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.CV) 2026-06-12

Modality Forcing for Scalable Spatial Generation

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale. Prior works adapt T2I models to leverage this prior for depth prediction, but they require dense depth data and involve complex recipes. We propose Modality Forcing, a simple, scalable post-training recipe for joint image-depth generation using a single DiT trained on sparse depth data. Modality Forcing enables conditional and joint generation of image and depth in any permutation by assigning separate noise levels per modality. Per-modality decoders let us train on sparse, real-world depth and achieve strong, generalizable depth prediction. We further show that Modality Forcing inherits the scalability of T2I pre-training: by training a set of T2I models from scratch (370M to 3.3B parameters), we find that larger models trained on more image data produce more accurate depth. Our strongest model is competitive with state-of-the-art monocular depth estimators and reduces AbsRel by 57% relative to existing joint image-depth generative models. These results provide strong evidence that image generation is a scalable pre-training objective for spatial perception. https://modality-forcing.github.io/

02.
medRxiv (Medicine) 2026-06-18

Digital self-efficacy as a potential intermediary between vision impairment and daily internet use among older adults: A cross-sectional analysis of HINTS 2024

Background: Older adults with vision impairment often experience barriers to using digital technology. The indirect associations between vision impairment and digital access and skills via digital self-efficacy and frustration among older adults remain largely unknown. Objective: This study aimed to 1) explore factors associated with digital access, skills, self-efficacy, and frustration among older adults with vision impairment; 2) examine associations between vision impairment and digital access, skills, self-efficacy, and frustration among older adults; and 3) examine whether digital self-efficacy and frustration may help explain associations between vision impairment and digital access and skills among older adults. Methods: This was a cross-sectional study using nationally representative data from the Health Information National Trends Survey (HINTS) 2024. Respondents aged 60 and older were included. Vision impairment was assessed using a self-reported item. Outcomes included self-reported digital access, skills, self-efficacy, and frustration. Survey-weighted multivariable logistic regression and generalized structural equation modeling were conducted, adjusting for age, sex, race/ethnicity, education, and the number of comorbidities. Results: Among 3,149 older adults (mean [SD] age, 70.7 [10.0] years; 45.6% female), 7.1% (n=223) reported vision impairment. Among older adults with vision impairment, 65.6% (95% CI, 53.5% to 75.9%) used the internet daily, and 79.5% (95% CI, 66.8% to 88.2%) used a smartphone in the past 12 months. In multivariable logistic regression analyses among older adults with vision impairment, older age was associated with lower odds of daily internet use (OR, 0.84; 95% CI, 0.79 to 0.90), smartphone use (OR, 0.85; 95% CI, 0.75 to 0.97), wearable device use (OR, 0.88; 95% CI, 0.79 to 0.97), and using the internet to send a message to a healthcare provider (OR, 0.87; 95% CI, 0.80 to 0.93). Older adults who self-identified as racial and ethnic minority groups (e.g., Black/African American, Hispanic) had lower odds of daily internet use (OR, 0.15; 95% CI, 0.05 to 0.50) and using the internet to send a message to a healthcare provider (OR, 0.17; 95% CI, 0.04 to 0.73) compared with Non-Hispanic White older adults. Vision impairment was associated with lower odds of daily internet use (OR, 0.60; 95% CI, 0.37 to 0.99) and digital self-efficacy (OR, 0.53; 95% CI, 0.32 to 0.86). Digital self-efficacy was associated with higher odds of daily internet use (OR, 2.95; 95% CI, 2.04 to 4.26). Generalized structural equation modeling identified an indirect association between vision impairment and daily internet use via digital self-efficacy (coefficient, -0.68; 95% CI, -1.24 to -0.12). Conclusions: Findings suggest that reduced digital self-efficacy may help explain the observed association between vision impairment and daily internet use among older adults. Interventions targeting digital self-efficacy, including accessible interface designs, personalized coaching, and peer support, may help bridge the digital divide among older adults with vision impairment.

03.
medRxiv (Medicine) 2026-06-19

Validation of an Artificial Intelligence-Assisted Mobile Application for Dietary Oxalate Assessment in Kidney Stone Prevention

Background: Calcium oxalate nephrolithiasis is the most common type of kidney stone disease. Dietary oxalate intake is an important modifiable factor. Assessing dietary oxalate exposure in clinical practice poses challenges due to limitations of traditional dietary recall tools and variability in food composition data. Artificial intelligence (AI) applications in mobile health may offer scalable solutions for better dietary monitoring and kidney stone prevention. We examined the ability of StoneFree AI to estimate dietary oxalate from verbal and image-based food inputs. Objective: To evaluate the accuracy and limitations of StoneFree AI, for estimating dietary oxalate intake from verbal food descriptions and meal images, and to evaluate errors from entries that may inform future clinical use in kidney stone prevention. Methods: StoneFree AI is a cross-platform mobile application that uses a multimodal large language model (Google Gemini) to interpret verbal food descriptions and visual food images. The identified foods were mapped to oxalate values using the Harvard Oxalate Database. System performance was evaluated using 804 verbal food entries and 276 portion-size food images obtained from the ASA24 dietary assessment database. Verbal inputs were compared with reference oxalate values using absolute error and predefined agreement thresholds ({+/-}1, {+/-}5, {+/-}10 mg). Image-based inputs were evaluated against mutually exclusive primary error categories, including food identification, portion estimation, ingredient recognition, oxalate reference selection, and non-analyzable cases. Results: For verbal food entries, the AI system showed strong agreement with reference oxalate values. Overall, 82.1% of estimates were within {+/-}1 mg, 91.5% within {+/-}5 mg, and 94.5% within {+/-}10 mg of reference values. The mean absolute error was 3.32 mg, the median absolute error was 0.10 mg, and the concordance correlation coefficient (CCC) was 0.860. Image-based inputs showed a higher overall error rate of 63.0%, primarily due to food identification errors (33.0%), inaccurate portion estimation (11.0%), and ingredient recognition errors (9.8%). Most errors occurred with visually complex meals, such as mixed dishes and grain-based foods. Conclusions: AI-assisted estimation of dietary oxalate intake demonstrated high accuracy when structured verbal inputs were used but was less reliable for image-based meal analysis. These findings suggest AI-enabled mobile tools may support dietary monitoring for kidney stone prevention, particularly when user input is structured. Further refinement of computer vision models and prospective clinical validation are required before widespread clinical implementation.

04.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

05.
arXiv (quant-ph) 2026-06-19

Variational Polaron Theory for Ground States of Strongly Coupled Light-Matter and Electron-Phonon Systems

arXiv:2606.19748v1 Announce Type: cross Abstract: Strong light-matter and electron-phonon coupling generate ground states dressed by virtual bosonic excitations, making bare-state truncations and perturbative treatments unreliable in the ultrastrong-coupling regime. We introduce a nonperturbative variational ground-state framework based on a state-dependent polaron transformation, combined with a product-state ansatz and a second-order perturbative correction for residual matter-boson entanglement. We show that the optimized transformed frame becomes asymptotically decoupled at infinite coupling, because the leading linear coupling is canceled while off-diagonal matter transitions are suppressed by displaced-oscillator overlaps. The approach is asymptotically correct in both weak- and strong-coupling limits and remains accurate in the intermediate regime, where fixed polaron transformations are least reliable. Dicke-model benchmarks reproduce ground-state energies, fidelities, and the superradiant transition, with second-order energy errors below 0.2%. Holstein-model benchmarks yield errors below 0.5% and clarify how translational symmetry affects wave-function quality. This dressed-basis framework enables nonperturbative modeling of strongly coupled light-matter and electron-phonon systems.

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

video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding

arXiv:2606.24477v1 Announce Type: cross Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA). A practical and efficient solution is a two-stage paradigm: first perform coarse video understanding to localize relevant segments, and then re-watch these segments at higher temporal or spatial fidelity. In this paper, we present video-SALMONN-R$^3$, the first end-to-end video-LLM that enables re-watch through reinforcement learning without relying on chain-of-thought (CoT) cold-start. This design removes the need for costly CoT data annotations and avoids CoT-based supervised fine-tuning (SFT), which can otherwise degrade the pretrained video understanding abilities. To address the mismatch between the reasoning-first behavior induced by re-watch and the answer-first tendency of pretrained video-LLMs, we propose a re-answer strategy, in which the model first produces a direct answer in the first watch and then refines it after re-watching. Finally, to improve question adherence during re-watching, we propose a re-ask mechanism that re-injects the query when revisiting localized segments. Experimental results show that video-SALMONN-R$^3$ consistently outperforms both the base model and the QA-SFT baseline, while surpassing prior re-watch-based approaches with significantly lower computational cost. Code, models, and data will be publicly released upon acceptance.

07.
arXiv (CS.CV) 2026-06-25

An Integrated Hardware-Software Design for Low-Data Spatial Defect Detection in Robotic Visual Inspection with Hybrid Optoelectronic Neural Networks

To address data overload and inefficient shape-level annotation in robotic visual inspection, this paper proposes a hardware-software integrated optoelectronic architecture. A non-imaging, low-data paradigm is established to minimize annotation dependency. First, a sensor-in-the-loop strategy reconfigures a Digital Micromirror Device (DMD) as a physical optical convolutional layer, enabling photonic-domain feature extraction that unifies sensing hardware and processing software. To suppress data volume at the source, a block-based compressed sensing strategy encodes spatial information into low-dimensional temporal signals, drastically reducing redundancy. Subsequently, to bypass laborious manual defect shape annotation, natural language descriptions guide the network to align with highly generalizable features from Contrastive Language-Image Pre-training (CLIP), steering the attention maps of the optoelectronic neural network toward defect shapes. Furthermore, a Localization Accuracy for Attention (LAA) metric is proposed to quantify shape-level defect localization performance. Experiments on transparent material defect detection validate the system's effectiveness. Parametric analysis reveals how measurement matrices, compression ratios, and block sizes affect accuracy. Results show that, compared to traditional imaging, the proposed architecture maintains equivalent accuracy while reducing data volume by 90% for Vision Transformers and computational workload by 60% for Convolutional Neural Networks. This low-data paradigm offers an efficient solution for industrial automation scenarios involving massive data streams, high acquisition costs, or constrained edge resources.

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

ARROW: Augmented Replay for RObust World models

arXiv:2603.11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks. Most existing approaches rely on model-free methods with replay buffers to mitigate catastrophic forgetting; however, these solutions often face significant scalability challenges due to large memory demands. Drawing inspiration from neuroscience, where the brain replays experiences to a predictive World Model rather than directly to the policy, we present ARROW (Augmented Replay for RObust World models), a model-based continual RL algorithm that extends DreamerV3 with a memory-efficient, distribution-matching replay buffer. Unlike standard fixed-size FIFO buffers, ARROW maintains two complementary buffers: a short-term buffer for recent experiences and a long-term buffer that preserves task diversity through intelligent sampling. We evaluate ARROW on two challenging continual RL settings: Tasks without shared structure (Atari), and tasks with shared structure, where knowledge transfer is possible (Procgen CoinRun variants). Compared to model-free and model-based baselines with replay buffers of the same-size, ARROW demonstrates substantially less forgetting on tasks without shared structure, while maintaining comparable forward transfer. Our findings highlight the potential of model-based RL and bio-inspired approaches for continual reinforcement learning, warranting further research.

09.
arXiv (quant-ph) 2026-06-11

A Cryogenic Uniaxial Strain Cell for Quantum Devices

arXiv:2606.11485v1 Announce Type: new Abstract: Mechanical strain is a powerful resource for tuning quantum systems, but existing piezoelectric strain cells are generally optimized for fragile, high-aspect-ratio single crystals rather than the thick, square-profile chips typical of semiconductor quantum devices. Furthermore, adapting these cells for qubits requires accommodating dense RF and DC wiring while maintaining strict electrical isolation from high-voltage piezo actuators. Here, we present a piezoelectric uniaxial strain cell designed to homogeneously strain thick, square-profile substrates. We introduce a highly symmetric dual-chip loading configuration that effectively suppresses flexural deformation and shear stress. The cell integrates a high-density RF/DC interposer to support standard wire bonding and encloses the actuators in a grounded Faraday cage to prevent unwanted Stark shifts in the device layer. Finite element simulations confirm that combining stiff actuators with this symmetric mounting drastically improves strain homogeneity. Finally, we validate the apparatus experimentally by applying uniaxial strain to a 200 $\mu$m thick silicon die. Surface strain measurements demonstrate an applied strain of 215 $\mu\epsilon$ for 200 V applied piezo bias.

10.
arXiv (CS.CL) 2026-06-19

GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs

作者:

Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining. Existing methods handle only single-direction injection; when multiple semantic directions are superposed without constraints, the model collapses. We show that this collapse decomposes into two independently acting sources: distributional deviation, where additive perturbations accumulate in norm across layers and drive activations outside the training distribution, and directional interference, where non-orthogonal semantic vectors mutually dampen when superposed. These two sources define the design constraints that any training-free multi-directional intervention must address. As one instantiation of these principles, we propose GEMS, a training-free method that maps each source to a corresponding geometric constraint: norm-preserving weighted superposition and targeted attention-pathway injection for distributional deviation, and real-time orthogonalization for directional interference. On GSM8K, injecting three concurrent non-mathematical directions preserves accuracy at 98% (baseline 92%), while unconstrained addition collapses to 4%; on Wikitext-2, the same injection incurs only 2.2% PPL increase. Component ablation isolates the causal role of each constraint, and layer-level probes confirm that orthogonalized signals survive the FFN pathway and reach the output distribution with semantic specificity. Qualitative steering effects transfer across architectures from 3B to 31B.

11.
arXiv (CS.AI) 2026-06-24

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

arXiv:2606.23604v2 Announce Type: replace-cross Abstract: The tracking-by-detection paradigm in multi-object tracking (MOT) typically relies on static appearance descriptors to complement motion estimation. However, these descriptors are frame-independent, limiting their robustness as visual cues. Since such descriptors are often obtained from computationally intensive pretrained backbones, real-time MOT systems frequently abandon appearance cues altogether and rely solely on motion prediction and geometric association. In this work, we introduce Polycepta, an object-centric appearance state estimation framework that reformulates appearance modeling as a recursive estimation problem rather than a frame-wise matching task. Polycepta constructs and continuously updates an independent appearance state for each tracked object, enabling future appearance representations to be estimated from accumulated observations. Polycepta is encouraged to learn the appearance-state construction of object-specific representations rather than memorize them through a proposed learning strategy, enabling appearance estimation for unseen classes. A key property of Polycepta is that the quality of appearance estimation improves as object states evolve during inference. While conventional appearance descriptors remain static or degrade over time, Polycepta progressively refines appearance estimates as additional observations are accumulated. Extensive experiments on KITTI, the Waymo Open Dataset, and MOT17 demonstrate consistent reductions in identity switches and improvements in tracking performance when integrated into the tracking-by-detection pipelines. Polycepta operates at 90.57 Hz and delivers state-of-the-art performance on the KITTI benchmark when integrated into the RobMOT framework, achieving a MOTA of 92.27\%.

12.
arXiv (CS.AI) 2026-06-18

The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics for ELbot

arXiv:2606.19197v1 Announce Type: cross Abstract: Abduction is a central approach to explain missing entailments from a knowledge base by providing a hypothesis, that would, if added to the knowledge base, make the missing entailment become true. Abduction under repair semantics has recently been investigated in detail, where several desirable properties and optimality criteria were considered, such as signature-restrictions and minimality in size and of introduced conflicts. Naturally, hypotheses that satisfy more than one of these properties or combine a property with an optimality criterion would be even more desirable for applications. So far, such hypotheses have not been investigated in the literature. In the present paper, we consider the ABox abduction problem for hypotheses satisfying more than one property or additional optimality criteria, for EL_bot under brave and AR semantics. Our main observation is that often requiring additional properties for hypotheses does not lead to an increase of complexity.

13.
arXiv (CS.CL) 2026-06-25

To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG

Multi-agent document assessment for retrieval-augmented generation is computationally expensive, driving practitioners toward smaller, deployable models whose assessment mechanisms remain poorly understood. We conduct a controlled study of training-free interventions on 7B-9B instruction-tuned models across diverse QA benchmarks, revealing a sharp dichotomy in how models benefit from assessment. For weaker baselines, the dominant mechanism is per-document isolation. Astoundingly, assessment-free isolation matches full multi-agent assessment, demonstrating that resolving multi-document context confusion, rather than scoring quality, drives outsized gains of up to 50 percentage points. Conversely, for strong baselines where scoring quality matters, we introduce Reasoning-Score Coupling, a label-free perturbation probe that classifies scoring behavior. Integrating these findings, we propose MADARA, a model-adaptive routing architecture. Crucially, MADARA's diagnostic thresholds derived from a single pilot model generalize zero-shot to four unseen model families, providing a robust, lightweight pipeline to eliminate computational overhead.

14.
Nature (Science) 2026-06-17

Reimagining machine vision with optical computing

作者: 未知作者

A general-purpose artificial-intelligence vision system for use in image-sensing devices has been developed by embedding fundamentals of core computer-vision operations into a light-manipulating planar material called an optical metasurface. A prototype enables accurate, real-time perception and processing across diverse tasks, suggesting that this could be a solution for rapid, low-energy, on-device vision intelligence. A specialized ‘metasurface’ can preprocess incoming scene information on image-generating devices.

15.
arXiv (CS.CL) 2026-06-12

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

16.
arXiv (CS.AI) 2026-06-19

FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

arXiv:2606.19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the dataset, generation pipeline, prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/datasets/datumo/FinRED.

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

Know Thy Reasoner: Not All Language Models Explore Alike

arXiv:2604.10827v2 Announce Type: replace Abstract: Compute scaling for LLM reasoning trades off exploring solution approaches (breadth) against refining promising ones (depth), yet why a given trade-off works, and why it often fails to transfer across models, remains unclear. We argue that the optimal strategy depends on the model's diversity profile, the spread of probability mass across solution approaches, and that this must be characterized before any exploration strategy is adopted. We formalize this with a framework decomposing reasoning uncertainty, deriving when depth-based refinement outperforms parallel sampling, and validate it across three model families at both inference and training. Our central finding is that the diversity regime dictates the strategy: low-diversity aligned models benefit from depth-based refinement with lightweight intrinsic signals, whereas high-diversity base models are often harmed by it, and instead need breadth or stronger signals to compensate.

18.
arXiv (CS.CV) 2026-06-12

Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration

The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost. Existing pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations. While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different pruning ratios or data distribution. In this work, we present a unified graph-based DP framework. By modeling the dataset as a weighted graph, where node weights encode intrinsic value and edge weights encode extrinsic value, DP can be cast as a Maximum Weight Clique Problem (MWCP). Although MWCP is NP-hard, its structure admits a principled greedy solution based on sample-wise marginal gains. Under a few mild conditions, we further prove that this unified objective enjoys a formal approximation guarantee, which applies to a broad family of importance metrics and provides practical design guidelines. Extensive experiments show that our method outperforms existing DP methods while substantially reducing training cost, reducing training time by over 40\% without sacrificing accuracy on ImageNet-1k with ResNet-50.

19.
arXiv (CS.LG) 2026-06-17

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

arXiv:2602.23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized to robustify alignment, known polylogarithmic regret guarantees remain heavily specific to KL. To investigate whether such fast rates extend beyond KL, we adopt the Generalized Bilinear Preference Model (GBPM) – capturing intransitive preferences over $d$-dimensional item-wise features via a rank-$2r$ skew-symmetric matrix – to isolate the impact of generic regularization. Crucially, under GBPM, we prove that the dual gap of any greedy policy is bounded by the squared estimation error, derived using only strong convexity and skew-symmetry. Under a feature coverage assumption, we establish a generic polylogarithmic regret of $\tilde{\mathcal{O}}(\eta d^4 C_{\min}^{-1} (\log T)^2 \wedge d^2 C_{\min}^{-1/2} \sqrt{T})$ with Greedy Sampling, and a dimension-wise improved regret (for well-conditioned arm-sets) of $\tilde{\mathcal{O}}(C_{\min}^{-2} \sqrt{\eta r T} \wedge r^{1/3} C_{\min}^{-4/3} T^{2/3})$ with Explore-Then-Commit, where $\eta^{-1}$ is the regularization coefficient, $T$ is the time horizon, and $C_{\min}$ is an arm-set dependent quantity. This demonstrates that ``fast'' regrets are not KL-specific, but rather a fundamental consequence of generic strongly convex geometry.

20.
arXiv (CS.LG) 2026-06-11

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

21.
arXiv (CS.LG) 2026-06-24

Aligning Audio Captions with Human Preferences

arXiv:2509.14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio captioning framework based on Reinforcement Learning from Human Feedback (RLHF). To capture nuanced preferences, we train a Contrastive Language-Audio Pretraining (CLAP) based reward model using human-labeled pairwise preference data. This reward model is integrated into an RL framework to fine-tune any baseline captioning system without ground-truth annotations. Extensive human evaluations across multiple datasets show that our method produces captions preferred over baseline models, particularly when baselines fail to provide correct and natural captions. Furthermore, our framework achieves performance comparable to supervised approaches with ground-truth data, demonstrating effective alignment with human preferences and scalability in real-world use.

22.
Nature (Science) 2026-06-10

Two-component exciton condensates in an electron–hole bilayer

作者:

Macroscopic quantum coherence emerges when bosons condense into a Bose–Einstein condensate (BEC)1–5. Excitons are a long-sought solid-state route to high-temperature BECs with strong interactions, electrical tunability and potentially multicomponent spinor order, but conclusive evidence for equilibrium condensation has remained elusive. Here we report evidence for two-component exciton BECs in MoSe2/hBN/WSe2 electron–hole bilayers6–9 by probing the spin–valley susceptibility of constituent electrons and holes. This heterostructure hosts equilibrium exciton fluids with four spin–valley flavours. Magneto-optical spectroscopy in a dilution refrigerator reveals three exciton condensate phases with distinct flavour polarizations. At zero magnetic field, the many-body ground state is a coherent superposition of two condensed intravalley exciton flavours. Under a magnetic field, the intravalley exciton condensate first switches to a two-component intervalley condensate through a first-order quantum phase transition at a weak critical field and then turns into a fully polarized single-component condensate at high fields. The condensate signatures form a dome in density–temperature space, persisting up to approximately 1.8 K. Our results establish van der Waals electron–hole bilayers as a versatile platform for strongly interacting, multicomponent exciton BECs. Macroscopic quantum coherence arises in two-component exciton Bose–Einstein condensates within MoSe2/hBN/WSe2 electron–hole bilayers, exhibiting distinct spin–valley polarized phases, quantum phase transitions under magnetic fields and stable condensate behaviour up to approximately 1.8 K.

23.
arXiv (CS.CL) 2026-06-16

LLM-Powered Virtual Population for Demand Simulation and Pricing

We develop an LLM-powered virtual population model that simulates demand for pricing decisions, in settings where products are described by rich unstructured information, such as text descriptions and images, and where decision makers need not only mean-demand predictions but also uncertainty estimates for counterfactual prices. Our model represents exposed customers as draws from a finite mixture of customer personas. For each persona, product, and candidate price, an LLM elicits a persona-level purchase probability using both structured persona information and unstructured product information. These probabilities are aggregated through calibrated mixture weights to form a predictive distribution of aggregate demand. The resulting simulator can evaluate counterfactual prices under various pricing objectives, including expected revenue and risk-aware criteria such as conditional value at risk. We test the framework on an online H&M fashion dataset with product descriptions and images. The calibrated LLM-based simulator achieves the best overall predictive performance among the models considered, and supports sample-efficient pricing decisions. Our framework provides a practical way to use LLMs as demand simulators for products with limited historical demand data but rich product information. By producing a full predictive demand distribution rather than only a point forecast, it enables managers to compare candidate prices, quantify demand uncertainty, and choose prices that target either average-case revenue or risk-aware objectives.

24.
arXiv (CS.CV) 2026-06-12

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.

25.
arXiv (CS.AI) 2026-06-15

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

arXiv:2601.22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations.