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 (quant-ph) 2026-06-17

Engineering entanglement and transport in interacting quantum walks with tailored potentials

arXiv:2606.17825v1 Announce Type: new Abstract: Controlling the interplay between particle propagation and quantum correlation generation is a central challenge in quantum transport. Here, we investigate two distinguishable continuous-time quantum walkers evolving on parallel one-dimensional lattices, interacting via distance-dependent potentials. While on-site interactions reproduce the typical bosonic behaviour, extending the interaction to a linear potential over multiple neighbors introduces controlled Bloch-like oscillations and shifts the bound-pair regime to stronger couplings. More generally, we explore a Coulomb-like interaction parameterized by strength, spatial scaling, and decay rate. This reveals a rich phase diagram including four distinct dynamical regimes: (i) a high-entropy, oscillatory regime akin to a linear potential; (ii) a strongly localized, bound-pair regime; (iii) a novel intermediate regime combining near-ballistic spreading with strong correlations; and (iv) a weakly interacting, free-propagation regime. Notably, regime (iii) achieves concurrent optimization of transport efficiency and entanglement, offering a sweet spot for correlated quantum dynamics. Our results provide a tool for designing interaction-engineered quantum walks with potential applications in quantum information processing and simulations.

02.
arXiv (CS.CV) 2026-06-17

Million-scale multimodal pollen microscopy with expert-guided foundation models

Automated pollen identification from microscopy remains a bottleneck in aerobiology, palaeoecology and biodiversity monitoring, because scalable systems must generalise across specimen preparation, scanner settings and geographic origins while retaining palynological interpretability. To address this gap, we present a million-scale multimodal pollen microscopy resource, Pollen AI Atlas, assembled from pure-species whole-slide bright-field images spanning four geographic origins, four scanner settings and 46 taxon labels across 31 botanical families. Seeded by one manually selected exemplar per source slide, token-level mining and filtering produced 1,511,390 released grain detections with 99.6\% proposal precision in expert-curated test regions. Each detection was paired with machine-generated grain-level morphological captions from five open-weight vision-language models, guided by expert-verified palynological anchors, yielding structured descriptions of aperture systems, wall ornamentation, shape and size. Among the evaluated models, Gemma4 provided the most controlled primary caption set, combining tight length control, no leakage and the strongest text-retrieval performance. Baseline benchmarks with frozen visual features reached 88.16\% top-1 accuracy, while cross-regional retrieval showed that caption-derived text embeddings remained robust when image similarity degraded (mAP@20 0.811 versus 0.262). Released data, annotations, captions, splits, code, and weights provide a benchmark for pollen recognition, cross-regional domain adaptation and domain-specific multimodal microscopy learning.

03.
arXiv (CS.LG) 2026-06-18

Smoothness-Based Derandomization of PAC-Bayes Bounds

arXiv:2606.19105v1 Announce Type: new Abstract: We study PAC-Bayes derandomization for smooth loss functions. Our goal is to obtain generalization bounds that hold with high probability for deterministic predictors by exploiting smoothness properties of both the loss and the predictor class. We show that passing from the Gibbs predictor to the deterministic predictor at the posterior mean has a precise cost, given by the generalization gap of the Jensen gap class. We control this class through its Rademacher complexity, leading to bounds for deterministic predictors that involve flatness quantities expressed in terms of parameter Jacobians and Hessians of the score map. The framework applies to both bounded and unbounded smooth loss functions, and we specialize the results to linear predictors and smooth neural networks. Finally, the Jacobian and Hessian quantities appearing in the theory motivate a practical regularizer. For BatchNorm networks, we compute this regularizer with respect to effective BatchNorm weights obtained by folding the BatchNorm transformation into the adjacent affine weights. Experiments on CIFAR-10 illustrate the behavior of this regularizer under different batch sizes.

04.
arXiv (CS.CL) 2026-06-12

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

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

MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers

Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps. Existing caching methods mainly operate at the token level, which becomes suboptimal in DiT-MoE because each token update is internally decomposed into multiple routed expert branches. Our analysis shows that cross-timestep redundancy in DiT-MoE is better characterized at the expert-branch level than at the whole-token level. Based on this observation, we propose MoECa, a fine-grained caching framework that performs branch-level feature reuse across timesteps. MoECa further introduces expert-aware adaptive control and synchronized cache updates across MoE and attention paths to maintain stable intermediate states. Experiments on multiple DiT-MoE models show that MoECa consistently achieves a better speed-quality trade-off than prior caching methods, with up to 2.83$\times$ inference speedup and minimal quality degradation.

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

Sequential Hiring of Contingent Workers Through Learning-Based Optimization

arXiv:2606.18438v1 Announce Type: cross Abstract: In this paper, we study a sequential workforce management problem in a contingent labor setting with uncertainty in both worker production and labor supply. A firm seeks to maximize cumulative profit by maintaining an active team of fixed size while learning worker productivity over time. We emphasize two critical operational frictions in this problem: replacing workers is costly, and workers may not be available immediately for hiring because of, for example, prior job commitments, scheduling constraints, or onboarding procedures. Thus, hiring decisions take effect only after a random delay. We formulate this problem as a stochastic multi-play bandit with costly switching and delayed actions, and develop a learning-based hiring policy, DR-UCB (DelayedReplacement-UCB), that makes replacement and hiring decisions sequentially through learning cycles. In each cycle, the policy uses real-time production data to determine when to initiate workforce changes and which workers to replace and hire. We show that the leading-order regret of the proposed policy matches its lower bound in its dependence on the time horizon. Our numerical experiments show that DR-UCB outperforms benchmark policies.

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

OpenMedQ: Broad Open Pretraining for Medical Vision-Language Models

We present OpenMedQ, a medical vision-language model pretrained on the broadest fully-open medical mix to date: 14 datasets totaling ~3.35M pretraining samples spanning pathology, radiology, microscopy, and text-only clinical QA. OpenMedQ reaches state-of-the-art BLEU-1 on PathVQA (75.9), beating Med-PaLM M variants up to 562B parameters (~80x larger), and matches the best reported VQA-MED BLEU-1 (64.5). Its vision encoder, transferred to 8 unseen medical classification benchmarks under an identical downstream recipe, obtains the highest average macro-F1 (0.757) among BiomedCLIP (0.745), PMC-CLIP (0.745), PubMedCLIP (0.746), and a from-scratch baseline (0.616). We release our code and an interactive demo is publicly available as a reproducible baseline for the community.

08.
Nature (Science) 2026-06-10

In situ nanocrystal confinement for efficient blue perovskite LEDs

Metal halide perovskites have emerged as promising semiconductors for light-emitting diodes (LEDs) owing to their excellent luminescence properties1. However, their performance remains limited, primarily owing to the inherent contradiction between ‘high crystallinity’ and ‘small size’ in the in situ synthesis of perovskite nanocrystals on substrates. Here we report efficient blue perovskite LEDs (PeLEDs) achieved via in situ polymerization-driven nanocrystal confinement to synthesize perovskite films composed of high-quality nanocrystals. The in situ-formed polymer network imposes nanoscale spatial constraints during perovskite nanocrystal growth, enabling nanocrystals with small sizes and a high photoluminescence quantum yield of 83%. Furthermore, polymerizable monomers with sufficient coordination sites allow a prolonged lattice rearrangement of perovskite clusters, promoting the crystallinity of the nanocrystals. The synthesized perovskite nanocrystals are utilized in the fabrication of PeLEDs, resulting in an external quantum efficiency of 21.8% at 491 nm, which is among the highest performances in blue PeLEDs. This work simultaneously controls the thermal dynamics of perovskite crystallization and organic ligand reactions, which helps to advance understanding of the effect of ligand engineering on nanocrystal synthesis, benefiting the development of efficient PeLEDs and other optoelectronic technologies. Efficient blue perovskite light-emitting diodes with an external quantum efficiency of 21.8% are achieved through in situ polymerization-driven nanocrystal confinement.

09.
arXiv (CS.AI) 2026-06-16

Sensory Restoration via Brain-Computer Interfaces: A Unified 2 x 2 Framework and Convergence Roadmap

arXiv:2606.15091v1 Announce Type: cross Abstract: Millions of individuals worldwide suffer from sensory and communication deficits caused by neurodegenerative diseases, stroke, or trauma. Brain-computer interfaces (BCIs) offer a promising avenue for sensory and motor restoration. However, the scientific literature remains highly fragmented between invasive neuroprosthetics and non-invasive electrophysiological decoders, with a lack of consistent terminology and comparison metrics. This chapter proposes a unified 2 x 2 framework categorizing BCIs along two axes: degree of invasiveness (invasive vs. non-invasive) and signal direction (afferent sensory-IN vs. efferent sensory-OUT). We define and distinguish the paradigms of restoration, substitution, and augmentation. Furthermore, we outline a structural roadmap for the convergence of these modalities over near-, medium-, and long-term horizons, focusing on physical limits and the integrative role of machine learning foundation models.

10.
arXiv (CS.AI) 2026-06-16

Decision-Weighted Flow Matching for Contextual Stochastic Optimization

arXiv:2606.16790v1 Announce Type: cross Abstract: Conditional generative models are increasingly used as scenario generators for stochastic optimization, but standard training objectives emphasize uniform distributional fit rather than the downstream decisions induced by generated scenarios. This creates an objective mismatch: errors in statistically common regions may have little effect on decision regret, whereas errors in decision-sensitive regions can substantially change the optimal action. We propose Decision-Weighted Flow Matching (DW-FM), a regret-aligned training framework that preserves the simplicity of standard flow matching while reweighting its velocity-regression objective using decision-sensitive endpoint information. Theoretically, we connect downstream regret to pathwise velocity mismatch through a loss-induced decision discrepancy and an adjoint transport argument, yielding an ideal regret-aligned surrogate and practical endpoint-weighted objectives with regret guarantees. Empirically, we demonstrate the effectiveness of DW-FM on three CVaR-based contextual stochastic optimization benchmarks spanning synthetic portfolio, semi-real financial, and traffic-CVaR tasks, where DW-FM improves downstream regret over standard baselines.

11.
arXiv (CS.CV) 2026-06-12

BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning

Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restricted information capacity of binary spike coding and the dense token interactions introduced by global self-attention. To address these challenges, this work proposes BSViT, a burst spiking-driven Vision Transformer featuring a Dual-Channel Burst Spiking Self-Attention (DBSSA) mechanism. DBSSA encodes queries with binary spikes and keys with burst spikes to enhance representational capacity. The value pathway adopts dual excitatory and inhibitory binary channels, enabling signed modulation and richer spike interactions. Importantly, the entire attention operation preserves addition-only computation, ensuring compatibility with energy-efficient neuromorphic hardware. To further reduce spike activity and incorporate spatial priors, a patch adjacency masking strategy is introduced to restrict attention to local neighborhoods, resulting in structure-aware sparsity and reduced computational overhead. In addition, burst spike coding is systematically integrated across the network to increase spike-level representational capacity beyond conventional binary spiking. Extensive experiments on both static and event-based vision benchmarks demonstrate that BSViT consistently outperforms existing spiking Transformers in accuracy while maintaining competitive energy efficiency.

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

Surprise-Guided MergeSort: Budget-Efficient Human-in-the-Loop Ranking via Adaptive Comparison Scheduling

arXiv:2606.15623v1 Announce Type: cross Abstract: Pairwise comparison is the gold standard for subjective ranking tasks; however, exhaustive annotation requires a massive number of human comparisons ($O(n^2)$). While sorting-based methods have reduced this burden to $O(n\log n)$, they still require expensive human judgment for every single comparison. To further improve annotation efficiency, we propose leveraging a Vision-Language Model (VLM) not as an annotator replacement, but as a question prioritizer to identify which comparisons genuinely require human judgment. The proposed Surprise-Guided MergeSort (SGS) framework achieves this through three integrated components: (1) a bottom-up MergeSort scheduler that structures comparisons and exploits transitivity, (2) a composite Surprise Scorer – combining position-bias-cancelled VLM confidence, Elo gap, and vote entropy – to quantify comparison ambiguity, and (3) an adaptive budget allocator that routes high-surprise pairs to humans while automating low-surprise pairs via transitivity inference. Validation was conducted on six diverse benchmarks spanning text similarity (STS-B, BIOSSES, SICKR-STS) and image quality assessment (KonIQ-10k, TID2013, LIVE Challenge). SGS effectively identified and skipped up to 535 non-informative comparisons per session. Consequently, it achieved Kendall's $\tau{\times}100$ improvements of $+6$ to $+12$ over Active Elo under the same total budget. These results demonstrate that combining VLM-guided surprise metrics with algorithmic sorting provides a generally consistent accuracy-efficiency trade-off across diverse domains.

13.
arXiv (CS.LG) 2026-06-12

The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning

arXiv:2606.13637v1 Announce Type: new Abstract: Catastrophic forgetting is often viewed as the destruction of previously learned knowledge during sequential learning. Building on the Accessibility Collapse framework, we investigate the geometric structure of recoverability in continual learning. Using Split CIFAR-100 and a sequentially trained ResNet-18, we analyze recoverability, representational drift, and recovery complexity across ten tasks. We introduce Recovery Subspace Dimensionality (k_t), a measure of the minimum number of singular directions required to preserve 90 percent of full probe performance. Contrary to our Recoverability Diffusion hypothesis, recovery dimensionality remains stable throughout training (mean k_t = 8.0) despite substantial representational drift. Principal-angle drift strongly predicts recoverability (r = -0.862), and a simple geometric model explains 82.2 percent of recoverability variance. These findings support the Stable Recovery Manifold hypothesis, suggesting that forgotten knowledge remains compactly decodable despite representational reorganization. The results indicate that catastrophic forgetting is primarily an accessibility and manifold-alignment problem rather than information destruction.

14.
arXiv (CS.CL) 2026-06-16

SimSiam Naming Game: A Unified Approach for Emergent Communication and Representation Learning

Emergent Communication (EmCom) investigates how agents develop symbolic communication through interaction without predefined language. Recent frameworks, such as the Metropolis–Hastings Naming Game (MHNG), formulate EmCom as the learning of shared external representations negotiated through interaction under joint attention, without explicit success or reward feedback. However, MHNG relies on sampling-based updates that suffer from high rejection rates in high-dimensional perceptual spaces, making the learning process sample-inefficient for complex visual datasets. In this work, we propose the SimSiam Naming Game (SSNG), a feedback-free EmCom framework that replaces sampling-based updates with a symmetric, self-supervised representation alignment objective between autonomous agents. Building on a variational inference–based probabilistic interpretation of self-supervised learning, SSNG formulates symbol emergence as an alignment process between agents' latent representations mediated by message exchange. To enable end-to-end gradient-based optimization, discrete symbolic messages are learned via a Gumbel–Softmax relaxation, preserving the discrete nature of communication while maintaining differentiability. Experiments on CIFAR-10 and ImageNet-100 show that the emergent messages learned by SSNG achieve substantially higher linear-probe classification accuracy than those produced by referential games, reconstruction games, and MHNG. These results indicate that self-supervised representation alignment provides an effective mechanism for feedback-free EmCom in multi-agent systems.

15.
arXiv (CS.AI) 2026-06-18

Skill-Guided Continuation Distillation for GUI Agents

arXiv:2606.18890v1 Announce Type: new Abstract: Improving GUI agents typically relies on behavior cloning on expert trajectories. However, as the current policy deviates from the expert policy, it inevitably encounters policy-induced off-trajectory states during closed-loop execution, i.e., states that fall outside the expert trajectories. Since expert trajectories provide no demonstrations for these unseen states, such states receive no effective supervision, leaving the policy unable to select the correct action. To close this supervision gap, we propose Skill-Guided Continuation Distillation (SGCD), an iterative self-improvement framework. SGCD first runs the plain policy without skill guidance for a few steps to reach realistic off-trajectory states. From these states, a skill-guided policy then completes the task and produces successful continuations, which are mixed with expert trajectories to supply supervision over policy-induced off-trajectory states. The skills are extracted from both successful and failed rollouts, consisting of Continuation Plans, Critical Targets, Failure Traps, and Success Criteria. On OSWorld-Verified, SGCD improves the success rate of three base models from the low-30\% range to over 50\%, demonstrating its effectiveness and generality.

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

FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection

Event cameras are bio-inspired sensors that asynchronously capture logarithmic intensity changes, offering inherent advantages in high-speed and high-dynamic-range scenarios. However, the sparse and asynchronous nature of event streams poses a fundamental challenge for modern deep learning architectures. To enable compatibility with standard models, most existing approaches partition the accumulation window into fixed temporal sub-bins. While effective for spatial processing, this internal discretization discards fine-grained temporal structure and constrains inference to the low temporal frequencies imposed by training supervision. To address this limitation, we propose FATE, a unified framework built upon a novel Pillar Encoding (PE). While operating over discrete macro-accumulation windows dictated by the target frequency, PE avoids internal temporal sub-binning. It organizes events into spatial pillars and approximates their intra-window evolution via projection onto a continuous-time orthogonal polynomial basis. This formulation yields an L2-optimal representation that retains rich temporal dynamics in a dense pseudo-image, mitigating information loss under sparse event conditions. To fully leverage this representation, we introduce Frequency-Aware Training (FAT), a soft mean-teacher curriculum that generates temporally dense pseudo-labels, effectively bridging the mismatch between low-frequency supervision and high-frequency inference. Extensive experiments demonstrate that FATE generalizes across architectural paradigms and consistently outperforms strong baselines. It enables robust object detection at high temporal resolutions up to 200 Hz, while incurring minimal overhead in parameter count and inference latency

17.
arXiv (CS.LG) 2026-06-18

Complementary Attention Head Pruning for Efficient Transformers

arXiv:2606.19150v1 Announce Type: new Abstract: The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments. While structured pruning offers a pathway to compression, existing state-of-the-art methods often rely on gradient-based importance ranking or stochastic gating, which suffer from instability, structural degeneration, and the need for extensive manual hyperparameter tuning. In this paper, we introduce CAHP (Complementary Attention Head Pruning), a novel post-hoc framework that redefines head selection as a global graph-theoretical problem. Rather than evaluating heads in isolation, CAHP utilizes graph-based clustering combined with information-theoretic distance measures to identify and preserve a topologically diverse subset of complementary attention heads. Without requiring a predefined sparsity level or pruning ratio, the framework automatically determines the number of selected attention heads across layers by identifying a diminishing marginal performance curve, where pruning additional heads leads to a sharp degradation in performance, as determined by the chosen polynomial degree. Extensive evaluations on the SST-5 and MNLI benchmarks, across different Transformer model scales, demonstrate that CAHP consistently outperforms competitive baselines, particularly in high-compression regimes. Furthermore, our structural analysis shows that CAHP avoids the "proximity bias" of gradient-based pruning methods, which tend to preserve heads mainly in layers close to the output, and instead retains a functionally critical set of attention heads in the model's intermediate layers.

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

CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions

arXiv:2604.05435v2 Announce Type: replace Abstract: Incomplete or inconsistent discharge documentation drives care fragmentation and avoidable readmissions. Despite its critical role in patient safety, auditing discharge summaries relies on manual review and does not scale. We propose an automated framework for auditing discharge summaries using large language models (LLMs). Our approach operationalizes the DISCHARGED framework into a checklist of 46 questions. Using 50 summaries from the MIMIC-IV database, with clinician ground-truth labels, we benchmark 11 LLMs. Model-assessed mean documentation completeness ranges from 54.9% to 74.2%, and the best-performing models achieve a Cohen's kappa values around 0.5 against clinician labels, indicating moderate agreement. All models struggle to identify ambiguous documentation (Unclear), highlighting a key gap in current automated auditing. This work provides a clinician-validated benchmark and zero-shot baselines for systematic quality improvement in clinical documentation.

19.
arXiv (CS.CV) 2026-06-15

Self-Evolving Visual Questioner

Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains underexplored. Existing visual questioners' performance is bottlenecked by the availability of high-quality training data or the cost of curating them. We show that a VLM can continuously improve itself as a visual questioner without any external supervision. We propose a self-evolving framework that uses a VLM itself as both a proposer and a filter to produce harder, more informative, and visual-centric questions, while maintaining their exploration diversity to avoid training collapse. These questions are then used to train the VLM in both questioner and answerer modes. To evaluate the questioner, we introduce an agentic protocol that assesses questions along perception, reasoning, and diversity dimensions. Experiments across various backbone VLMs show that our method substantially enhances the quality and substantially expands the difficulty boundary of autonomous question generation. Under the same budget, our self-supervision is more effective than training on the static source data. Moreover, the self-evolving questioner remains a competitive or even better answerer.

20.
Nature (Science) 2026-06-08

Targeting Cancer-Specific Mutations with RNA-Triggered Chromatin Shredding

作者:

Genetic mutations that drive cancer often occur in tumor suppressor proteins, including the p53 transcription factor which is altered in ~40-50% of cases1,2. However, current therapies fail to target most such mutations because the mutant proteins typically lack defined drug-binding pockets, and restoring the endogenous function has proven challenging. Here, we programmed CRISPR-Cas12a2, an RNA-guided nuclease with trans-nucleolytic cleavage activities3,4, to selectively kill cancer cells by targeting cancer-specific transcripts. This approach limits cell growth by inducing trans shredding of chromatin, triggering DNA damage responses and cell death. Unlike existing methods, RNA-guided Cas12a2 senses cellular RNA signatures, enabling precise targeting of undruggable mutations. Transcript-activated chromatin shredding provides a new approach to precision disease treatments for undruggable targets.

21.
arXiv (quant-ph) 2026-06-12

Beyond the Unruh vacuum: multi-time correlations in black hole collapse and evaporation

arXiv:2606.13383v1 Announce Type: new Abstract: The black hole information paradox originates from the thermal character of Hawking radiation, which appears to erase information about the collapsing matter. However, thermality constrains only observables defined at a single time and leaves the structure of temporal quantum correlations largely unexplored. Here we show that multi-time quantum-field correlations provide a concrete mechanism for the survival of pre-collapse information in black hole evaporation. Using a two-dimensional model of gravitational collapse and evaporation, we demonstrate that late-time multi-time correlations are not fully reproduced by the Unruh vacuum. In particular, they contain a contribution that depends explicitly on parameters characterizing the pre-collapse state, despite the thermal character of the asymptotic radiation. Our results identify measurable multi-time correlations as carriers of information in Hawking radiation and suggest that formulations of the black hole information paradox based solely on single-time observables are incomplete.

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.
bioRxiv (Bioinfo) 2026-06-11

GermRL: Alleviating The Germline Bias In Autoregressive Antibody Language Models Through Reinforcement Learning

Antibodies are powerful therapeutics whose antigen specificity arises from sequence diversity shaped during development. Recently, language models trained on large antibody repertoire datasets have enabled the generation and screening of novel candidates, but these models retain a strong germline bias. As AI adoption increases in therapeutic workflows, it is crucial to develop models that harness the diversity of antibodies necessary for the discovery of mutations that encode desirable properties. Previous work explored the germline bias in masked antibody language models, yet the bias in generative autoregressive language models has not yet been addressed. Here, we present GermRL, a lightweight and modular reinforcement learning (RL) framework capable of alleviating the germline bias in pre-trained antibody autoregressive language models through group relative policy optimization (GRPO). GermRL achieves consistent one-shot generation of antibodies that satisfy specified mutation thresholds from germline while maintaining structural plausibility. Under the lowest and highest mutation thresholds tested (5 and 35 mutations from germline), GermRL scores 0.992 and 0.950 pass@1, respectively, compared to 0.398 and 0.034 for the pre-trained language model. Within GermRL, we introduce a key pair of modifications to GRPO that increase training efficiency by discouraging reward hacking under our antibody application. Furthermore, comparison of RL generated and natural antibody sequences reveals how RL based optimization can explore alternative evolutionary mutational patterns and residue compositional strategies while preserving key global properties of natural antibodies, including identifiable germline assignments, embedding-level similarity and comparable developability profiles. Thus, RL-trained generative models optimized to promote antibody mutations through diversity from germline provide a promising framework for navigating the antibody sequence landscape, enabling exploration of novel yet biologically plausible candidates for therapeutic design.

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

Resilient Consensus in Agentic AI

arXiv:2606.15024v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions. We ask whether classical resilient consensus theory, developed for deterministic agents, transfers to LLM agents that may behave adversarially. Framing LLM agreement as a Byzantine consensus game, we run controlled experiments on complete and general communication graphs. We find that prompted LLM agents fail to reach agreement that is achievable in principle: consensus can fail even in settings where classical theory guarantees that a convergent algorithm exists, and this failure persists across temperatures and horizons. At the same time, wrapping the agents with classical resilient consensus filters improves agreement. The benefit of filtering depends on how much robustness the underlying topology already provides. Our results suggest that classical resilient consensus theory is a useful lens for the safety of agentic AI.

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

Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unlearning as learning a refusal behavior, but their on-policy optimization repeatedly samples from the same forget and retain/boundary prompts throughout training. We identify a critical inefficiency in this process: easy cases quickly converge and provide little useful gradient signal, while hard cases near the forget/retain boundary continue to produce low-reward rollouts that are discarded after a single use. To address this issue, we propose ReRULE, an off-policy replay enhancement for reinforcement unlearning. ReRULE stores low-reward hard-case rollout groups in a replay buffer during early GRPO training and reuses them in later stages through importance-sampled off-policy updates, redirecting computation toward boundary cases that still require learning. Theoretically, we show that ReRULE yields a tighter hard-case convergence bound than pure on-policy RULE. Empirically, ReRULE improves MUSE-Books Retain Quality from 46.3 to 56.2 while adding only 5–11% training time across benchmarks. Its limited improvement on the simpler TOFU setting further supports the intended conditional behavior: replay is most beneficial when the hard/easy disparity is pronounced.