arXiv:2607.16543v1 Announce Type: new
Abstract: As enterprises increasingly adopt Software-as-a-Service (SaaS) platforms for mission-critical functions, onboarding these services has emerged as a complex challenge extending well beyond procurement and basic security review. In regulated environments, SaaS onboarding must address multiple interdependent control domains, including Third-Party Risk Management (TPRM), cybersecurity assessment, Identity and Access Management (IAM), and disaster recovery (DR), which are often executed in isolation, resulting in delayed go-lives, duplicated assessments, unclear ownership, and residual operational risk. This paper proposes a control-driven, end-to-end SaaS onboarding framework that integrates TPRM, cybersecurity, IAM, and DR into a unified lifecycle model. The framework introduces a stage-based approach spanning intake and risk scoping, architecture validation, identity design, resilience assessment, and post-production governance. Key contributions include: (1) a structured SaaS onboarding lifecycle emphasizing sequencing and dependency management across control domains; (2) a cross-domain control mapping highlighting failure modes caused by siloed reviews; and (3) practical design patterns for secure connectivity, federated identity, least-privilege access, and shared-responsibility disaster recovery. Supported by operational lessons from enterprise-scale implementations and a reference governance checklist, the framework helps organizations reduce onboarding friction, improve auditability, and strengthen the security and resilience posture of SaaS-enabled platforms.
Science Journals
arXiv:2607.17117v1 Announce Type: new
Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not expose information that persists across a sequence. We introduce Persistent Sparse Autoencoders (Persistent SAEs), which extend standard SAEs by learning a persistence coefficient for each feature, allowing the model to learn which features should persist and for how long. Our experiments show that they retain competitive reconstruction quality while learning a spectrum of feature timescales: fast features behave as locally interpretable detectors, whereas slow features concentrate topic-level information in a persistent state. Moreover, as shown in a prompt-injection monitoring case study, slow features preserve detection signals and remain causally effective over long contexts. These results suggest that Persistent SAEs open up new opportunities for interpreting and monitoring language models through persistent semantic representations.
arXiv:2105.00990v3 Announce Type: replace
Abstract: Autonomous control in high-dimensional, continuous state spaces is a persistent and important challenge in the fields of robotics and artificial intelligence. Because of high risk and complexity, the adoption of AI for autonomous combat systems has been a long-standing difficulty. In order to address these issues, DARPA's AlphaDogfight Trials (ADT) program sought to vet the feasibility of and increase trust in AI for autonomously piloting an F-16 in simulated air-to-air combat. Our submission to ADT solves the high-dimensional, continuous control problem using a novel hierarchical deep reinforcement learning approach consisting of a high-level policy selector and a set of separately trained low-level policies specialized for excelling in specific regions of the state space. Both levels of the hierarchy are trained using off-policy, maximum entropy methods with expert knowledge integrated through reward shaping. Our approach outperformed human expert pilots and achieved a second-place rank in the ADT championship event.
arXiv:2607.18144v1 Announce Type: new
Abstract: Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are capable of navigating complex 3D constraints compared to established baselines such as specialized diffusion models. We consider 3D ligand generation conditioned on protein pockets together with ligand- and interaction-derived spatial constraints, including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. To enable this evaluation, we introduce 3D-Fit - a token-efficient benchmarking strategy for assessing LLM performance on multi-conditioned spatial molecule generation. Our findings reveal a clear pattern in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.
arXiv:2607.16812v1 Announce Type: new
Abstract: The rapid emergence of sixth-generation (6G) networks and the low-altitude economy has accelerated the evolution of wireless infrastructures toward air-ground integrated coverage networks (AGICNs), which seamlessly fuse terrestrial and aerial communication resources. However, existing AGICN studies primarily focus on coverage enhancement, while ignoring sustainability. Pursuing sustainable AGICNs introduces new challenges due to the multidimensional resource coupling across heterogeneous air-ground segments. In view of this, this paper presents a comprehensive survey and tutorial on sustainable AGICNs, aiming to balance coverage capacity with carbon efficiency in low-altitude economies. An integrated sensing, communication, and computation (ISCC)-driven architecture, which enables dynamic resource orchestration through closed-loop control, is proposed. We thus introduce a multi-dimensional sustainability metric system, which covers operational efficiency, task-oriented performance, and full lifecycle carbon emissions, to quantify energy and carbon footprints. We review enabling technologies, including artificial intelligence, hybrid precoding, integrated sensing and communication, and simultaneous wireless information and power transfer, and discuss their integration into the ISCC framework to minimize energy consumption while maintaining robust coverage. Experimental results on a real-world testbed demonstrate a 20% reduction in power consumption while achieving over 90% coverage probability, highlighting the feasibility of sustainable AGICNs for future green networks.
arXiv:2607.17336v1 Announce Type: new
Abstract: Drift detection is a core component of production machine learning monitoring systems, where detectors are used to compare incoming data with a reference distribution and trigger alerts when changes occur. However, these detectors are often evaluated in research settings that emphasize detection accuracy under synthetic shifts, while overlooking false alarms under continuous monitoring. In production environments, models are monitored repeatedly over time and across many features, and even small false positive rates can accumulate into frequent alerts, leading to alarm fatigue. We empirically analyze false positive behavior across five commonly used drift detectors: PSI, KS, MMD, LSDD, and adversarial validation. Consistent with existing literature, PSI exhibits strong sensitivity to batch size, producing frequent false alarms at small sample sizes; however, we further observe that its behavior stabilizes and improves substantially once batch sizes exceed approximately 200 samples. In contrast, KS, MMD, and LSDD display persistent fluctuations across batch sizes, while remaining comparatively more reliable than PSI in low-data regimes. Applying a Bonferroni correction reduces false positive rates, but often at the cost of reduced true positive sensitivity, reinforcing the well-known stability - sensitivity trade-off in drift detection. This work provides a systematic comparison of false positive behavior across multiple drift detectors under continuous monitoring conditions. We identify tradeoffs across detector families and provide practical guidelines for selecting and calibrating drift detectors in production ML systems.
arXiv:2607.18033v1 Announce Type: new
Abstract: As with most ``in the wild'' collections of the natural world, the North America Camera Trap Images (NACTI) dataset exhibits long-tailed class imbalance, with the largest class covering over 50% of its 3.7M images. Building on the PyTorch Wildlife model, we systematically evaluate Long-Tail Recognition (LTR) methodologies to benchmark species recognition performance, including specialised loss functions and LTR-sensitive regularisation. Our optimised configuration achieves state-of-the-art 99.40% Top-1 accuracy on the NACTI test split, significantly outperforming standard baselines and previously reported top performances. To assess robustness under domain shifts (e.g., night-time captures, occlusion, motion-blur), we extend our evaluation across three independent reduced-bias test sets (including ENA-Detection, Caltech Camera Traps and Missouri Camera Traps). Across these out-of-distribution (OOD) evaluations, our LTR-enhanced model consistently demonstrates substantially stronger generalisation capabilities compared to standard cross-entropy approaches. However, qualitative and quantitative analyses underline that current LTR optimisations cannot fully overcome representational bottlenecks, resulting in catastrophic predictive breakdown for rare `Tail' classes under severe domain shift. For maximum reproducibility, all dataset splits, key code, and network weights are published with this paper at https://github.com/ZehuaLiuY/Species-Classification.
arXiv:2607.16612v1 Announce Type: cross
Abstract: Backpropagation makes training deep networks memory intensive because it must store intermediate activations. Forward-mode methods avoid this cost, but their gradient estimates become increasingly noisy as the number of trained parameters grows. We introduce Split Forward Gradient (Split-FG), which splits a network at an intermediate representation: it computes the output head gradient exactly and estimates only the trunk gradient with a Jacobian--vector product. This reduces estimator variance and requires no backward pass through the trunk, while retaining an Adam-style convergence guarantee. Our experiments reveal an important practical failure mode. On WikiText-103, naive forward-gradient training of the trunk performs worse than leaving a randomly initialized trunk frozen, likely because Adam updates every noisy, under-determined trunk coordinate too aggressively. Simply using a much smaller learning rate for the trunk reverses this result: a $16$M-parameter GPT-2-style model reaches validation perplexity $387$, compared with $668$ for the frozen-trunk control and $2{,}885$ for a matched pure forward-gradient baseline (backpropagation reaches $150$). Split-FG also produces the strongest backprop-free results on our tabular benchmarks and reaches $60.5\%$ on CIFAR-10 and $35.2\%$ on CIFAR-100 with a heavy-head design. It reduces peak memory by up to $35\%$ relative to matched backpropagation, although the performance gap widens as the forward-mode trunk grows.
arXiv:2607.17121v1 Announce Type: new
Abstract: Skeleton-based emotion recognition from body motion remains challenging because emotional expressions are often characterized by subtle dynamic and relational motion cues, and hard labels may not fully capture ambiguity among related emotion categories. For the DIEM-A task in the MMAC ACII 2026 Challenge, we propose a multi-branch skeleton-based emotion recognition framework that combines a 6D rotation-based branch, a part-aware kinetic multi-stream branch, and a metadata-conditioned weak label distribution learning (LDL) branch. The branches are trained independently and fused by a probability-level ensemble at inference time. In 10-fold leave-performer-out cross-validation, the proposed framework improves Accuracy from 0.271 to 0.366 and Macro-F1 from 0.252 to 0.353 over the rotation-based baseline. Explainability ablations show that velocity and bone streams, as well as arm and leg regions, provide important cues for recognizing emotional body motion.
arXiv:2607.17888v1 Announce Type: new
Abstract: In this work, we investigate the nonlinear dynamics of isolated current-carrying edge-localized mode (ELM) filaments using a reduced electromagnetic fluid model in slab geometry. Numerical simulations show that unidirectional parallel current significantly suppresses radial filament velocity and reduces the outward propagation velocity by weakening the curvature-driven interchange force. The reduction in radial velocity is found to follow a modified scaling relation, demonstrating that increasing current progressively weakens outward filament propagation. Analysis of the vorticity equation shows that the electromagnetic current source changes from a dipolar structure to a remarkable spiral pattern, and overcomes the conventional curvature drive in the nonlinear phase. This current-driven source directly imprints its topology on the vorticity field, resulting in spiral vorticity, enhanced angular momentum, increased rotational energy, and localized shear layers. The filament therefore undergoes a transition from a conventional propagating state to a rotationally self-organized electromagnetic structure. These findings demonstrate that parallel current acts as an effective electromagnetic vorticity source and provides new insight into the nonlinear dynamics of ELM filaments in tokamak edge plasmas.
arXiv:2106.04770v2 Announce Type: replace
Abstract: We study parameter nonuniqueness in continuous-width depth-two fully connected neural networks. Our main contribution is a direct method for solving the neural-network equation $S[\gamma]=f$. Starting from the Fourier expression of the synthesis operator, separation of variables produces a ridgelet particular solution and identifies every homogeneous direction. To isolate the argument, we first prove an abstract reconstruction formula for unitary factorizations, yielding the adjoint, normalized right inverse, and orthogonal solution geometry. We then specialize this formula to neural-network synthesis: for tempered-distribution activations such as ReLU, we equip the activation class $A_{s,t}$ with a Hilbert structure, construct compatible coefficient and parameter Hilbert spaces $H_{s,t}$ and $G_{s,t}$, and prove that $S:G_{s,t}\to L^2(\mathbb R^m)$ is bounded. The resulting ridgelet expansion exhausts the null space and the complete solution set and identifies the unique minimum-norm parameter distribution. Concrete examples give adjoint ridgelet functions for standard activations. Further developments show that finite-measure null elements admit normalized width-$N$ discretizations with $O(N^{-1/2})$ output error and characterize how additive parameter perturbations can reveal information encoded in the null space. A Lean 4 blueprint for the main results is available at https://shosonoda.github.io/lean-ridgelet/ .
arXiv:2607.16616v1 Announce Type: cross
Abstract: Solid oxide fuel cells enable efficient conversion of hydrogen into electricity. However, the limited availability of materials for their cathode, anode, and electrolyte remains a concern. This study introduces three high-entropy oxide perovskites as novel electrolyte materials for fuel cells (Ba0.50Sr0.50)(Ti0.33Zr0.33Hf0.33)O3 with s0/d0 cations, (Ba0.50Sr0.50)(Ga0.33In0.33Sn0.33)O3 with s0/d10 cations, and (Ba0.50Sr0.50)(Ti0.33Zr0.33Sn0.33)O3 with mixed s0/d0/d10 cations. Through sequential sintering by high-pressure torsion processing and calcination, these perovskites were synthesized and then printed with a thickness of about 6-10 microns on a Ni-SrZr0.5Ce0.4Y0.1O3 substrate as an anode and then coated with Ba0.5La0.5CoO3 as a cathode. Electrochemical analysis and impedance spectroscopy show that (Ba0.50Sr0.50)(Ti0.33Zr0.33Sn0.33)O3 with s0/d0/d10 cations exhibits the best performance with negligible current leakage and lowest ohmic resistance, while its maximum power density reaches 0.53 W.cm-2 at 973 K. Complementary synchrotron X-ray absorption and photoelectron spectroscopy analyses indicate that the superior performance of (Ba0.50Sr0.50)(Ti0.33Zr0.33Sn0.33)O3 correlates with its heterogeneous electronic structure characterized by tailored unoccupied d-orbital states, and favorable local metal-oxygen bond lengths and extrinsic oxygen vacancies. This investigation demonstrates the significance of high-entropy perovskites with mixed s0/d0/d10 cations as new rare-earth metal-free ion-conducting electrolytes, particularly for protonic solid oxide fuel cells.
arXiv:2607.17122v1 Announce Type: new
Abstract: Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports.
arXiv:2607.18062v1 Announce Type: new
Abstract: This paper focuses on the problem of Embodied Task Planning, where an agent is required to execute a sequence of atomic actions within an interactive environment to complete a user-specified task. Though a variety of simulators and datasets have previously been built for this task, these efforts are largely isolated, with each using its own observation format, action type, and task domain. This fragmentation complicates comprehensive model evaluation and hinders the scalability of training data. As an effort towards generalizable embodied planning, we propose UniETP, a unified interface integrating four commonly-used simulators (AI2-THOR, VirtualHome, Habitat, BEHAVIOR). UniETP is characterized by both standardization and diversity. On one hand, it formalizes all the simulators into a consistent observation and action space, and builds an evaluation system to support complicated task goal. On the other hand, it enhances task diversity and complexity across dimensions like task logic, instance grounding, and instruction understanding, constructing a new dataset with varied levels of difficulty in an automatic manner. Extensive experiments on the proposed benchmark are conducted to evaluate the embodied planning capabilities of recent models and analyze the performance bottlenecks. Codes and data will be available at https://github.com/woyut/UniETP .
arXiv:2607.16638v1 Announce Type: cross
Abstract: Principal component regression (PCR) regularizes high-dimensional prediction by choosing a spectral cutoff, but rank selection cannot correct systematic inflation of the retained empirical eigenvalues. We study clean Gaussian random designs in which the aggregate covariance tail creates a nearly scalar sample-space floor comparable to the predictive head scale. De-floored principal component regression (dPCR) retains the cutoff and subtracts an estimated floor from the retained denominators. We prove an ordinary-PCR prediction-risk lower bound uniform over all ranks and a high-probability dPCR upper bound. When the floor is sharp and inexpensive to remove in population prediction risk, the conditional risk of dPCR is asymptotically negligible relative to that of the best ordinary PCR rank. An exact risk decomposition explains the separation: denominator inflation is governed by first spectral mass, whereas the clean prediction cost of correction is governed by squared spectral mass. A same-sample trimmed-mean floor estimate attains the oracle dPCR upper-bound rate at a prespecified rank, and the separation persists under approximate predictive alignment when the tail prediction-energy fraction vanishes. Separate pointwise fixed-aspect formulas show that the risk-optimal positive scalar correction improves rank-$1$ PCR, whereas mean-floor subtraction is generally not optimal for a broad Marchenko--Pastur bulk.
arXiv:2607.16981v1 Announce Type: new
Abstract: An agent acting under partial observability must decide when to gather information and which observations are worth their cost. Standard POMDPs value information only through its eventual effect on reward. The $\rho$-POMDP framework instead rewards uncertainty reduction directly, through a belief-dependent utility $\rho$, but in practice both the choice of $\rho$ and the weight placed on it are tuned by hand for every task. We show that active inference removes this tuning entirely. Minimizing Expected Free Energy (EFE) is exactly equivalent to solving a $\rho$-POMDP whose utility is expected information gain, and the exploration weight is fixed at $w=1$ because the variational bound expresses pragmatic and epistemic value in the same units (nats). We prove this equivalence for observe-then-commit POMDPs and extend it to factored observation POMDPs, a broader class that covers interleaved observe-act problems such as non-destructive testing and mobile sensing, where gathering information leaves the hidden state unchanged. Experiments support the theory. Across environments ranging from the classic Tiger problem to RockSample and a new Structural Inspection benchmark with over 65,000 states, the untuned weight matches or outperforms reward-only planning at the same horizon, avoids the over-exploration of bonuses tuned per task, and sits near the reward-maximizing knee of the success-reward Pareto frontier. The practical payoff is an exploration objective that works out of the box. In applications such as fault detection and medical screening, where every test has a price and every missed fault has a cost, EFE supplies a belief-dependent utility that is derived rather than tuned.
arXiv:2607.16264v1 Announce Type: new
Abstract: The study of the Earth's behavior has greatly benefited from the widespread deployment of Global Navigation Satellite Systems (GNSS), enabling large-scale monitoring of crustal deformation and long-term geophysical trends. In this work, we focus on the North American region, where complex tectonic activity, particularly along the western margin, requires methods capable of processing and analyzing large collections of GNSS time series distributed across extensive spatial domains. Analyzing the full GNSS network provides a coherent view of deformation across multiple scales, allowing detection of long-wavelength signals, subtle intraplate strain and regionally consistent velocity fields that are difficult to capture through local or subsampled analyses. Despite the availability of such data, existing methodologies remain computationally prohibitive for large-scale analyses across this region (or others). To address this limitation, we introduce a highly scalable framework (implemented in open-source software) that enables inference on crustal deformation across the full North American GNSS network using standard computational resources. The proposed method achieves substantial computational gains while maintaining inferential performance comparable to existing approaches and confirms existing tectonic trends, thereby supporting efficient large-scale monitoring and contributing to ongoing efforts toward "Open Science".
arXiv:2607.17133v1 Announce Type: new
Abstract: Wireless communication networks are evolving toward extremely large antenna arrays, millimeter-wave and terahertz bands, and dense heterogeneous deployments, all of which increase channel dimensionality and make channel acquisition increasingly costly. Channel knowledge map (CKM) establishes a mapping from geographical locations to channel characteristics, providing location-specific prior information to reduce the overhead of channel acquisition. Most existing CKM research, however, has focused on quasi-static propagation features shaped by quasi-static environmental structures such as buildings and terrain, leaving unaddressed the time-varying channel component introduced by dynamic scatterers, terminal attitude changes, and radio-frequency (RF) impairments. This article presents a new concept of dynamic CKM as a middle layer that links quasi-static environmental priors to physical-layer signal processing by providing time-evolving channel representations. We first introduce the fundamentals of dynamic CKM, clarifying its relationship with the quasi-static CKM and the physical layer. We then survey representative construction methods and discuss how dynamic CKM can support pilot design, interference suppression, and integrated sensing and communications. Finally, we outline key open research directions in the co-design of dynamic CKM construction and physical-layer signal processing. These discussions offer an architectural perspective on the role of dynamic CKM in emerging 6G systems.
arXiv:2607.16381v1 Announce Type: new
Abstract: We develop a deterministic, scale-resolved formulation of energy transfer in the three-dimensional incompressible Navier-Stokes equations based on an explicit triadic decomposition of the nonlinear term in Fourier space. Using a systematic dyadic localization of the velocity field, we derive an exact representation of the nonlinear energy flux across scales and organize it in terms of interactions between well-defined scale components. Under suitable smoothness assumptions, we obtain an absolutely convergent triadic expansion and quantitative bounds that distinguish local and nonlocal contributions in scale space. This framework provides a transparent and fully explicit description of how energy transfer is mediated by triadic interactions and how scale locality emerges as a structural property of the nonlinearity. Building on this formulation, we revisit the classical inertial-range picture of turbulence from a deterministic perspective. We show that, under a scale-invariant flux assumption, the Kolmogorov $-5/3$ scaling is formally consistent with the triadic energy-transfer mechanism at a structural level. The result does not rely on statistical assumptions, but instead follows from the structural properties of the Navier-Stokes equations combined with a scale-resolved representation of the energy flux. The present work thus provides a coherent synthesis of triadic interaction analysis, dyadic scale decomposition, and classical turbulence phenomenology, offering a deterministic framework that clarifies how Kolmogorov-type scaling constraints arise in the scale-resolved structure of the underlying equations.
arXiv:2607.17595v1 Announce Type: new
Abstract: We establish mean-square and concentration bounds for stochastic approximation (SA) with arbitrary norm contractive mappings, under a multiplicative noise model where the noise may scale affinely with the norm of the iterates, and the iterates are potentially unbounded. These settings arise in reinforcement learning, where operators are often contractive in the $\ell_\infty$ norm and the noise scales with the iterates. To address the arbitrary norm, earlier works replace the non-smooth squared norm with a smooth Lyapunov function constructed via the generalized Moreau envelope. For concentration analysis, these works handle multiplicative noise and unbounded iterates through a multi-stage bootstrapping argument that starts from a time-varying worst-case bound and iteratively refines it. We instead present a unified and elementary analysis that yields both bounds. Using an averaged noise sequence and corresponding auxiliary iterates, we obtain a one-step Lyapunov drift inequality for the normed error directly, without smoothing the norm or constructing an envelope. For the mean-square bound, we combine this drift inequality with an induction argument showing that the iterates remain bounded in expectation. For the concentration bound, we develop a probabilistic induction over a sequence of "good" events on which the iterates are controlled, allowing the standard Azuma-Hoeffding bound to be applied. Our approach yields the first sub-Gaussian tailed maximal (all-time) concentration bound for SA under multiplicative noise, by allowing the stepsize to depend logarithmically on the confidence level. Beyond the specific setting considered here, we discuss the generalizability of these proof techniques to other noise models and iterative algorithms.
arXiv:2607.16546v1 Announce Type: new
Abstract: Affective behavior recognition in the wild requires joint prediction of continuous valence-arousal, categorical facial expression, and multi-label action units from unconstrained face images. We present our system for the Multi-Task Learning (MTL) track of the 11th Affective Behavior Analysis in-the-wild (ABAW) competition on s-Aff-Wild2, the static selected-frame version of Aff-Wild2. The method focuses on post-encoder adaptation: frozen AffectNet-supervised backbones provide multi-resolution features, while task-specific temporal heads and cross-task fusion modules select the useful signals for each target. For action-unit recognition, we adapt MAE-Face with Low-Rank Adaptation (LoRA) and use DISFA through per-unit expert routing rather than direct sequential transfer. Ablations over backbone, temporal, fusion, and AU-adaptation choices define the final configuration. The final system obtains P = 1.7302 on the official validation split, showing that post-encoder adaptation and task-wise modeling choices provide a strong MTL pipeline without training a new large-scale face foundation model.
arXiv:2607.16685v1 Announce Type: cross
Abstract: Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data. In practice, however, acquiring high-quality labels is costly and time-consuming, leaving large volumes of unlabeled data unused. To address this, we introduce label-augmented conditional diffusion (LACD), a simple and effective approach that incorporates unlabeled examples by assigning them a designated trivial label and performing joint denoising score matching over the augmented dataset. We provide sufficient conditions guaranteeing population-level identifiability of the target conditional distribution under this scheme. Moreover, we establish rigorous statistical guarantees: when sufficiently many unlabeled samples are available, the sampling distribution produced by LACD converges strictly faster than the purely supervised estimator in total variation distance, and at least as fast in Wasserstein-1 distance. Extensive experiments on synthetic, image, and tabular benchmarks corroborate our theory and show substantial gains in sample efficiency and generative performance compared with the purely supervised estimator.
arXiv:2201.05000v3 Announce Type: replace
Abstract: Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is progressively becoming popular in other fields, such as combinatorial optimization, where researchers and system designers are not necessarily RL experts. Besides, many modeling decisions are typically made manually, such as defining state and action space, size of batches, batch update frequency, and time steps. For these reasons, automating different components of RL is of great importance, and it has attracted much attention in recent years. Automated RL provides a framework in which different components of RL, including MDP modeling, algorithm selection, and hyper-parameter optimization, are modeled and defined automatically. In this article, we present the literature on automated RL (AutoRL), including the recent large language model (LLM) based techniques. We also discuss the recent work on techniques that are not presently tailored for automated RL but hold promise for future integration into AutoRL. Furthermore, we discuss the challenges, open questions, and research directions in AutoRL.
arXiv:2607.16717v1 Announce Type: cross
Abstract: This paper proposes a causal independence principle for value -- the value Causal Markov Condition (v-CMC) -- and develops the conceptual and mathematical foundations of a "causal value theory" linking causality and utility. After motivating a local formulation of the v-CMC, we introduce a probability-value duality that translates standard causal-inference results into the value setting. In particular, we formulate local, global, and decomposition versions of the v-CMC and prove their equivalence. We also define v-separation and show that it is sound and complete for conditional value independence. Furthermore, we derive a Bellman-type recursion as a special case of the v-CMC, thereby generalizing standard Bellman recursion from linear chains to causal DAGs. Finally, we show how the v-CMC supports modular transfer and updating of utility information across causal contexts and develop algorithms for causally structured utility elicitation and canonical influence-diagram construction.
arXiv:2607.16673v1 Announce Type: new
Abstract: Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one token at a time. Speculative decoding can reduce this cost by verifying several draft tokens in one target pass, yet existing speculative systems are designed for Transformer KV caches. For stateful linear-attention targets, verification must follow recurrent dependencies across chains and branches, acceptance must update only the accepted state trajectory, and the drafter must avoid submitting candidates that waste stateful verification work. This paper presents SpecLA, a speculative decoding runtime for stateful linear-attention models. SpecLA verifies chains and trees with topology-aware kernels, stores compact factors produced during verification to recover accepted states, and uses confidence pruning plus a target-aligned EAGLE-style drafter to feed useful candidates to the verifier. On an NVIDIA H100 with a public GDN-1.3B target, SpecLA achieves up to 1.70x end-to-end speedup over autoregressive decoding.