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) 2026-06-12

Non-invertible symmetries out of equilibrium: Eigenstate order and Floquet physics

arXiv:2508.14213v2 Announce Type: replace-cross Abstract: Through the study of the Rep($D_8$) non-invertible symmetry, we show how non-invertible symmetries manifest in dynamics. Results are presented for dynamics generated by Hamiltonians as well as Floquet unitaries. For both examples, the role of the non-invertible symmetry is studied through the appearance of non-invertible symmetry protected edge modes. In addition, the role of the non-invertible symmetry for the Hamiltonian is studied through eigenstate order. In particular, by considering the effect of symmetry preserving disorder, the non-invertible symmetry is shown to give rise to degeneracies in the spectra of the Hamiltonian that can only be completely lifted at orders of perturbation that scale with system size. The eigenstates of disordered Hamiltonians, whose ground state correspond to non-trivial symmetry protected topological (SPT) states, are shown to have either trivial or non-trivial SPT order that are detected as non-zero expectation value of string order-parameters. In contrast, non-trivial SPT order is absent in the eigenstates of trivial SPT Hamiltonians with disorder. The interface between two different SPT phases host edge modes whose dynamics is studied numerically and analytically. The edge mode is shown to oscillate at frequencies related to different effective chain lengths that are weighted by the temperature, becoming an exact zero mode in the limit of zero temperature. A Floquet model with the non-invertible symmetry is constructed whose edge mode is shown to exhibit period-doubled dynamics at low effective-temperatures. The zero and period-doubled edge modes differ from those in conventional SPTs by being symmetric under the invertible symmetry, while being charged under the non-invertible symmetry.

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

Speech-Driven End-to-End Language Discrimination towards Chinese Dialects

Language discrimination among similar languages, varieties, and dialects is a challenging natural language processing task. The traditional text-driven focus leads to poor results. In this paper, we explore the effectiveness of speech-driven features towards language discrimination among Chinese dialects. First, we systematically explore the appropriateness of speech-driven MFCC features towards CNN-based language discrimination. Then, we design an end-to-end speech recognition model based on HMM-DNN to predict Chinese dialect words. We adopt attention to extract the discriminative words related to different Chinese dialects. Finally, through a CNN, we combine the word-level embedding and the MFCC-based features. Evaluation of two benchmark Chinese dialect corpora shows the appropriateness and effectiveness of the proposed speech-driven approach to fine-grained Chinese dialect discrimination compared to the state-of-the-art methods.

03.
arXiv (quant-ph) 2026-06-16

Scalable generation of heralded single photons via active feed-forward switching of a fiber delay line

arXiv:2606.16741v1 Announce Type: new Abstract: Quasi-deterministic single-photon generation is a key requirement for many photonic quantum technologies. Photon sources based on spontaneous parametric down-conversion (SPDC) are widely used for producing high-quality photons; however, the probabilistic nature of the process limits the generation of synchronized multi-photon states. Here, we demonstrate temporal synchronization of multiple photon-generation events using a free-space-fiber hybrid delay line with feed-forward control, enabling fast and efficient switching and scalable operation. Narrow-band, telecom-wavelength photons compatible for fiber transmission are heralded from a monolithic cavity SPDC source and synchronized across 20 time bins. This yields a sixfold enhancement in synchronized rates and enables multi-photon synchronization, with only a marginal increase of higher-order photon-number contributions.

04.
medRxiv (Medicine) 2026-06-22

Deep-Tissue Hemodynamic Sensing: Comparing Impedance and Photoplethysmography for Wearable Blood Pressure Estimation

The pursuit of continuous, cuffless blood pressure (BP) monitoring is constrained by the superficial sensing depth of photoplethysmography (PPG). Impedance plethysmography (IPG) offers deeper tissue penetration, but its comparative value over PPG remains unquantified at scale. In this comparative study of 261 participants (130 hypertensive, 131 non-hypertensive), we utilized a custom dual-modality wearable prototype to capture simultaneous IPG and PPG signals. Over 150,000 cardiac cycles were analyzed using an unsupervised archetype discovery pipeline to quantify beat-to-beat morphological heterogeneity. IPG resolved up to three distinct morphological modes per participant, whereas co-located PPG converged into highly conserved, uniform profiles. IPG captured specific signatures of pathological arterial remodeling and physiological habitus; ventral forearm IPG pulse amplitude exhibited a significant main effect for BP status (p = 0.024), a relationship absent in the co-located PPG signal. Furthermore, increasing body mass index (BMI) significantly attenuated the prevalence of steep-upstroke archetypes in IPG (p = 0.035), quantifying a likely damping effect of adipose tissue. Deep-tissue bioimpedance captures rich, heterogeneous hemodynamic signatures including arterial-dominant morphologies that are invisible to optical sensors. Transitioning from optical pulse wave analysis to bioimpedance-based models may offer a promising pathway for accurate wearable cardiovascular monitoring.

05.
arXiv (CS.LG) 2026-06-15

Compressed Computation is (probably) not Computation in Superposition

arXiv:2606.14673v1 Announce Type: new Abstract: We study whether the Compressed Computation (CC) toy model (Braun et al., 2025) is an instance of computation in superposition. The CC model appears to compute 100 ReLU functions with just 50 neurons, achieving a better loss than expected from only representing 50 ReLU functions. We show that the model mixes inputs via its noisy residual stream, corresponding to an unintended mixing matrix in the labels. Splitting the training objective into the ReLU term and the mixing term, we find that performance gains scale with the magnitude of the mixing matrix and vanish when the matrix is removed. The learned neuron directions concentrate in the subspace associated with the top 50 eigenvalues of the mixing matrix, suggesting that the mixing term governs the solution. Finally, a semi-non-negative matrix factorization (SNMF) baseline derived solely from the mixing matrix reproduces the qualitative loss profile and improves on prior baselines, though it does not match the trained model. These results suggest CC is not a suitable toy model of computation in superposition.

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

NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama

Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, with cross-lingual evaluation across four Indic languages (Hindi, Tamil, Telugu, Marathi). We introduce N-VSSM, a Narrative Variational State-Space Model that maintains a structured 256-dimensional latent world state over more than 200 episodes via a Mamba-2 backbone with an event-conditioned posterior and an 8B decoder. N-VSSM holds plot-beat F1 >= 0.84 across all horizons at 4x lower compute than the closed-frontier band. A learned Cultural Transfer Function lifts cross-language fidelity by +0.20 to +0.23 Likert points. In a within-subjects writer study (n = 12 professional authors, 240 trials), N-VSSM is preferred over Claude Opus 4.5 on long-arc consistency 71% of the time and rated +1.3 Likert points higher on controllability.

07.
arXiv (CS.AI) 2026-06-11

On the Geometry of On-Policy Distillation

arXiv:2606.07082v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of OPD updates in parameter space and compare it with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). A suite of parameter-space diagnostics consistently places OPD in a relaxed off-principal regime: compared with SFT, its updates affect fewer weights and avoid principal directions more strongly, while compared with RLVR, they remain less tightly constrained. Beyond this static localization, OPD exhibits subspace locking: its cumulative updates rapidly enter a narrow low-dimensional channel. Constraining training to the update subspace formed early in training preserves OPD performance but substantially degrades SFT, indicating that the locked subspace is functionally sufficient for OPD. Control experiments further show that sparsifying the update tokens and shifting rollout generation off-policy preserve the rank dynamics, whereas mixing the OPD objective with RLVR changes them. Overall, these results suggest that OPD is not merely an intermediate point between SFT and RLVR, but induces its own update geometry in parameter space.

08.
arXiv (CS.CL) 2026-06-19

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing complex instructions into actionable denoising steps, even with correct MLLM encodings. To this end, we propose Endogenous Chain-of-Thought (EndoCoT), a novel framework that first activates MLLMs' reasoning potential by iteratively refining latent thought states through an iterative thought guidance module, and then bridges these states to the DiT's denoising process. Second, a terminal thought grounding module is applied to ensure the reasoning trajectory remains grounded in textual supervision by aligning the final state with ground-truth answers. With these two components, the MLLM text encoder delivers meticulously reasoned guidance, enabling the DiT to execute it progressively and ultimately solve complex tasks in a step-by-step manner. Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points. The code and dataset are publicly available at https://internlm.github.io/EndoCoT/.

09.
arXiv (CS.LG) 2026-06-12

Auditing Discriminatory Patterns in Mortgage Lending Through Association Rules and Fair Binning

arXiv:2606.12435v1 Announce Type: cross Abstract: Mortgage lending in the United States exhibits persistent racial and gender disparities. We investigate whether standard data preprocessing steps, specifically attribute binning, amplify these disparities in downstream pattern mining. Using 103,481 cleaned mortgage applications from the HMDA 2023 dataset (Chicago metropolitan area), we build a three-stage pipeline: (1) a PySpark data cleaning and binning pipeline that implements both standard equal-frequency binning and the epsilon-biased fair binning algorithm from Asudeh et al. [1], (2) FP-Growth association rule mining that compares denial patterns under both binning regimes, and (3) K-Means clustering with a per-cluster disparate impact audit. Our standard binning shows 9.63% racial bias in income discretization, consistent with the 8-10% reported in prior work. Fair binning with seven race groups is infeasible at epsilon=0.03 and only succeeds at epsilon=0.08 with a Price of Fairness of 29.4%. FP-Growth reveals that high debt-to-income ratio is the dominant denial predictor (67.2% confidence, 2.81 lift), while racial bias does not appear as explicit high-support rules. However, K-Means clustering followed by a disparate impact audit flags 10 out of 45 cluster-group pairs, showing that Black applicants face significantly higher denial rates than White applicants even among financially similar groups.

10.
arXiv (CS.CV) 2026-06-17

Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition

Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework in which (i) a VLM orchestrator chunks the video and proposes a top-k candidate label list per segment, (ii) an ensemble of heterogeneous VLM specialists, drawn from different open model families, engages in a structured deliberation that includes a peer-consultation round of questions, and (iii) agent rankings are aggregated with a Borda count and the orchestrator re-ranks its own prediction in light of the specialists' evidence. The entire pipeline runs locally with no fine-tuning. Experiments show that our method positively improves zero-shot action recognition performance over the baseline, highlighting the influence of a heterogeneous deliberation step, showing that the gain stems from decorrelated model priors rather than from additional compute.

11.
arXiv (CS.CV) 2026-06-16

Semantic Editing with Coupled Stochastic Differential Equations

Editing the content of an image with a pretrained text-to-image model remains challenging. Existing methods often distort fine details or introduce unintended artifacts. We propose using coupled stochastic differential equations (coupled SDEs) to guide the sampling process of any pre-trained generative model that can be sampled by solving an SDE, including diffusion and rectified flow models. By driving both the source image and the edited image with the same correlated noise, our approach steers new samples toward the desired semantics while preserving visual similarity to the source. The method works out-of-the-box, without retraining or auxiliary networks, and achieves high prompt fidelity along with near-pixel-level consistency. These results position coupled SDEs as a simple yet powerful tool for controlled generative AI. Project page: https://z-jianxin.github.io/syncSDE-release/. Code: https://github.com/Z-Jianxin/syncSDE-release.

12.
arXiv (quant-ph) 2026-06-17

Fabless Quantum Chip Design and Commercial Production

arXiv:2606.17956v1 Announce Type: new Abstract: This paper proposes a fabless quantum-chip design and production architecture for superconducting quantum computing, centered on the SPICE-Q multiphysics simulation framework. The proposed ecosystem connects process-certified quantum PDKs, parameterized device cells, traceable model cards, SPICE-Q physical modeling languages, unified Q-EDA flows, foundry sign-off rules, cryogenic test feedback, and reusable quantum IP. In this model, design firms do not merely outsource fabrication; they prepare verified tape-outs under standardized process constraints and calibrated physical models. Its economic value lies in reducing repetitive device debugging, process exploration, and low-level layout effort, while its feasibility depends on PDK maturity, foundry yield, cryogenic test throughput, model-prediction accuracy, data-feedback mechanisms, and IP licensing boundaries. We argue that superconducting quantum chips can move from the current largely vertically integrated development model toward a fabless-foundry ecosystem only when hardware design is supported by standardized, verifiable, and reusable software and process interfaces. The required pillars are certified PDKs, PCell-based parameterized design, SPICE-Q cross-physics simulation, end-to-end Q-EDA automation, and a tradable quantum-IP market. By adapting lessons from the classical semiconductor industry to quantum hardware, this framework defines a path toward scalable, manufacturable, and commercially reusable superconducting quantum-chip design.

13.
arXiv (CS.CL) 2026-06-11

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

14.
arXiv (CS.AI) 2026-06-12

Foresight: Iterative Reasoning About Clues that Matter for Navigation

arXiv:2606.12550v1 Announce Type: cross Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal. For instance, reaching an out-of-view destination may require interpreting ramps, signs, or detours that reveal where to go or which route to take. Prior works are limited by their reliance on known navigation factors and closed-set factor categories, or identify cues before motion planning and miss plan-dependent cues. We argue that pretrained Vision-Language Models (VLMs) can discover novel instruction-relevant cues, but require adaptation to focus on which cues matter and how they should influence motion planning. We realize these ideas in Foresight, a test-time framework in which a finetuned VLM alternates between proposing image-space motion plans and critiquing them using the language goal and visual context. Subsequent plans are conditioned on prior critiques, enabling iterative motion refinement before execution. To align plan critiques and refinements with open-set behavior preferences, we learn a reward model from human feedback and use it to post-train the VLM with reinforcement learning in the plan-critique loop. In offline evaluations and 6 real-world environments, Foresight improves average task success by 37% and reduces interventions per mission by 52% relative to state-of-the-art test-time reasoning and foundation-model baselines, while running in real-time on a Jetson AGX Orin. We will release code, data, and training details to support future work on test-time reasoning for robot motion refinement. Additional videos at: https://amrl.cs.utexas.edu/foresight

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

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

arXiv:2606.12918v1 Announce Type: cross Abstract: Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

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

Towards Understanding What State Space Models Learn About Code

arXiv:2602.06774v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture. Prior work shows that, when trained under comparable conditions, SSMs can match or surpass Transformers on code understanding tasks. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models learn along with the direct comparison between SSM and Transformer models in this domain. Our analysis shows that SSMs capture syntactic and semantic structure more effectively than Transformers during pretraining but forgets certain relations during fine-tuning on some tasks. To investigate this behavior, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model by upto +6 MRR on NLCodeSearch. This demonstrates that our analysis not only explains model behavior but also leads directly to better designs.

17.
medRxiv (Medicine) 2026-06-23

Innate immunity associates with protection from pneumococcal colonisation, but colonisation does not confer capsule-independent protection

Nasopharyngeal colonisation with Streptococcus pneumoniae is a prerequisite for transmission and disease and represents an important immunising event. While colonisation induces serotype-specific immunity, the mechanisms underlying heterologous protection remain unclear. We developed a controlled human infection model using pneumococcal serotype 15B and investigated colonisation dynamics, immunogenicity, and cross-protection against subsequent heterologous challenge with serotype 6B. Fifty-four healthy adults were intranasally inoculated with 15B at escalating doses. Colonisation rates peaked at 31.4% with 8 x 10 CFU per naris, lower than those historically observed with 6B and 3 strains. Density was also lower than previously observed with other strains. In vitro assays demonstrated that 15B adhered more readily to epithelial cells than 6B, but was less efficiently internalised, potentially reducing attack rates and colonisation density. Colonisation with 15B induced capsular polysaccharide-specific serum IgG, but baseline humoral immune measures did not predict protection from acquisition. Prior colonisation with 15B did not reduce acquisition of 6B upon re-challenge. Analysis of nasal microbiopsy samples revealed distinct innate activation signatures. Resistance to colonisation was associated with elevated baseline MIP-1 and MIP-1{beta} responses upon in vitro stimulation, whereas carriage was associated with enhanced chemokine and IL-6 responses. Local innate immune activation, rather than circulating antibody responses alone, may therefore contribute to colonisation control. We demonstrate that experimental colonisation with 15B does not confer heterologous protection against 6B and highlight the importance of mucosal innate immune conditioning in serotype-independent defence. Strategies enhancing nasal innate immune recruitment and activation may be required for broader protection against pneumococcal colonisation.

18.
arXiv (quant-ph) 2026-06-17

Time-spectral control of accidental coincidences in daylight entanglement-based free-space QKD

arXiv:2606.17365v1 Announce Type: new Abstract: Daylight entanglement-based free-space quantum key distribution (QKD) is limited by accidental coincidences from receiver-admitted background light. We develop and experimentally validate a receiver-level framework linking receiver bandwidth, accepted temporal width, and background-noise density to Bob singles, sifted-key rate, error rate, and quantum bit error rate (QBER) in telecom-wavelength BBM92 QKD. Indoor sweeps show that useful sifted counts saturate near the source-matched bandwidth, whereas broader bandwidth or higher background mainly increases accidental contamination. Increasing the accepted temporal width leaves Bob singles nearly unchanged but directly raises QBER by enlarging the random-overlap probability. A two-dimensional design map shows that the temporal-window margin contracts rapidly with increasing background-to-signal ratio, while the bandwidth margin remains comparatively broad near source-matched filtering. A 10 m rooftop daylight experiment demonstrates operation in the predicted low-accidental regime, yielding a mean sifted-key rate of 2,811 cps and a mean QBER of 4.43%.

19.
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.

20.
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.

21.
arXiv (CS.CL) 2026-06-12

Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates. To unlock this potential, we present Spiffy, a speculative decoding algorithm to accelerate dLLM inference while provably preserving the model's output distribution. This work addresses the unique challenges involved in applying ideas from speculative decoding of AR-LLMs to dLLMs. Spiffy performs auto-speculation to eliminate the overheads of an independent draft model, structuring draft states in the form of a novel directed draft graph to take advantage of the bidirectional, blockwise nature of dLLM generation. These draft graphs are calibrated offline to maximize acceptance rates and are dynamically pruned during inference for improved computational efficiency. We present a detailed formulation of Spiffy and demonstrate its ability to accelerate LLaDA, Dream, and SDAR models in combination with KV caching and threshold-based dynamic unmasking leading to up to $8.6\times$ reduction in model inferences and $6.3\times$ acceleration in token rate.

22.
arXiv (math.PR) 2026-06-16

The Ornstein$-$Uhlenbeck process on $\mathscr P_2$ with a volatility operator

arXiv:2606.14917v1 Announce Type: new Abstract: We analyze a diffusion ${(\mu_t)}_{t\geq 0}$ on the $2$-Wasserstein space $\mathscr P_2$ over $\mathbb R^d$ for which \begin{equation*} |\mu_t|_2^2-|\mu_0|_2^2-2ct+2\int_0 ^t|\mu_s|_2^2\,d s,\qquad t\geq 0, \end{equation*} is a martingale, where the constant $c\in(0,\infty)$ equals the trace of a volatility operator on a Hilbert space and $|\mu_t|_2:=(\int_{\mathbb R^d}x^T x\mu_t(d x ))^{1/2}$. The invariant measure of ${(\mu_t)}_{t\geq 0}$ is a Gaussian on $\mathscr P_2$, as introduced by P. Ren and F.-Y. Wang. Moreover, the Dirichlet form and its generator are given explicitly on a dense subspace of $L^2$.

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

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

arXiv:2606.15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety. Yet most known instances have been discovered post hoc in frontier systems where controlled study is impractical. We adapt the AI Safety Gridworlds framework into a text-based evaluation suite that reformulates classic reinforcement learning safety tasks for language-based agents. Across frontier and mid-scale models, we find that specification gaming emerges zero-shot: models systematically achieve high observed reward while underperforming on hidden safety objectives, and even apparently safe behaviors can reflect misunderstanding rather than principled safety. Reinforcement learning does not correct these failures: direct reward optimization widens the gap between observed and hidden reward, as the model's initial competence causes it to lock into locally rewarding strategies before discovering safer alternatives. This pattern persists across model scales (1.5B–14B) and is not resolved by finer credit assignment, exploration prompts, or entropy regularization. Our results show that reward hacking arises naturally when optimizing proxy objectives with capable language model agents and resists standard mitigations, suggesting that proxy-reward failures in agentic settings may require approaches beyond standard exploration and credit-assignment fixes. To facilitate reproducibility, the code for this work is available at \href{https://github.com/asparius/verl-agent-safety}{our public repository}.

24.
PLOS Computational Biology 2026-06-18

Mechanisms underlying spontaneous and evoked calcium responses in oligodendrocyte precursor cells: A modeling investigation

作者:

by Martin Lardy, Leqi Wang, Claire Guerrier, Veronica T. Cheli, Pablo M. Paez, Anmar Khadra Calcium (Ca2+) signaling has emerged as a central regulator of activity-dependent myelination in oligodendrocytes. These Ca2+ signals encompass both the stimulus-independent spontaneous Ca2+ local transients (SCaLTs) generated intrinsically in a voltage-independent manner or facilitated by the membrane voltage, as well as evoked responses triggered by ATP and glutamate release. To investigate the regulatory mechanisms underlying this combined spiking activity, we developed a stochastic spatiotemporal flux-balance model of Ca2+ transients in oligodendrocyte precursor cells (OPCs). The model incorporates all the relevant fluxes in these cells and integrates membrane voltage dynamics with a Ca2+-induced Ca2+-release (CICR) mechanism using parameters fitted to Ca2+ fluorescence recordings. The model reproduced the intrinsic and voltage-facilitated SCaLTs in OPCs in the absence of purinergic and glutamatergic receptors, and captured the three distinct patterns of evoked Ca2+ responses induced by prolonged ATP and glutamate stimulations identified using machine classifier. The model highlighted the role of ATP and glutamate in generating these clusters, and showed that the fast dynamics of CICR is key to producing these evoked responses. Further analysis of the model also revealed that voltage-gated L- and T-type Ca2+ channels slightly increase the frequency of SCaLTs, while stimulation with ATP and glutamate, using randomly distributed pulses mimicking in vivo conditions, leads to an increase in both the amplitudes of Ca2+ spikes (i.e., the combination of SCaLTs and evoked responses) and the prevalence of wide spikes, especially upon glutamate stimulation. Bifurcation analysis of the deterministic version of the model, in the absence of diffusion, demonstrated that ATP and glutamate stimulation can shift the system into an oscillatory regime, thereby increasing the deterministic component of SCaLT dynamics. This study thus offers a comprehensive representation of OPC Ca2+ transients linking recorded in vitro behaviors to in vivo dynamics.

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

Adversarial Attacks Leverage Interference Between Features in Superposition

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decision boundary structure, but none provides a representation-level mechanism that explains why specific perturbations succeed and why attacks transfer between models. In this paper, we show that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, vulnerability can arise from superposition - the phenomenon where networks represent more concepts than they have dimensions, forcing non-orthogonal representation and thus interference. This interference causes perturbations targeting one representation to affect others, creating vulnerabilities determined by interference patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. The resulting attacks are predictable: PGD-discovered perturbations align with theoretically optimal perturbations derived from the interference geometry. Models trained on similar data develop similar interference patterns, explaining attack transferability. We then show that successful attacks on image classifiers exhibit the structure predicted by our proposed mechanism. These findings reveal that adversarial vulnerability can be a byproduct of networks' representational compression, complementing existing explanations based on data properties or architectural factors.