accuracy, we analyze how standard assistants follow misleading user hypotheses in diagnostic cases. The results show that the proposed approach identifies the problem more accurately than direct prompting and reasoning-only baselines, while its evidence-first protocol helps reduce user-induced conversational bias.

07.
arXiv (CS.LG) 2026-06-16

Overcoming Rank Collapse in Feedback Alignment

arXiv:2606.11123v2 Announce Type: replace Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation. Interestingly, when training a network with fixed random feedback weights to circumvent this issue, learning aligns the forward weights with the feedback weights, leading the backpropagated error signal to become an approximation of the standard gradient used by BP. This process, called Feedback Alignment (FA), occurs in MLPs and very shallow CNNs but does not scale well to deeper architectures. In this work, we first investigated differences between BP and FA models, trained on CIFAR10, specifically focusing on the effective rank of the signal. We found that the FA error has a considerably lower rank and hence is constrained to a lower-dimensional subspace compared to BP, limiting exploration of the parameter space. Motivated by this observation, we evaluated two mechanisms for increasing the effective dimensionality of FA: Muon, an optimiser that orthogonalises weight updates; and hidden activity normalisation, which promotes activation orthogonality. Across larger architectures and benchmarks, we find that these methods consistently improve over FA baselines, for example, on CIFAR100 with a Resnet-18, accuracy increases by 9 percentage points. Our results identify low-dimensional gradient dynamics as a key obstacle to scaling FA and suggest that inducing higher-dimensional update geometry is a promising route toward scaling alternatives to backpropagation.

08.
arXiv (CS.AI) 2026-06-12

Interaction-Centered Intelligence: Toward an Interaction-Based Theory of Human-AI Co-Creation

arXiv:2606.00807v2 Announce Type: replace Abstract: Traditional artificial intelligence has largely conceptualized intelligence as isolated computation occurring within bounded agents. Across classical AI, machine learning, and many generative systems, the dominant unit of analysis remains the individual model or autonomous system evaluated through outputs, benchmarks, prediction accuracy, or optimization performance. While these approaches have produced major advances, they often under-theorize the role of interaction in the emergence of intelligence, creativity, meaning, and adaptive behavior. This paper proposes interaction as the primary unit of analysis for co-creative AI and interaction-centered intelligence more broadly. Drawing from distributed cognition, embodied cognition, enaction, participatory sense-making, human-computer interaction, and computational creativity, the paper traces a historical progression toward increasingly relational accounts of intelligence. Building upon prior work in Creative Sense-Making, quantified co-creation, and co-creative systems such as the Drawing Apprentice and AI Drawing Partner, it argues that intelligence emerges through evolving interaction dynamics among agents, environments, and socio-technical systems rather than solely through internal computation. The paper introduces Interaction-Centered Intelligence as a framework for understanding human-AI co-creation, collaborative emergence, adaptive participation, and interactional dynamics. Rather than evaluating intelligence solely through generated outputs, the framework emphasizes interaction trajectories, coordination patterns, participatory engagement, adaptive regulation, and interactional drift unfolding through time. Implications for explainable co-creative AI, hybrid intelligence, enactive AI, and future human-AI systems are discussed.

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

AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization

Large reasoning models typically follow a read-then-think paradigm: they observe the complete input, reason over a static context, and then produce the answer. Yet many real-world scenarios are inherently dynamic, such as audio and video stream, where information arrives as a continuous stream and models must reason, update, and respond under partial observations. Recent streaming reasoning methods allow models to think while reading, but they largely rely on supervised imitation of pre-constructed trajectories, which limits their flexibility. In this paper, we propose AdaSR, an adaptive streaming reasoning framework that enables models to reason during input streaming and perform final deliberation once the stream is complete, learning when to think, and how much computation to allocate across different stages. To optimize this hierarchical reasoning process, we introduce Hierarchical Relative Policy Optimization (HRPO), which decomposes policy optimization into streaming reasoning and deep reasoning phases, providing more fine-grained advantage assignment instead of uniformly distributing a single sequence-level advantage over all tokens. HRPO integrates format, accuracy, and adaptive thinking rewards to enforce valid reasoning protocols, preserve final task performance, and encourage latency-aware computation allocation. Experiments show that AdaSR achieves a better balance among reasoning accuracy, computational efficiency, and streaming latency compared with supervised fine-tuning baseline. We release our code at https://github.com/EIT-NLP/StreamingLLM/tree/main/AdaSR.

10.
medRxiv (Medicine) 2026-06-22

Clinical-grade Cuffless Blood Pressure Monitoring via Deep-tissue Diffuse Speckle Pulsatile Flowmetry

Blood pressure (BP) is a vital sign which is measured to diagnose and manage hypertension. However, current methods to measure BP use inflatable cuffs which cause discomfort and limit the frequency at which measurements can be made, or intra-arterial catheters which are invasive and pose infection risks. Here, we propose and evaluate the use of Diffuse Speckle Pulsatile Flowmetry (DSPF) as a cuffless BP measurement method to address these limitations. DSPF is a laser speckle-based technique which simultaneously records blood flow rate and blood volume (i.e. photoplethysmography or PPG) signals from relatively deep vascular tissue. Using information from these signals, we studied DSPFs effectiveness in measuring systolic BP (SBP) and diastolic BP (DBP) through an outpatient study in which 133 patients were recruited, and in measuring beat-to-beat BP waveforms through an inpatient study in which two patients were recruited. In the outpatient study, the DSPF method was able to achieve mean absolute errors (MAEs) of 4.17 mmHg and 2.42 mmHg for SBP and DBP respectively compared to conventional cuff-based methods. It was also able to fulfil the requirements of the AAMI/ESH/ISO 81060-2:2018 standard for BP measurement devices and attain an "A" grade according to the British Hypertension Society grading scheme. For the inpatient study, it produced BP waveforms which had MAEs of 2.35 mmHg and 3.06 mmHg compared to arterial-line measurements for the two patients, respectively. Compared to PPG which has been studied more extensively as a cuffless BP measurement method, we found through ablation studies that DSPF was able to reach significantly lower MAEs and hence better accuracies. DSPF augments the performance of PPG-only methods by leveraging additional information from the blood flow rate signal, and we therefore find it to be a superior cuffless BP measurement method which can potentially be used in outpatient, inpatient, and remote settings.

11.
bioRxiv (Bioinfo) 2026-06-17

Beyond phylogeny: Genome-wide DNA sequence patterns suggest DNA physical properties associated with thermal adaptation in extremophile microbes

Authors:

Temperature is a fundamental constraint on biological systems, yet how it is reflected in genome sequence organization remains unclear. Here, we show that genome-wide distributions of short DNA sequences contain a robust signal of thermal adaptation that is largely independent of phylogeny. Using Structural Topic Modelling (STM), a machine-learning approach for identifying groups of co-occurring sequence motifs, we analyze canonical 6-mer and 9-mer frequency profiles of bacterial and archaeal genome proxies (randomly sampled genomic regions) and identify motif families systematically associated with thermophiles and psychrophiles. In bacterial thermophiles, the identified motif families are dominated by highly specific, overrepresented and co-occurring C- and G-stacked hexamers, and a distinct family of CG-periodic hexamers recurring across multiple temperature comparisons. In contrast, bacterial psychrophile-associated motifs are dominated by low-complexity A-, T-, and AT-run hexamers. Thermophilic archaea generally exhibit a distinct CTAG-centred hexamer family, suggesting that different domains may adapt to similar environmental constraints through different sequence-level solutions. However, this domain-level contrast is not absolute: in a targeted analysis of two thermophilic bacterium–archaeon pairs, we find unusually similar frequencies of all the STM-identified thermophile-associated hexamer families, suggesting that shared high-temperature environments can, in specific cases, partially override phylogenetic divergence. Notably, the identified motif families constitute only a small and highly selective subset of the vast space of possible G+C-rich or A+T-rich sequences. This indicates that thermal adaptation is associated with specific sequence architectures rather than broad shifts in nucleotide composition. Accordingly, the observed signal cannot be explained by overall base composition alone, but instead arises from structured combinations and positional arrangements of nucleotides within short sequence contexts. Related motif families are recovered at both k=6 and k=9, indicating that the signal reflects systematic shifts in genome-wide sequence organization rather than isolated sequence motifs. These patterns are consistent with known sequence-dependent DNA physical properties documented in biochemical and biophysical studies, including differences in base-stacking interactions and conformational flexibility. Together, our results suggest that genome-wide sequence organization reflects sequence-dependent DNA physical properties associated with thermal adaptation, revealing a previously underappreciated physical layer of genomic information beyond phylogenetic history.

12.
arXiv (CS.AI) 2026-06-16

Can Artificial Intelligence Accelerate Technological Progress? Researchers' Perspectives on AI in Manufacturing and Materials Science

arXiv:2511.14007v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) raises expectations of substantial increases in rates of technological progress, but such anticipations are often not connected to detailed ground-level studies of AI use in innovation processes. Accordingly, it remains unclear how and to what extent AI can accelerate innovation. To help to fill this gap, we explore and assess results from 32 interviews with U.S.-based academic manufacturing and materials sciences researchers experienced with AI and machine learning (ML) techniques. We found that AI was primarily used for modeling of materials and manufacturing processes, facilitating cheaper and more rapid search of design spaces for materials and manufacturing processes alike. Benefits included cost, time, and computation savings in technology development. However, AI/ML tools were unreliable outside design spaces for which dense data were already available; they required skilled and judicious application in tandem with older research techniques; and concerns were raised about the potential to detrimentally circumvent opportunities for disruptive theoretical advancement. Based on these results, we suggest there is reason for optimism about acceleration in sustaining innovations through the use of AI/ML; but that support for conventional empirical, computational, and theoretical research is required to maintain the likelihood of further disruptive advances in manufacturing and materials.

13.
arXiv (CS.AI) 2026-06-16

Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving

arXiv:2603.18897v2 Announce Type: replace-cross Abstract: LLM-powered agents execute tasks through a sequential loop of model generation and tool execution. Today's serving systems serialize this loop, leaving tool latency exposed on the task critical path. This paper presents PASTE, a tool-aware agent-serving system that predicts concrete future tool invocations from recurring agent patterns and executes them speculatively while the LLM is still generating. PASTE isolates speculative results until confirmed by the LLM and jointly schedules tool execution and returning LLM sessions to avoid shifting bottlenecks to the GPU. Across deep research, coding, and scientific-agent workloads, PASTE reduces average task completion time by 43.5% and lowers observed tool latency by 1.8x.

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

Spectral Retrieval-Augmented Time-Series Forecasting

arXiv:2606.19412v1 Announce Type: new Abstract: Time series forecasting leverages historical patterns to predict future values, but traditional methods face challenges when dealing with complex, non-stationary patterns that are difficult to memorize during training. Retrieval-augmented approaches have emerged as promising solutions by retrieving similar historical patterns to enhance predictions. However, existing retrieval methods suffer from two fundamental limitations: spectral blindness, which overlooks critical frequency-domain characteristics that capture underlying periodic structures, and temporal recency, which treats all historical data equally without emphasizing recent, more relevant patterns. In this paper, we propose SpecReTF, a novel retrieval method that addresses these issues by converting time series into windowed frequency representations, measuring similarity with a combined metric that captures both amplitude and phase information. To balance recency and historical context, we apply an exponential moving average weighting scheme that emphasizes recent windows. Extensive experiments on benchmark datasets demonstrate that SpecReTF outperforms time-domain retrieval methods, achieving superior forecasting accuracy across diverse, non-stationary time series.

15.
Nature (Science) 2026-06-12

‘Student Geng’ ignites research-integrity scandal in China after calling out senior academics<b> </b>

Authors:

Video blogger’s viral accusations of data manipulation in Nature journals have sparked intense debate and speedy institutional investigations. Video blogger’s viral accusations of data manipulation in Nature journals have sparked intense debate and speedy institutional investigations.

16.
arXiv (CS.AI) 2026-06-15

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties

arXiv:2606.14240v1 Announce Type: new Abstract: Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and increasingly critical for Large Language Models (LLMs). However, existing affordance benchmarks largely expose explicit object identities in the evaluation setup, allowing models to rely on memorized object-affordance mappings rather than reasoning over physical properties. To address this gap, we introduce Affordance20Q, a novel affordance reasoning benchmark formulated as a 20-Questions game without exposing the object's identity. In each game, the model identifies a hidden object's affordance from a candidate set by asking yes/no questions about its physical properties. Affordance20Q comprises 1,009 games over 454 objects and 59 affordances, all manually filtered, refined, and annotated. We conduct comprehensive experiments with 15 state-of-the-art LLMs and find a substantial gap (~20 points) compared to human performance. A KL-based information-gain (IG) analysis further shows that models fail to ask discriminating questions as the game progresses. To close the gap, we develop KB-Anchored Rule Induction (KARI), a pipeline based on LLMs that generates affordance rules grounded in evidence from knowledge bases (KBs). KARI improves open-source LLMs by up to 15.2 points, while the limited coverage of KBs hinders further gains. We release all our code and data at https://github.com/1171-jpg/Affordance20Q.git

17.
arXiv (CS.LG) 2026-06-16

Photon: Federated LLM Pre-Training

arXiv:2411.02908v2 Announce Type: replace Abstract: Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training. Low-bandwidth methods like federated learning (FL) could enable collaborative training of larger models across weakly-connected GPUs if they can effectively be used for pre-training. To achieve this, we introduce Photon, the first complete system for federated end-to-end LLM training, leveraging cross-silo FL for global-scale training with minimal communication overheads. Using Photon, we train the first federated family of decoder-only LLMs from scratch. We show that: (1) Photon can train model sizes up to 7B in a federated fashion while reaching an even better perplexity than centralized pre-training; (2) Photon model training time decreases with available compute, achieving a similar compute-time trade-off to centralized; and (3) Photon outperforms the wall-time of baseline distributed training methods by 35% via communicating 64x-512xless. Our proposal is robust to data heterogeneity and converges twice as fast as previous methods like DiLoCo. This surprising data efficiency stems from a unique approach combining small client batch sizes with extremely high learning rates, enabled by federated averaging's robustness to hyperparameters. Photon thus represents the first economical system for global internet-wide LLM pre-training.

18.
PLOS Medicine 2026-06-01

Prenatal exposure to asthma medications and risk of neurodevelopmental disorders and educational difficulties: A systematic review and meta-analysis

by Lama A. Shakhshir, Alexia Karain, Jill P. Pell, Claire E. Hastie, Scott M. Nelson, Michael Fleming Background Since asthma exacerbations during pregnancy risk maternal and fetal health, continued medication is important. However, some studies have reported adverse neurodevelopmental outcomes following prenatal exposure to asthma medication. Therefore, this systematic review aimed to collate the existing evidence on the associations between prenatal exposure to asthma medication and neurodevelopmental and educational outcomes. Methods and findings A systematic review was conducted in accordance with PRISMA guidelines and the PECO framework. PubMed, Medline and Embase databases were searched for studies investigating prenatal exposure to one or more asthma medication and neurodevelopmental or educational outcomes published, in English, between January 2003 and September 2024, and updated in November 2025. Studies of asthma medication used for other indications were excluded. Study quality was assessed using the Newcastle-Ottawa scale. Random-effects meta-analyses were conducted where appropriate and heterogeneity was evaluated using Cochran’s Q and I2 tests.Of 16,824 studies identified by the initial search, seven were eligible for inclusion. All investigated beta-2-adrenergic agonists (B2AA), with one including B2AA as mono- and polytherapy—and one study also investigated inhaled corticosteroids (ICS) exposure. Two reported associations with autism spectrum disorder (ASD) and one with attention-deficit hyperactivity disorder (ADHD). An updated search identified one additional eligible study, which examined both ADHD and ASD, as well as other neurodevelopmental disorders. The included eight studies (n = 3,867,170 participants) comprised cohort (n = 5) and case-control (n = 3) designs and reported inconsistent results. Meta-analysis of three studies (n = 1,380,871) indicated significant associations with ASD for exposure to B2AA both preconception (aOR 1.34, 95% CI [1.19,1.52]) and during pregnancy (aOR 1.29, 95% CI [1.16,1.42]). Heterogeneity was low, with no evidence of significant publication bias. Limitations of the included studies comprised residual confounding and exposure misclassification. Additionally, studies included in the meta-analysis were few in number and did not adequately distinguish between medication effects and underlying maternal asthma. Conclusion Meta-analysis suggested an association between prenatal exposure to B2AA and ASD. An association with ADHD, reported in a single study, requires corroboration. To date, based on our search strategy, no association has been reported with communication skills, motor skills, problem-solving and personal-social skills, or cerebral palsy.

19.
arXiv (CS.LG) 2026-06-19

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

arXiv:2605.05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

20.
arXiv (CS.CV) 2026-06-18

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-$\lambda$ Mix Interaction ($L\lambda MI$) block. Comprising Local-$\lambda$ and Interactive-$\lambda$ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a $>15\times$ acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.

21.
arXiv (CS.AI) 2026-06-11

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

arXiv:2606.12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and behaviors. However, as models become increasingly evaluation and training aware, they may be motivated to resist training when the perceived objective conflicts with their current values, undermining developers' ability to detect misalignment and correct model behavior through further training. In this paper, we demonstrate generalization hacking, in which a model collects reward during RL while preventing the rewarded behavior from generalizing. We construct a model organism on Qwen3-235B-A22B, finetuning on synthetic documents describing training awareness and self-inoculation, a novel mechanism in which the model frames compliance as context-specific in its chain of thought, without demonstrating or instructing either behavior. The model organism achieves train-time harmfulness comparable to controls while maintaining a persistent ${\sim}15$ percentage point compliance gap across 700 steps of RL. Additionally, a control organism trained only on training awareness documents independently discovers inoculation-like reasoning under RL pressure, developing its own compliance gap despite never being exposed to the concept. Because the generalization-hacking organism receives high reward throughout, standard training metrics provide no signal that generalization has failed. Our results constitute the first demonstration that a model can actively resist RL behavioral modification while maintaining high reward, suggesting that as models become more capable and training-aware, they may be able to undermine the training process itself.

22.
arXiv (CS.AI) 2026-06-18

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arXiv:2606.19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69–77\% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.

23.
arXiv (CS.CV) 2026-06-11

Multi-View In-Cabin Monitoring System for Public Transport Vehicles

We introduce a multi-view in-cabin monitoring dataset for public transportation with synchronized RGB and depth images from four inward-facing cameras and a rotating LiDAR covering the vehicle interior of a digitalized and partly automated German city bus. The dataset contains 9.136 synchronized samples with annotations and is accompanied by a calibration and pseudo-labeling pipeline that generates 3D human pose estimates and oriented 3D bounding boxes for occupants. We further provide a nuScenes-format conversion and benchmark representative multi-view 3D detection models (e.g., Lift-Splat-Shoot and BEVFusion), supporting comparative evaluation and small-scale training of multi-view in-cabin perception models. The dataset and tools are available at https://github.com/EvgenyGorelik/multiview_incabin_dataset.

24.
arXiv (CS.CV) 2026-06-19

Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance

With the recent advent of image generative models, synthetic data are increasingly being used to supplement limited real datasets for training computer vision models. However, not all synthetic datasets improve performance equally, and their effectiveness can only be assessed by training a downstream model, which is computationally expensive and time-consuming. This problem is pronounced in the task of object detection, where the required annotations are much more dense due to bounding boxes. In this paper, we propose a pre-computable metric family, dubbed Conditional-Composition Domain Match (CCDM), which serves as a proxy for the relative utility of candidate synthetic training sets for downstream detection. Experiments on the VisDrone-DET dataset show that the CCDM metric families achieve a Spearman correlation of 1.0 with the downstream performance of YOLOv8, clearly outperforming existing metrics for synthetic image evaluation.

25.
arXiv (CS.LG) 2026-06-16

Task-Error Residual Learning for Real-Robot Five-Ball Juggling

arXiv:2606.16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional task-error supervision and a task error model that drives sample selection, we achieve stable three-, four-, and five-ball juggling on anthropomorphic Barrett WAM arms. Despite planning and controlling through a simple, idealized stack, the system converges from the second attempt. The first attempt drops, after which task error decreases monotonically without further failures. In comparison, five-ball juggling typically takes humans years of practice. We compare residual learners across two ternary axes, the directional information in the learning feedback and the commitment of the analytic prior, spanning Newton-style Jacobian updates, Composite Bayesian Optimization, and stochastic search methods. Both axes prove necessary: neither directional feedback nor an informative prior suffices alone, and the simplest method that combines them, a fixed-Jacobian Newton update, is the most reliable. The learned residual tolerates substantial prior misalignment and degraded joint tracking, affecting mainly convergence speed. The bottleneck for residual learning on real robots is therefore the information content of the supervision signal and how the learner uses it, not the accuracy of the surrounding stack. Video documentation of all experiments is available at https://kai-ploeger.com/residual-juggling.