arXiv:2607.12452v2 Announce Type: replace
Abstract: Autonomous vehicles (AVs) must be thoroughly tested to meet high safety standards and avoid endangering both AV passengers and road users. Scenario-based testing implements driving scenarios in virtual simulation environments as a cost-effective alternative to field testing. Common scenario-based testing approaches set the environment and the surrounding traffic and test a single AV. Recent studies show that the approaches that test single AVs miss critical behaviors that emerge from interactions among multiple AVs. Effective approaches to test scenarios that emerge from n-way interactions must address the combinatorial explosion that the presence of multiple AVs further exacerbates. In this paper, we propose EVITA, an approach that leverages multi-objective optimization to generate scenarios that trigger multiple and diverse AVs interactions, while minimizing the complexity of the generated scenarios, to effectively test multiple interacting AVs and reveal safety-critical scenarios that current approaches overlook. The experimental results that we discuss in this paper confirm that EVITA triggers a higher variety of AVs interactions than state-of-the-art approaches, thus improving the likelihood to reveal safety-critical behaviors.
Science Journals
arXiv:2607.12474v2 Announce Type: replace
Abstract: Recent advances in foundation models have transformed AI for Science, enabling remarkably accurate predictive performance across domains ranging from protein folding to weather forecasting. Yet prediction alone does not constitute scientific discovery. Scientific understanding depends on uncovering the reusable explanatory mechanisms that generate observations, whereas contemporary machine learning remains fundamentally organised around predictive mappings rather than explanatory structure. In this paper, we argue that scientific discovery is fundamentally a problem of knowledge organisation. To this end, we introduce Mechanistic World Models, a new design paradigm that places reusable mechanisms at the centre of representation, computation and learning. Drawing on insights from the philosophy of science, we derive the computational capabilities required for discovery, identify the design principles and inductive pressures that encourage explanatory knowledge to emerge, and formalise the anatomy of a mechanism-centric world model. Finally, we show how diverse research directions including mechanistic interpretability, causal representation learning, equation discovery and modular architectures capture complementary ingredients of this paradigm while lacking a unified framework. We propose Mechanistic World Models as a conceptual foundation and computational blueprint for moving AI beyond predictive forecasting towards autonomous scientific discovery.
arXiv:2607.12477v2 Announce Type: replace
Abstract: Autonomous UAV systems increasingly rely on multimodal large language models (MLLMs) to operate in complex real-world environments. Such embodied scenarios require not only understanding the surrounding space but also maintaining a coherent representation of the agent itself. However, existing UAV-oriented approaches and benchmarks remain largely environment-centric, primarily focusing on spatial understanding tasks, with the agent's self-awareness remaining implicit. To address this gap, we introduce SIS-Bench, a benchmark for evaluating embodied spatial intelligence in UAV scenarios under a unified self-in-space formulation. SIS-Bench organizes evaluation along two complementary dimensions, space and self, and a three-level hierarchy of perception, memory, and reasoning. It contains 4,856 question--answer pairs across 13 tasks derived from 1,646 real-world UAV videos through a task-conditioned construction pipeline with expert verification. Extensive evaluations reveal that current MLLMs exhibit fundamental limitations in modeling dynamic and agent-centered processes. In particular, we observe a clear imbalance between spatial cognition and self-awareness, as well as a progressive performance degradation across cognitive levels. Motivated by these findings, we further explore a motion-aware representation that incorporates self-related dynamics through optical flow and visual feature fusion. Experimental results show that modeling agent motion consistently improves perception and memory performance, not only in spatial cognition but also in self-awareness, and generalizes to downstream UAV decision-making tasks. Our results highlight the importance of self-awareness for advancing embodied spatial intelligence, and provide both a new benchmark and empirical evidence for motion-aware self-in-space modeling.
arXiv:2607.14001v1 Announce Type: new
Abstract: We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion. With LCE, the agent not only successfully found the oscillatory motion known as the Kapitza pendulum but also damped the pendulum's pivoting, leaving it in a strictly upright position.
arXiv:2607.13037v1 Announce Type: new
Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author. Existing provenance systems operate at file or dataset level, forcing catastrophic over-deletion. We present ob, a record- and token-level data provenance system that propagates author identity through data processing pipelines and resolves revocation requests into precise forget sets via deterministic queries. Evaluation on 219,555 Wikipedia pages demonstrates that record-level provenance eliminates dataset-level over-deletion (from 101x to 1.3x), while integration adds 1.3-4.0% throughput overhead (HuggingFace) and 2.1-19.0% (Datatrove) on wiki data. On a 1.7B model, provenance-based forget sets improve unlearning by 42% over random baselines.
arXiv:2607.13040v1 Announce Type: new
Abstract: This paper examines where final authority should sit once capable AI systems are embedded in organizational workflows. It compares two governance models. The first, frontier-provider sovereignty, assigns privileged authority to the provider of the most capable models and is reflected in contemporary arguments for frontier-model testing, release gating, transparency duties, and compute-related controls. The second, action-centered deployer sovereignty, places final authority over high-impact actions with the organization that authorizes the action, embeds it in a business process, and bears the downstream legal, operational, and commercial consequences. The paper combines comparative reading of public governance frameworks with implementation-informed analysis of runtime heterogeneity and enterprise control requirements. It compares EU AI Act guidance, the NIST AI Risk Management Framework, Singapore's Model AI Governance Framework for Agentic AI, recent Japanese AI policy instruments, and Canada's voluntary code and managerial guidance. Across these materials, the paper finds stronger support for distributed operational accountability than for unilateral frontier-provider control. It further argues that rapid enterprise adoption, declining provider transparency, and widening control gaps increase the value of a portable governance layer centered on governed action rather than on provider-native session objects. The conclusion is layered rather than absolutist: strong upstream authority remains justified for frontier capability gating, but final authority over concrete enterprise action is better located with the deployer and consequence-bearer.
arXiv:2607.12503v2 Announce Type: replace
Abstract: 4D spatio-temporal reasoning, jointly modeling 3D spatial structure and temporal evolution, is essential for understanding dynamic worlds and enabling embodied interaction. While current Multimodal Large Language Models (MLLMs) show strong capabilities in static scene understanding and coarse-grained 4D tasks, they still have notable limitations in continuous dynamic scene perception, especially in tracking dynamic object evidence for coherent 4D spatio-temporal reasoning. This shortcoming stems mainly from relying on sparse frame-level observations, fragmenting continuous dynamic cues and leaving models unable to disentangle genuine object dynamics from camera-induced apparent motion. Inspired by humans tracking dynamic cues while compensating for viewpoint changes, we propose DynTrace, a training-free framework for 4D spatio-temporal reasoning with two complementary components. Dynamic Trajectory Visualization (DTV) reprojects world-coordinate trajectories onto the image plane, providing geometry-informed visual priors that disentangle genuine object dynamics from camera-induced apparent motion. Meanwhile, the Dynamic Trace Token (DT-Token), organized into a Dynamic Trace Graph (DTG), tracks object-level dynamic cues, trace evolution, and key moments, maintaining continuous dynamic object evidence for coherent 4D reasoning. Together, these two components equip MLLMs with continuously tracked dynamic object evidence, grounded in geometry-informed visual priors and structured spatio-temporal traces. DynTrace consistently improves open-source MLLMs, achieving state-of-the-art results on Dyn-Bench, VLM4D, and DSI-Bench, validating the importance of tracking dynamic object evidence for robust 4D spatio-temporal reasoning.
arXiv:2607.12505v2 Announce Type: replace
Abstract: Vision Transformers (ViTs) achieve strong accuracy but incur high inference latency. Semi-structured N:M sparsity can reduce arithmetic cost, yet its theoretical savings often fail to translate into proportional end-to-end speedups on modern GPUs. This mismatch arises because deployment latency depends not only on arithmetic reduction but also on execution regularity and hardware scheduling under sparsity. Achieving practical acceleration, therefore, requires coordinated design across sparse execution and sparsity configuration. To this end, we propose a hardware-software co-design framework for N:M sparse ViT inference. On the hardware side, we design MD-SpMM, an N:M sparse CUDA kernel that reorganizes sparse GEMM into micro-dense, Tensor-Core-aligned dataflow and uses inference-aware adaptive parallelism to sustain utilization. On the software side, we perform layer-wise sparsity search under explicit end-to-end latency budgets using a three-stage heuristic search with constraint relaxation to avoid premature convergence and enable deployment-aware sparsity allocation. Experiments on multiple ViT/Swin models and GPU platforms show that the framework achieves over 2.2x latency speedup while maintaining comparable accuracy and delivering superior accuracy under the same latency constraint. The source code is publicly available at https://github.com/liuganhuo/realizable-nm-sparse-transformer.
arXiv:2607.12547v2 Announce Type: replace
Abstract: We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control. We introduce Hi-LeWM, an extension that freezes the pretrained low-level LeWM and adds high-level planning over latent subgoals. We evaluate Hi-LeWM on PushT and Cube across increasing goal offsets. Hierarchy does not automatically improve performance: at short horizons, the best configuration uses a one-step high-level horizon, while longer horizons reveal a mismatch between the learned high-level action space and the inference-time search distribution. Experiments with true future latent subgoals show that the frozen low-level controller can execute well-aligned intermediate targets, indicating that high-level subgoal generation is the main bottleneck. Unconstrained search can select latent macro-actions that appear favorable under the learned model but produce poor control targets. Constraining search around macro-actions encoded from training trajectories, with appropriate subgoal execution timing, recovers useful hierarchical regimes, improving over flat LeWM by +11.3 percentage points at medium-range horizons and +14.7 percentage points at the longest PushT horizon. Overall, temporal abstraction can benefit compact frozen LeWM, but only when high-level search remains compatible with the low-level controller
arXiv:2607.12625v2 Announce Type: replace
Abstract: OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience. To resolve these issues, we propose the Know Deeply, Act Perfectly paradigm for personal assistants, which holds that accumulated user interaction and task-running experience directly improve execution accuracy and efficiency, unifying cognitive comprehension and operational execution. Based on this paradigm, we introduce KnowAct-GUIClaw, a novel Know-Route-Act-Reflect framework designed to address OpenClaw's GUI manipulation deficits and break through its cross-platform and recursive self-improvement constraints. First, the host agent leverages accumulated interaction experience and task-relevant knowledge for long-horizon task decomposition and allocation (Know). Second, a pluggable GUI subagent with an experience-attributable memory system (Know) and self-evolving skill library (Act), enabling seamless cross-platform migration and fast-path integration. Especially, this framework continuously stores user profiles and feedback to improve the accuracy of task decomposition and tool calls. Extensive experiments across Android, iOS, HarmonyOS and Windows show that KnowAct-GUIClaw achieves superior efficiency, accuracy and cross-platform adaptability. Especially, the GUIClaw with open-source Kimi-2.6 models achieves the best performance (64.1%) on the long-horizon MobileWorld benchmark, beating all agentical frameworks and closed-source agentical models, e.g., Seed-2.0-Pro and GPT-5.5. Additionally, the knowledgeable memory and execution skills supported by our framework are transferable across diverse base models, improving by 8.5% with Kimi-2.6.
arXiv:2607.12752v2 Announce Type: replace
Abstract: While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric consistency, leading to spatial hallucinations such as duplicated structures and misaligned geometry. These issues become more severe in 4D generation, where maintaining consistency across viewpoints and temporal evolution introduces additional challenges, including jitter, identity flicker, and structural drift. We present \textbf{Hallo4D}, a unified and model-agnostic framework for mitigating spatiotemporal hallucinations in 3D and 4D content generation. Hallo4D introduces a generation-detection-correction paradigm that leverages large multimodal language models (LMMs) to identify and summarize spatial and temporal inconsistencies from multi-view and multi-frame renderings. These insights guide a consensus-driven image-space consistency optimization, where an LMM-based selector evaluates candidate corrections through multi-model voting, without requiring retraining or architectural modifications. To further improve temporal consistency and optimization efficiency, Hallo4D incorporates motion-aware keyframe sampling, LMM-guided initialization, and appearance alignment. We additionally introduce exposure-aware optimization and visibility pruning to enhance robustness under challenging viewpoints. Extensive experiments demonstrate that Hallo4D consistently outperforms strong baselines across diverse 3D and 4D generation settings, providing a scalable and generalizable solution for consistency-aware content generation.
arXiv:2607.12818v2 Announce Type: replace
Abstract: Visual place recognition (VPR) is a key enabler of accurate localization and long-term autonomous navigation in robotics applications, such as loop closure detection for simultaneous localisation and mapping (SLAM). However, real-world VPR deployment relies on selecting an image matching threshold that balances precision and recall. These thresholds are typically tuned using labeled validation data and fixed during deployment, making them unreliable under environmental changes where ground truth is unavailable. This is particularly problematic in safety-critical robotics, where accepting a false loop closure can corrupt the estimated trajectory and map. In this work, we introduce Visual Place Recognition Auditing, an independent post-retrieval verification framework that leverages Vision-Language Models (VLMs) to assess retrieved matches by reasoning jointly over query and candidate images. Unlike conventional verification methods, our approach performs instance-level verification without requiring architecture-specific confidence measures, dataset-dependent thresholds, or prior knowledge of the deployment environment. We evaluate our method on six benchmark datasets using five state-of-the-art VPR methods and four VLMs. Results show that VLM-based auditing improves recall@1 by 13.6% on average as compared to state-of-the-art methods while reducing false acceptance rates to 12%, maintaining precision above 95% and coverage above 75%.
arXiv:2607.12870v2 Announce Type: replace
Abstract: In this work, we provide a comprehensive survey of the code equivalence problem and its variants. We explain the existing results, highlighting the relationships between different problem formulations, algorithmic techniques, and hardness assumptions. In addition, we systematically review known attacks, identify the parameter regimes in which they are effective, and discuss their limitations. Lastly, we outline several open problems and research directions, with the aim of clarifying the current landscape and guiding future work toward a deeper understanding of the hardness of code equivalence.
arXiv:2607.12924v2 Announce Type: replace
Abstract: In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot estimators, which makes their training sample inefficient. Though in most PAMDP environments explicit but incomplete knowledge (e.g., rules, safety constraints, or expert heuristics) is available, it is rarely directly used to increase the sample-efficiency of training Reinforcement Learning agents. We step into this gap and propose our novel Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL) algorithm. KGRL uses domain knowledge in a Datalog knowledge base to derive the set of applicable actions and feasible parameters for a given state. This allows it to prune non-applicable actions from the decision-space and constrain the parameter spaces of the remaining actions. We then use a gradient-based parameter refinement loop to estimate the optimal parameters during training and deployment of the agent. By recording activated rules along the trajectory, KGRL additionally provides local procedural explanations on the pruning of actions and constraining of parameters. Overall, KGRL guides the agent's exploration and deployment toward feasible and constraint-aware decisions, while increasing sample efficiency during training. KGRL outperforms state-of-the-art RL baselines for PAMDPs in both, sample efficiency and episodic return.
arXiv:2607.12993v2 Announce Type: replace
Abstract: We present X-lens, a compact feed-forward model for metric depth estimation from a variable number of calibrated fisheye and pinhole views. To support real-time downstream perception, X-lens is built around a geometry-aware heterogeneous camera formulation with two key components. Learnable calibration tokens provide a coarse alignment between fisheye and pinhole projective spaces, while a Jacobian-parameterized distortion bias injected into cross-attention models local projection changes and promotes cross-camera consistency, enabling robust generalization with only 0.04B parameters and up to 41 FPS. The model predicts dense depth together with a global metric scale, avoiding auxiliary reconstruction targets that increase computation and optimization complexity. To learn such cross-camera generalization at scale and depth, X-lens is trained on multiple public datasets and OmniScene, our newly released large-scale synthetic dataset containing approximately 266K synchronized six-view frames, 1.7M individual images, and 103 indoor and outdoor scenes. Extensive experiments on both real-world and synthetic indoor and outdoor datasets demonstrate superior heterogeneous-camera metric depth accuracy, reducing AbsRel by 25.4\% on OmniScene-Full over the strongest baseline while using 88.9\% fewer parameters, with competitive performance on conventional fisheye-only and pinhole-only settings.
arXiv:2607.13006v2 Announce Type: replace
Abstract: A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different question: whether \emph{adding context}, a longer lookback, a retrieval plug-in, or a pretrained model, will help. These are not the same question. The value of context is a property of the operating point, not of the series. Any index built from the power spectrum is invariant under phase randomization, whereas the beyond-second-order value that retrieval and foundation models supply is not, because a phase-randomized series is asymptotically Gaussian. We state this as an impossibility result and isolate it with surrogate pairs that fix the spectrum and the marginal by construction. We then give a label-free, configuration-level diagnostic, the coverage deficit, whose principal term measures beyond-spectrum structure as the gain of analog over linear prediction. On seven benchmarks the prediction holds: window-keyed retrieval's value collapses across surrogate pairs (ECL median $+33\%\!\to\!-35\%$, $p{<}10^{-40}$) while every spectral index stays frozen; a foundation model's value splits into a surviving second-order part and a small beyond-linear margin that collapses; a longer linear window's value survives. Leave-one-dataset-out, the structure term predicts the sign of beyond-spectrum value where the spectral indices trail it, and the reverse holds for the second-order mechanism. We introduce no new forecaster; the contribution is the distinction, a controlled comparison, and a diagnostic for the deployment decision. Code: https://github.com/KurbanIntelligenceLab/SINE
arXiv:2604.21206v3 Announce Type: replace-cross
Abstract: We study the magnetic-field dependence of the interactions between two alkaline-earth(-like) Rydberg atoms, ${}^{88}$Sr and ${}^{174}$Yb. Considering the pair of Rydberg states $|ns,{}^3S_1,m_J\rangle$ and $|(n+1)s,{}^3S_1,m_J\rangle$, we show that the effective Hamiltonian takes the form of an {\it XXZ}-type quantum spin model, as in the alkali-atom case [M. Kunimi and T. Tomita, Phys. Rev. A {\bf 112}, L051301 (2025)]. We find that the behavior of the anisotropy parameter for ${}^{174}$Yb at zero magnetic field is significantly different from that for other atomic species. This behavior arises from the interplay of strong spin-orbit coupling and the resulting multichannel redistribution of F\"orster defects in ${}^{174}$Yb. We systematically calculate the interaction parameters of the {\it XXZ} model in the presence of a magnetic field and show that they can be tuned by the field. As applications to quantum many-body problems, we investigate one-dimensional systems in the large-anisotropy regime and show that the folded {\it XXZ} model can be realized in ${}^{174}$Yb systems without fine-tuning of the field. We also investigate two-dimensional square-lattice systems and show that a supersolid phase can emerge in the ground state at the mean-field level.
arXiv:2607.08803v2 Announce Type: replace-cross
Abstract: The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology. However, existing biological resources, such as molecular databases, protein repositories, genomic annotations, single-cell atlases, and pathway databases, are scattered across heterogeneous formats and remain unorganized into a cohesive corpus for language model training. We present TheBioCollection, a 52.6B-token pre-training-scale corpus that converts these disparate resources into a unified, training-ready form spanning small molecules, proteins, genomic sequences, cells, and pathways. Beyond consolidating existing data, TheBioCollection enriches each record with tool-computed biological properties and introduces new instruction tasks for capabilities that current corpora barely cover. We pair the corpus with TheBioCollection-Eval, a matched suite probing recognition, generation, and prediction across molecular, protein, genomic, cellular, and cross-domain settings. Holding the base Gravity-16B-A3B architecture fixed, training on TheBioCollection more than doubles its overall score on TheBioCollection-Eval with gains in every domain, while leaving general linguistic ability nearly intact.
arXiv:2607.13188v1 Announce Type: new
Abstract: Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws $\textit{together}$, each modality reshapes the other. In this paper, we bring this coupled loop to artificial systems. Masked Diffusion Models (MDMs) are ideally suited to this task, yet existing samplers either decode text and image interleavedly or independently update them in parallel branches that share only previous-step history, but not the other modality's latest decisions $\textit{within}$ the same step; combined with MDMs' inability to remask, cross-modal contradictions are neither detected nor repaired. We introduce $\textbf{Self-Correcting Coupled Markov Jump Processes (SC-CMJP)}$, a framework in which one modality's transition rates are functionals of the other modality's confidence score, as weighted by cross-modal attention. Furthermore, a remasking jump retracts commitments the moment cross-modal evidence turns against them. In conjunction with SC-CMJP, we introduce $\texttt{CO}_\texttt{2}\texttt{Jump}$ (Self-$\underline{\text{CO}}$rrecting $\underline{\text{CO}}$upled $\underline{\text{Jump}}$), a novel training-free single-pass sampler for joint multimodal geneneration. For training and evaluation purposes, we have created and will release three large-scale joint multimodal generation corpora: $\text{JEdit-1M}$, $\text{JMaze-200K}$, $\text{JNono-200K}$, with matching in- and out-of-distribution benchmarks. $\texttt{CO}_\texttt{2}\texttt{Jump}$ achieves best joint performance for image understanding and editing as well as visual reasoning (maze and nonogram solving). The performance of the sampler scales monotonically with the number of denoising steps, evidence that the benefits of cross-modal coupling $\textit{compound}$ across the trajectory. Project page: https://coupled-jump.github.io
arXiv:2607.13218v1 Announce Type: new
Abstract: In this work, we study various graph partitioning problems under a general demand model. In each such task, we are given a graph $G=(V,E,c,w)$ with a capacity function $c\colon E\to \mathbb{N}$ and a demand function $w\colon V\times V\to \mathbb{N}$. Our main focus is the problem of finding a cut $(S, \bar{S})$ minimizing the quantity
\[
\psi_w( S ) = \frac{c( S, \bar{S} )}{w( S, V )\cdot w( \bar{S}, V )}.
\]
Here, $c( S, \bar{S} )$ is the cost of edges between $S$ and the complement of $S$, $\bar{S}$, and $w( S, V )=w( S )+w( S, \bar{S} )$ is the sum of the internal demand within $S$, $w( S )$, and the demand between vertices of $S$ and $\bar{S}$, $w( S, \bar{S} )$. We call $\psi_w( S )$ the \emph{generalized conductance} of the cut $(S, \bar{S})$, and the task of minimizing $\psi_w( S )$ the Generalized Conductance Problem. Our main contribution is an algorithm with an $\mathcal{O}(\log n)$-approximation guarantee for this objective. Our result is achieved via a two-way reduction: first to the well-known Generalized $k$-Multicut Problem, and then to a constrained variant of the classic Sparsest-Cut Problem, with an additional upper-bound constraint on the amount of demand that may be cut.
Moreover, we show that the above procedure can be used to obtain an $\mathcal{O}(\log n)$-bicriteria approximation for Graph Partitioning with Demands, where the goal is to find a minimum-cost subset of edges $C$ such that for every component $H$ of $G\setminus C$, $w( H )\leq \rho\cdot w( V )$. This, in turn, yields an $\mathcal{O}(\log n)$-approximation for Hierarchical Clustering with Demands, the problem of finding a hierarchy of cuts that partitions the graph into increasingly refined clusters. For multiplicative demand functions, we improve these guarantees to $\mathcal{O}(\sqrt{\log n})$ and for trees we get an $\mathcal{O}(1)$-approximation for all of our objectives.
arXiv:2607.13821v1 Announce Type: new
Abstract: Android memory forensics recovers evidence that never touches disk: decrypted messages, session credentials, and the live internal state of a running application. The tools that perform this recovery depend on debug symbols embedded in libart.so, the Android Runtime library, to locate data structures and interpret their layout. Across recent releases Google has stripped most of that information from the binaries that ship on consumer phones as part of a broader security hardening effort, yet no prior work has measured how far the stripping has progressed on the devices examiners actually encounter, or whether the memory architecture beneath the stripped surface still resembles what the forensics literature describes. This paper measures the gap between the unstripped development builds researchers use and the production builds that ship on real hardware, using binaries extracted from Pixel factory images across Android 8 through Android 15. Static symbols fell from 20,495 entries to zero, dynamic symbols dropped by roughly 60 percent, and source file references disappeared entirely. A compressed fallback section in the Android 15 binary restores thousands of function names but carries no structure layouts. Source code review and memory map comparisons across Android 8 and 15 show that the heap spaces, garbage collector infrastructure, and allocation bitmaps remain structurally intact, with visible changes limited to naming and arithmetic optimization. Live validation on a rooted, fully stripped Pixel 7 confirms that the runtime entry point is still locatable through the dynamic symbol table, and that structural offsets pulled from a version-matched development build resolve to valid pointers inside production memory.
arXiv:2607.13503v1 Announce Type: new
Abstract: Understanding and generation are often treated as two separate paradigms in training deep neural networks, despite the fact that both are trained with closely related objectives such as denoising and masked prediction. While prior studies have shown that generative models often learn suboptimal representations for understanding tasks in vision, it is less understood whether a similar gap exists in the protein domain. In this work, we systematically investigate this question by benchmarking state-of-the-art protein generative models on widely-used protein understanding tasks, and observe that these models exhibit consistently poor performance compared to existing protein encoders. Furthermore, inspired by the Representation Alignment (REPA) framework, we propose to explicitly align generative protein diffusion models with pretrained protein understanding models during training. Experiments on the MotifBench demonstrate that representation alignment significantly improves functional protein generation, boosting the MotifBench score of Protpardelle-1c from 39.2 to 47.1, corresponding to a 20% relative improvement. Our results suggest that representation alignment provides a general and effective mechanism for bridging understanding and generation in protein structure modeling.
arXiv:2607.13505v1 Announce Type: new
Abstract: ColumnDisturb is a new data-disturbance error in which activations to an aggressor row cause bitflips in a victim row located hundreds of rows away (intra-subarray bitflips) and in victim rows in adjacent subarrays (inter-subarray bitflips). Intra-subarray ColumnDisturb can be tolerated by solutions (such as SALT and REGA) that operate at subarray granularity. However, to tolerate inter-subarray ColumnDisturb, such solutions must be extended with ColumnDisturb Protection (CDP), which performs additional {\em Adjacent-Counter Increment (ACI)} for the neighboring subarrays. The ACIs ensure that adjacent subarrays also undergo mitigation, even if they receive no demand activations. Unfortunately, because ACIs occur at a 200\% rate relative to demand activations, they effectively increase the activations perceived by the bank to 3x, which causes significant slowdowns (17\% at a TRHD of 500) and refresh overheads. The goal of our paper is to tolerate ColumnDisturb while incurring negligible overheads.
We propose CODA, a ColumnDisturb mitigation that significantly reduces the rate of ACI required to securely tolerate ColumnDisturb. We present three variants of CODA. First, CODA-E (Evade), which leverages the insight that ACI can be skipped if the neighboring subarray receives a demand activation, and reduces ACI by 2x. Second, CODA-F (Fraction), which uses the timing duration of ColumnDisturb to do only a fractional increment for ACI, thereby reducing the rate of ACI by 2x-16x. Finally, CODA-G (Gangskip), which operates at multi-subarray granularity and skips ACI for neighboring subarrays within the same gang, further reduces overall ACI by 2x-8x. Overall, CODA reduces ACI by 12x-1300x, thereby making it possible to tolerate ColumnDisturb while incurring zero performance and power overhead.
arXiv:2607.13539v1 Announce Type: new
Abstract: While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based generators predominantly adopt a one-shot paradigm where the full layout is planned at once. This one-shot approach often requires global re-optimization or complete reconstruction during interactive editing (e.g., inserting or moving objects) and can lead to physically or semantically poorly organized arrangements. To address these challenges, we propose ThinkBLOX, a VLM-based progressive reasoning framework that iteratively designs and refines 3D scenes. ThinkBLOX treats layout generation as a state-conditioned, step-by-step reasoningand-action process. To power this, we construct the ThinkBLOX-Data-200K dataset, containing 224,757 procedural placement pairs annotated with multi-view scene context, explicit Chain-of-Thought (CoT) rationales, and structured JSON layouts. Through supervised fine-tuning (SFT) on this dataset, the VLM learns to bridge the reasoning-action gap under incremental updates. Furthermore, recognizing that scene synthesis is inherently a multisolution task where SFT suffers from reward conflict, we introduce Tier-Decoupled GDPO. This reinforcement learning scheme organizes heterogeneous rewards into distinct tiers, stabilizing policy optimization across physical validity, semantic plausibility, and reasoning-action consistency. Extensive experiments show that ThinkBLOX significantly outperforms recent one-shot and iterative baselines in physical plausibility, semantic alignment, and interactive editability. Additionally, we show that it supports diverse applications, including both global and local generation and rearrangement of 3D scenes.
arXiv:2506.09775v2 Announce Type: replace-cross
Abstract: We consider the proximal gradient method on Riemannian manifolds for functions that are possibly not geodesically convex. Starting from the forward-backward-splitting, we define an intrinsic variant of the proximal gradient method that uses proximal maps defined on the manifold and therefore does not require or work in the embedding. We investigate its convergence properties and illustrate its numerical performance, particularly for nonconvex or nonembedded problems that are hence out of reach for other methods.