arXiv:2607.17052v1 Announce Type: new
Abstract: Vision-language models normally execute the same complete vision encoder for every question, even when OCR, counting, object, attribute, and spatial queries may not require identical computation. We study whether fixed-budget combinations of vision blocks can be skipped without fine-tuning. A shared K-block route skips one searched set of exactly K blocks for every question, while a capability-specific K-block policy selects one same-size route using a known capability label. We introduce a source-balanced evolutionary search and compare it with independent ranking, contiguous removal, and random routes at matched budgets. Experiments use Qwen2.5-VL-3B-Instruct, SmolVLM2-2.2B-Instruct, and an 876-example image-disjoint selection split. Search transfers across architectures: on SmolVLM2, the searched shared four-block route beats independent construction by 4.91 percentage points. Capability specialization is less stable. On Qwen, the six-block capability policy beats the shared route by 2.17 points, driven by a 7.10-point OCR gain. On sealed IIIT5K, however, the SmolVLM2 OCR-specific route trails its shared route by 13.6 points. Combinatorial search reliably improves route construction, but capability labels do not define universally transferable vision pathways.
Science Journals
arXiv:2607.17111v1 Announce Type: new
Abstract: We present the Bangladesh Legal Acts Dataset (BLAD), a curated collection of 1{,}484 legislative acts enacted between 1799 and 2025. Each act is represented with its full text, structured sections and footnotes, repeal status, and metadata linking it to the governing regime, head of state, and prevailing legal framework at the time of enactment. The corpus spans English, Bengali, and mixed-language documents, supporting temporal and multilingual analysis of statutory law. BLAD addresses a persistent gap in legal natural language processing (NLP) resources for low-resource, civil-law jurisdictions in South Asia. We describe the acquisition and enrichment pipeline, report descriptive statistics over more than two centuries of legislation, and outline the research directions the corpus enables. The dataset is publicly available under the CC~BY-SA~4.0 license at https://www.kaggle.com/datasets/sakhadib/bangladesh-legal-acts-dataset.
arXiv:2607.17328v1 Announce Type: new
Abstract: Traditional time-lock puzzles enforce delayed access to encrypted secrets by relying on inherently sequential computational steps. However, since software-based constructions impose no fundamental bound on the physical execution speed of individual steps, they remain vulnerable to hardware acceleration and improved implementations. In practice, this renders existing schemes ``step-lock'' rather than true ``time-lock'' puzzles, making long-term delay guarantees highly speculative against decades of unpredictable hardware advancement. To address this fundamental limitation, we introduce the Physical Time-Lock Puzzle (P-TLP), a new paradigm that anchors solving delay directly to the intrinsic, hardware-bounded evaluation latency of silicon hardware. By leveraging noisy Physical Unclonable Functions (PUFs) as non-parallelizable delay oracles, P-TLPs establish resistance against both parallel computation and algorithmic acceleration under the random oracle model. To tolerate PUF evaluation noise while maintaining a tightly concentrated and predictable solving-delay window, we propose a composite puzzle architecture that combines multiple independent basic puzzles. We formally prove the optimality of a sequential greedy solving strategy and derive tightly concentrated solving-delay windows using Hoeffding and Berry-Esseen bounds. We additionally prove early-solve hardness, establishing that adversaries with substantial classical computation budgets cannot bypass the physically-enforced PUF evaluation bottleneck. We validate our theoretical analysis with an FPGA prototype built around a configurable Ring Oscillator PUF, confirming that our analytical delay predictions tightly match empirical measurements. Our results demonstrate that P-TLPs can deliver highly predictable, long-term delay guarantees, enabling practical deployment in high-value applications such as digital legacy management.
arXiv:2607.16378v1 Announce Type: new
Abstract: Estimating the apparent age of individuals from facial images is challenging due to the subjective nature of perception and the inherent variability of the data. We investigate the role of uncertainty estimation, attributing uncertainty jointly to a lack of knowledge (epistemic) or inherent noise/chance (aleatoric). Leveraging the APPA-REAL dataset, we train Bayesian Neural Networks on datasets of varying sizes using three BNN approximations: MC-DropConnect, Flipout, and Deep Ensembles using supervision on human aleatoric uncertainty available in the APPA-REAL dataset. Each model outputs both the predicted apparent age and the amount of aleatoric and epistemic uncertainty. Our results confirm the hypothesis that the inherent aleatoric uncertainty remains stable across dataset sizes, while epistemic uncertainty increases as training data decreases. These findings demonstrate that different sources of uncertainty can be quantified in face age estimation.
arXiv:2607.16379v1 Announce Type: new
Abstract: One of us is a realist and believes that reality fundamentally consists in an external physical world, governed by laws of physics. Observers are either emergent (physicalism) or exist in addition to physical reality. The other defends a version of idealism and believes that reality fundamentally consists in first-person states, unembedded into worlds, on which laws of nature act directly. Shared "physical worlds" are merely emergent. The disagreement ultimately centers on the overall coherence of a formal model, known as Algorithmic Idealism, and its ability to resolve observer paradoxes, such as the Boltzmann brain paradox. Our aim is to confront this issue in the form of an adversarial collaboration, where we avoid misunderstanding each other, so that readers can see the true source of the disagreement, and decide for themselves. Our work represents an attempt to establish a form of exchange that may help overcome the fragmentation of scholarly communities in philosophy, physics, and elsewhere. The collaboration was conducted using a discipline-neutral template for theoretical adversarial collaboration developed in a companion paper [1], which we hope will be useful in other theoretical disciplines.
arXiv:2607.16383v1 Announce Type: new
Abstract: Verifying academic credentials remains difficult: records are held by individual institutions in proprietary systems, verification is slow and manual, and counterfeit qualifications are widespread. Blockchain-based registries have been proposed as a remedy, but existing systems tend to anchor certificate hashes without binding them to a verifiable identity, without an explicit mechanism to accredit issuing institutions, and without support for correcting or revoking credentials once issued. This paper investigates whether an infrastructure designed for regulated financial instruments can be repurposed to close these gaps. We present the design of a registry for identity-bound academic credentials that composes OnchainID self-sovereign identities (ERC-734/ERC-735) with the T-REX suite (ERC-3643): its trusted-issuer registry becomes an on-chain issuer-accreditation whitelist, and each certificate is represented as a signed, updatable claim bound to a student's identity and verifiable by any third party without a wallet, while sensitive fields are kept off-chain. We make explicit the tension between a transferable-security-token standard and non-transferable credentials, clarifying which of its guarantees carry over. We validate the design with a reference implementation covering the full certificate life cycle and evaluate it in terms of gas cost, scalability, latency, and security, quantifying the overhead relative to a hash-anchoring baseline.
arXiv:2607.16540v1 Announce Type: new
Abstract: Understanding and characterizing human color perception is a longstanding research goal. One of the most traditional approaches is looking for the human color discrimination thresholds, the minimum chromatic differences perceptible to human observers. In recent years, deep neural networks have become the standard networks for computer vision tasks. In particular, deep vision encoders, foundation models trained on large-scale visual data, map images into latent feature representations. Despite the widespread use of deep vision encoders, few studies have investigated whether their internal representations exhibit human-like discrimination thresholds. In this work, we present a large-scale exploratory study probing the chromatic sensitivity of more than 50 pretrained vision encoders, including convolutional networks and vision transformers, against human discrimination thresholds. Using controlled chromatic stimuli at multiple chroma levels, we compare model-derived chromatic discrimination thresholds with human discrimination ellipses through a region-overlap metric (mIoU). Our analysis reveals generally weak alignment between model representations and human perceptual thresholds across all model families, with the best mIoU < 0.25. Moreover, we find that self-supervised encoders consistently outperform supervised ones, while language-supervised models show the most polarized behavior, occupying both the top and bottom of the ranking. These findings suggest that human-like chromatic sensitivity does not emerge naturally from current large-scale visual training objectives for any of the analyzed architectures.
arXiv:2607.16979v1 Announce Type: new
Abstract: Repository mining studies increasingly analyze AI-evidence projects, yet it remains unclear how to measure whether architectural changes create deferred stabilization obligations. A natural metric, post-anchor stabilization density, counts tests, CI gates, documentation, and fixes appearing after a durable boundary is introduced. We show that this metric fails. In a diff-level study of 338 high-visibility 2026 GitHub repositories, anchors are common (321 of 338 contain real changed-file anchor evidence), but a controlled 308-event contiguous-window experiment finds no post-anchor uplift: broad and strict stabilization signals both yield median post/pre density ratios near 1.0, and non-anchor controls are equally dense. We introduce stabilization regimes, six recurring patterns that explain why the density metric fails, and use human validation to calibrate them. Two independent coders label 100 stratified candidate-anchor events from blinded packets (kappa = 0.50 on debt attribution). The validation exposes a two-layer trap: many candidate anchors are not durable boundaries (45 of 100), and even among valid anchors in this calibration sample the no-uplift result holds: only 3 of 100 events survive as attributable delayed obligations; the remaining 97 are explained by classifier error, anchor-local hardening, background maintenance, or pre-anchor hardening. Post-anchor density conflates pervasive maintenance with genuine debt; controlled designs with regime-aware attribution are necessary before repository mining can reliably identify stabilization obligations.
arXiv:2607.17329v1 Announce Type: new
Abstract: Medical image segmentation models require both high accuracy and lightweight design to accommodate real-world medical applications. The deployment of these models on resource-limited medical platforms remains a significant challenge due to their high computational and parameter requirements. Existing pruning methods for model compression mostly overlook the intrinsic connections and similarity between the internal structures of complex deep neural networks. As a result, compressed models may not effectively retain the basic features of the pretrained network. To solve this problem, we propose a hierarchical clustering compression method for medical image segmentation models (MIS-HCC). This approach employs hierarchical clustering to partition channels and fuse their parameters efficiently. Specifically, it leverages the Wasserstein distance to represent similarity of channels within layers of pre-trained network, forming a similarity matrix that guides the clustering process. Channels within each cluster are then fused to produce a compressed network. Experimental results on three medical image datasets application demonstrate that MIS-HCC outperforms the state-of-the-art methods in both accuracy and compression efficiency, offering an effective solution for deploying medical image segmentation models on resource-limited medical platforms.
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.
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: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:2607.17053v1 Announce Type: new
Abstract: Large language models (LLMs) can automatically repair register-transfer-level (RTL) designs. However, fixing complex sequential logic errors requires reusing past debugging experience. Existing retrieval-augmented generation (RAG) relies on task-text similarity to provide this experience. This text-based approach often misguides the model because natural language poorly reflects cycle-level hardware execution semantics. To address this, we present MechMem-RTL, a repair framework that reuses verifier-confirmed repair records instead of text similarity. Each stored record strictly links trigger evidence, a diagnosed failure mechanism, a local repair action, preservation constraints, and a verification summary. For a new failure, MechMem-RTL injects a past record only when deterministic verifier evidence is strictly compatible with the stored trigger. Otherwise, the system uses only current verifier evidence. We evaluate MechMem-RTL on 48 public sequential RTL tasks across six repair models. With at most two repair attempts per task, MechMem-RTL successfully resolves 180 out of 288 task-model pairs, outperforming standard feedback repair (109 pairs) and task-similarity RAG (107 pairs).
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:2607.17122v1 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:2607.16981v1 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:2607.17684v1 Announce Type: cross
Abstract: We study universal monotonicity and Frank--Wolfe stability properties for atomic splittable congestion games. Specifically, we characterize the largest resource cost class for which the associated variational inequality operator is monotone for every game. This characterization is given by a curvature inequality involving the first two derivatives of the allowable cost functions and the number of players. Our framework yields exact characterizations for universal monotonicity, strict monotonicity, and strong monotonicity; the strict and strong variants require corresponding stricter curvature conditions. We then draw a perhaps surprising connection to learning dynamics in atomic splittable congestion games. We show that the very same curvature condition also characterizes universal \emph{local and global stability} of the Euclidean-regularized Frank--Wolfe dynamics on arbitrary convex strategy spaces, provided the cost class is closed under positive affine transformations. Finally, we study games on simplices and show that an interior equilibrium of the regularized Frank--Wolfe dynamic is locally exponentially stable, even without the curvature condition.
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:2607.16267v1 Announce Type: new
Abstract: Continual learning in visual navigation remains challenging due to catastrophic forgetting and the difficulties associated with adapting to diverse and evolving environments. To address these issues, we propose Hyperbolic Dynamic Cluster Memory (HyperDCM), a structure-aware memory mechanism that enhances diffusion policy-based navigation through scene graph modeling and principled memory replay. HyperDCM extracts semantic scene triples from RGB observations using large vision-language models, encodes them into scene graph embeddings via a Relational Graph Convolutional Network (R-GCN), and projects the embeddings into hyperbolic space to enhance structural separability and retention in continual navigation. A dynamic clustering and structure-sensitive update strategy selects representative samples for memory replay, thereby preserving knowledge diversity and mitigating catastrophic forgetting. Experiments on multi-scene indoor and outdoor datasets demonstrate that HyperDCM achieves superior retention of past navigation capabilities and improved generalization compared to representative continual learning baselines adapted to diffusion policy navigation.
arXiv:2607.17058v1 Announce Type: new
Abstract: Precise metric depth estimation is fundamental for autonomous robot navigation, yet monocular systems inherently suffer from scale ambiguity and scale drift. While recent recurrent flow-based SLAM systems have demonstrated state-of-the-art robustness, they remain scale-ambiguous. In this paper, we propose Metric-DROID, an end-to-end recurrent architecture that anchors visual SLAM to physical reality by integrating proprioceptive odometry. Our framework introduces the following innovations: (1) A LSTM Update Operator that encodes high-frequency odometry sequences into spatial feature maps, providing a persistent metric bias for iterative refinement. (2) An Uncertainty-Aware Metric Backend ($BA_{odom}$) that treats odometry as a geometric anchor with learned heteroscedastic covariance. By regressing a time-varying metric uncertainty $\Sigma_{o}$, our system intelligently balances visual re-projection and metric translation residuals, effectively mitigating the impact of wheel-slip and sensor noise. (3) We further propose a selective residual fine-tuning strategy to preserve pre-trained geometric priors while enabling zero-shot metric alignment.
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.