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 (math.PR) 2026-06-12

Symmetric Cooperative Motion in Higher Dimensions

arXiv:2606.13459v1 Announce Type: new Abstract: We prove a distributional convergence result for a multidimensional version of symmetric cooperative motion which was introduced and studied in one dimension in [HRW, SCM1]. Our approach relies on framing the associated recursive distributional equation as a discretization of the porous medium equation. A major challenge is to analyze the behaviour of finite difference schemes which approximate weak solutions of the porous medium equation with unbounded initial data. In overcoming this difficulty, we perform a detailed analysis of the probability mass function of symmetric cooperative motion, in which we introduce several new comparison arguments for the discrete process. Consequently, along the way, we establish a novel multidimensional convergence result for a finite difference scheme approximating the ZKB/Barenblatt solution of the porous medium equation, which is of independent interest.

02.
arXiv (CS.LG) 2026-06-11

Impact of Connectivity on Laplacian Representations in Reinforcement Learning

arXiv:2603.08558v3 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories. In this work, we prove an upper bound on the approximation error of linear value function approximation under the learned spectral features. We show how this error scales with the algebraic connectivity of the state-graph, grounding the approximation quality in the topological structure of the MDP. We further bound the error introduced by the eigenvector estimation itself, leading to an end-to-end error decomposition across the representation learning pipeline. Additionally, our expression of the Laplacian operator for the RL setting, although equivalent to existing ones, prevents some common misunderstandings, of which we show some examples from the literature. Our results hold for general (non-uniform) policies without any assumptions on the symmetry of the induced transition kernel. We validate our theoretical findings with numerical simulations on gridworld environments.

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

Segmentation-based Detection for Efficient Multi-Task Spacecraft Perception

Vision-based perception is fundamental to Space Situational Awareness and autonomous on-orbit operations such as rendezvous, docking, servicing, and navigation. However, progress in this area is limited by the scarcity of annotated space imagery and by challenging visual-domain characteristics including severe illumination changes, low signal-to-noise ratio, and high contrast. We address Stream 1 of the SPARK 2026 Challenge, which requires a single model for spacecraft classification, detection, and fine-grained component segmentation across multiple target types. We propose a compact architecture that integrates a MobileNetV3 encoder with a U-Net-style decoder, combining computational efficiency with accurate dense prediction. Detection is derived analytically from the union of predicted component masks, avoiding a separate bounding-box regression head in the single-spacecraft setting. Our method achieved an overall leaderboard score of 0.9482, with task-specific scores of 1.0000 in classification, 0.9788 in detection, and 0.8917 in segmentation. The proposed approach ranked second overall in the SPARK 2026 Challenge, demonstrating that lightweight encoder-decoder architectures can deliver strong multi-task performance for practical onboard space vision systems.

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

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, or evolving instructions, require decomposing instructions, verifying intermediate results, and making iterative corrections. While test-time scaling (TTS) has demonstrated that allocating additional inference compute for iterative reasoning substantially improves language model performance, extending this paradigm to unified multimodal models remains an open challenge. We introduce UniT, a framework for multimodal chain-of-thought test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds. UniT combines agentic data synthesis, unified model training, and flexible test-time inference to elicit cognitive behaviors including verification, subgoal decomposition, and content memory. Our key findings are: (1) unified models trained on short reasoning trajectories generalize to longer inference chains at test time; (2) sequential chain-of-thought reasoning provides a more scalable and compute-efficient TTS strategy than parallel sampling; (3) training on generation and editing trajectories improves out-of-distribution visual reasoning. These results establish multimodal test-time scaling as an effective paradigm for advancing both generation and understanding in unified models.

05.
arXiv (CS.LG) 2026-06-12

Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models

arXiv:2606.13104v1 Announce Type: new Abstract: Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual content remains poorly understood. We introduce AuthorityBench, a 220,564-prompt multi-domain benchmark that isolates how citation-based authority signals influence epistemic behavior in LLMs. The benchmark uses a fully balanced 2x2 factorial design crossing claim veracity with citation veracity, the first to do so, across four domains (general knowledge, science, law, and medicine), with controlled variation over 40 prompt templates, four venue prestige tiers, and a country-coded author name dataset. Evaluating seven models on 12 structured research questions, we find that citation presence, whether real or fabricated, consistently increases hallucination rates relative to a no-citation baseline. The effect is strongest when fabricated citations accompany true claims, raising hallucination rates by 3 to 22 percentage points and reaching 35 to 77% in the general knowledge domain, while legal claims are comparatively robust and venue prestige and author demographics show negligible impact. All datasets and evaluation code are available at: https://github.com/floating-reeds/AuthorityBench

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

Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation

arXiv:2606.13285v1 Announce Type: cross Abstract: We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such as economics and healthcare modeling. Unlike existing approaches that predict one system at a time, ESE forecasts all systems in a single pass. It first estimates the equilibrium state across systems, then generates holistic forecasts based on the difference between the current state and the estimated equilibrium. Extensive experiments on synthetic and real-world datasets, including currency exchange and COVID-19 spread modeling, demonstrate that ESE is at least as accurate as state-of-the-art (SOTA) methods while being significantly faster. In addition, ESE integrates seamlessly with conventional predictors, combining their accuracy with its exceptional efficiency and delivering a 10-70x speedup. With linear-time complexity, ESE scales far better than SOTA methods as the number of systems increases. Moreover, it remains accurate under diverse perturbations, establishing ESE as a fast, generalizable, robust, and scalable multi-prediction method.

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

Can I Buy Your KV Cache?

arXiv:2606.13361v1 Announce Type: new Abstract: Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

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

Towards Graph-Based Deep Learning for Map Generalization: Insights from Building Footprints Simplification and Aggregation

arXiv:2606.19956v1 Announce Type: new Abstract: Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-based deep learning to both tasks, reformulating simplification as node movement prediction and aggregation as link prediction within a unified graph learning framework. We evaluate representative graph neural network architectures (GCN, GAT, and GraphSAGE) on multi-scale building datasets, showing that GraphSAGE demonstrates relative strengths in link prediction accuracy, while also revealing persistent challenges in precise node movement prediction. Beyond quantitative performance, the results highlight that aggregation poses greater complexity and challenges than simplification, underscoring the difficulty of capturing higher-level spatial relationships in map generalization with current deep learning approaches. Although limitations such as data imbalance and the need for post-processing remain, the study provides valuable insights and methodological directions for advancing automated map generalization with deep learning approaches.

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

Lect\=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose Lect\=uraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, Lect\=uraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate Lect\=uraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning Lect\=uraAgents as a pedagogically well-grounded framework for personalized learning at scale.

10.
arXiv (quant-ph) 2026-06-15

Real-time pseudo entropy and modular-Hamiltonian correlations

arXiv:2606.14208v1 Announce Type: cross Abstract: Pseudo entropy is a complex-valued generalization of entanglement entropy defined from a reduced transition matrix. We study the pseudo entropy associated with a real-time transition matrix between an initial pure state and its unitary time evolution. For a subsystem $A$, we show that the short-time behavior of real-time pseudo entropy is governed by the correlation between the physical Hamiltonian $H$ and the modular Hamiltonian $K_A=-\log\rho_A$ of the initial reduced state, $ S_A(t,0)=S_A(0)-it \langle K_A(H-\langle H\rangle)\rangle + \mathcal{O}(t^2)$. For Hermitian dynamics, the initial imaginary response is controlled by the symmetrized covariance of $H$ and $K_A$ with an overall minus sign, while the initial real response is governed by their commutator. Thus the imaginary part of real-time pseudo entropy is not merely a branch artifact: it is a time-oriented modular response generated by the correlation between microscopic time evolution and subsystem coarse graining. We clarify the relation of this result to the known first law of pseudo entropy, derive an all-order expression in a Schmidt-diagonal model, recover thermal pseudo entropy as a special case, illustrate the covariance/commutator decomposition in a two-qubit model, and confirm the covariance response in transverse-field Ising-chain quenches, including a finite-size study of a modular susceptibility near the Ising critical region. We discuss how this amplitude-level oriented response can be related to ordinary entropy production, and also give a concrete $\mathcal{PT}$-symmetric toy-model illustration of the non-Hermitian extension.

11.
arXiv (CS.AI) 2026-06-18

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

arXiv:2606.18325v1 Announce Type: cross Abstract: Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner–Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

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

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

arXiv:2606.17006v1 Announce Type: cross Abstract: We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated on our held-out test split, supporting data filtering via a simple score threshold. TuneJury generalizes to both held-out test pairs and out-of-distribution benchmarks, remaining competitive with prior baselines on the latter. For generators released after training, we introduce anchor calibration, a post-hoc, per-system Bradley-Terry calibration that recovers agreement at substantially better data efficiency than from-scratch retraining. The same frozen reward drives consistent reward-axis gains across three downstream applications: inference-time best-of-N selection, DITTO-style latent optimization, and expert-iteration post-training. TuneJury is available at https://github.com/yonghyunk1m/TuneJury.

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

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents

Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms. However, existing approaches either rely on lossy compression or similarity-based retrieval, which often fail to capture temporal structure and causal dependencies required for multi-step agentic tasks. In this work, we present HORMA, a Hierarchical Organize-and-Retrieve Memory Agent that organizes experience into a file-system-like hierarchical structure, where summarized entities are linked to the corresponding raw trajectories, enabling efficient access without losing detailed information. HORMA decomposes working memory into two stages: structured memory construction and navigation-based retrieval. The construction module iteratively refines how experiences are structured by distinguishing between failures caused by missing information and those caused by misleading or overloaded context. The navigation module retrieves task-relevant context by traversing the hierarchy using a lightweight agent trained with reinforcement learning to select minimal yet sufficient context, thereby reducing latency along the critical execution path. Across ALFWorld, LoCoMo, and LongMemEval, HORMA improves task performance under constrained context budgets while requiring at most 22.17% of the baseline token usage in long conversation tasks. Compared to existing methods, it consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.

14.
arXiv (quant-ph) 2026-06-17

Intrinsic Pointer Basis and Irreversible Classicality from Coherence Contraction

arXiv:2604.23304v4 Announce Type: replace Abstract: This work analyzes an operational route to classical behavior for reduced quantum states using the intrinsic reference basis (IRB). Relative to a fixed physical conjugation, the IRB separates intrinsic populations from a real antisymmetric cohesion sector. A globally bounded cohesion index is defined and its exponential contraction is proved for phase-free dephasing dynamics aligned with the IRB; for general aligned dephasing, the corresponding modulus-based coherence functional contracts at the same computable rates. The results provide distance bounds to the IRB-diagonal description and a logarithmic upper bound on the time required to reach a prescribed experimental tolerance. The IRB projectors constitute state-derived candidate pointer sectors, and they become dynamically stable pointer sectors when the effective dephasing generator is aligned with them and damps the relevant inter-sector coherences. Degenerate population sectors lead naturally to block-classicality and protected intra-block coherence. In a two-level active sector, the cohesion index equals fringe visibility, giving a direct interferometric test of the contraction law. The construction is independent of any spacetime- or unification-emergence hypothesis and is intended as a channel-level complement to environment-induced einselection.

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

PlaceRep: Geospatial Place Representation Learning from Large-Scale Point-of-Interest Data

arXiv:2507.02921v4 Announce Type: replace-cross Abstract: Learning effective representations of urban environments requires capturing spatial structure beyond fixed administrative boundaries. Existing geospatial representation learning approaches typically aggregate Points of Interest (POIs) into pre-defined administrative regions such as census units or ZIP code areas, assigning a single embedding to each region. However, POIs often form semantically meaningful groups that extend across, within, or beyond these boundaries, defining places that better reflect human activity and urban function. To address this limitation, we propose PlaceRep, a geospatial representation learning method that constructs place-level representations by clustering spatially and semantically related POIs. PlaceRep summarizes large-scale POI graphs from U.S. Foursquare data to produce general-purpose urban region embeddings while automatically identifying places across multiple spatial scales. By eliminating model pre-training, PlaceRep provides a scalable and efficient solution for multi-granular geospatial analysis. Experiments using the tasks of population density estimation and housing price prediction as downstream tasks show that PlaceRep outperforms most state-of-the-art graph-based geospatial representation learning methods and achieves up to a x100 speedup in generating region-level representations on large-scale POI graphs. The implementation of PlaceRep is available at https://github.com/mohammadhashemii/PlaceRep.

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

Nonlinear Two-Time-Scale Stochastic Approximation: A Sharp Phase Transition and How to Beat It

arXiv:2606.14488v1 Announce Type: cross Abstract: Recent finite-time analyses of nonlinear two-time-scale stochastic approximation show that under contractive assumptions the slow iterate $Y_k$ with stepsizes $\beta_k=\Theta(k^{-1})$ and $\alpha_k=\Theta(k^{-a})$, $a\in(1/2,1)$, generally satisfies a mean-square rate of order $k^{-a}$; decoupled $k^{-1}$ rates require strong local linearity. We identify a sharp regularity-dependent boundary. In a rate-determining normal form where the slow drift contains a locally linear leakage and a nonlinear remainder of order $1+\rho$ ($\rho\in[0,1]$), the uncorrected recursion satisfies \[ \mathbb{E}\|Y_k\|^2 \le C\bigl(k^{-1}+k^{-a(1+\rho)}\bigr), \] and a matching scalar Gaussian lower bound shows that the slower term is unavoidable without modifying the update. Thus the decoupled $k^{-1}$ rate is guaranteed for the uncorrected recursion exactly when $a(1+\rho)\ge 1$. This lower bound concerns only the naive update; it is not an information-theoretic obstruction. We demonstrate this by equipping the normal-form recursion with an auxiliary online bias estimator \[ M_{k+1}=M_k+\gamma_k(R(X_k)-M_k),\qquad \beta_k\ll\gamma_k\ll\alpha_k, \] and subtracting $M_k$ from the slow update. Under the same stability, moment, and remainder assumptions, the corrected recursion achieves $\mathbb{E}\|\widetilde Y_k\|^2=O(k^{-1})$ for every $\rho\in[0,1]$, including regimes where the uncorrected update provably suffers the slower rate. Finally, we prove localized transfer theorems that extend the phase-transition mechanism to general nonlinear TTSA in fast-manifold coordinates. The proofs are non-asymptotic and rely on two Abel-transform cancellations: one for the locally linear fast-error leakage, and one for the tracked nonlinear bias.

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

Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning

arXiv:2606.19823v1 Announce Type: cross Abstract: Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WER, nearly matching the 24.44% and 25.12% seen with Real and Hybrid FT, respectively. Notably, Clone and Hybrid FT outperform Real FT for moderate-severe speakers. Clone FT achieves the best results (11.45% relative) in cross-corpus evaluation on the SAP-1102. These results suggest that zero-shot cloning provides scalable training data that circumvents the costly data collection bottleneck.

18.
arXiv (quant-ph) 2026-06-16

Quantum vortex in a fluid flow: negative effective mass and a novel mechanism for turbulence formation

arXiv:2606.15803v1 Announce Type: cross Abstract: We explore the movement of a thin, circular quantum vortex filament within an infinite cylindrical pipe. The fluid surrounding the vortex ring moves through the pipe at a non-zero velocity denoted by $v$. Our study examines the energy spectrum $E = E(p)$, where $p$ represents the total momentum of a vortex ring. We have demonstrated that the function $E(p)$ significantly depends on the velocity $v$. The discovered spectrum $E(p)$ reveals the existence of states with both negative and extremely large effective masses. We also explored the hypothesis regarding the existence of coupled vortex pairs possessing finite summary effective masses. Every pair consists of vortices that possess both positive and negative masses, with the magnitude of these masses being unrestricted. In our model, the criterion for the appearance of these states is based on comparing two numbers. The first is seen as a quantum counterpart to the Reynolds number, while the second represents its critical value for a flow with a single vortex. We also explore how this studied effect might contribute to the emergence of quantum turbulence. This study discusses a method for determining the critical Reynolds number in quantum turbulence, using the proposed model as a framework. Here, we use a new quantization technique for classical closed vortex filaments developed by the author earlier.

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

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models

arXiv:2506.17639v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and strong potential in complex robotic manipulation. However, their large parameter sizes and high inference latency hinder real-world deployment, especially on resource-constrained platforms. To address this, we conduct a systematic empirical study of model compression for VLAs. Building on these insights, we present RLRC, a three-stage compression and recovery pipeline consisting of structured pruning, performance recovery via SFT and RL, and subsequent quantization. The RL stage incorporates a critic warm-up strategy and BC loss regularization to stabilize training and preserve policy behavior. RLRC achieves up to an 8 times memory reduction and 2.3 times inference speedup while maintaining the original task success rate. Extensive experiments across multiple VLA backbones show that RLRC consistently outperforms existing compression baselines, highlighting its effectiveness for on-device deployment. Project website: https://rlrc-vla.github.io

20.
arXiv (math.PR) 2026-06-11

A Hybrid LSMC-PDE Method for Bermudan Option Pricing under the Gatheral Double Mean-Reverting Model

arXiv:2606.11237v1 Announce Type: cross Abstract: We study Bermudan option pricing under the Gatheral Double Mean-Reverting (GDMR) stochastic volatility model. The model features a variance process together with a stochastic long-run mean variance process and allows Constant Elasticity of Variance (CEV)-type exponents in the diffusion coefficients. This model is attractive since it provides a flexible specification for volatility dynamics. However, the pricing of early-exercise derivatives under the GDMR model remains largely unexplored in the literature. To address this challenge, we adapt a Hybrid Least-Squares Monte Carlo-Partial Differential Equation (LSMC-PDE) framework to the GDMR model and provide a detailed model-specific implementation. Conditioning on simulated variance paths, the pricing problem reduces to a one-dimensional problem in the asset price, which is solved by a Fourier-based approach, while the remaining dependence on the variance variables is approximated by least-squares regression. Our numerical experiments demonstrate that the Hybrid LSMC-PDE approach yields accurate pricing estimates and often lower pricing errors than plain LSMC, particularly for low and moderate numbers of simulation paths, showing the benefit of using the model structure in early-exercise option pricing.

21.
arXiv (CS.CV) 2026-06-16

Temporal Difference Learning for Diffusion Models

Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for few-step samplers. We introduce a temporal difference (TD) objective that penalizes inconsistency of the model's multi-step progress along the denoising path. By reformulating the diffusion process as a Markov reward process and casting denoising as a policy evaluation problem in reinforcement learning, we derive a unified TD approach that applies to both discrete- and continuous-time diffusion formulations. We further propose a principled sample-based reweighting method that stabilizes training. Empirically, we show that using our TD training can significantly improve sample quality measured by FID, with stronger advantages when the number of sampling steps is small, highlighting its practical utility under low-computation-budget scenarios. We provide ablation studies to justify our design choices, including pairwise loss reweighting, regularization weight, and one-step stride. Overall, our TD approach can be a general drop-in that enforces cross-time consistency and improves generation quality across different diffusion generative models.

22.
arXiv (CS.LG) 2026-06-19

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

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

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

Unassigned Agents in Compilation-based Multi-agent Path Finding

arXiv:2606.15797v1 Announce Type: new Abstract: Compilation-based techniques represent an important stream of solvers for multi-agent path finding (MAPF) due to their modularity and adaptability for non-standard variants of the problem. While in the standard MAPF the task is to navigate all agents from their initial positions to given individual goal positions without any collision, variants where a different requirement for agents is used are also relevant. Such a variant is MAPF with unassigned agents (UA-MAPF) where some agents have the same setting as in the standard MAPF with initial positions and goals while the remaining agents have the initial position but have no goal - unassigned agents. Despite unassigned agent do not need to reach any goal position they have to be moved out of the way of the standard agents if needed which represent a specific challenge. We show in this paper that UA-MAPF can be expressed in recent compilation-based techniques for MAPF based on formulating the problem as Boolean satisfiability, namely we adapt SMT-CBS and NRF-SAT, the recent solvers based on counterexample guided abstraction refinement and non-refined abstractions.

24.
arXiv (CS.LG) 2026-06-17

Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere

arXiv:2606.17603v1 Announce Type: new Abstract: In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, current frameworks typically rely on sliced statistical regularizers such as SIGReg (used in LeJEPA) and SUSReg (used in SPHERE-JEPA), which approximate this continuous objective via Monte Carlo sampling along random 1D directions. This stochasticity injects projection variance into the training gradients, destabilizing optimization, and hindering convergence. In this work, we first show that analytically integrating out these random projections natively yields a deterministic Maximum Mean Discrepancy (MMD), bypassing the variance of sliced methods. Motivated by this equivalence, we formulate full-dimensional objectives for MMD, Kernel Stein Discrepancy (KSD), and Kullback-Leibler (KL) divergence directly on the sphere to enforce a uniform distribution. To prevent spatial bias, we equip these tests with rotationally invariant kernels constructed via spectral theory, systematically evaluating two canonical families: smooth exponential decay (Heat) and strict frequency cutoff (Bandlimited) filters. Empirically, removing projection-induced noise results in more stable optimization, faster convergence, and consistent improvements over stochastic sliced regularizers on ImageNet and Galaxy10. Furthermore, we reveal that the choice of the statistical test shapes the geometry of the learned latent space: MMD and KSD favor locally clustered organization suitable for object-centric domains, whereas the continuous KDE-based KL divergence promotes fine-grained instance separation, yielding the strongest results on unclustered procedural texture retrieval.

25.
arXiv (CS.AI) 2026-06-18

Rescaling MLM-Head for Neural Sparse Retrieval

arXiv:2606.18811v1 Announce Type: cross Abstract: Learned sparse retrieval (LSR) models such as SPLADE have traditionally used BERT-style masked language models as backbone encoders. A natural expectation is that replacing BERT with stronger pretrained encoders should improve retrieval effectiveness. However, we find that under standard SPLADE training recipes, backbones with large MLM-head L2 norms can suffer performance degradation and even training collapse under standard SPLADE training recipes. We identify this failure as a scale mismatch in the MLM head: SPLADE directly uses MLM-head outputs to construct sparse lexical representations, and query-document relevance is computed by an unnormalized dot product over these representations. As a result, an inflated MLM-head scale can amplify sparse activations, distort matching scores, and destabilize contrastive training under common training settings. To address this issue, we introduce a simple initialization-time correction that rescales the MLM-head projection by a constant factor before SPLADE training. This zero-cost adjustment improves training stability without modifying the model architecture or training objective. Across both in-domain and out-of-domain retrieval benchmarks, this simple correction substantially improves large-norm backbones such as ModernBERT and Ettin, turning unstable training runs into competitive sparse retrievers. In several settings, the corrected models further match or surpass the classic BERT-SPLADE baseline. These findings suggest that the bottleneck in adapting pretrained encoders to LSR is not encoder capacity alone, but the calibration of the MLM-head scale used to construct sparse lexical representations.